diff options
| author | Cliff Click <cliffc@acm.org> | 2024-11-26 11:01:47 -0800 |
|---|---|---|
| committer | Cliff Click <cliffc@acm.org> | 2025-01-15 15:07:30 -0800 |
| commit | 3507afb1602bcf159dede6bde2c70d620d6563da (patch) | |
| tree | 8204ed3d21df5ef3697ff1e750bc9e266db44e69 | |
| parent | 49c3e09e522d5c9d7524b48d1dda9419dd5da429 (diff) | |
| download | Simple-3507afb1602bcf159dede6bde2c70d620d6563da.tar.gz Simple-3507afb1602bcf159dede6bde2c70d620d6563da.zip | |
Initial push
93 files changed, 14891 insertions, 0 deletions
diff --git a/chapter18/Makefile b/chapter18/Makefile new file mode 100644 index 00000000..c14ffa27 --- /dev/null +++ b/chapter18/Makefile @@ -0,0 +1,98 @@ +SHELL := /bin/bash +.DELETE_ON_ERROR: + +# for printing variable values +# usage: make print-VARIABLE +# > VARIABLE = value_of_variable +print-% : ; @echo $* = $($*) + +# literal space +space := $() $() + +# Decide OS-specific questions +# jar-file seperator +ifeq ($(OS),Windows_NT) + SEP = ; +else + SEP = : +endif +# Find a reasonable ctags. +CTAGS = $(shell which ctags) +# Hack for MacOS: /usr/bin/ctags is unfriendly, so look for ctags from brew +ifeq ($(UNAME),Darwin) + CTAGS = $(shell brew list ctags 2> /dev/null | grep bin/ctags) +endif + +# Fun Args to javac. Mostly limit to java8 source definitions, and fairly +# aggressive lint warnings. +JAVAC_ARGS = -g + +# Source code +SIMPLE := com/seaofnodes/simple +SRC := src/main/java +TST := src/test/java +CLZDIR:= build/classes +main_javas := $(wildcard $(SRC)/$(SIMPLE)/*java $(SRC)/$(SIMPLE)/*/*java) +test_javas := $(wildcard $(TST)/$(SIMPLE)/*java $(TST)/$(SIMPLE)/*/*java) +main_classes := $(patsubst $(SRC)/%java,$(CLZDIR)/main/%class,$(main_javas)) +test_classes := $(patsubst $(TST)/%java,$(CLZDIR)/test/%class,$(test_javas)) +test_cp := $(patsubst $(TST)/$(SIMPLE)/%.java,com.seaofnodes.simple.%,$(wildcard $(TST)/$(SIMPLE)/*Test.java)) +classes = $(main_classes) $(test_classes) +# All the libraries +libs = $(wildcard lib/*jar) +jars = $(subst $(space),$(SEP),$(libs)) + + +default_targets := $(main_classes) $(test_classes) +# Optionally add ctags to the default target if a reasonable one was found. +ifneq ($(CTAGS),) +default_targets += tags +endif + +default: $(default_targets) + +# Compile just the out-of-date files +$(main_classes): build/classes/main/%class: $(SRC)/%java + @echo "compiling " $@ " because " $? + @[ -d $(CLZDIR)/main ] || mkdir -p $(CLZDIR)/main + @javac $(JAVAC_ARGS) -cp "$(CLZDIR)/main$(SEP)$(jars)" -sourcepath $(SRC) -d $(CLZDIR)/main $(main_javas) + +$(test_classes): $(CLZDIR)/test/%class: $(TST)/%java $(main_classes) + @echo "compiling " $@ " because " $? + @[ -d $(CLZDIR)/test ] || mkdir -p $(CLZDIR)/test + @javac $(JAVAC_ARGS) -cp "$(CLZDIR)/test$(SEP)$(CLZDIR)/main$(SEP)$(jars)" -sourcepath $(TST) -d $(CLZDIR)/test $(test_javas) + +# Base launch line for JVM tests +JVM=nice java -ea -cp "build/classes/main${SEP}${jars}${SEP}$(CLZDIR)/test" + +tests: $(default_targets) + @echo "testing " $(test_cp) + @$(JVM) org.junit.runner.JUnitCore $(test_cp) com.seaofnodes.simple.FuzzerWrap + +fuzzer: $(default_targets) + @echo "fuzzing " $(test_cp) + @$(JVM) org.junit.runner.JUnitCore com.seaofnodes.simple.FuzzerWrap + + +.PHONY: clean +clean: + rm -rf build + rm -f TAGS + (find . -name "*~" -exec rm {} \; 2>/dev/null; exit 0) + +# Download libs from maven +lib: lib/junit-4.12.jar lib/hamcrest-core-1.3.jar + +# Jars +lib/junit-4.12.jar: + @[ -d lib ] || mkdir -p lib + @(cd lib; wget https://repo1.maven.org/maven2/junit/junit/4.12/junit-4.12.jar) + +lib/hamcrest-core-1.3.jar: + @[ -d lib ] || mkdir -p lib + @(cd lib; wget https://repo1.maven.org/maven2/org/hamcrest/hamcrest-core/1.3/hamcrest-core-1.3.jar) + +# Build emacs tags (part of a tasty emacs ide experience) +tags: $(main_javas) $(test_javas) + @rm -f TAGS + @$(CTAGS) -e --recurse=yes --extra=+q --fields=+fksaiS $(SRC) $(TST) diff --git a/chapter18/README.md b/chapter18/README.md new file mode 100644 index 00000000..46c3790f --- /dev/null +++ b/chapter18/README.md @@ -0,0 +1,107 @@ +# Chapter 18: Functions + +Some thinking on function syntax: + +Function Types: +``` +{ argtype, argtype, ... -> rettype } +``` + +Leading `{` character denotes the start of a function or function type. + +Functions are normal variables and assigned the same way: + +```functiontype var = function-typed-expr``` + +Functions themselves using the same syntax with as types, but filled in: + +``` +{ int x, int y -> + sqrt(x*x+y*y); +} +``` + +Used in a declaration statement: +``` +// TYPE VAR = EXPR +{flt,flt->flt} dist = { flt x, flt y -> + sqrt(x*x+y*y); +} +``` + +With `var`: +``` +var dist = { flt x, flt y -> sqrt(x*x*,y*y); } +``` + +Functions are called in the usual way: +`dist( 1.2, 2.3 ) // yields 2.59422435` + +Functions can have zero arguments, in which case the `->` argument seperator is +optional. This allows any section of code to be "thunked" by wrapping it in +`{}`. + +`just5 = { -> 5 } // With arrow` +`just5 = { 5 } // Without arrow` + +Called: +`just5() // Returns 5` + + +Functions can be declared inside `struct`s, and will take a hidden `self` +argument to allow access to the struct members - basically the function becomes +a method. + +Also new this chapter, fields with a leading underscore `_` are private fields, +and only accessible to 'self'. + +```cpp +struct String { + u8[] _chars; // Private, not nullable, final, must be initialized in constructor + + // Functions declared inside of a struct become instance methods + // and have access to the struct members. + val len = { -> _chars#; } + + val at = { idx -> _chars[idx]; } + + // 'self' keyword returns an instance of itself. + val append = { String? str -> + // Appending a null appends nothing + if( !str ) return self; + + // Manual array copy _chars to cs + u8[] cs = new u8[_chars# + str.len()]; + for( int i=0; i<_chars#; i++ ) + cs[i] = _chars[i]; + + // Manual array copy str._chars to cs + for( int i=0; i<str.len(); i++ ) + cs[_chars#+i] = str.at(i); + + // Append returns a new String + return new String { _chars=cs; }; + } + + +}; + +``` + +With some syntax sugar from the parser we can produce `Hello, Cliff` +with method calls. +``` +String name = "Cliff"; +String greet = "Hello"; +return greet.append(", ").append(name); +``` + +There's only a little special syntax going on here with method calls. The +normal field lookup is used for `greet.append`, yielding a function-typed +value. Since it was loaded from the field, the function is **pre-bound** +(curried) to the `self` it was loaded from. + +`{int->u8} atCliff = name.at; // The "at" for Cliff; function does not take a String anymore` +`var atHello = greet.at;` +`atCliff[0]; // Returns 'C'` +`atHello[0]; // Returns 'H'` diff --git a/chapter18/docs/18-grammar.md b/chapter18/docs/18-grammar.md new file mode 100644 index 00000000..7b611fbf --- /dev/null +++ b/chapter18/docs/18-grammar.md @@ -0,0 +1,132 @@ +# Grammar for Chapter 16 + +```antlrv4 +grammar SimpleLanguage; + +program : block EOF ; + +block : statement+ ; + + +statement + : '{' block '}' + | returnStatement + | ifStatement + | whileStatement + | breakStatement + | continueStatement + | metaStatement + | structDeclaration + | expressionStatement + ; + + +returnStatement : 'return' expression ';' ; + +ifStatement : 'if' '(' expression ')' statement ('else' statement)? ; + +whileStatement : 'while' '(' expression ')' statement ; + +breakStatement : 'break' ';' ; + +continueStatement : 'continue' ';' ; + +metaStatement : '#showGraph' ';' ; + +structDeclaration : 'struct' IDENTIFIER '{' block '}' ; + +expressionStatement + : type IDENTIFIER ';' + | type IDENTIFIER '=' expression ';' + | IDENTIFIER '=' expression ';' + | expression + ; + +PRIMTYPE + : 'int' + | 'i8' + | 'i16' + | 'i32' + | 'i64' + | 'u8' + | 'u16' + | 'u32' + | 'flt' + | 'f32' + | 'f64' + | 'bool' + ; + +type + : PRIMTYPE + | typeName '?'? + | typeName nestedArray+ + ; + +nestedArray : '?'? '[]'* ; + +typeName : IDENTIFIER ; + + +expression : bitWiseExpression ; + +bitWiseExpression + : comparisonExpression ( '&' | '|' | '^' ) comparisonExpression)* + ; + +comparisonExpression + : shiftExpression (('==' | '!='| '>'| '<'| '>='| '<=') shiftExpression)* + ; + +shiftExpression + : additiveExpression ( '<<' | '>>>' | '>>' ) additiveExpression)* + ; + +additiveExpression + : multiplicativeExpression (('+' | '-') multiplicativeExpression)* + ; + +multiplicativeExpression + : unaryExpression (('*' | '/') unaryExpression)* + ; + +unaryExpression + : ('-') unaryExpression + | '!' unaryExpression + | primaryExpression postAssign + ; + +primaryExpression + : INTEGER_LITERAL + | FLOAT_LITERAL + | '(' expression ')' + | 'true' + | 'false' + | 'null' + | newExpression + | IDENTIFIER + ; + +newExpression + : 'new' IDENTIFIER [ '{' block '}' ] + | 'new' IDENTIFIER '[' expression ']' + ; + +postAssign : postFix [ '=' expression ] | [ '#' ]; + +postFix + : '.' IDENTIFIER postFix + | '[' expression ']' postFix + ; + + +IDENTIFIER : NON_DIGIT (NON_DIGIT | DIGIT)* ; + +INTEGER_LITERAL + : [1-9]DIGIT* + | [0] + ; + +NON_DIGIT: [a-zA-Z_]; +DIGIT: [0-9]; +``` diff --git a/chapter18/docs/Makefile b/chapter18/docs/Makefile new file mode 100644 index 00000000..12659b8f --- /dev/null +++ b/chapter18/docs/Makefile @@ -0,0 +1,12 @@ +GV := $(wildcard *.gv) +SVG := $(patsubst %.gv,%.svg,$(GV)) + +.PHONY: all +all: $(SVG) + +%.svg: %.gv + dot -Tsvg $< > $@ + +.PHONY: clean +clean: + @rm -f $(SVG) diff --git a/chapter18/pom.xml b/chapter18/pom.xml new file mode 100644 index 00000000..fbe22605 --- /dev/null +++ b/chapter18/pom.xml @@ -0,0 +1,14 @@ +<?xml version="1.0" encoding="UTF-8"?> +<project xmlns="http://maven.apache.org/POM/4.0.0" + xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" + xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> + <modelVersion>4.0.0</modelVersion> + <parent> + <groupId>com.seaofnodes</groupId> + <artifactId>simple</artifactId> + <version>1.0</version> + </parent> + <artifactId>chapter17</artifactId> + <packaging>jar</packaging> + <name>Chapter 17</name> +</project> diff --git a/chapter18/src/main/java/com/seaofnodes/simple/Ary.java b/chapter18/src/main/java/com/seaofnodes/simple/Ary.java new file mode 100644 index 00000000..8654d41e --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/Ary.java @@ -0,0 +1,217 @@ +package com.seaofnodes.simple; + +import java.lang.StringBuilder; +import java.lang.reflect.Array; +import java.util.*; + +// ArrayList with saner syntax +public class Ary<E> extends AbstractList<E> implements List<E> { + public E[] _es; + public int _len; + + public Ary(E[] es) { this(es,es.length); } + public Ary(E[] es, int len) { if( es.length==0 ) es=Arrays.copyOf(es,1); _es=es; _len=len; } + @SuppressWarnings("unchecked") + public Ary(Class<E> clazz) { this((E[]) Array.newInstance(clazz, 1),0); } + + /** @return list is empty */ + public boolean isEmpty() { return _len==0; } + /** @return active list length */ + public int len() { return _len; } + public int size() { return len(); } + + /** @param i element index + * @return element being returned; throws if OOB + * @exception AIOOBE if !(0 <= i < _len) + */ + public E get( int i ) { return at(i); } + public E at( int i ) { + range_check(i); + return _es[i]; + } + + /** @return last element */ + public E last( ) { return at(_len-1); } + + /** Add element in amortized constant time + * @param e Element to add at end of list + **/ + public E push( E e ) { + if( _len >= _es.length ) _es = Arrays.copyOf(_es,Math.max(1,_es.length<<1)); + return (_es[_len++] = e); + } + /** @return remove and return last element */ + public E pop( ) { + range_check(0); + return _es[--_len]; + } + @Override public E removeLast() { return pop(); } + + + /** Add element in amortized constant time + * @param e Element to add at end of list + * @return true */ + public boolean add( E e ) { + if( _len >= _es.length ) _es = Arrays.copyOf(_es,Math.max(1,_es.length<<1)); + _es[_len++] = e; + return true; + } + + ///** Slow, linear-time, element insert. Preserves order. + // * @param i index to insert at, between 0 and _len inclusive. + // * @param e Element to insert + // */ + //public void insert( int i, E e ) { + // if( i < 0 || i>_len ) + // throw new ArrayIndexOutOfBoundsException(""+i+" >= "+_len); + // if( _len >= _es.length ) _es = Arrays.copyOf(_es,Math.max(1,_es.length<<1)); + // System.arraycopy(_es,i,_es,i+1,(_len++)-i); + // _es[i] = e; + //} + + /** Fast, constant-time, element removal. Does not preserve order + * @param i element to be removed + * @return element removed */ + public E del( int i ) { + range_check(i); + E tmp = _es[i]; + _es[i]=_es[--_len]; + return tmp; + } + + ///** Element removal, using '=='. Does not preserve order. + // * @param e element to be removed + // * @return element removed */ + //public E del( E e ) { + // for( int i=0; i<_len; i++ ) { + // E tmp = _es[i]; + // if( tmp==e ) { + // _es[i]=_es[--_len]; + // return tmp; + // } + // } + // return null; + //} + + /** Slow, linear-time, element removal. Preserves order. + * @param i element to be removed + * @return element removed */ + @Override public E remove( int i ) { + range_check(i); + E e = _es[i]; + System.arraycopy(_es,i+1,_es,i,(--_len)-i); + return e; + } + + /** Remove all elements */ + public void clear( ) { _len=0; } + + /** Set existing element + * @param i element to set + * @param e value to set + * @return old value + * @exception AIOOBE if !(0 <= i < _len) + */ + public E set( int i, E e ) { + range_check(i); + E old = _es[i]; + _es[i] = e; + return old; + } + + public Ary<E> setLen( int len ) { + if( len > _len ) + while( len>= _es.length ) _es = Arrays.copyOf(_es,_es.length<<1); + _len = len; + while( _es.length > (len<<1) ) // Shrink if hugely too large + _es = Arrays.copyOf(_es,_es.length>>1); + Arrays.fill(_es,len,_es.length,null); + return this; + } + + /** @param c Collection to be added */ + public boolean addAll( Collection<? extends E> c ) { + if( c==null ) return false; + for( E e : c ) add(e); + return true; + } + public Ary<E> addAll( Iterable<? extends E> it ) { for( E e : it ) add(e); return this; } + + /** @param es Array to be added */ + public <F extends E> Ary<E> addAll( F[] es ) { + if( es==null || es.length==0 ) return this; + while( _len+es.length > _es.length ) _es = Arrays.copyOf(_es,_es.length<<1); + System.arraycopy(es,0,_es,_len,es.length); + _len += es.length; + return this; + } + + /** @param c Collection to be added */ + public Ary<E> addAll( Ary<? extends E> c ) { + if( c==null || c._len==0 ) return this; + while( _len+c._len > _es.length ) _es = Arrays.copyOf(_es,_es.length<<1); + System.arraycopy(c._es,0,_es,_len,c._len); + _len += c._len; + return this; + } + + /** @return compact array version */ + public E[] asAry() { return Arrays.copyOf(_es,_len); } + + /** Sorts in-place + * @param c Comparator to sort by */ + public void sort_update(Comparator<? super E> c ) { Arrays.sort(_es, 0, _len, c); } + + /** Find the first matching element using ==, or -1 if none. Note that + * most del calls shuffle the list, so the first element might be random. + * @param e Element to find + * @return index of first matching element, or -1 if none */ + public int find( E e ) { + for( int i=0; i<_len; i++ ) if( _es[i]==e ) return i; + return -1; + } + + + /** @return an iterator */ + @Override public Iterator<E> iterator() { return new Iter(); } + private class Iter implements Iterator<E> { + int _i=0; + @Override public boolean hasNext() { return _i<_len; } + @Override public E next() { return _es[_i++]; } + } + + @Override public String toString() { + StringBuilder sb = new StringBuilder().append('{'); + for( int i=0; i<_len; i++ ) { + if( i>0 ) sb.append(','); + if( _es[i] != null ) sb.append(_es[i].toString()); + } + return sb.append('}').toString(); + } + + private void range_check( int i ) { + if( i < 0 || i>=_len ) + throw new ArrayIndexOutOfBoundsException(""+i+" >= "+_len); + } + + // Note that the hashCode() and equals() are not invariant to changes in the + // underlying array. If the hashCode() is used (e.g., inserting into a + // HashMap) and the then the array changes, the hashCode() will change also. + @Override public boolean equals( Object o ) { + if( this==o ) return true; + if( !(o instanceof Ary ary) ) return false; + if( _len != ary._len ) return false; + if( _es == ary._es ) return true; + for( int i=0; i<_len; i++ ) + if( !(_es[i]==null ? (ary._es[i] == null) : _es[i].equals(ary._es[i])) ) + return false; + return true; + } + @Override public int hashCode( ) { + int sum=_len; + for( int i=0; i<_len; i++ ) + sum += _es[i]==null ? 0 : _es[i].hashCode(); + return sum; + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/GlobalCodeMotion.java b/chapter18/src/main/java/com/seaofnodes/simple/GlobalCodeMotion.java new file mode 100644 index 00000000..9698abd9 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/GlobalCodeMotion.java @@ -0,0 +1,228 @@ + package com.seaofnodes.simple; + +import com.seaofnodes.simple.IterPeeps.WorkList; +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.*; +import java.util.*; + +public abstract class GlobalCodeMotion { + + // Arrange that the existing isCFG() Nodes form a valid CFG. The + // Node.use(0) is always a block tail (either IfNode or head of the + // following block). There are no unreachable infinite loops. + public static void buildCFG( StopNode stop ) { + schedEarly(); + Parser.SCHEDULED = true; + schedLate( stop); + } + + + // ------------------------------------------------------------------------ + // Visit all nodes in CFG Reverse Post-Order, essentially defs before uses + // (except at loops). Since defs are visited first - and hoisted as early + // as possible, when we come to a use we place it just after its deepest + // input. + private static void schedEarly() { + ArrayList<CFGNode> rpo = new ArrayList<>(); + BitSet visit = new BitSet(); + _rpo_cfg(Parser.START, visit, rpo); + // Reverse Post-Order on CFG + for( int j=rpo.size()-1; j>=0; j-- ) { + CFGNode cfg = rpo.get(j); + cfg.loopDepth(); + for( Node n : cfg._inputs ) + _schedEarly(n,visit); + if( cfg instanceof RegionNode ) + for( Node phi : cfg._outputs ) + if( phi instanceof PhiNode ) + _schedEarly(phi,visit); + } + } + + // Post-Order of CFG + private static void _rpo_cfg(Node n, BitSet visit, ArrayList<CFGNode> rpo) { + if( !(n instanceof CFGNode cfg) || visit.get(cfg._nid) ) + return; // Been there, done that + visit.set(cfg._nid); + for( Node use : cfg._outputs ) + _rpo_cfg(use,visit,rpo); + rpo.add(cfg); + } + + private static void _schedEarly(Node n, BitSet visit) { + if( n==null || visit.get(n._nid) ) return; // Been there, done that + assert !(n instanceof CFGNode); + visit.set(n._nid); + // Schedule not-pinned not-CFG inputs before self. Since skipping + // Pinned, this never walks the backedge of Phis (and thus spins around + // a data-only loop, eventually attempting relying on some pre-visited- + // not-post-visited data op with no scheduled control. + for( Node def : n._inputs ) + if( def!=null && !(def instanceof PhiNode) ) + _schedEarly(def,visit); + // If not-pinned (e.g. constants, projections, phi) and not-CFG + if( !n.isPinned() ) { + // Schedule at deepest input + CFGNode early = Parser.START; // Maximally early, lowest idepth + if( n.in(0) instanceof CFGNode cfg ) early = cfg; + for( int i=1; i<n.nIns(); i++ ) + if( n.in(i).cfg0().idepth() > early.idepth() ) + early = n.in(i).cfg0(); // Latest/deepest input + n.setDef(0,early); // First place this can go + } + } + + // ------------------------------------------------------------------------ + private static void schedLate( StopNode stop) { + CFGNode[] late = new CFGNode[Node.UID()]; + Node[] ns = new Node[Node.UID()]; + // Breadth-first scheduling + breadth(stop,ns,late); + + // Copy the best placement choice into the control slot + for( int i=0; i<late.length; i++ ) + if( ns[i] != null && !(ns[i] instanceof ProjNode) ) + ns[i].setDef(0,late[i]); + } + + private static void breadth(Node stop, Node[] ns, CFGNode[] late) { + // Things on the worklist have some (but perhaps not all) uses done. + WorkList<Node> work = new WorkList<>(); + work.push(stop); + Node n; + outer: + while( (n = work.pop()) != null ) { + assert late[n._nid]==null; // No double visit + // These I know the late schedule of, and need to set early for loops + if( n instanceof CFGNode cfg ) late[n._nid] = cfg.blockHead() ? cfg : cfg.cfg(0); + else if( n instanceof PhiNode phi ) late[n._nid] = phi.region(); + else if( n instanceof ProjNode && n.in(0) instanceof CFGNode cfg ) late[n._nid] = cfg; + else { + + // All uses done? + for( Node use : n._outputs ) + if( use!=null && late[use._nid]==null ) + continue outer; // Nope, await all uses done + + // Loads need their memory inputs' uses also done + if( n instanceof LoadNode ld ) + for( Node memuse : ld.mem()._outputs ) + if( late[memuse._nid]==null && + // Load-use directly defines memory + (memuse._type instanceof TypeMem || + // Load-use indirectly defines memory + (memuse._type instanceof TypeTuple tt && tt._types[ld._alias] instanceof TypeMem)) ) + continue outer; + + // All uses done, schedule + _doSchedLate(n,ns,late); + } + + // Walk all inputs and put on worklist, as their last-use might now be done + for( Node def : n._inputs ) + if( def!=null && late[def._nid]==null ) { + work.push(def); + // if the def has a load use, maybe the load can fire + for( Node ld : def._outputs ) + if( ld instanceof LoadNode && late[ld._nid]==null ) + work.push(ld); + } + } + } + + private static void _doSchedLate(Node n, Node[] ns, CFGNode[] late) { + // Walk uses, gathering the LCA (Least Common Ancestor) of uses + CFGNode early = n.in(0) instanceof CFGNode cfg ? cfg : n.in(0).cfg0(); + assert early != null; + CFGNode lca = null; + for( Node use : n._outputs ) + if( use != null ) + lca = use_block(n,use, late)._idom(lca,null); + + // Loads may need anti-dependencies, raising their LCA + if( n instanceof LoadNode load ) + lca = find_anti_dep(lca,load,early,late); + + // Walk up from the LCA to the early, looking for best place. This is + // the lowest execution frequency, approximated by least loop depth and + // deepest control flow. + CFGNode best = lca; + lca = lca.idom(); // Already found best for starting LCA + for( ; lca != early.idom(); lca = lca.idom() ) + if( better(lca,best) ) + best = lca; + assert !(best instanceof IfNode); + ns [n._nid] = n; + late[n._nid] = best; + } + + // Block of use. Normally from late[] schedule, except for Phis, which go + // to the matching Region input. + private static CFGNode use_block(Node n, Node use, CFGNode[] late) { + if( !(use instanceof PhiNode phi) ) + return late[use._nid]; + CFGNode found=null; + for( int i=1; i<phi.nIns(); i++ ) + if( phi.in(i)==n ) + if( found==null ) found = phi.region().cfg(i); + else Utils.TODO(); // Can be more than once + assert found!=null; + return found; + } + + + // Least loop depth first, then largest idepth + private static boolean better( CFGNode lca, CFGNode best ) { + return lca.loopDepth() < best.loopDepth() || + (lca.idepth() > best.idepth() || best instanceof IfNode); + } + + private static CFGNode find_anti_dep(CFGNode lca, LoadNode load, CFGNode early, CFGNode[] late) { + // We could skip final-field loads here. + // Walk LCA->early, flagging Load's block location choices + for( CFGNode cfg=lca; early!=null && cfg!=early.idom(); cfg = cfg.idom() ) + cfg._anti = load._nid; + // Walk load->mem uses, looking for Stores causing an anti-dep + for( Node mem : load.mem()._outputs ) { + switch( mem ) { + case StoreNode st: + assert late[st._nid]!=null; + lca = anti_dep(load,late[st._nid],st.cfg0(),lca,st); + break; + case NewNode st: + assert late[st._nid]!=null; + lca = anti_dep(load,late[st._nid],st.cfg0(),lca,st); + break; + case PhiNode phi: + // Repeat anti-dep for matching Phi inputs. + // No anti-dep edges but may raise the LCA. + for( int i=1; i<phi.nIns(); i++ ) + if( phi.in(i)==load.mem() ) + lca = anti_dep(load,phi.region().cfg(i),load.mem().cfg0(),lca,null); + break; + case LoadNode ld: break; // Loads do not cause anti-deps on other loads + case ReturnNode ret: break; // Load must already be ahead of Return + case ScopeMinNode ret: break; // Mem uses now on ScopeMin + case NeverNode never: break; + default: throw Utils.TODO(); + } + } + return lca; + } + + // + private static CFGNode anti_dep( LoadNode load, CFGNode stblk, CFGNode defblk, CFGNode lca, Node st ) { + // Walk store blocks "reach" from its scheduled location to its earliest + for( ; stblk != defblk.idom(); stblk = stblk.idom() ) { + // Store and Load overlap, need anti-dependence + if( stblk._anti==load._nid ) { + lca = stblk._idom(lca,null); // Raise Loads LCA + if( lca == stblk && st != null && st._inputs.find(load) == -1 ) // And if something moved, + st.addDef(load); // Add anti-dep as well + return lca; // Cap this stores' anti-dep to here + } + } + return lca; + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/GraphVisualizer.java b/chapter18/src/main/java/com/seaofnodes/simple/GraphVisualizer.java new file mode 100644 index 00000000..de6d65a3 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/GraphVisualizer.java @@ -0,0 +1,288 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; + +import java.util.*; + +import static com.seaofnodes.simple.Utils.TODO; + +/** + * Simple visualizer that outputs GraphViz dot format. + * The dot output must be saved to a file and run manually via dot to generate the SVG output. + * Currently, this is done manually. + */ +public class GraphVisualizer { + + /** + * If set to true we put the control nodes in a separate cluster from + * data nodes. + */ + boolean _separateControlCluster = false; + + public GraphVisualizer(boolean separateControlCluster) { this._separateControlCluster = separateControlCluster; } + public GraphVisualizer() { this(false); } + + public String generateDotOutput(Parser parse) { return generateDotOutput(parse.STOP,parse._scope,parse._xScopes); } + public String generateDotOutput(StopNode stop, Node scope, Stack<ScopeNode> xScopes) { + + // Since the graph has cycles, we need to create a flat list of all the + // nodes in the graph. + Collection<Node> all = findAll(stop, scope); + StringBuilder sb = new StringBuilder(); + sb.append("digraph chapter11 {\n"); + sb.append("/*\n"); + sb.append(stop._src); + sb.append("\n*/\n"); + + // To keep the Scopes below the graph and pointing up into the graph we + // need to group the Nodes in a subgraph cluster, and the scopes into a + // different subgraph cluster. THEN we can draw edges between the + // scopes and nodes. If we try to cross subgraph cluster borders while + // still making the subgraphs DOT gets confused. + sb.append("\trankdir=BT;\n"); // Force Nodes before Scopes + + // CNC - turned off Apr/8/2024, gives more flex in the layout and + // removes some of the more ludicrous layout choices. + // Preserve node input order + //sb.append("\tordering=\"in\";\n"); + + // Merge multiple edges hitting the same node. Makes common shared + // nodes much prettier to look at. + sb.append("\tconcentrate=\"true\";\n"); + + // Force nested scopes to order + sb.append("\tcompound=\"true\";\n"); + + // Just the Nodes first, in a cluster no edges + nodes(sb, all); + + // Now the scopes, in a cluster no edges + if( xScopes != null ) + for( ScopeNode xscope : xScopes ) + if( !xscope.isDead() ) + scope( sb, xscope ); + + // Walk the Node edges + nodeEdges(sb, all); + + // Walk the active Scope edges + if( xScopes != null ) + for( ScopeNode xscope : xScopes ) + if( !xscope.isDead() ) + scopeEdges( sb, xscope ); + + sb.append("}\n"); + return sb.toString(); + } + + private void nodesByCluster(StringBuilder sb, boolean doCtrl, Collection<Node> all) { + if (!_separateControlCluster && doCtrl) // all nodes in 1 cluster + return; + // Just the Nodes first, in a cluster no edges + sb.append(doCtrl ? "\tsubgraph cluster_Controls {\n" : "\tsubgraph cluster_Nodes {\n"); // Magic "cluster_" in the subgraph name + for (Node n : all) { + if (n instanceof ProjNode || n instanceof CProjNode || n instanceof ScopeMinNode || n==Parser.XCTRL) + continue; // Do not emit, rolled into MultiNode or Scope cluster already + if( _separateControlCluster && doCtrl && !(n instanceof CFGNode) ) continue; + if( _separateControlCluster && !doCtrl && (n instanceof CFGNode) ) continue; + sb.append("\t\t").append(n.uniqueName()).append(" [ "); + String lab = n.glabel(); + if (n instanceof MultiNode) { + // Make a box with the MultiNode on top, and all the projections on the bottom + sb.append("shape=plaintext label=<\n"); + sb.append("\t\t\t<TABLE BORDER=\"0\" CELLBORDER=\"1\" CELLSPACING=\"0\" CELLPADDING=\"4\">\n"); + sb.append("\t\t\t<TR><TD BGCOLOR=\"yellow\">").append(lab).append("</TD></TR>\n"); + sb.append("\t\t\t<TR>"); + boolean doProjTable = false; + n._outputs.sort((x,y) -> x instanceof ProjNode xp && y instanceof ProjNode yp ? (xp._idx - yp._idx) : (x._nid - y._nid)); + for (Node use : n._outputs) { + if (use instanceof ProjNode proj) { + if (!doProjTable) { + doProjTable = true; + sb.append("<TD>").append("\n"); + sb.append("\t\t\t\t<TABLE BORDER=\"0\" CELLBORDER=\"1\" CELLSPACING=\"0\">").append("\n"); + sb.append("\t\t\t\t<TR>"); + } + sb.append("<TD PORT=\"p").append(proj._idx).append("\">").append(proj.glabel()).append("</TD>"); + } + if (use instanceof CProjNode proj) { + if (!doProjTable) { + doProjTable = true; + sb.append("<TD>").append("\n"); + sb.append("\t\t\t\t<TABLE BORDER=\"0\" CELLBORDER=\"1\" CELLSPACING=\"0\">").append("\n"); + sb.append("\t\t\t\t<TR>"); + } + sb.append("<TD PORT=\"p").append(proj._idx).append("\" BGCOLOR=\"yellow\">").append(proj.glabel()).append("</TD>"); + } + } + if (doProjTable) { + sb.append("</TR>").append("\n"); + sb.append("\t\t\t\t</TABLE>").append("\n"); + sb.append("\t\t\t</TD>"); + } + sb.append("</TR>\n"); + sb.append("\t\t\t</TABLE>>\n\t\t"); + + } else { + // control nodes have box shape + // other nodes are ellipses, i.e. default shape + if( n instanceof CFGNode ) sb.append("shape=box style=filled fillcolor=yellow "); + else if (n instanceof PhiNode) sb.append("style=filled fillcolor=lightyellow "); + sb.append("label=\"").append(lab).append("\" "); + } + sb.append("];\n"); + } + if (!_separateControlCluster) { + // Force Region & Phis to line up + for (Node n : all) { + if (n instanceof RegionNode region) { + sb.append("\t\t{ rank=same; "); + sb.append(region).append(";"); + for (Node phi : region._outputs) + if (phi instanceof PhiNode) sb.append(phi.uniqueName()).append(";"); + sb.append("}\n"); + } + } + } + sb.append("\t}\n"); // End Node cluster + } + + private void nodes(StringBuilder sb, Collection<Node> all) { + nodesByCluster(sb, true, all); + nodesByCluster(sb, false, all); + } + + // Build a nested scope display, walking the _prev edge + private void scope( StringBuilder sb, ScopeNode scope ) { + sb.append("\tnode [shape=plaintext];\n"); + int last = scope.nIns(); + int max = scope._lexSize.size(); + for( int i = 0; i < max; i++ ) { + int level = max-i-1; + String scopeName = makeScopeName(scope, level); + sb.append("\tsubgraph cluster_").append(scopeName).append(" {\n"); // Magic "cluster_" in the subgraph name + // Special for memory ScopeMinNode + if( level==0 ) { + ScopeMinNode n = scope.mem(); + sb.append("\t\t").append(n.uniqueName()).append(" [label=\"").append(n.glabel()).append("\"];\n"); + } + sb.append("\t\t").append(scopeName).append(" [label=<\n"); + sb.append("\t\t\t<TABLE BORDER=\"0\" CELLBORDER=\"1\" CELLSPACING=\"0\">\n"); + // Add the scope level + sb.append("\t\t\t<TR><TD BGCOLOR=\"cyan\">").append(level).append("</TD>"); + int lexStart=scope._lexSize.at(level); + for( int j=lexStart; j<last; j++ ) { + var v = scope._vars.at(j); + sb.append("<TD PORT=\"").append(makePortName(scopeName, v._name)).append("\">").append(v._name).append("</TD>"); + } + last = lexStart; + sb.append("</TR>\n"); + sb.append("\t\t\t</TABLE>>];\n"); + } + // Scope clusters nest, so the graphics shows the nested scopes, so + // they are not closed as they are printed; so they just keep nesting. + // We close them all at once here. + sb.append( "\t}\n".repeat( max ) ); // End all Scope clusters + } + + private String makeScopeName(ScopeNode sn, int level) { return sn.uniqueName() + "_" + level; } + private String makePortName(String scopeName, String varName) { return scopeName + "_" + varName; } + + // Walk the node edges + private void nodeEdges(StringBuilder sb, Collection<Node> all) { + // All them edge labels + sb.append("\tedge [ fontname=Helvetica, fontsize=8 ];\n"); + for( Node n : all ) { + // Do not display the Constant->Start edge; + // ProjNodes handled by Multi; + // ScopeNodes are done separately + if( n instanceof ConstantNode || n instanceof ProjNode || n instanceof CProjNode || n instanceof ScopeNode || n==Parser.XCTRL ) + continue; + for( int i=0; i<n.nIns(); i++ ) { + Node def = n.in(i); + if( n instanceof PhiNode && def instanceof RegionNode ) { + // Draw a dotted use->def edge from Phi to Region. + sb.append('\t').append(n.uniqueName()); + sb.append(" -> "); + sb.append(def.uniqueName()); + sb.append(" [style=dotted taillabel=").append(i).append("];\n"); + } else if( def != null ) { + // Most edges land here use->def + sb.append('\t').append(n.uniqueName()).append(" -> "); + if( def instanceof CProjNode proj ) { + String mname = proj.ctrl().uniqueName(); + sb.append(mname).append(":p").append(proj._idx); + } else if( def instanceof ProjNode proj ) { + String mname = proj.in(0).uniqueName(); + sb.append(mname).append(":p").append(proj._idx); + } else sb.append(def.uniqueName()); + // Number edges, so we can see how they track + sb.append("[taillabel=").append(i); + // The edge from New to ctrl is just for anchoring the New + if ( n instanceof NewNode ) + sb.append(" color=green"); + // control edges are colored red + else if( def instanceof CFGNode ) + sb.append(" color=red"); + else if( def.isMem() ) + sb.append(" color=blue"); + // Backedges do not add a ranking constraint + if( i==2 && (n instanceof PhiNode || n instanceof LoopNode) ) + sb.append(" constraint=false"); + sb.append("];\n"); + } + } + } + } + + // Walk the scope edges + private void scopeEdges( StringBuilder sb, ScopeNode scope ) { + sb.append("\tedge [style=dashed color=cornflowerblue];\n"); + int level=0; + for( var v : scope._vars ) { + Node def = scope.in(v._idx); + while( def instanceof ScopeNode lazy ) + def = lazy.in(v._idx); + if( def==null ) continue; + while( level < scope._lexSize.size() && v._idx >= scope._lexSize.at(level) ) + level++; + String scopeName = makeScopeName(scope, level-1); + sb.append("\t") + .append(scopeName).append(":") + .append('"').append(makePortName(scopeName, v._name)).append('"') // wrap port name with quotes because $ctrl is not valid unquoted + .append(" -> "); + if( def instanceof CProjNode proj ) { + sb.append(def.in(0).uniqueName()).append(":p").append(proj._idx); + } else if( def instanceof ProjNode proj ) { + sb.append(def.in(0).uniqueName()).append(":p").append(proj._idx); + } else sb.append(def.uniqueName()); + sb.append(";\n"); + } + } + + /** + * Finds all nodes in the graph. + */ + private Collection<Node> findAll(Node stop, Node scope) { + final HashMap<Integer, Node> all = new HashMap<>(); + for( Node n : stop._inputs ) + walk(all, n); + if( scope != null ) + for( Node n : scope._inputs ) + walk(all, n); + return all.values(); + } + + /** + * Walk a subgraph and populate distinct nodes in the all list. + */ + private void walk(HashMap<Integer,Node> all, Node n) { + if(n == null ) return; + if (all.get(n._nid) != null) return; // Been there, done that + all.put(n._nid, n); + for (Node c : n._inputs) + walk(all, c); + for( Node c : n._outputs ) + walk(all, c); + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/IRPrinter.java b/chapter18/src/main/java/com/seaofnodes/simple/IRPrinter.java new file mode 100644 index 00000000..7ef55a3f --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/IRPrinter.java @@ -0,0 +1,286 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import java.lang.StringBuilder; +import java.util.ArrayList; +import java.util.BitSet; +import java.util.HashMap; + +public class IRPrinter { + + // Print a node on 1 line, columnar aligned, as: + // NNID NNAME DDEF DDEF [[ UUSE UUSE ]] TYPE + // 1234 sssss 1234 1234 1234 1234 1234 1234 tttttt + public static void _printLine( Node n, StringBuilder sb ) { + sb.append("%4d %-7.7s ".formatted(n._nid,n.label())); + if( n._inputs==null ) { + sb.append("DEAD\n"); + return; + } + for( Node def : n._inputs ) + sb.append(def==null ? "____ " : "%4d ".formatted(def._nid)); + for( int i = n._inputs.size(); i<4; i++ ) + sb.append(" "); + sb.append(" [[ "); + for( Node use : n._outputs ) + sb.append(use==null ? "____ " : "%4d ".formatted(use._nid)); + int lim = 6 - Math.max(n._inputs.size(),4); + for( int i = n._outputs.size(); i<lim; i++ ) + sb.append(" "); + sb.append(" ]] "); + if( n._type!= null ) sb.append(n._type.str()); + sb.append("\n"); + } + + private static StringBuilder nodeId(StringBuilder sb, Node n) { + sb.append("%%%d".formatted(n._nid)); + if (n instanceof ProjNode proj) { + sb.append(".").append(proj._idx); + } + return sb; + } + + // Print a node on 1 line, format is inspired by LLVM + // %id: TYPE = NODE(inputs ....) + // Nodes as referred to as %id + public static void _printLineLlvmFormat( Node n, StringBuilder sb ) { + nodeId(sb, n).append(": "); + if( n._inputs==null ) { + sb.append("DEAD\n"); + return; + } + if( n._type!= null ) n._type.typeName(sb); + sb.append(" = ").append( n.label() ).append( "(" ); + for( int i = 0; i < n._inputs.size(); i++ ) { + Node def = n.in(i); + if (i > 0) + sb.append(", "); + if (def == null) sb.append("_"); + else nodeId(sb, def); + } + sb.append(")").append("\n"); + } + + public static void printLine( Node n, StringBuilder sb, boolean llvmFormat ) { + if (llvmFormat) _printLineLlvmFormat( n, sb ); + else _printLine ( n, sb ); + } + + public static String prettyPrint(Node node, int depth) { + return Parser.SCHEDULED + ? prettyPrintScheduled( node, depth, false ) + : prettyPrint( node, depth, false ); + } + + // Another bulk pretty-printer. Makes more effort at basic-block grouping. + public static String prettyPrint( Node node, int depth, boolean llvmFormat ) { + // First, a Breadth First Search at a fixed depth. + BFS bfs = new BFS(node,depth); + // Convert just that set to a post-order + ArrayList<Node> rpos = new ArrayList<>(); + BitSet visit = new BitSet(); + for( int i=bfs._lim; i< bfs._bfs.size(); i++ ) + postOrd( bfs._bfs.get(i), rpos, visit, bfs._bs); + // Reverse the post-order walk + StringBuilder sb = new StringBuilder(); + boolean gap=false; + for( int i=rpos.size()-1; i>=0; i-- ) { + Node n = rpos.get(i); + if( n instanceof CFGNode || n.isMultiHead() ) { + if( !gap ) sb.append("\n"); // Blank before multihead + printLine( n, sb, llvmFormat ); // Print head + while( --i >= 0 ) { + Node t = rpos.get(i); + if( !t.isMultiTail() ) { i++; break; } + printLine( t, sb, llvmFormat ); + } + sb.append("\n"); // Blank after multitail + gap = true; + } else { + printLine( n, sb, llvmFormat ); + gap = false; + } + } + return sb.toString(); + } + + private static void postOrd(Node n, ArrayList<Node> rpos, BitSet visit, BitSet bfs) { + if( !bfs.get(n._nid) ) + return; // Not in the BFS visit + if( visit.get(n._nid) ) return; // Already post-order walked + visit.set(n._nid); + // First walk the CFG, then everything + if( n instanceof CFGNode ) { + for( Node use : n._outputs ) + if( use instanceof CFGNode && use.nOuts() >= 1 && !(use._outputs.get( 0 ) instanceof LoopNode) ) + postOrd(use, rpos,visit,bfs); + for( Node use : n._outputs ) + if( use instanceof CFGNode ) + postOrd(use,rpos,visit,bfs); + } + for( Node use : n._outputs ) + if( use != null ) + postOrd(use, rpos,visit,bfs); + // Post-order + rpos.add(n); + } + + // Breadth-first search, broken out in a class to keep in more independent. + // Maintains a root-set of Nodes at the limit (or past by 1 if MultiHead). + public static class BFS { + // A breadth first search, plus MultiHeads for any MultiTails + public final ArrayList<Node> _bfs; + public final BitSet _bs; // Visited members by node id + public final int _depth; // Depth limit + public final int _lim; // From here to _bfs._len can be roots for a reverse search + public BFS( Node base, int d ) { + _depth = d; + _bfs = new ArrayList<>(); + _bs = new BitSet(); + + add(base); // Prime the pump + int idx=0, lim=1; // Limit is where depth counter changes + while( idx < _bfs.size() ) { // Ran out of nodes below depth + Node n = _bfs.get(idx++); + for( Node def : n._inputs ) + if( def!=null && !_bs.get(def._nid) ) + add(def); + if( idx==lim ) { // Depth counter changes at limit + if( --d < 0 ) + break; // Ran out of depth + lim = _bfs.size(); // New depth limit + } + } + // Toss things past the limit except multi-heads + while( idx < _bfs.size() ) { + Node n = _bfs.get(idx); + if( n.isMultiHead() ) idx++; + else del(idx); + } + // Root set is any node with no inputs in the visited set + lim = _bfs.size(); + for( int i=_bfs.size()-1; i>=0; i-- ) + if( !any_visited(_bfs.get(i)) ) + swap( i,--lim); + _lim = lim; + } + void swap( int x, int y ) { + if( x==y ) return; + Node tx = _bfs.get(x); + Node ty = _bfs.get(y); + _bfs.set(x,ty); + _bfs.set(y,tx); + } + void add(Node n) { + _bfs.add(n); + _bs.set(n._nid); + } + void del(int idx) { + _bs.clear(_bfs.get(idx)._nid); + Utils.del(_bfs, idx); + } + boolean any_visited( Node n ) { + for( Node def : n._inputs ) + if( def!=null && _bs.get(def._nid) ) + return true; + return false; + } + } + + // Bulk pretty printer, knowing scheduling information is available + public static String prettyPrintScheduled( Node node, int depth, boolean llvmFormat ) { + // Backwards DFS walk to depth. + HashMap<Integer,Integer> ds = new HashMap<>(); + ArrayList<Node> ns = new ArrayList<>(); + _walk(ds,ns,node,depth); + // Remove data projections, these are force-printed behind their multinode head + for( int i=0; i<ns.size(); i++ ) { + if( ns.get(i) instanceof ProjNode proj && !(proj.in(0) instanceof CFGNode) ) { + Utils.del(ns,i--); + ds.remove(proj._nid); + } + } + // Print by block with least idepth + StringBuilder sb = new StringBuilder(); + ArrayList<Node> bns = new ArrayList<>(); + while( !ds.isEmpty() ) { + CFGNode blk = null; + for( Node n : ns ) { + CFGNode cfg = n instanceof CFGNode cfg0 && cfg0.blockHead() ? cfg0 : n.cfg0(); + if( blk==null || cfg.idepth() < blk.idepth() ) + blk = cfg; + } + ds.remove(blk._nid); + ns.remove(blk); + + // Print block header + sb.append("%-13.13s".formatted(label(blk)+":")); + sb.append( " ".repeat(4) ).append(" [[ "); + if( blk instanceof StartNode ) ; + else if( blk instanceof RegionNode || blk instanceof StopNode ) + for( int i=(blk instanceof StopNode ? 0 : 1); i<blk.nIns(); i++ ) + label(sb,blk.cfg(i)); + else + label(sb,blk.cfg(0)); + sb.append(" ]] \n"); + + // Collect block contents that are in the depth limit + bns.clear(); + int xd = Integer.MAX_VALUE; + for( Node use : blk._outputs ) { + Integer i = ds.get(use._nid); + if( i!=null && !(use instanceof CFGNode cfg && cfg.blockHead()) ) { + bns.add(use); + xd = Math.min(xd,i); + } + } + // Print Phis up front, if any + for( int i=0; i<bns.size(); i++ ) + if( bns.get(i) instanceof PhiNode phi ) + printLine( phi, sb, llvmFormat,bns,i--,ds,ns); + + // Print block contents in depth order, bumping depth until whole block printed + for( ; !bns.isEmpty(); xd++ ) + for( int i=0; i<bns.size(); i++ ) { + Node n = bns.get(i); + if( ds.get(n._nid)==xd ) { + printLine( n, sb, llvmFormat, bns, i--, ds,ns ); + if( n instanceof MultiNode && !(n instanceof CFGNode) ) { + for( Node use : n._outputs ) { + printLine(use,sb,llvmFormat,bns,bns.indexOf(use),ds,ns); + } + } + } + } + sb.append("\n"); + } + return sb.toString(); + } + + private static void _walk( HashMap<Integer,Integer> ds, ArrayList<Node> ns, Node node, int d ) { + Integer nd = ds.get(node._nid); + if( nd!=null && d <= nd ) return; // Been there, done that + if( ds.put(node._nid,d) == null ) + ns.add(node); + if( d == 0 ) return; // Depth cutoff + for( Node def : node._inputs ) + if( def != null ) + _walk(ds,ns,def,d-1); + } + + static String label( CFGNode blk ) { + if( blk instanceof StartNode ) return "START"; + return (blk instanceof LoopNode ? "LOOP" : "L")+blk._nid; + } + static void label( StringBuilder sb, CFGNode blk ) { + if( !blk.blockHead() ) blk = blk.cfg(0); + sb.append( "%-9.9s ".formatted( label( blk ) ) ); + } + static void printLine( Node n, StringBuilder sb, boolean llvmFormat, ArrayList<Node> bns, int i, HashMap<Integer,Integer> ds, ArrayList<Node> ns ) { + printLine( n, sb, llvmFormat ); + if( i != -1 ) Utils.del(bns,i); + ds.remove(n._nid); + ns.remove(n); + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/IterPeeps.java b/chapter18/src/main/java/com/seaofnodes/simple/IterPeeps.java new file mode 100644 index 00000000..36f053f9 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/IterPeeps.java @@ -0,0 +1,205 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; + +import java.util.Arrays; +import java.util.BitSet; +import java.util.Random; + +/** + * The IterPeeps runs after parsing. It iterates the peepholes to a fixed point + * so that no more peepholes apply. This should be linear because peepholes rarely + * (never?) increase code size. The graph should monotonically reduce in some + * dimension, which is usually size. It might also reduce in e.g. number of + * MulNodes or Load/Store nodes, swapping out more "expensive" Nodes for cheaper + * ones. + * <br> + * The theoretical overall worklist is mindless just grabbing the next thing and + * doing it. If the graph changes, put the neighbors on the worklist. + * <br> + * Lather, Rinse, Repeat until the worklist runs dry. + * <p> + * The main issues we have to deal with: + * + * <ul> + * <li>Nodes have uses; replacing some set of Nodes with another requires more graph + * reworking. Not rocket science, but it can be fiddly. Its helpful to have a + * small set of graph munging utilities, and the strong invariant that the graph + * is stable and correct between peepholes. In our case `Node.subsume` does + * most of the munging, building on our prior stable Node utilities.</li> + * + * <li>Changing a Node also changes the graph "neighborhood". The neighbors need to + * be checked to see if THEY can also peephole, and so on. After any peephole + * or graph update we put a Nodes uses and defs on the worklist.</li> + * + * <li>Our strong invariant is that for all Nodes, either they are on the worklist + * OR no peephole applies. This invariant is easy to check, although expensive. + * Basically the normal "iterate peepholes to a fixed point" is linear, and this + * check is linear at each peephole step... so quadratic overall. Its a useful + * assert, but one we can disable once the overall algorithm is stable - and + * then turn it back on again when some new set of peepholes is misbehaving. + * The code for this is turned on in `IterPeeps.iterate` as `assert + * progressOnList(stop);`</li> + * </ul> + */ +public abstract class IterPeeps { + + private static final WorkList<Node> WORK = new WorkList<>(); + + public static <N extends Node> N add( N n ) { + return (N)WORK.push(n); + } + + public static void addAll( Ary<Node> ary ) { + WORK.addAll(ary); + } + + /** + * Iterate peepholes to a fixed point + */ + public static StopNode iterate(StopNode stop) { + assert progressOnList(stop); + int cnt=0; + + Node n; + while( (n=WORK.pop()) != null ) { + if( n.isDead() ) continue; + cnt++; // Useful for debugging, searching which peephole broke things + Node x = n.peepholeOpt(); + if( x != null ) { + if( x.isDead() ) continue; + // peepholeOpt can return brand-new nodes, needing an initial type set + if( x._type==null ) x.setType(x.compute()); + // Changes require neighbors onto the worklist + if( x != n || !(x instanceof ConstantNode) ) { + // All outputs of n (changing node) not x (prior existing node). + for( Node z : n._outputs ) WORK.push(z); + // Everybody gets a free "go again" in case they didn't get + // made in their final form. + WORK.push(x); + // If the result is not self, revisit all inputs (because + // there's a new user), and replace in the graph. + if( x != n ) { + for( Node z : n. _inputs ) WORK.push(z); + n.subsume(x); + } + } + // If there are distant neighbors, move to worklist + n.moveDepsToWorklist(); + assert progressOnList(stop); // Very expensive assert + } + if( n.isUnused() && !(n instanceof StopNode) ) + n.kill(); // Just plain dead + } + + return stop; + } + + // Visit ALL nodes and confirm the invariant: + // Either you are on the WORK worklist OR running `iter()` makes no progress. + + // This invariant ensures that no progress is missed, i.e., when the + // worklist is empty we have indeed done all that can be done. To help + // with debugging, the {@code assert} is broken out in a place where it is easy to + // stop if a change is found. + + // Also, the normal usage of `iter()` may attempt peepholes with distance + // neighbors and these should fail, but will then try to add dependencies + // {@link #Node.addDep} which is a side effect in an assert. The {@link + // #midAssert} is used to stop this side effect. + private static boolean MID_ASSERT; + public static boolean midAssert() { return MID_ASSERT; } + private static boolean progressOnList(Node stop) { + MID_ASSERT = true; + int old_cnt = Node.ITER_CNT, old_nop = Node.ITER_NOP_CNT; + Node changed = stop.walk( n -> { + Node m = n; + if( n.compute().isa(n._type) && (!n.iskeep() || n._nid<=5) ) { // Types must be forwards, even if on worklist + if( WORK.on(n) ) return null; + m = n.peepholeOpt(); + if( m==null ) return null; + } + System.err.println("BREAK HERE FOR BUG"); + return m; + }); + Node.ITER_CNT = old_cnt; Node.ITER_NOP_CNT = old_nop; + MID_ASSERT = false; + return changed==null; + } + + public static void reset() { + WORK.clear(); + } + + /** + * Classic WorkList, with a fast add/remove, dup removal, random pull. + * The Node's nid is used to check membership in the worklist. + */ + public static class WorkList<E extends Node> { + + private Node[] _es; + private int _len; + private final BitSet _on; // Bit set if Node._nid is on WorkList + private final Random _R; // For randomizing pull from the WorkList + private final long _seed; + + /* Useful stat - how many nodes are processed in the post parse iterative opt */ + private long _totalWork = 0; + + WorkList() { this(123); } + WorkList(long seed) { + _es = new Node[1]; + _len=0; + _on = new BitSet(); + _seed = seed; + _R = new Random(); + _R.setSeed(_seed); + } + + /** + * Pushes a Node on the WorkList, ensuring no duplicates + * If Node is null it will not be added. + */ + public E push( E x ) { + if( x==null ) return null; + int idx = x._nid; + if( !_on.get(idx) ) { + _on.set(idx); + if( _len==_es.length ) + _es = Arrays.copyOf(_es,_len<<1); + _es[_len++] = x; + _totalWork++; + } + return x; + } + + public void addAll( Ary<E> ary ) { + for( E n : ary ) + push(n); + } + + /** + * True if Node is on the WorkList + */ + boolean on( E x ) { return _on.get(x._nid); } + + /** + * Removes a random Node from the WorkList; null if WorkList is empty + */ + E pop() { + if( _len == 0 ) return null; + int idx = _R.nextInt(_len); + E x = (E)_es[idx]; + _es[idx] = _es[--_len]; // Compress array + _on.clear(x._nid); + return x; + } + + public void clear() { + _len = 0; + _on.clear(); + _R.setSeed(_seed); + _totalWork = 0; + } + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/Parser.java b/chapter18/src/main/java/com/seaofnodes/simple/Parser.java new file mode 100644 index 00000000..1cdf27fb --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/Parser.java @@ -0,0 +1,1427 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.*; + +import java.util.*; + +/** + * The Parser converts a Simple source program to the Sea of Nodes intermediate + * representation directly in one pass. There is no intermediate Abstract + * Syntax Tree structure. + * <p> + * This is a simple recursive descent parser. All lexical analysis is done here as well. + */ +public class Parser { + + /** + * A Global Static, unique to each compilation. This is a public, so we + * can make constants everywhere without having to thread the StartNode + * through the entire parser and optimizer. + * <p> + * To make the compiler multithreaded, this field will have to move into a TLS. + */ + public static StartNode START; + + public static ConstantNode ZERO; // Very common node, cached here + public static XCtrlNode XCTRL; // Very common node, cached here + + // Next available memory alias number + static int ALIAS; + + public StopNode STOP; + + // Debugger Printing. + public static boolean SCHEDULED; // True if debug printer can use schedule info + + // The Lexer. Thin wrapper over a byte[] buffer with a cursor. + private final Lexer _lexer; + + /** + * Current ScopeNode - ScopeNodes change as we parse code, but at any point of time + * there is one current ScopeNode. The reason the current ScopeNode can change is to do with how + * we handle branching. See {@link #parseIf()}. + * <p> + * Each ScopeNode contains a stack of lexical scopes, each scope is a symbol table that binds + * variable names to Nodes. The top of this stack represents current scope. + * <p> + * We keep a list of all ScopeNodes so that we can show them in graphs. + * @see #parseIf() + * @see #_xScopes + */ + public ScopeNode _scope; + + /** + * List of keywords disallowed as identifiers + */ + private static final HashSet<String> KEYWORDS = new HashSet<>(){{ + add("bool"); + add("break"); + add("byte"); + add("continue"); + add("else"); + add("f32"); + add("f64"); + add("false"); + add("flt"); + add("i16"); + add("i32"); + add("i64"); + add("i8"); + add("if"); + add("int"); + add("new"); + add("null"); + add("return"); + add("struct"); + add("true"); + add("u1"); + add("u16"); + add("u32"); + add("u8"); + add("while"); + }}; + + + /** + * We clone ScopeNodes when control flows branch; it is useful to have + * a list of all active ScopeNodes for purposes of visualization of the SoN graph + */ + public final Stack<ScopeNode> _xScopes = new Stack<>(); + + ScopeNode _continueScope; + ScopeNode _breakScope; // Merge all the while-breaks here + + // Mapping from a type name to a Type. The string name matches + // `type.str()` call. No TypeMemPtrs are in here, because Simple does not + // have C-style '*ptr' references. + public static HashMap<String, Type> TYPES; + + // Mapping from a type name to the constructor for a Type. + public final HashMap<String, StructNode> INITS; + + + public Parser(String source, TypeInteger arg) { + Node.reset(); + IterPeeps.reset(); + SCHEDULED = false; + _lexer = new Lexer(source); + _scope = new ScopeNode(); + _continueScope = _breakScope = null; + START = new StartNode(arg); + STOP = new StopNode(source); + ZERO = con(0).keep(); + XCTRL= new XCtrlNode().peephole().keep(); + ALIAS = 2; // alias 0 for the control, 1 for memory + TYPES = defaultTypes(); + INITS = new HashMap<>(); + } + + public Parser(String source) { + this(source, TypeInteger.BOT); + } + + @Override + public String toString() { return _lexer.toString(); } + + public static HashMap<String, Type> defaultTypes() { + return new HashMap<>() {{ + put("bool",TypeInteger.U1 ); + put("byte",TypeInteger.U8 ); + put("f32" ,TypeFloat .B32); + put("f64" ,TypeFloat .BOT); + put("flt" ,TypeFloat .BOT); + put("i16" ,TypeInteger.I16); + put("i32" ,TypeInteger.I32); + put("i64" ,TypeInteger.BOT); + put("i8" ,TypeInteger.I8 ); + put("int" ,TypeInteger.BOT); + put("u1" ,TypeInteger.U1 ); + put("u16" ,TypeInteger.U16); + put("u32" ,TypeInteger.U32); + put("u8" ,TypeInteger.U8 ); + put("val" ,Type.TOP); // Marker type, indicates type inference + put("var" ,Type.BOTTOM); // Marker type, indicates type inference + }}; + } + + // Debugging utility to find a Node by index + public static Node find(int nid) { return START.find(nid); } + + private Node ctrl() { return _scope.ctrl(); } + private <N extends Node> N ctrl(N n) { return _scope.ctrl(n); } + + public StopNode parse() { return parse(false); } + public StopNode parse(boolean show) { + _xScopes.push(_scope); + // Enter a new scope for the initial control and arguments + _scope.push(); + ScopeMinNode mem = new ScopeMinNode(); + mem.addDef(null); + _scope.define(ScopeNode.CTRL, Type.CONTROL , false, new CProjNode(START, 0, ScopeNode.CTRL).peephole()); + mem.addDef( new ProjNode(START, 1, ScopeNode.MEM0).peephole()); + _scope.define(ScopeNode.MEM0, TypeMem.TOP , false, mem .peephole()); + _scope.define(ScopeNode.ARG0, TypeInteger.BOT, false, new ProjNode(START, 2, ScopeNode.ARG0).peephole()); + + // Parse whole program + parseBlock(false); + + if( ctrl()._type==Type.CONTROL ) + STOP.addReturn(new ReturnNode(ctrl(), ZERO, _scope).peephole()); + _scope.kill(); + _xScopes.pop(); + for( StructNode init : INITS.values() ) + init.unkeep().kill(); + INITS.clear(); + if (!_lexer.isEOF()) throw error("Syntax error, unexpected " + _lexer.getAnyNextToken()); + STOP.peephole(); + if( show ) showGraph(); + return STOP; + } + + /** + * Parses a block + * + * <pre> + * '{' statements '}' + * </pre> + * Does not parse the opening or closing '{}' + * @return a {@link Node} or {@code null} + */ + private Node parseBlock(boolean inCon) { + // Enter a new scope + _scope.push(inCon); + while (!peek('}') && !_lexer.isEOF()) + parseStatement(); + // Exit scope + _scope.pop(); + return null; + } + + /** + * Parses a statement + * + * <pre> + * returnStatement | declStatement | blockStatement | ifStatement | expressionStatement + * </pre> + * @return a {@link Node} or {@code null} + */ + private Node parseStatement() { + if( false ) return null; + else if (matchx("return") ) return parseReturn(); + else if (match ("{") ) return require(parseBlock(false),"}"); + else if (matchx("if") ) return parseIf(); + else if (matchx("while") ) return parseWhile(); + else if (matchx("for") ) return parseFor(); + else if (matchx("break") ) return parseBreak(); + else if (matchx("continue")) return parseContinue(); + else if (matchx("struct") ) return parseStruct(); + else if (matchx("#showGraph")) return require(showGraph(),";"); + else if (matchx(";") ) return null; // Empty statement + // Declaration or normal assignment/expression + else return parseDeclarationStatement(); + } + + /** + * Parses a while statement + * + * <pre> + * while ( expression ) statement + * </pre> + * @return a {@link Node}, never {@code null} + */ + private Node parseWhile() { + require("("); + return parseLooping(false); + } + + + /** + * Parses a for statement + * + * <pre> + * for( var x=init; test; incr ) body + * </pre> + * @return a {@link Node}, never {@code null} + */ + private Node parseFor() { + // { var x=init,y=init,...; + // while( pred ) { + // body; + // next; + // } + // } + require("("); + _scope.push(); // Scope for the index variables + if( !match(";") ) // Can be empty init "for(;test;next) body" + parseDeclarationStatement(); // Non-empty init + Node rez = parseLooping(true); + _scope.pop(); // Exit index variable scope + return rez; + } + + // Shared by `for` and `while` + private Node parseLooping( boolean doFor ) { + + var savedContinueScope = _continueScope; + var savedBreakScope = _breakScope; + + // Loop region has two control inputs, the first is the entry + // point, and second is back edge that is set after loop is parsed + // (see end_loop() call below). Note that the absence of back edge is + // used as an indicator to switch off peepholes of the region and + // associated phis; see {@code inProgress()}. + + ctrl(new LoopNode(ctrl()).peephole()); // Note we set back edge to null here + + // At loop head, we clone the current Scope (this includes all + // names in every nesting level within the Scope). + // We create phis eagerly for all the names we find, see dup(). + + // Save the current scope as the loop head + ScopeNode head = _scope.keep(); + // Clone the head Scope to create a new Scope for the body. + // Create phis eagerly as part of cloning + _xScopes.push(_scope = _scope.dup(true)); // The true argument triggers creating phis + + // Parse predicate + var pred = peek(';') ? con(1) : parseAsgn(); + require( doFor ? ";" : ")" ); + + // IfNode takes current control and predicate + Node ifNode = new IfNode(ctrl(), pred.keep()).peephole(); + // Setup projection nodes + Node ifT = new CProjNode(ifNode. keep(), 0, "True" ).peephole().keep(); + Node ifF = new CProjNode(ifNode.unkeep(), 1, "False").peephole(); + + // for( ;;next ) body + int nextPos = -1, nextEnd = -1; + if( doFor ) { + // Skip the next expression and parse it later + nextPos = pos(); + skipAsgn(); + nextEnd = pos(); + require(")"); + } + + // Clone the body Scope to create the break/exit Scope which accounts for any + // side effects in the predicate. The break/exit Scope will be the final + // scope after the loop, and its control input is the False branch of + // the loop predicate. Note that body Scope is still our current scope. + ctrl(ifF); + _xScopes.push(_breakScope = _scope.dup()); + _breakScope.addGuards(ifF,pred,true); // Up-cast predicate + + // No continues yet + _continueScope = null; + + // Parse the true side, which corresponds to loop body + // Our current scope is the body Scope + ctrl(ifT.unkeep()); // set ctrl token to ifTrue projection + _scope.addGuards(ifT,pred.unkeep(),false); // Up-cast predicate + parseStatement(); // Parse loop body + _scope.removeGuards(ifT); + + // Merge the loop bottom into other continue statements + if (_continueScope != null) { + _continueScope = jumpTo(_continueScope); + _scope.kill(); + _scope = _continueScope; + } + + // Now append the next code onto the body code + if( doFor ) { + int old = pos(nextPos); + if( !peek(')') ) + parseAsgn(); + if( pos() != nextEnd ) + throw errorSyntax( "Unexpected code after expression" ); + pos(old); + } + + // The true branch loops back, so whatever is current _scope.ctrl gets + // added to head loop as input. endLoop() updates the head scope, and + // goes through all the phis that were created earlier. For each phi, + // it sets the second input to the corresponding input from the back + // edge. If the phi is redundant, it is replaced by its sole input. + var exit = _breakScope; + head.endLoop(_scope, exit); + head.unkeep().kill(); + + _xScopes.pop(); // Cleanup + _xScopes.pop(); // Cleanup + + _continueScope = savedContinueScope; + _breakScope = savedBreakScope; + + // At exit the false control is the current control, and + // the scope is the exit scope after the exit test. + _xScopes.pop(); + _xScopes.push(exit); + _scope = exit; + return _scope; + } + + private ScopeNode jumpTo(ScopeNode toScope) { + ScopeNode cur = _scope.dup(); + ctrl(XCTRL); // Kill current scope + // Prune nested lexical scopes that have depth > than the loop head + // We use _breakScope as a proxy for the loop head scope to obtain the depth + while( cur._lexSize.size() > _breakScope._lexSize.size() ) + cur.pop(); + // If this is a continue then first time the target is null + // So we just use the pruned current scope as the base for the + // "continue" + if( toScope == null ) + return cur; + // toScope is either the break scope, or a scope that was created here + assert toScope._lexSize.size() <= _breakScope._lexSize.size(); + toScope.ctrl(toScope.mergeScopes(cur).peephole()); + return toScope; + } + + private void checkLoopActive() { if (_breakScope == null) throw Parser.error("No active loop for a break or continue"); } + + private Node parseContinue() { checkLoopActive(); return (_continueScope = require(jumpTo( _continueScope ),";")); } + private Node parseBreak () { + checkLoopActive(); + // At the time of the break, and loop-exit conditions are only valid if + // they are ALSO valid at the break. It is the intersection of + // conditions here, not the union. + _breakScope.removeGuards(_breakScope.ctrl()); + _breakScope = require(jumpTo(_breakScope ),";"); + _breakScope.addGuards(_breakScope.ctrl(), null, false); + return _breakScope; + } + + // Look for an unbalanced `)`, skipping balanced + private Type skipAsgn() { + int paren=0; + while( true ) + // Next X char handles skipping complex comments + switch( _lexer.nextXChar() ) { + case Character.MAX_VALUE: + throw Utils.TODO(); + case ')': + if( --paren<0 ) + return posT(pos()-1); // Leave the `)` behind + break; + case '(': paren ++; break; + default: break; + } + } + + + /** + * Parses a statement + * + * <pre> + * if ( expression ) statement [else statement] + * </pre> + * @return a {@link Node}, never {@code null} + */ + private Node parseIf() { + // Parse predicate + require("("); + var pred = require(parseAsgn(), ")"); + return parseTrinary(pred,true,"else"); + } + + // Parse a conditional expression, merging results. + private Node parseTrinary( Node pred, boolean stmt, String fside ) { + pred.keep(); + + // IfNode takes current control and predicate + Node ifNode = new IfNode(ctrl(), pred).peephole(); + // Setup projection nodes + Node ifT = new CProjNode(ifNode. keep(), 0, "True" ).peephole().keep(); + Node ifF = new CProjNode(ifNode.unkeep(), 1, "False").peephole().keep(); + // In if true branch, the ifT proj node becomes the ctrl + // But first clone the scope and set it as current + int ndefs = _scope.nIns(); + ScopeNode fScope = _scope.dup(); // Duplicate current scope + _xScopes.push(fScope); // For graph visualization we need all scopes + + // Parse the true side + ctrl(ifT.unkeep()); // set ctrl token to ifTrue projection + _scope.addGuards(ifT,pred,false); // Up-cast predicate + Node lhs = stmt ? parseStatement() : parseAsgn().keep(); // Parse true-side + _scope.removeGuards(ifT); + + ScopeNode tScope = _scope; + + // Parse the false side + _scope = fScope; // Restore scope, then parse else block if any + ctrl(ifF.unkeep()); // Ctrl token is now set to ifFalse projection + // Up-cast predicate, even if not else clause, because predicate can + // remain true if the true clause exits: `if( !ptr ) return 0; return ptr.fld;` + _scope.addGuards(ifF,pred,true); + boolean doRHS = match(fside); + Node rhs = doRHS + ? (stmt ? parseStatement() : parseAsgn()) + : (stmt ? null : con(lhs._type.makeZero())); + _scope.removeGuards(ifF); + if( doRHS ) + fScope = _scope; + pred.unkeep(); + + // Check for `if(pred) int x=17;` + if( tScope.nIns() != ndefs || fScope.nIns() != ndefs ) + throw error("Cannot define a new name on one arm of an if"); + + // Check the trinary widening int/flt + if( !stmt ) { + rhs = widenInt( rhs, lhs._type ).keep(); + lhs = widenInt( lhs.unkeep(), rhs._type ).keep(); + rhs.unkeep(); + } + + // Merge results + _scope = tScope; + _xScopes.pop(); // Discard pushed from graph display + + RegionNode r = ctrl(tScope.mergeScopes(fScope)); + Node ret = stmt ? r : peep(new PhiNode("",lhs._type.meet(rhs._type),r,lhs.unkeep(),rhs)); + r.peephole(); + return ret; + } + + /** + * Parses a return statement; "return" already parsed. + * The $ctrl edge is killed. + * + * <pre> + * 'return' expr ; + * </pre> + * @return an expression {@link Node}, never {@code null} + */ + private Node parseReturn() { + var expr = require(parseAsgn(), ";"); + Node ret = STOP.addReturn(new ReturnNode(ctrl(), expr, _scope).peephole()); + ctrl(XCTRL); // Kill control + return ret; + } + + /** + * Dumps out the node graph + * @return {@code null} + */ + Node showGraph() { + System.out.println(new GraphVisualizer().generateDotOutput(STOP,_scope,_xScopes)); + return null; + } + + /** Parse: [name '='] expr + */ + private Node parseAsgn() { + int old = pos(); + String name = _lexer.matchId(); + // Just a plain expression, no assignment. + // Distinguish `var==expr` from `var=expr` + if( name==null || KEYWORDS.contains(name) || !matchOpx('=','=') ) + { pos(old); return parseExpression(); } + + // Parse assignment expression + Node expr = parseAsgn(); + + // Final variable to update + ScopeMinNode.Var def = _scope.lookup(name); + if( def==null ) + throw error("Undefined name '" + name + "'"); + + // TOP fields are for late-initialized fields; these have never + // been written to, and this must be the final write. Other writes + // outside the constructor need to check the final bit. + if( _scope.in(def._idx)._type!=Type.TOP && def._final && !_scope.inCon() ) + throw error("Cannot reassign final '"+name+"'"); + + // Lift expression, based on type + Node lift = liftExpr(expr, def.type(), def._final); + // Update + _scope.update(name,lift); + // Return un-lifted expr + return expr; + } + + // Make finals deep; widen ints to floats; narrow wide int types. + // Early error if types do not match variable. + private Node liftExpr( Node expr, Type t, boolean xfinal ) { + assert !(expr._type instanceof TypeMemPtr tmp) || !tmp.isFRef(); + // Final is deep on ptrs + if( xfinal && t instanceof TypeMemPtr tmp ) { + t = tmp.makeRO(); + expr = peep(new ReadOnlyNode(expr)); + } + // Auto-widen int to float + expr = widenInt( expr, t ); + // Auto-narrow wide ints to narrow ints + expr = zsMask(expr,t); + // Type is sane + if( !expr._type.isa(t) ) + throw error("Type " + expr._type.str() + " is not of declared type " + t.str()); + return expr; + } + + private Node widenInt( Node expr, Type t ) { + return expr._type instanceof TypeInteger && t instanceof TypeFloat + ? peep(new ToFloatNode(expr)) : expr; + } + + /** + * Parse declaration or expression statement + * declStmt = type var['=' exprAsgn][, var['=' exprAsgn]]* ';' | exprAsgn ';' + * <p> + * exprAsgn = var '=' exprAsgn | expr + */ + private Node parseDeclarationStatement() { + Type t = type(); + if( t == null ) + return require(parseAsgn(),";"); + + // now parse var['=' asgnexpr] in a loop + Node n = parseDeclaration(t); + while( match(",") ) + n = parseDeclaration(t); + return require(n,";"); + } + + /** Parse final: [!]var['=' asgn] + */ + private Node parseDeclaration(Type t) { + assert t!=null; + // Has var/val instead of a user-declared type + boolean inferType = t==Type.TOP || t==Type.BOTTOM; + boolean hasBang = match("!"); + String name = requireId(); + + // Optional initializing expression follows + boolean xfinal = false; + Node expr; + if( match("=") ) { + expr = parseAsgn(); + // `val` is always final + xfinal = (t==Type.TOP) || + // var is always not-final, final if no Bang AND TMP since primitives are not-final by default + (t!=Type.BOTTOM && !hasBang && (t instanceof TypeMemPtr)); + // var/val, then type comes from expression + if( inferType ) + t = expr._type.glb(); + + } else { + if( inferType && !_scope.inCon() ) + throw errorSyntax("=expression"); + expr = con(t.makeInit()); + } + + // Lift expression, based on type + Node lift = liftExpr(expr, t, xfinal); + if( xfinal && t instanceof TypeMemPtr tmp ) + t = tmp.makeRO(); + + // Define a new name, + if( !_scope.define(name,t,xfinal,lift) ) + throw error("Redefining name '" + name + "'"); + return null; + } + + + + /** + * Parse a struct declaration, and return the following statement. + * Only allowed in top level scope. + * Structs cannot be redefined. + * + * @return The statement following the struct + */ + private Node parseStruct() { + if (_xScopes.size() > 1) throw errorSyntax("struct declarations can only appear in top level scope"); + String typeName = requireId(); + Type t = TYPES.get(typeName); + if( t!=null && !(t instanceof TypeMemPtr tmp && tmp.isFRef() ) ) + throw errorSyntax("struct '" + typeName + "' cannot be redefined"); + + // A Block scope parse, and inspect the scope afterward for fields. + _scope.push(true); + _xScopes.push(_scope); + require("{"); + while (!peek('}') && !_lexer.isEOF()) + parseStatement(); + + // Grab the declarations and build fields and a Struct + int lexlen = _scope._lexSize.last(); + int varlen = _scope._vars._len; + StructNode s = new StructNode(); + Field[] fs = new Field[varlen-lexlen]; + for( int i=lexlen; i<varlen; i++ ) { + s.addDef(_scope.in(i)); + ScopeMinNode.Var v = _scope._vars.at(i); + fs[i-lexlen] = Field.make(v._name,v.type(),ALIAS++,v._final); + } + TypeStruct ts = s._ts = TypeStruct.make(typeName, fs); + TYPES.put(typeName, TypeMemPtr.make(ts)); + INITS.put(typeName,s.peephole().keep()); + // Done with struct/block scope + require("}"); + require(";"); + _xScopes.pop(); + _scope.pop(); + return null; + } + + + // Parse and return a type or null. Valid types always are followed by an + // 'id' which the caller must parse. This lets us distinguish forward ref + // types (which ARE valid here) from local vars in an (optional) forward + // ref type position. + + // t = int|i8|i16|i32|i64|u8|u16|u32|u64|byte|bool | flt|f32|f64 | val | var | struct[?] + private Type type() { + int old1 = pos(); + String tname = _lexer.matchId(); + if( tname==null ) return null; + // Convert the type name to a type. + Type t0 = TYPES.get(tname); + // No new types as keywords + if( t0 == null && KEYWORDS.contains(tname) ) + return posT(old1); + Type t1 = t0 == null ? TypeMemPtr.make(TypeStruct.makeFRef(tname)) : t0; // Null: assume a forward ref type + // Nest arrays and '?' as needed + Type t2 = t1; + while( true ) { + assert !(t2 instanceof TypeStruct); + if( match("?") ) { + if( !(t2 instanceof TypeMemPtr tmp) ) + throw error("Type "+t0+" cannot be null"); + if( tmp._nil ) throw error("Type "+t2+" already allows null"); + t2 = TypeMemPtr.make(tmp._obj,true); + } else if( match("[]") ) { + t2 = typeAry(t2); + } else + break; + } + + // Check no forward ref + if( t0 != null ) return t2; + // Check valid forward ref, after parsing all the type extra bits. + // Cannot check earlier, because cannot find required 'id' until after "[]?" syntax + int old2 = pos(); + String id = _lexer.matchId(); + pos(old2); // Reset lexer to reparse + if( id==null || _scope.lookup(id)!=null ) + return posT(old1); // Reset lexer to reparse + // Yes a forward ref, so declare it + TYPES.put(tname,t1); + return t2; + } + + // Make an array type of t + private TypeMemPtr typeAry( Type t ) { + if( t instanceof TypeMemPtr tmp && !tmp._nil ) + throw error("Arrays of reference types must always be nullable"); + String tname = "["+t.str()+"]"; + Type ta = TYPES.get(tname); + if( ta != null ) return (TypeMemPtr)ta; + // Need make an array type. + TypeStruct ts = TypeStruct.makeAry(TypeInteger.BOT,ALIAS++,t,ALIAS++); + assert ts.str().equals(tname); + TypeMemPtr tary = TypeMemPtr.make(ts); + TYPES.put(tname,tary); + return tary; + } + + // Fixup forward refs lazily. Basically a Union-Find flavored read + // barrier. + Type lazyFRef(Type t) { + //if( !t.isFRef() ) return t; + //Type def = Parser.TYPES.get(((TypeMemPtr)t)._obj._name); + throw Utils.TODO(); + + } + + + /** + * Parse an expression of the form: + * + * <pre> + * expr : bitwise [? expr [: expr]] + * </pre> + * @return an expression {@link Node}, never {@code null} + */ + private Node parseExpression() { + Node expr = parseBitwise(); + return match("?") ? parseTrinary(expr,false,":") : expr; + } + + /** + * Parse an bitwise expression + * + * <pre> + * bitwise : compareExpr (('&' | '|' | '^') compareExpr)* + * </pre> + * @return a bitwise expression {@link Node}, never {@code null} + */ + private Node parseBitwise() { + Node lhs = parseComparison(); + while( true ) { + if( false ) ; + else if( match("&") ) lhs = new AndNode(lhs,null); + else if( match("|") ) lhs = new OrNode(lhs,null); + else if( match("^") ) lhs = new XorNode(lhs,null); + else break; + lhs.setDef(2,parseComparison()); + lhs = peep(lhs); + } + return lhs; + } + + /** + * Parse an expression of the form: + * + * <pre> + * expr : additiveExpr op additiveExpr + * </pre> + * @return an comparator expression {@link Node}, never {@code null} + */ + private Node parseComparison() { + var lhs = parseShift(); + while( true ) { + int idx=0; boolean negate=false; + // Test for any local nodes made, and "keep" lhs during peepholes + if( false ) ; + else if( match("==") ) { idx=2; lhs = new BoolNode.EQ(lhs, null); } + else if( match("!=") ) { idx=2; lhs = new BoolNode.EQ(lhs, null); negate=true; } + else if( match("<=") ) { idx=2; lhs = new BoolNode.LE(lhs, null); } + else if( match("<" ) ) { idx=2; lhs = new BoolNode.LT(lhs, null); } + else if( match(">=") ) { idx=1; lhs = new BoolNode.LE(null, lhs); } + else if( match(">" ) ) { idx=1; lhs = new BoolNode.LT(null, lhs); } + else break; + // Peepholes can fire, but lhs is already "hooked", kept alive + lhs.setDef(idx,parseShift()); + lhs = peep(lhs.widen()); + if( negate ) // Extra negate for != + lhs = peep(new NotNode(lhs)); + } + return lhs; + } + + /** + * Parse an additive expression + * + * <pre> + * shiftExpr : additiveExpr (('<<' | '>>' | '>>>') additiveExpr)* + * </pre> + * @return a shift expression {@link Node}, never {@code null} + */ + private Node parseShift() { + Node lhs = parseAddition(); + while( true ) { + if( false ) ; + else if( match("<<") ) lhs = new ShlNode(lhs,null); + else if( match(">>>")) lhs = new ShrNode(lhs,null); + else if( match(">>") ) lhs = new SarNode(lhs,null); + else break; + lhs.setDef(2,parseAddition()); + lhs = peep(lhs.widen()); + } + return lhs; + } + + /** + * Parse an additive expression + * + * <pre> + * additiveExpr : multiplicativeExpr (('+' | '-') multiplicativeExpr)* + * </pre> + * @return an add expression {@link Node}, never {@code null} + */ + private Node parseAddition() { + Node lhs = parseMultiplication(); + while( true ) { + if( false ) ; + else if( match("+") ) lhs = new AddNode(lhs,null); + else if( match("-") ) lhs = new SubNode(lhs,null); + else break; + lhs.setDef(2,parseMultiplication()); + lhs = peep(lhs.widen()); + } + return lhs; + } + + /** + * Parse an multiplicativeExpr expression + * + * <pre> + * multiplicativeExpr : unaryExpr (('*' | '/') unaryExpr)* + * </pre> + * @return a multiply expression {@link Node}, never {@code null} + */ + private Node parseMultiplication() { + var lhs = parseUnary(); boolean mul; + while( true ) { + if( false ) ; + else if( match("*") ) lhs = new MulNode(lhs,null); + else if( match("/") ) lhs = new DivNode(lhs,null); + else break; + lhs.setDef(2,parseUnary()); + lhs = peep(lhs.widen()); + } + return lhs; + } + + /** + * Parse a unary minus expression. + * + * <pre> + * unaryExpr : ('-') unaryExpr | '!') unaryExpr | postfixExpr | primaryExpr | '--' Id | '++' Id + * </pre> + * @return a unary expression {@link Node}, never {@code null} + */ + private Node parseUnary() { + // Pre-dec/pre-inc + int old = pos(); + if( match("--") || match("++") ) { + int delta = _lexer.peek(-1)=='+' ? 1 : -1; // Pre vs post + String name = _lexer.matchId(); + if( name!=null ) { + ScopeMinNode.Var n = _scope.lookup(name); + if( n != null ) { + if( n._final ) + throw error("Cannot reassign final '"+n._name+"'"); + Node expr = zsMask(peep(new AddNode(_scope.in(n),con(delta))),n.type()); + _scope.update(n,expr); + return expr; + } + } + // Reset, try again + pos(old); + } + if (match("-")) return peep(new MinusNode(parseUnary()).widen()); + if (match("!")) return peep(new NotNode(parseUnary())); + return parsePostfix(parsePrimary()); + } + + /** + * Parse a primary expression: + * + * <pre> + * primaryExpr : integerLiteral | true | false | null | new Type | '(' expression ')' | Id['++','--'] + * </pre> + * @return a primary {@link Node}, never {@code null} + */ + private Node parsePrimary() { + if( _lexer.isNumber(_lexer.peek()) ) return parseLiteral(); + if( matchx("true" ) ) return con(1); + if( matchx("false") ) return ZERO; + if( matchx("null" ) ) return con(TypeMemPtr.NULLPTR); + if( match("(") ) return require(parseAsgn(), ")"); + if( matchx("new" ) ) return alloc(); + // Expect an identifier now + ScopeMinNode.Var n = requireLookupId("an identifier or expression"); + Node rvalue = _scope.in(n); + if( rvalue._type == Type.BOTTOM ) + throw error("Cannot read uninitialized field '"+n._name+"'"); + // Check for assign-update, x += e0; + char ch = _lexer.matchOperAssign(); + if( ch==0 ) return rvalue; + if( n._final ) + throw error("Cannot reassign final '"+n._name+"'"); + Node op = switch(ch) { + case '+' -> new AddNode(rvalue,null); + case '-' -> new SubNode(rvalue,null); + case '*' -> new MulNode(rvalue,null); + case '/' -> new DivNode(rvalue,null); + case 1 -> new AddNode(rvalue,con( 1)); + case (char)-1 -> new AddNode(rvalue,con(-1)); + default -> throw Utils.TODO(); + }; + // Return pre-value (x+=1) or post-value (x++) + boolean pre = op.in(2)==null; + // Parse RHS argument as needed + if( pre ) + { op.keep().setDef(2,parseAsgn()); op.unkeep(); } + else rvalue.keep(); // Keep post-value across peeps + op = zsMask(peep(op),n.type()); + _scope.update(n,op); + return pre ? op : rvalue.unkeep(); + } + + ScopeMinNode.Var requireLookupId(String msg) { + String id = _lexer.matchId(); + if( id == null || KEYWORDS.contains(id) ) + throw errorSyntax(msg); + ScopeMinNode.Var n = _scope.lookup(id); + if( n==null ) + throw error("Undefined name '" + id + "'"); + return n; + } + + /** + Parse an allocation + */ + private Node alloc() { + Type t = type(); + if( t==null ) throw error("Expected a type"); + // Parse ary[ length_expr ] + if( match("[") ) { + Node len = parseAsgn(); + if( !(len._type instanceof TypeInteger) ) + throw error("Cannot allocate an array with length "+len._type); + require("]"); + TypeMemPtr tmp = typeAry(t); + return newArray(tmp._obj,len); + } + + if( !(t instanceof TypeMemPtr tmp) ) + throw error("Cannot allocate a "+t.str()); + + // Parse new struct { default_initialization } + StructNode s = INITS.get(tmp._obj._name); + if( s==null ) throw error("Unknown struct type '" + tmp._obj._name + "'"); + + Field[] fs = s._ts._fields; + // if the object is fully initialized, we can skip a block here. + // Check for constructor block: + boolean hasConstructor = match("{"); + Ary<Node> init=s._inputs; int idx=0; + if( hasConstructor ) { + idx = _scope.nIns(); + // Push a scope, and pre-assign all struct fields. + _scope.push(); + for( int i=0; i<fs.length; i++ ) + _scope.define(fs[i]._fname, fs[i]._type, fs[i]._final, s.in(i)._type==Type.TOP ? con(Type.BOTTOM) : s.in(i)); + // Parse the constructor body + parseBlock(true); + require("}"); + init = _scope._inputs; + } + // Check that all fields are initialized + for( int i=idx; i<init.size(); i++ ) + if( /*init.at(i)._type == Type.TOP ||*/ init.at(i)._type == Type.BOTTOM ) + throw error("'"+tmp._obj._name+"' is not fully initialized, field '" + fs[i-idx]._fname + "' needs to be set in a constructor"); + Node ptr = newStruct(tmp._obj, con(tmp._obj.offset(fs.length)), idx, init ); + if( hasConstructor ) + _scope.pop(); + return ptr; + } + + + /** + * Return a NewNode initialized memory. + * @param obj is the declared type, with GLB fields + * @param init is a collection of initialized fields + */ + private Node newStruct( TypeStruct obj, Node size, int idx, Ary<Node> init ) { + Field[] fs = obj._fields; + if( fs==null ) + throw error("Unknown struct type '" + obj._name + "'"); + int len = fs.length; + Node[] ns = new Node[2+len+len]; + ns[0] = ctrl(); // Control in slot 0 + // Total allocated length in bytes + ns[1] = size; + // Memory aliases for every field + for( int i = 0; i < len; i++ ) + ns[2 +i] = memAlias(fs[i]._alias); + // Initial values for every field + for( int i = 0; i < len; i++ ) + ns[2+len+i] = init.get(i+idx); + Node nnn = new NewNode(TypeMemPtr.make(obj), ns).peephole(); + for( int i = 0; i < len; i++ ) + memAlias(fs[i]._alias, new ProjNode(nnn,i+2,memName(fs[i]._alias)).peephole()); + return new ProjNode(nnn,1,obj._name).peephole(); + } + + private static final Ary<Node> ALTMP = new Ary<>(Node.class); + private Node newArray(TypeStruct ary, Node len) { + int base = ary.aryBase (); + int scale= ary.aryScale(); + Node size = peep(new AddNode(con(base),peep(new ShlNode(len.keep(),con(scale))))); + ALTMP.clear(); ALTMP.add(len.unkeep()); ALTMP.add(con(ary._fields[1]._type.makeInit())); + return newStruct(ary,size,0,ALTMP); + } + + // We set up memory aliases by inserting special vars in the scope these + // variables are prefixed by $ so they cannot be referenced in Simple code. + // Using vars has the benefit that all the existing machinery of scoping + // and phis work as expected + private Node memAlias(int alias ) { return _scope.mem(alias ); } + private void memAlias(int alias, Node st) { _scope.mem(alias, st); } + public static String memName(int alias) { return ("$"+alias).intern(); } + + /** + * Parse postfix expression. For now this is just a field + * expression, but in future could be array index too. + * + * <pre> + * expr ('.' IDENTIFIER)* [ = expr ] + * expr # + * expr ('[' expr ']')* = [ = expr ] + * </pre> + */ + private Node parsePostfix(Node expr) { + String name = null; + if( match(".") ) name = requireId(); + else if( match("#") ) name = "#"; + else if( match("[") ) name = "[]"; + else return expr; // No postfix + + // Sanity check expr for being a reference + if( !(expr._type instanceof TypeMemPtr ptr) ) + throw error("Expected reference but got " + expr._type.str()); + + // Happens when parsing known dead code, which often has other typing + // issues. Since the code is dead, possibly due to inlining, lets not + // spoil the user experience with error messages. + if( ctrl()._type==Type.XCONTROL ) + // Exit out via parsing the trailing expression + return matchOpx('=','=') ? parseAsgn() : parsePostfix(con(Type.TOP)); + + // Sanity check field name for existing + TypeMemPtr tmp = (TypeMemPtr)TYPES.get(ptr._obj._name); + if( tmp == null ) throw error("Accessing unknown field '" + name + "' from '" + ptr + "'"); + TypeStruct base = tmp._obj; + int fidx = base.find(name); + if( fidx == -1 ) throw error("Accessing unknown field '" + name + "' from '" + ptr.str() + "'"); + + // Get field type and layout offset from base type and field index fidx + Field f = base._fields[fidx]; // Field from field index + Type tf = f._type; + if( tf instanceof TypeMemPtr ftmp && ftmp.isFRef() ) + tf = ftmp.makeFrom(((TypeMemPtr)(TYPES.get(ftmp._obj._name)))._obj); + + // Field offset; fixed for structs, computed for arrays + Node off = (name.equals("[]") // If field is an array body + // Array index math + ? peep(new AddNode(con(base.aryBase()),peep(new ShlNode(require(parseAsgn(),"]"),con(base.aryScale()))))) + // Struct field offsets are hardwired + : con(base.offset(fidx))).keep(); + + // Disambiguate "obj.fld==x" boolean test from "obj.fld=x" field assignment + if( matchOpx('=','=') ) { + Node val = parseAsgn().keep(); + Node lift = liftExpr( val, tf, f._final ); + + Node st = new StoreNode(name, f._alias, tf, memAlias(f._alias), expr, off.unkeep(), lift, false); + // Arrays include control, as a proxy for a safety range check. + // Structs don't need this; they only need a NPE check which is + // done via the type system. + if( base.isAry() ) st.setDef(0,ctrl()); + memAlias(f._alias, st.peephole()); + return val.unkeep(); // "obj.a = expr" returns the expression while updating memory + } + + Node load = new LoadNode(name, f._alias, tf.glb(), memAlias(f._alias), expr.keep(), off); + // Arrays include control, as a proxy for a safety range check + // Structs don't need this; they only need a NPE check which is + // done via the type system. + if( base.isAry() ) load.setDef(0,ctrl()); + load = peep(load); + + // ary[idx]++ or ptr.fld++ + if( matchx("++") || matchx("--") ) { + if( f._final && !f._fname.equals("[]") ) + throw error("Cannot reassign final '"+f._fname+"'"); + Node inc = peep(new AddNode(load,con( _lexer.peek(-1)=='+' ? 1 : -1))); + Node val = zsMask(inc,tf); + Node st = new StoreNode(name, f._alias, tf, memAlias(f._alias), expr.unkeep(), off, val, false); + // Arrays include control, as a proxy for a safety range check. + // Structs don't need this; they only need a NPE check which is + // done via the type system. + if( base.isAry() ) st.setDef(0,ctrl()); + memAlias(f._alias, peep(st)); + // And use the original loaded value as the result + } else expr.unkill(); + off.unkill(); + + return parsePostfix(load); + } + + + // zero/sign extend. "i" is limited to either classic unsigned (min==0) or + // classic signed (min=minus-power-of-2); max=power-of-2-minus-1. + private Node zsMask(Node val, Type t ) { + if( !(val._type instanceof TypeInteger tval && t instanceof TypeInteger t0 && !tval.isa(t0)) ) { + if( !(val._type instanceof TypeFloat tval && t instanceof TypeFloat t0 && !tval.isa(t0)) ) + return val; + // Float rounding + return peep(new RoundF32Node(val)); + } + if( t0._min==0 ) // Unsigned + return peep(new AndNode(val,con(t0._max))); + // Signed extension + int shift = Long.numberOfLeadingZeros(t0._max)-1; + Node shf = con(shift); + if( shf._type==TypeInteger.ZERO ) + return val; + return peep(new SarNode(peep(new ShlNode(val,shf.keep())),shf.unkeep())); + } + + + /** + * Parse integer literal + * + * <pre> + * integerLiteral: [1-9][0-9]* | [0] + * floatLiteral: [digits].[digits]?[e [digits]]? + * </pre> + */ + private ConstantNode parseLiteral() { return con(_lexer.parseNumber()); } + public static Node con( long con ) { return con(TypeInteger.constant(con)); } + public static ConstantNode con( Type t ) { return (ConstantNode)new ConstantNode(t).peephole(); } + public Node peep( Node n ) { + // Peephole, then improve with lexically scoped guards + return _scope.upcastGuard(n.peephole()); + } + + ////////////////////////////////// + // Utilities for lexical analysis + + // Return true and skip if "syntax" is next in the stream. + private boolean match (String syntax) { return _lexer.match (syntax); } + // Match must be "exact", not be followed by more id letters + private boolean matchx(String syntax) { return _lexer.matchx(syntax); } + private boolean matchOpx(char c0, char c1) { return _lexer.matchOpx(c0,c1); } + // Return true and do NOT skip if 'ch' is next + private boolean peek(char ch) { return _lexer.peek(ch); } + private boolean peekIsId() { return _lexer.peekIsId(); } + + private int pos() { return _lexer._position; } + private int pos(int pos) { + int old = _lexer._position; + _lexer._position = pos; + return old; + } + private Type posT(int pos) { _lexer._position = pos; return null; } + + // Require and return an identifier + private String requireId() { + String id = _lexer.matchId(); + if (id != null && !KEYWORDS.contains(id) ) return id.intern(); + throw error("Expected an identifier, found '"+id+"'"); + } + + private String matchId() { + int old = pos(); + String id = _lexer.matchId(); + if( id==null ) return null; + if( !KEYWORDS.contains(id) ) return id; + pos(old); + return null; + } + + // Require an exact match + private Parser require(String syntax) { require(null, syntax); return this; } + private <N> N require(N n, String syntax) { + if (match(syntax)) return n; + throw errorSyntax(syntax); + } + + RuntimeException errorSyntax(String syntax) { + return error("Syntax error, expected " + syntax + ": " + _lexer.getAnyNextToken()); + } + + public static RuntimeException error( String errorMessage ) { + return new RuntimeException(errorMessage); + } + + //////////////////////////////////// + // Lexer components + + private static class Lexer { + + // Input buffer; an array of text bytes read from a file or a string + private final byte[] _input; + // Tracks current position in input buffer + private int _position = 0; + + /** + * Record the source text for lexing + */ + public Lexer(String source) { + this(source.getBytes()); + } + + /** + * Direct from disk file source + */ + public Lexer(byte[] buf) { + _input = buf; + } + + // Very handy in the debugger, shows the unparsed program + @Override + public String toString() { + return new String(_input, _position, _input.length - _position); + } + + // True if at EOF + private boolean isEOF() { + return _position >= _input.length; + } + + // Peek next character, or report EOF + private char peek() { + return isEOF() ? Character.MAX_VALUE // Special value that causes parsing to terminate + : (char) _input[_position]; + } + // Just crash if misused + public byte peek(int off) { return _input[_position+off]; } + + private char nextChar() { + char ch = peek(); + _position++; + return ch; + } + + // True if a white space + private boolean isWhiteSpace() { + return peek() <= ' '; // Includes all the use space, tab, newline, CR + } + + /** + * Return the next non-white-space character + */ + private void skipWhiteSpace() { + while( true ) { + if( isWhiteSpace() ) _position++; + // Skip // to end of line + else if( _position+2 < _input.length && + _input[_position ] == '/' && + _input[_position+1] == '/') { + _position += 2; + while( !isEOF() && _input[_position] != '\n' ) _position++; + } else break; + } + } + + // Next non-white-space character, or EOF + public char nextXChar() { skipWhiteSpace(); return nextChar(); } + + // Return true, if we find "syntax" after skipping white space; also + // then advance the cursor past syntax. + // Return false otherwise, and do not advance the cursor. + boolean match(String syntax) { + skipWhiteSpace(); + int len = syntax.length(); + if (_position + len > _input.length) return false; + for (int i = 0; i < len; i++) + if ((char) _input[_position + i] != syntax.charAt(i)) + return false; + _position += len; + return true; + } + + // Match must be exact and not followed by more ID characters. + // Prevents identifier "ifxy" from matching an "if" statement. + boolean matchx(String syntax) { + if( !match(syntax) ) return false; + if( !isIdLetter(peek()) ) return true; + _position -= syntax.length(); + return false; + } + boolean matchOpx(char c0, char c1) { + skipWhiteSpace(); + if( _position+1 >= _input.length || _input[_position]!=c0 || _input[_position+1]==c1 ) + return false; + _position++; + return true; + } + + private boolean peek(char ch) { + skipWhiteSpace(); + return peek()==ch; + } + + boolean peekIsId() { + skipWhiteSpace(); + return isIdStart(peek()); + } + + // Return an identifier or null + String matchId() { + return peekIsId() ? parseId() : null; + } + + // Used for errors + String getAnyNextToken() { + if (isEOF()) return ""; + if (isIdStart(peek())) return parseId(); + if (isNumber(peek())) return parseNumberString(); + if (isPunctuation(peek())) return parsePunctuation(); + return String.valueOf(peek()); + } + + + boolean isNumber(char ch) {return Character.isDigit(ch);} + + // Return a constant Type, either TypeInteger or TypeFloat + private Type parseNumber() { + int old = _position; + int len = isLongOrDouble(); + if( len > 0 ) { + if( len > 1 && _input[old]=='0' ) + throw error("Syntax error: integer values cannot start with '0'"); + return TypeInteger.constant(Long.parseLong(new String(_input,old,len))); + } + return TypeFloat.constant(Double.parseDouble(new String(_input,old,-len))); + } + private String parseNumberString() { + int old = _position; + int len = Math.abs(isLongOrDouble()); + _position += len; + return new String(_input,old,len); + } + + // Return +len that ends a long + // Return -len that ends a double + private int isLongOrDouble() { + int old = _position; + char c; + while( Character.isDigit(c=nextChar()) ) ; + if( !(c=='e' || c=='.') ) + return --_position - old; + while( Character.isDigit(c=nextChar()) || c=='e' || c=='.' ) ; + return -(--_position - old); + } + + // First letter of an identifier + private boolean isIdStart(char ch) { + return Character.isAlphabetic(ch) || ch == '_'; + } + + // All characters of an identifier, e.g. "_x123" + private boolean isIdLetter(char ch) { + return Character.isLetterOrDigit(ch) || ch == '_'; + } + + private String parseId() { + int start = _position; + while (isIdLetter(nextChar())) ; + return new String(_input, start, --_position - start); + } + + // + private boolean isPunctuation(char ch) { + return "=;[]<>()+-/*&|^".indexOf(ch) != -1; + } + + private String parsePunctuation() { + int start = _position; + return new String(_input, start, 1); + } + + // Next oper= character, or 0. + // As a convenience, mark "++" as a char 1 and "--" as char -1 (65535) + public char matchOperAssign() { + skipWhiteSpace(); + if( _position+2 >= _input.length ) return 0; + char ch0 = (char)_input[_position]; + if( "+-/*&|^".indexOf(ch0) == -1 ) return 0; + char ch1 = (char)_input[_position+1]; + if( ch1 == '=' ) { _position += 2; return ch0; } + if( ch0 == '+' && ch1 == '+' ) { _position += 2; return (char) 1; } + if( ch0 == '-' && ch1 == '-' ) { _position += 2; return (char)-1; } + return 0; + } + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/Utils.java b/chapter18/src/main/java/com/seaofnodes/simple/Utils.java new file mode 100644 index 00000000..1346c3ea --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/Utils.java @@ -0,0 +1,53 @@ +package com.seaofnodes.simple; + +import java.util.ArrayList; + +public class Utils { + public static RuntimeException TODO() { return TODO("Not yet implemented"); } + public static RuntimeException TODO(String msg) { return new RuntimeException(msg); } + + /** + * Fast, constant-time, element removal. Does not preserve order + * + * @param array ArrayList to modify + * @param i element to be removed + * @return element removed + */ + public static <E> void del(ArrayList<E> array, int i) { + E last = array.removeLast(); + if (i < array.size()) array.set(i, last); + } + + /** + * Search a list for an element by reference + * + * @param ary List to search in + * @param x Object to be searched + * @return >= 0 on success, -1 on failure + */ + public static <E> int find( ArrayList<E> ary, E x ) { + for( int i=0; i<ary.size(); i++ ) + if( ary.get(i)==x ) + return i; + return -1; + } + /** + * Search a list for an element by reference + * + * @param ary List to search in + * @param x Object to be searched + * @return >= 0 on success, -1 on failure + */ + public static <E> int find( E[] ary, E x ) { + for( int i=0; i<ary.length; i++ ) + if( ary[i]==x ) + return i; + return -1; + } + + // Rotate a long, nice for hashes + public static long rot( long x, int n ) { return (x<<n) | (x>>>n); } + + // Fold a 64bit hash into 32 bits + public static int fold( long x ) { return (int)((x>>32) ^ x); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/AddFNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/AddFNode.java new file mode 100644 index 00000000..e5a2440c --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/AddFNode.java @@ -0,0 +1,44 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; + +import java.util.BitSet; + +public class AddFNode extends Node { + public AddFNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "AddF"; } + + @Override public String glabel() { return "+"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("+"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeFloat i0 && + in(2)._type instanceof TypeFloat i1) { + if (i0.isConstant() && i1.isConstant()) + return TypeFloat.constant(i0.value()+i1.value()); + } + return in(1)._type.meet(in(2)._type); + } + + @Override + public Node idealize() { + Node lhs = in(1); + Type t2 = in(2)._type; + + // Add of 1. + if ( t2.isConstant() && t2 instanceof TypeFloat i && i.value()==0 ) + return lhs; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new AddFNode(lhs,rhs); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/AddNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/AddNode.java new file mode 100644 index 00000000..0834a381 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/AddNode.java @@ -0,0 +1,187 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.*; + +import java.util.BitSet; + +public class AddNode extends Node { + public AddNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Add"; } + + @Override public String glabel() { return "+"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("+"), visited); + return sb.append(")"); + } + + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if( t1 instanceof TypeInteger i1 && + t2 instanceof TypeInteger i2 ) { + if (i1.isConstant() && i2.isConstant()) + return TypeInteger.constant(i1.value()+i2.value()); + // Fold ranges like {0-1} + {2-3} into {2-4}. + if( !overflow(i1._min,i2._min) && + !overflow(i1._max,i2._max) ) + return TypeInteger.make(i1._min+i2._min,i1._max+i2._max); + } + return TypeInteger.BOT; + } + + static boolean overflow( long x, long y ) { + if( (x ^ y ) < 0 ) return false; // unequal signs, never overflow + return (x ^ (x + y)) < 0; // sum has unequal signs, so overflow + } + @Override + public Node idealize () { + Node lhs = in(1); + Node rhs = in(2); + Type t2 = rhs._type; + + // Add of 0. We do not check for (0+x) because this will already + // canonicalize to (x+0) + if( t2 instanceof TypeInteger i && i.isConstant() && i.value()==0 ) + return lhs; + + // Add of same to a multiply by 2 + if( lhs==rhs ) + return new MulNode(lhs,new ConstantNode(TypeInteger.constant(2)).peephole()); + + // Goal: a left-spine set of adds, with constants on the rhs (which then fold). + + // Move non-adds to RHS + if( !(lhs instanceof AddNode) && rhs instanceof AddNode ) + return swap12(); + + // x+(-y) becomes x-y + if( rhs instanceof MinusNode minus ) + return new SubNode(lhs,minus.in(1)); + + // Now we might see (add add non) or (add non non) or (add add add) but never (add non add) + + // Do we have x + (y + z) ? + // Swap to (x + y) + z + // Rotate (add add add) to remove the add on RHS + if( rhs instanceof AddNode add ) + return new AddNode(new AddNode(lhs,add.in(1)).peephole(), add.in(2)); + + // Now we might see (add add non) or (add non non) but never (add non add) nor (add add add) + if( !(lhs instanceof AddNode) ) + // Rotate; look for (add (phi cons) con/(phi cons)) + return spine_cmp(lhs,rhs,this) ? swap12() : phiCon(this,true); + + // Now we only see (add add non) + + // Dead data cycle; comes about from dead infinite loops. Do nothing, + // the loop will peep as dead after a bit. + if( lhs.in(1) == lhs ) + return null; + + // Do we have (x + con1) + con2? + // Replace with (x + (con1+con2) which then fold the constants + // lhs.in(2) is con1 here + // If lhs.in(2) is not a constant, we add ourselves as a dependency + // because if it later became a constant then we could make this + // transformation. + if( lhs.in(2).addDep(this)._type.isConstant() && rhs._type.isConstant() ) + return new AddNode(lhs.in(1),new AddNode(lhs.in(2),rhs).peephole()); + + + // Do we have ((x + (phi cons)) + con) ? + // Do we have ((x + (phi cons)) + (phi cons)) ? + // Push constant up through the phi: x + (phi con0+con0 con1+con1...) + Node phicon = phiCon(this,true); + if( phicon!=null ) return phicon; + + // Now we sort along the spine via rotates, to gather similar things together. + + // Do we rotate (x + y) + z + // into (x + z) + y ? + if( spine_cmp(lhs.in(2),rhs,this) ) + return new AddNode(new AddNode(lhs.in(1),rhs).peephole(),lhs.in(2)); + + return null; + } + + // Rotation is only valid for associative ops, e.g. Add, Mul, And, Or, Xor. + // Do we have ((phi cons)|(x + (phi cons)) + con|(phi cons)) ? + // Push constant up through the phi: x + (phi con0+con0 con1+con1...) + static Node phiCon(Node op, boolean rotate) { + Node lhs = op.in(1); + Node rhs = op.in(2); + if( rhs._type==TypeInteger.TOP ) return null; + // LHS is either a Phi of constants, or another op with Phi of constants + PhiNode lphi = pcon(lhs,op); + if( rotate && lphi==null && lhs.nIns() > 2 ) { + // Only valid to rotate constants if both are same associative ops + if( lhs.getClass() != op.getClass() ) return null; + lphi = pcon(lhs.in(2),op); // Will rotate with the Phi push + } + if( lphi==null ) return null; + + // RHS is a constant or a Phi of constants + if( !(rhs instanceof ConstantNode) && pcon(rhs,op)==null ) + return null; + + // If both are Phis, must be same Region + if( rhs instanceof PhiNode && lphi.in(0) != rhs.in(0) ) + return null; + + // Note that this is the exact reverse of Phi pulling a common op down + // to reduce total op-count. We don't get in an endless push-up + // push-down peephole cycle because the constants all fold first. + Node[] ns = new Node[lphi.nIns()]; + ns[0] = lphi.in(0); + // Push constant up through the phi: x + (phi con0+con0 con1+con1...) + for( int i=1; i<ns.length; i++ ) + ns[i] = op.copy(lphi.in(i), rhs instanceof PhiNode ? rhs.in(i) : rhs).peephole(); + String label = lphi._label + (rhs instanceof PhiNode rphi ? rphi._label : ""); + Node phi = new PhiNode(label,lphi._declaredType,ns).peephole(); + // Rotate needs another op, otherwise just the phi + return lhs==lphi ? phi : op.copy(lhs.in(1),phi); + } + + /** + * Tests if the op is a phi and has all constant inputs. + * If not, returns null. + * If op is a phi, but its inputs are not all constants, then dep is added as + * a dependency to the phi's non-const input, because if later the input turn into a constant + * dep can make progress. + */ + static PhiNode pcon(Node op, Node dep) { + return op instanceof PhiNode phi && phi.allCons(dep) ? phi : null; + } + + // Compare two off-spine nodes and decide what order they should be in. + // Do we rotate ((x + hi) + lo) into ((x + lo) + hi) ? + // Generally constants always go right, then Phi-of-constants, then muls, then others. + // Ties with in a category sort by node ID. + // TRUE if swapping hi and lo. + static boolean spine_cmp( Node hi, Node lo, Node dep ) { + if( lo._type.isConstant() ) return false; + if( hi._type.isConstant() ) return true ; + + if( lo instanceof PhiNode lphi && lphi.region()._type==Type.XCONTROL ) return false; + if( hi instanceof PhiNode hphi && hphi.region()._type==Type.XCONTROL ) return false; + + if( lo instanceof PhiNode && lo.allCons(dep) ) return false; + if( hi instanceof PhiNode && hi.allCons(dep) ) return true ; + + if( lo instanceof PhiNode && !(hi instanceof PhiNode) ) return true; + if( hi instanceof PhiNode && !(lo instanceof PhiNode) ) return false; + + // Same category of "others" + return lo._nid > hi._nid; + } + + @Override Node copy(Node lhs, Node rhs) { return new AddNode(lhs,rhs); } + @Override Node copyF() { return new AddFNode(null,null); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/AndNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/AndNode.java new file mode 100644 index 00000000..17a4e0ca --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/AndNode.java @@ -0,0 +1,68 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class AndNode extends Node { + public AndNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "And"; } + + @Override public String glabel() { return "&"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("&"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if( t1 instanceof TypeInteger i0 && + t2 instanceof TypeInteger i1 ) { + if( i0.isConstant() && i1.isConstant() ) + return TypeInteger.constant(i0.value()&i1.value()); + // Sharpen allowed bits if either value is narrowed + long mask = i0.mask() & i1.mask(); + return mask < 0 ? TypeInteger.BOT : TypeInteger.make(0,mask); + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // And of -1. We do not check for (-1&x) because this will already + // canonicalize to (x&-1) + if( t2.isConstant() && t2 instanceof TypeInteger i && i.value()==-1 ) + return lhs; + + // Move constants to RHS: con*arg becomes arg*con + if ( t1.isConstant() && !t2.isConstant() ) + return swap12(); + + // Do we have ((x & (phi cons)) & con) ? + // Do we have ((x & (phi cons)) & (phi cons)) ? + // Push constant up through the phi: x & (phi con0&con0 con1&con1...) + Node phicon = AddNode.phiCon(this,true); + if( phicon!=null ) return phicon; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new AndNode(lhs,rhs); } + @Override String err() { + if( !(in(1)._type instanceof TypeInteger) ) return "Cannot '&' " + in(1)._type; + if( !(in(2)._type instanceof TypeInteger) ) return "Cannot '&' " + in(2)._type; + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/BoolNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/BoolNode.java new file mode 100644 index 00000000..238be00e --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/BoolNode.java @@ -0,0 +1,120 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; +import com.seaofnodes.simple.type.TypeFloat; +import com.seaofnodes.simple.type.TypeMemPtr; + +import java.util.BitSet; +import static com.seaofnodes.simple.type.TypeInteger.*; + +abstract public class BoolNode extends Node { + + public BoolNode(Node lhs, Node rhs) { + super(null, lhs, rhs); + } + + abstract String op(); // String opcode name + + @Override + public String label() { return getClass().getSimpleName(); } + + @Override + public String glabel() { return op(); } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append(op()), visited); + return sb.append(")"); + } + + @Override + public TypeInteger compute() { + Type t1 = in(1)._type; + Type t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return BOOL.dual(); + if( t1 instanceof TypeInteger i1 && + t2 instanceof TypeInteger i2 ) + return doOp(i1,i2); + if( t1 instanceof TypeFloat f1 && + t2 instanceof TypeFloat f2 && + f1.isConstant() && f2.isConstant() ) + return TypeInteger.constant(doOp(f1.value(), f2.value()) ? 1 : 0); + return BOOL; + } + + TypeInteger doOp(TypeInteger t1, TypeInteger t2) { throw Utils.TODO(); } + boolean doOp(double lhs, double rhs) { throw Utils.TODO(); } + Node copyF(Node lhs, Node rhs) { return null; } + + @Override + public Node idealize() { + // Compare of same + if( in(1)==in(2) ) + return new ConstantNode(doOp(ZERO,ZERO)); + + // Equals pushes constant to the right; 5==X becomes X==5. + if( this instanceof EQ ) { + if( !(in(2) instanceof ConstantNode) ) { + // con==noncon becomes noncon==con + if( in(1) instanceof ConstantNode || in(1)._nid > in(2)._nid ) + // Equals sorts by NID otherwise: non.high == non.low becomes non.low == non.high + return in(1)._type instanceof TypeFloat ? new EQF(in(2),in(1)) : new EQ(in(2),in(1)); + } + // Equals X==0 becomes a !X + if( (in(2)._type == ZERO || in(2)._type == TypeMemPtr.NULLPTR) ) + return new NotNode(in(1)); + } + + // Do we have ((x * (phi cons)) * con) ? + // Do we have ((x * (phi cons)) * (phi cons)) ? + // Push constant up through the phi: x * (phi con0*con0 con1*con1...) + Node phicon = AddNode.phiCon(this,this instanceof EQ); + if( phicon!=null ) return phicon; + + return null; + } + + public static class EQ extends BoolNode { + public EQ(Node lhs, Node rhs) { super(lhs,rhs); } + String op() { return "=="; } + TypeInteger doOp(TypeInteger i1, TypeInteger i2) { + if( i1==i2 && i1.isConstant() ) return TRUE; + if( i1._max < i2._min || i1._min > i2._max ) return FALSE; + return BOOL; + } + Node copy(Node lhs, Node rhs) { return new EQ(lhs,rhs); } + Node copyF() { return new EQF(null,null); } + } + public static class LT extends BoolNode { + public LT(Node lhs, Node rhs) { super(lhs,rhs); } + String op() { return "<" ; } + TypeInteger doOp(TypeInteger i1, TypeInteger i2) { + if( i1._max < i2._min ) return TRUE; + if( i1._min >= i2._max ) return FALSE; + return BOOL; + } + Node copy(Node lhs, Node rhs) { return new LT(lhs,rhs); } + Node copyF() { return new LTF(null,null); } + } + public static class LE extends BoolNode { + public LE(Node lhs, Node rhs) { super(lhs,rhs); } + String op() { return "<="; } + TypeInteger doOp(TypeInteger i1, TypeInteger i2) { + if( i1._max <= i2._min ) return TRUE; + if( i1._min > i2._max ) return FALSE; + return BOOL; + } + Node copy(Node lhs, Node rhs) { return new LE(lhs,rhs); } + Node copyF() { return new LEF(null,null); } + } + + public static class EQF extends EQ { public EQF(Node lhs, Node rhs) { super(lhs,rhs); } boolean doOp(double lhs, double rhs) { return lhs == rhs; } } + public static class LTF extends LT { public LTF(Node lhs, Node rhs) { super(lhs,rhs); } boolean doOp(double lhs, double rhs) { return lhs < rhs; } } + public static class LEF extends LE { public LEF(Node lhs, Node rhs) { super(lhs,rhs); } boolean doOp(double lhs, double rhs) { return lhs <= rhs; } } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/CFGNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/CFGNode.java new file mode 100644 index 00000000..052ad8fc --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/CFGNode.java @@ -0,0 +1,132 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.*; +import com.seaofnodes.simple.Utils; + +import java.util.BitSet; +import java.util.HashSet; +import java.util.HashMap; + +/** Control Flow Graph Nodes + * <p> + * CFG nodes have a immediate dominator depth (idepth) and a loop nesting + * depth(loop_depth). + * <p> + * idepth is computed lazily upon first request, and is valid even in the + * Parser, and is used by peepholes during parsing and afterward. + * <p> + * loop_depth is computed after optimization as part of scheduling. + * + */ +public abstract class CFGNode extends Node { + + public CFGNode(Node... nodes) { super(nodes); } + + public CFGNode cfg(int idx) { return (CFGNode)in(idx); } + + // Block head is Start, Region, CProj, but not e.g. If, Return, Stop + public boolean blockHead() { return false; } + + // ------------------------------------------------------------------------ + /** + * Immediate dominator tree depth, used to approximate a real IDOM during + * parsing where we do not have the whole program, and also peepholes + * change the CFG incrementally. + * <p> + * See {@link <a href="https://en.wikipedia.org/wiki/Dominator_(graph_theory)">...</a>} + */ + public int _idepth; + public int idepth() { return _idepth==0 ? (_idepth=idom().idepth()+1) : _idepth; } + + // Return the immediate dominator of this Node and compute dom tree depth. + public CFGNode idom(Node dep) { return cfg(0); } + public final CFGNode idom() { return idom(null); } + + // Return the LCA of two idoms + public CFGNode _idom(CFGNode rhs, Node dep) { + if( rhs==null ) return this; + CFGNode lhs = this; + while( lhs != rhs ) { + var comp = lhs.idepth() - rhs.idepth(); + if( comp >= 0 ) lhs = ((CFGNode)lhs.addDep(dep)).idom(); + if( comp <= 0 ) rhs = ((CFGNode)rhs.addDep(dep)).idom(); + } + return lhs; + } + + // Anti-dependence field support + public int _anti; // Per-CFG field to help find anti-deps + + // ------------------------------------------------------------------------ + // Loop nesting + public LoopNode loop() { return _ltree._head; } + public int loopDepth() { return _ltree==null ? 0 : _ltree.depth(); } + + LoopTree _ltree; + int _pre; // Pre-order numbers for loop tree finding + private static class LoopTree { + LoopTree _par; + final LoopNode _head; + int _depth; + LoopTree(LoopNode head) { _head = head; } + @Override public String toString() { return "LOOP"+_head._nid; } + int depth() { + return _depth==0 ? (_par==null ? 0 : (_depth = _par.depth()+1)) : _depth; + } + } + + // ------------------------------------------------------------------------ + // Tag all CFG Nodes with their containing LoopNode; LoopNodes themselves + // also refer to *their* containing LoopNode, as well as have their depth. + // Start is a LoopNode which contains all at depth 1. + public void buildLoopTree(StopNode stop) { + _ltree = stop._ltree = Parser.XCTRL._ltree = new LoopTree((StartNode)this); + _bltWalk(2,stop, new BitSet()); + } + private int _bltWalk(int pre, StopNode stop, BitSet post) { + // Pre-walked? + if( _pre!=0 ) return pre; + _pre = pre++; + // Pre-walk + for( Node use : _outputs ) + if( use instanceof CFGNode usecfg ) + pre = usecfg._bltWalk(pre,stop,post); + + // Post-order work: find innermost loop + LoopTree inner = null, ltree; + for( Node use : _outputs ) { + if( !(use instanceof CFGNode usecfg) ) continue; + // Child visited but not post-visited? + if( !post.get(usecfg._nid) ) { + // Must be a backedge to a LoopNode then + ltree = usecfg._ltree = new LoopTree((LoopNode)usecfg); + } else { + // Take child's loop choice, which must exist + ltree = usecfg._ltree; + // If falling into a loop, use the target loop's parent instead + if( ltree._head == usecfg ) { + if( ltree._par == null ) + // This loop never had an If test choose to take its + // exit, i.e. it is a no-exit infinite loop. + ltree._par = ltree._head.forceExit(stop)._ltree; + ltree = ltree._par; + } + } + // Sort inner loops. The decision point is some branch far removed + // from either loop head OR either backedge so requires pre-order + // numbers to figure out innermost. + if( inner == null ) { inner = ltree; continue; } + if( inner == ltree ) continue; // No change + LoopTree outer = ltree._head._pre > inner._head._pre ? inner : ltree; + inner = ltree._head._pre > inner._head._pre ? ltree : inner; + inner._par = outer; + } + // Set selected loop + if( inner!=null ) + _ltree = inner; + // Tag as post-walked + post.set(_nid); + return pre; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/CProjNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/CProjNode.java new file mode 100644 index 00000000..d2f1bbe1 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/CProjNode.java @@ -0,0 +1,60 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeMem; +import com.seaofnodes.simple.type.TypeTuple; +import java.util.BitSet; + +public class CProjNode extends CFGNode { + + // Which slice of the incoming multipart value + public final int _idx; + + // Debugging label + public final String _label; + + public CProjNode(Node ctrl, int idx, String label) { + super(ctrl); + _idx = idx; + _label = label; + } + + @Override public String label() { return _label; } + + @Override StringBuilder _print1(StringBuilder sb, BitSet visited) { return sb.append(_label); } + + @Override public boolean isMultiTail() { return in(0).isMultiHead(); } + @Override public boolean blockHead() { return true; } + + public CFGNode ctrl() { return cfg(0); } + + @Override + public Type compute() { + Type t = ctrl()._type; + return t instanceof TypeTuple tt ? tt._types[_idx] : Type.BOTTOM; + } + + @Override + public Node idealize() { + if( ctrl()._type instanceof TypeTuple tt ) { + if( tt._types[_idx]==Type.XCONTROL ) + return Parser.XCTRL; // We are dead + if( ctrl() instanceof IfNode && tt._types[1-_idx]==Type.XCONTROL ) // Only true for IfNodes + return ctrl().in(0); // We become our input control + } + + // Flip a negating if-test, to remove the not + if( ctrl() instanceof IfNode iff && iff.pred().addDep(this) instanceof NotNode not ) + return new CProjNode(new IfNode(iff.ctrl(),not.in(1)).peephole(),1-_idx,_idx==0 ? "False" : "True"); + + return null; + } + + @Override + boolean eq( Node n ) { return _idx == ((CProjNode)n)._idx; } + + @Override + int hash() { return _idx; } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/CastNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/CastNode.java new file mode 100644 index 00000000..462d6cba --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/CastNode.java @@ -0,0 +1,40 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; +import com.seaofnodes.simple.IterPeeps; + +import java.util.BitSet; + +// Upcast (join) the input to a t. Used after guard test to lift an input. +// Can also be used to make a type-assertion if ctrl is null. +public class CastNode extends Node { + private final Type _t; + public CastNode(Type t, Node ctrl, Node in) { + super(ctrl, in); + _t = t; + setType(compute()); + } + + @Override public String label() { return "("+_t.str()+")"; } + + @Override + public String uniqueName() { return "Cast_" + _nid; } + + @Override public boolean isPinned() { return true; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return in(1)._print0(sb.append(label()), visited); + } + + @Override + public Type compute() { + return in(1)._type.join(_t); + } + + @Override + public Node idealize() { + return in(1)._type.isa(_t) ? in(1) : null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ConstantNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ConstantNode.java new file mode 100644 index 00000000..845b9d08 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ConstantNode.java @@ -0,0 +1,54 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.Type; + +import java.util.BitSet; + +/** + * A Constant node represents a constant value. At present, the only constants + * that we allow are integer literals; therefore Constants contain an integer + * value. As we add other types of constants, we will refactor how we represent + * Constants. + * <p> + * Constants have no semantic inputs. However, we set Start as an input to + * Constants to enable a forward graph walk. This edge carries no semantic + * meaning, and it is present <em>solely</em> to allow visitation. + * <p> + * The Constant's value is the value stored in it. + */ +public class ConstantNode extends Node { + Type _con; + public ConstantNode( Type type ) { + super(Parser.START); + _con = type; + } + + @Override + public String label() { return "#"+_con; } + + @Override + public String uniqueName() { return "Con_" + _nid; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return _con.print(sb); + } + + @Override public boolean isMultiTail() { return true; } + + @Override + public Type compute() { return _con; } + + @Override + public Node idealize() { return null; } + + @Override + boolean eq(Node n) { + ConstantNode con = (ConstantNode)n; // Contract + return _con==con._con; + } + + @Override + int hash() { return _con.hashCode(); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/DivFNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/DivFNode.java new file mode 100644 index 00000000..36fd4524 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/DivFNode.java @@ -0,0 +1,46 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; + +import java.util.BitSet; + +public class DivFNode extends Node { + public DivFNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "DivF"; } + + @Override public String glabel() { return "/"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("/"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeFloat i0 && + in(2)._type instanceof TypeFloat i1) { + if (i0.isConstant() && i1.isConstant()) + return TypeFloat.constant(i0.value()/i1.value()); + } + return in(1)._type.meet(in(2)._type); + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // Div of 1. + if ( t2.isConstant() && t2 instanceof TypeFloat i && i.value()==1 ) + return lhs; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new DivFNode(lhs,rhs); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/DivNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/DivNode.java new file mode 100644 index 00000000..76e98678 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/DivNode.java @@ -0,0 +1,47 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class DivNode extends Node { + public DivNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Div"; } + + @Override public String glabel() { return "//"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("/"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if( t1 instanceof TypeInteger i1 && + t2 instanceof TypeInteger i2 ) { + if (i1.isConstant() && i2.isConstant()) + return i2.value() == 0 + ? TypeInteger.ZERO + : TypeInteger.constant(i1.value()/i2.value()); + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + // Div of 1. + if( in(2)._type == TypeInteger.TRUE ) + return in(1); + return null; + } + + @Override Node copy(Node lhs, Node rhs) { return new DivNode(lhs,rhs); } + @Override Node copyF() { return new DivFNode(null,null); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/IfNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/IfNode.java new file mode 100644 index 00000000..513b4721 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/IfNode.java @@ -0,0 +1,66 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.IterPeeps; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; +import com.seaofnodes.simple.type.TypeTuple; +import java.util.BitSet; +import java.util.HashSet; + +public class IfNode extends CFGNode implements MultiNode { + + public IfNode(Node ctrl, Node pred) { + super(ctrl, pred); + IterPeeps.add(this); // Because idoms are complex, just add it + } + + @Override + public String label() { return "If"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("if( "); + return in(1)._print0(sb, visited).append(" )"); + } + + @Override public boolean isMultiHead() { return true; } + + public Node ctrl() { return in(0); } + public Node pred() { return in(1); } + + @Override + public Type compute() { + // If the If node is not reachable then neither is any following Proj + if (ctrl()._type != Type.CONTROL && ctrl()._type != Type.BOTTOM ) + return TypeTuple.IF_NEITHER; + Node pred = pred(); + Type t = pred._type; + // High types mean NEITHER side is reachable. + // Wait until the type falls to decide which way to go. + if( t == Type.TOP || t == TypeInteger.TOP ) + return TypeTuple.IF_NEITHER; + // If constant is 0 then false branch is reachable + // Else true branch is reachable + if( t.isConstant() ) + return t.makeInit()==t ? TypeTuple.IF_FALSE : TypeTuple.IF_TRUE; + // Integers allow non-zero ranges: "1-65535" + if( t.makeZero().meet(t) != t ) + return TypeTuple.IF_TRUE; + + return TypeTuple.IF_BOTH; + } + + @Override + public Node idealize() { + // Hunt up the immediate dominator tree. If we find an identical if + // test on either the true or false branch, that side wins. + if( !pred()._type.isHighOrConst() ) + for( CFGNode dom = idom(), prior=this; dom!=null; prior = dom, dom = dom.idom() ) + if( dom.addDep(this) instanceof IfNode iff && iff.pred().addDep(this)==pred() && prior instanceof CProjNode prj ) { + setDef(1,new ConstantNode(TypeInteger.make(true,prj._idx==0?1:0)).peephole()); + return this; + } + return null; + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/LoadNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/LoadNode.java new file mode 100644 index 00000000..1528f2e9 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/LoadNode.java @@ -0,0 +1,172 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.*; +import java.util.BitSet; + +/** + * Load represents extracting a value from inside a memory object, + * in chapter 10 this means Struct fields. + */ +public class LoadNode extends MemOpNode { + + /** + * Load a value from a ptr.field. + * + * @param name The field we are loading + * @param mem The memory alias node - this is updated after a Store + * @param ptr The ptr to the struct base from where we load a field + * @param off The offset inside the struct base + */ + public LoadNode(String name, int alias, Type glb, Node mem, Node ptr, Node off) { + super(name, alias, glb, mem, ptr, off); + } + + // GraphVis DOT code (must be valid Java identifiers) and debugger labels + @Override public String label() { return "ld_"+mlabel(); } + // GraphVis node-internal labels + @Override public String glabel() { return "." +_name; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { return sb.append(".").append(_name); } + + @Override + public Type compute() { + if( mem()._type instanceof TypeMem mem ) { + // Update declared forward ref to the actual + if( _declaredType.isFRef() && mem._t instanceof TypeMemPtr tmp && !tmp.isFRef() ) + _declaredType = tmp; + // No lifting if ptr might null-check + if( err()==null ) + return _declaredType.join(mem._t); + } + return _declaredType; + } + + @Override + public Node idealize() { + Node ptr = ptr(); + + // Simple Load-after-Store on same address. + if( mem() instanceof StoreNode st && + ptr == st.ptr() && off() == st.off() ) { // Must check same object + assert _name.equals(st._name); // Equiv class aliasing is perfect + return st.val(); + } + + // Simple Load-after-New on same address. + if( mem() instanceof ProjNode p && p.in(0) instanceof NewNode nnn && + ptr == nnn.proj(1) ) // Must check same object + return nnn.in(nnn.findAlias(_alias)); // Load from New init + + // Load-after-Store on same address, but bypassing provably unrelated + // stores. This is a more complex superset of the above two peeps. + // "Provably unrelated" is really weak. + if( ptr instanceof ReadOnlyNode ro ) + ptr = ro.in(1); + Node mem = mem(); + outer: + while( true ) { + switch( mem ) { + case StoreNode st: + if( ptr == st.ptr() && off() == st.off() ) + return castRO(st.val()); // Proved equal + // Can we prove unequal? Offsets do not overlap? + if( !off()._type.join(st.off()._type).isHigh() && // Offsets overlap + !neverAlias(ptr,st.ptr()) ) // And might alias + break outer; // Cannot tell, stop trying + // Pointers cannot overlap + mem = st.mem(); // Proved never equal + break; + case PhiNode phi: break outer; // Assume related + case ConstantNode top: break outer; // Assume shortly dead + case ProjNode mproj: + if( mproj.in(0) instanceof NewNode nnn1 ) { + if( ptr instanceof ProjNode pproj && pproj.in(0) == mproj.in(0) ) + return castRO(nnn1.in(nnn1.findAlias(_alias))); // Load from New init + if( !(ptr instanceof ProjNode pproj && pproj.in(0) instanceof NewNode nnn2) ) + break outer; // Cannot tell, ptr not related to New + mem = nnn1.in(_alias);// Bypass unrelated New + break; + } else if( mproj.in(0) instanceof StartNode ) { + break outer; + } else throw Utils.TODO(); + default: + throw Utils.TODO(); + } + } + + // Push a Load up through a Phi, as long as it collapses on at least + // one arm. If at a Loop, the backedge MUST collapse - else we risk + // spinning the same transform around the loop indefinitely. + // BEFORE (2 Sts, 1 Ld): AFTER (1 St, 0 Ld): + // if( pred ) ptr.x = e0; val = pred ? e0 + // else ptr.x = e1; : e1; + // val = ptr.x; ptr.x = val; + if( mem() instanceof PhiNode memphi && memphi.region()._type == Type.CONTROL && memphi.nIns()== 3 && + // Offset can be hoisted + off() instanceof ConstantNode && + // Pointer can be hoisted + hoistPtr(ptr,memphi) ) { + + // Profit on RHS/Loop backedge + if( profit(memphi,2) || + // Else must not be a loop to count profit on LHS. + (!(memphi.region() instanceof LoopNode) && profit(memphi,1)) ) { + Node ld1 = ld(1); + Node ld2 = ld(2); + return new PhiNode(_name,_declaredType,memphi.region(),ld1,ld2); + } + } + + return null; + } + + private Node ld( int idx ) { + Node mem = mem(), ptr = ptr(); + return new LoadNode(_name,_alias,_declaredType,mem.in(idx),ptr instanceof PhiNode && ptr.in(0)==mem.in(0) ? ptr.in(idx) : ptr, off()).peephole(); + } + + private static boolean neverAlias( Node ptr1, Node ptr2 ) { + return ptr1.in(0) != ptr2.in(0) && + // Unrelated allocations + ptr1 instanceof ProjNode && ptr1.in(0) instanceof NewNode && + ptr2 instanceof ProjNode && ptr2.in(0) instanceof NewNode; + } + + private static boolean hoistPtr(Node ptr, PhiNode memphi ) { + // Can I hoist ptr above the Region? + if( !(memphi.region() instanceof RegionNode r) ) + return false; // Dead or dying Region/Phi + // If ptr from same Region, then yes, just use hoisted split pointers + if( ptr instanceof PhiNode pphi && pphi.region() == r ) + return true; + + // No, so can we lift this ptr? + CFGNode cptr = ptr.cfg0(); + if( cptr != null ) + // Pointer is controlled high + // TODO: Really needs to be the LCA of all inputs is high + return cptr.idepth() <= r.idepth(); + + // Dunno without a longer walk + return false; + } + + // Profitable if we find a matching Store on this Phi arm. + private boolean profit(PhiNode phi, int idx) { + Node px = phi.in(idx); + if( px==null ) return false; + if( px._type instanceof TypeMem mem && mem._t.isHighOrConst() ) { px.addDep(this); return true; } + if( px instanceof StoreNode st1 && ptr()==st1.ptr() && off()==st1.off() ) { px.addDep(this); return true; } + return false; + } + + // Read-Only is a deep property, and cannot be cast-away + private Node castRO(Node rez) { + if( ptr()._type.isFinal() && !rez._type.isFinal() ) + return new ReadOnlyNode(rez).peephole(); + return rez; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/LoopNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/LoopNode.java new file mode 100644 index 00000000..ecda9c63 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/LoopNode.java @@ -0,0 +1,61 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; +import java.util.BitSet; +import java.util.HashSet; + +public class LoopNode extends RegionNode { + public LoopNode( Node entry ) { super(null,entry,null); } + + public CFGNode entry() { return cfg(1); } + public CFGNode back () { return cfg(2); } + + @Override + public String label() { return "Loop"; } + + @Override + public Type compute() { + if( inProgress() ) return Type.CONTROL; + return entry()._type; + } + + @Override + public Node idealize() { + return inProgress() ? null : super.idealize(); + } + + // Bypass Region idom, same as the default idom() using use in(1) instead of in(0) + @Override public int idepth() { return _idepth==0 ? (_idepth=idom().idepth()+1) : _idepth; } + // Bypass Region idom, same as the default idom() using use in(1) instead of in(0) + @Override public CFGNode idom(Node dep) { return entry(); } + + // If this is an unreachable loop, it may not have an exit. If it does not + // (i.e., infinite loop), force an exit to make it reachable. + public StopNode forceExit( StopNode stop ) { + // Walk the backedge, then immediate dominator tree util we hit this + // Loop again. If we ever hit a CProj from an If (as opposed to + // directly on the If) we found our exit. + CFGNode x = back(); + while( x != this ) { + if( x instanceof CProjNode exit && exit.in(0) instanceof IfNode iff ) { + CFGNode other = iff.cproj(1-exit._idx); + if( other.loopDepth() < loopDepth() ) + return stop; // Found an exit, not an infinite loop + } + x = x.idom(); + } + // Found a no-exit loop. Insert an exit + NeverNode iff = new NeverNode(back()); + for( Node use : _outputs ) + if( use instanceof PhiNode phi ) + iff.addDef(use); + CProjNode t = new CProjNode(iff,0,"True" ); + CProjNode f = new CProjNode(iff,1,"False"); + setDef(2,f); + stop.addDef(new ReturnNode(t,Parser.ZERO,null)); + return stop; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/MemOpNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/MemOpNode.java new file mode 100644 index 00000000..82aab8ac --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/MemOpNode.java @@ -0,0 +1,55 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeMemPtr; + +/** + * Convenience common base for Load and Store. + */ +public abstract class MemOpNode extends Node { + + public final String _name; + public final int _alias; + // Declared type; not final because it might be a forward-reference + // which will be lazily improved when the reference is declared. + public Type _declaredType; + + public MemOpNode(String name, int alias, Type glb, Node mem, Node ptr, Node off) { + super(null, mem, ptr, off); + _name = name; + _alias = alias; + _declaredType = glb; + } + public MemOpNode(String name, int alias, Type glb, Node mem, Node ptr, Node off, Node value) { + this(name, alias, glb, mem, ptr, off); + addDef(value); + } + + // + static String mlabel(String name) { return name.equals("[]") ? "ary" : (name.equals("#") ? "len" : name); } + String mlabel() { return mlabel(_name); } + + public Node mem() { return in(1); } + public Node ptr() { return in(2); } + public Node off() { return in(3); } + + @Override + boolean eq(Node n) { + MemOpNode mem = (MemOpNode)n; // Invariant + return _alias==mem._alias; // When comparing types error to use "equals"; always use "==" + } + + @Override + int hash() { return _alias; } + + @Override + String err() { + Type ptr = ptr()._type; + // Already an error, but better error messages come from elsewhere + if( ptr == Type.BOTTOM ) return null; + // Better be a not-nil TMP + if( ptr instanceof TypeMemPtr tmp && !tmp._nil ) + return null; + return "Might be null accessing '" + _name + "'"; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/MinusFNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/MinusFNode.java new file mode 100644 index 00000000..9727f58b --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/MinusFNode.java @@ -0,0 +1,36 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; + +import java.util.BitSet; + +public class MinusFNode extends Node { + public MinusFNode(Node in) { super(null, in); } + + @Override public String label() { return "MinusF"; } + + @Override public String glabel() { return "-"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("(-"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeFloat i0) + return i0.isConstant() ? TypeFloat.constant(-i0.value()) : i0; + return TypeFloat.BOT; + } + + @Override + public Node idealize() { + // -(-x) is x + if( in(1) instanceof MinusFNode minus ) + return minus.in(1); + + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/MinusNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/MinusNode.java new file mode 100644 index 00000000..760a4274 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/MinusNode.java @@ -0,0 +1,42 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; +import com.seaofnodes.simple.Utils; + +import java.util.BitSet; + +public class MinusNode extends Node { + public MinusNode(Node in) { super(null, in); } + + @Override public String label() { return "Minus"; } + + @Override public String glabel() { return "-"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("(-"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if( in(1)._type instanceof TypeInteger i0 ) { + if( i0.isHigh() ) return TypeInteger.TOP; + if( i0==TypeInteger.BOT || i0._min == Long.MIN_VALUE || i0._max == Long.MIN_VALUE ) + return TypeInteger.BOT; + return TypeInteger.make(-i0._max,-i0._min); + } + return TypeInteger.TOP.meet(in(1)._type); + } + + @Override + public Node idealize() { + // -(-x) is x + if( in(1) instanceof MinusNode minus ) + return minus.in(1); + + return null; + } + @Override Node copyF() { return new MinusFNode(null); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/MulFNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/MulFNode.java new file mode 100644 index 00000000..2d44a9fb --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/MulFNode.java @@ -0,0 +1,51 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; + +import java.util.BitSet; + +public class MulFNode extends Node { + public MulFNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "MulF"; } + + @Override public String glabel() { return "*"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("*"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeFloat i0 && + in(2)._type instanceof TypeFloat i1) { + if (i0.isConstant() && i1.isConstant()) + return TypeFloat.constant(i0.value()*i1.value()); + } + return in(1)._type.meet(in(2)._type); + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // Mul of 1. We do not check for (1*x) because this will already + // canonicalize to (x*1) + if ( t2.isConstant() && t2 instanceof TypeFloat i && i.value()==1 ) + return lhs; + + // Move constants to RHS: con*arg becomes arg*con + if ( t1.isConstant() && !t2.isConstant() ) + return swap12(); + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new MulFNode(lhs,rhs); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/MulNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/MulNode.java new file mode 100644 index 00000000..b5ef91e9 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/MulNode.java @@ -0,0 +1,63 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class MulNode extends Node { + public MulNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Mul"; } + + @Override public String glabel() { return "*"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("*"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if( t1 instanceof TypeInteger i1 && + t2 instanceof TypeInteger i2 ) { + if( i1==TypeInteger.ZERO || i2==TypeInteger.ZERO) + return TypeInteger.ZERO; + if (i1.isConstant() && i2.isConstant()) + return TypeInteger.constant(i1.value()*i2.value()); + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // Mul of 1. We do not check for (1*x) because this will already + // canonicalize to (x*1) + if ( t2.isConstant() && t2 instanceof TypeInteger i && i.value()==1 ) + return lhs; + + // Move constants to RHS: con*arg becomes arg*con + if ( t1.isConstant() && !t2.isConstant() ) + return swap12(); + + // Do we have ((x * (phi cons)) * con) ? + // Do we have ((x * (phi cons)) * (phi cons)) ? + // Push constant up through the phi: x * (phi con0*con0 con1*con1...) + Node phicon = AddNode.phiCon(this,true); + if( phicon!=null ) return phicon; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new MulNode(lhs,rhs); } + @Override Node copyF() { return new MulFNode(null,null); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/MultiNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/MultiNode.java new file mode 100644 index 00000000..ac9c0045 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/MultiNode.java @@ -0,0 +1,20 @@ +package com.seaofnodes.simple.node; + +public interface MultiNode extends OutNode { + + // Find a projection by index + default ProjNode proj( int idx ) { + for( Node out : outs() ) + if( out instanceof ProjNode prj && prj._idx==idx ) + return prj; + return null; + } + + // Find a projection by index + default CProjNode cproj( int idx ) { + for( Node out : outs() ) + if( out instanceof CProjNode prj && prj._idx==idx ) + return prj; + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/NeverNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/NeverNode.java new file mode 100644 index 00000000..e77ed653 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/NeverNode.java @@ -0,0 +1,21 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.TypeInteger; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeTuple; + +import java.util.BitSet; + +// "Never true" for infinite loop exits +public class NeverNode extends IfNode { + public NeverNode(Node ctrl) { super(ctrl,Parser.ZERO); } + + @Override public String label() { return "Never"; } + + @Override StringBuilder _print1(StringBuilder sb, BitSet visited) { return sb.append("Never"); } + + @Override public Type compute() { return TypeTuple.IF_BOTH; } + + @Override public Node idealize() { return null; } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/NewNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/NewNode.java new file mode 100644 index 00000000..ddb1e09a --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/NewNode.java @@ -0,0 +1,75 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.*; +import com.seaofnodes.simple.Utils; +import java.util.BitSet; + +/** + * Allocation! Allocate a chunk of memory, and pre-zero it. + * The inputs include control and size, and ALL aliases being set. + * The output is large tuple, one for every alias plus the created pointer. + * New is expected to be followed by projections for every alias. + */ +public class NewNode extends Node implements MultiNode { + + public final TypeMemPtr _ptr; + public final int _len; + + public NewNode(TypeMemPtr ptr, Node... nodes) { + super(nodes); + _ptr = ptr; + _len = ptr._obj._fields.length; + // Control in slot 0 + assert nodes[0]._type==Type.CONTROL || nodes[0]._type == Type.XCONTROL; + // Malloc-length in slot 1 + assert nodes[1]._type instanceof TypeInteger; + for( int i=0; i<_len; i++ ) { + // Memory slices for all fields. + assert nodes[2+ i]._type instanceof TypeMem; + // Value slices for all fields. + assert nodes[2 + _len + i]._type != null; + } + } + + @Override public String label() { + return "new_"+glabel(); + } + @Override public String glabel() { + return _ptr._obj.isAry() ? "ary_"+_ptr._obj._fields[1]._type.str() : _ptr._obj.str(); + } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("new "); + return sb.append(_ptr._obj.str()); + } + + // Find matching alias input + int findAlias(int alias) { + return 2+_ptr._obj.findAlias(alias)+_len; + } + + + @Override + public TypeTuple compute() { + Field[] fs = _ptr._obj._fields; + Type[] ts = new Type[fs.length+2]; + ts[0] = Type.CONTROL; + ts[1] = _ptr; + for( int i=0; i<fs.length; i++ ) { + TypeMem mem = (TypeMem)in(i+2)._type; + Type tfld = in(2+_len+i)._type.meet(mem._t); + ts[i+2] = TypeMem.make(fs[i]._alias,tfld); + } + return TypeTuple.make(ts); + } + + @Override + public Node idealize() { return null; } + + @Override + boolean eq(Node n) { return this == n; } + + @Override + int hash() { return _ptr.hashCode(); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/Node.java b/chapter18/src/main/java/com/seaofnodes/simple/node/Node.java new file mode 100644 index 00000000..3827fdac --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/Node.java @@ -0,0 +1,649 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Ary; +import com.seaofnodes.simple.IRPrinter; +import com.seaofnodes.simple.IterPeeps; +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; +import java.util.*; +import java.util.function.Function; + +/** + * All Nodes in the Sea of Nodes IR inherit from the Node class. + * The Node class provides common functionality used by all subtypes. + * Subtypes of Node specialize by overriding methods. + */ +public abstract class Node implements OutNode { + + /** + * Each node has a unique dense Node ID within a compilation context + * The ID is useful for debugging, for using as an offset in a bitvector, + * as well as for computing equality of nodes (to be implemented later). + */ + public final int _nid; + + /** + * Inputs to the node. These are use-def references to Nodes. + * <p> + * Generally fixed length, ordered, nulls allowed, no unused trailing space. + * Ordering is required because e.g. "a/b" is different from "b/a". + * The first input (offset 0) is often a {@link CFGNode} node. + */ + public final Ary<Node> _inputs; + + /** + * Outputs reference Nodes that are not null and have this Node as an + * input. These nodes are users of this node, thus these are def-use + * references to Nodes. + * <p> + * Outputs directly match inputs, making a directed graph that can be + * walked in either direction. These outputs are typically used for + * efficient optimizations but otherwise have no semantics meaning. + */ + public final Ary<Node> _outputs; + + + /** + * Current computed type for this Node. This value changes as the graph + * changes and more knowledge is gained about the program. + */ + public Type _type; + + + /** + * A private Global Static mutable counter, for unique node id generation. + * To make the compiler multithreaded, this field will have to move into a TLS. + * Starting with value 1, to avoid bugs confusing node ID 0 with uninitialized values. + * */ + private static int UNIQUE_ID = 1; + public static int UID() { return UNIQUE_ID; } + + protected Node(Node... inputs) { + _nid = UNIQUE_ID++; // allocate unique dense ID + _inputs = new Ary<>(Node.class); + Collections.addAll(_inputs,inputs); + _outputs = new Ary<>(Node.class); + for( Node n : _inputs ) + if( n != null ) + n.addUse( this ); + } + + // Easy reading label for debugger, e.g. "Add" or "Region" or "EQ" + public abstract String label(); + + // Unique label for graph visualization, e.g. "Add12" or "Region30" or "EQ99" + public String uniqueName() { + // Get rid of $ as graphviz doesn't like it + String label = label().replaceAll("\\$", ""); + return label + _nid; + } + + // Graphical label, e.g. "+" or "Region" or "==" + public String glabel() { return label(); } + + + // ------------------------------------------------------------------------ + + // Debugger Printing. + + // {@code toString} is what you get in the debugger. It has to print 1 + // line (because this is what a debugger typically displays by default) and + // has to be robust with broken graph/nodes. + @Override + public final String toString() { return print(); } + + // This is a *deep* print. We print with a tik-tok style; the common + // _print0 calls the per-Node _print1, which calls back to _print0; + public final String print() { + return _print0(new StringBuilder(), new BitSet()).toString(); + } + + // This is the common print: check for repeats, check for DEAD and print + // "DEAD" else call the per-Node print1. + final StringBuilder _print0(StringBuilder sb, BitSet visited) { + if (visited.get(_nid) && !(this instanceof ConstantNode) ) + return sb.append(label()); + visited.set(_nid); + return isDead() + ? sb.append(uniqueName()).append(":DEAD") + : _print1(sb, visited); + } + // Every Node implements this; a partial-line recursive print + abstract StringBuilder _print1(StringBuilder sb, BitSet visited); + + public String p(int depth) { return IRPrinter.prettyPrint(this,depth); } + + public boolean isMultiHead() { return false; } + public boolean isMultiTail() { return false; } + + // ------------------------------------------------------------------------ + // Graph Node & Edge manipulation + + /** + * Gets the ith input node + * @param i Offset of the input node + * @return Input node or null + */ + public Node in(int i) { return _inputs.get(i); } + public Node out(int i) { return _outputs.get(i); } + @Override public Ary<Node> outs() { return _outputs; } + + public int nIns() { return _inputs.size(); } + + public int nOuts() { return _outputs.size(); } + + public boolean isUnused() { return nOuts() == 0; } + + public CFGNode cfg0() { return (CFGNode)in(0); } + + /** + * Change a <em>def</em> into a Node. Keeps the edges correct, by removing + * the corresponding <em>use->def</em> edge. This may make the original + * <em>def</em> go dead. This function is co-recursive with {@link #kill}. + * <p> + + * This method is the normal path for altering a Node, because it does the + * proper default edge maintenance. It also <em>immediately</em> kills + * Nodes that lose their last use; at times care must be taken to avoid + * killing Nodes that are being used without having an output Node. This + * definitely happens in the middle of recursive {@link #peephole} calls. + * + * @param idx which def to set + * @param new_def the new definition + * @return new_def for flow coding + */ + public <N extends Node> N setDef(int idx, N new_def ) { + unlock(); + Node old_def = in(idx); + if( old_def == new_def ) return new_def; // No change + // If new def is not null, add the corresponding def->use edge + // This needs to happen before removing the old node's def->use edge as + // the new_def might get killed if the old node kills it recursively. + if( new_def != null ) + new_def.addUse(this); + // Set the new_def over the old (killed) edge + _inputs.set(idx,new_def); + if( old_def != null && // If the old def exists, remove a def->use edge + old_def.delUse(this) ) // If we removed the last use, the old def is now dead + old_def.kill(); // Kill old def + moveDepsToWorklist(); + // Return new_def for easy flow-coding + return new_def; + } + + // Remove the numbered input, compressing the inputs in-place. This + // shuffles the order deterministically - which is suitable for Region and + // Phi, but not for every Node. If the def goes dead, it is recursively + // killed, which may include 'this' Node. + Node delDef(int idx) { + unlock(); + Node old_def = in(idx); + _inputs.del(idx); + if( old_def.delUse(this) ) // If we removed the last use, the old def is now dead + old_def.kill(); // Kill old def + old_def.moveDepsToWorklist(); + return this; + } + + // Insert the numbered input, sliding other inputs to the right + Node insertDef(int idx, Node new_def) { + _inputs.add(idx,null); + return setDef(idx,new_def); + } + + + /** + * Add a new def to an existing Node. Keep the edges correct by + * adding the corresponding <em>def->use</em> edge. + * + * @param new_def the new definition, appended to the end of existing definitions + * @return new_def for flow coding + */ + public Node addDef(Node new_def) { + unlock(); + // Add use->def edge + _inputs.add(new_def); + // If new def is not null, add the corresponding def->use edge + if( new_def != null ) + new_def.addUse(this); + return new_def; + } + + // Breaks the edge invariants, used temporarily + protected <N extends Node> N addUse(Node n) { _outputs.add(n); return (N)this; } + + // Remove node 'use' from 'def's (i.e. our) output list, by compressing the list in-place. + // Return true if the output list is empty afterward. + // Error is 'use' does not exist; ok for 'use' to be null. + protected boolean delUse( Node use ) { + _outputs.del(_outputs.find(use)); + return _outputs.isEmpty(); + } + + // Shortcut for "popping" until n nodes. A "pop" is basically a + // setDef(last,null) followed by lowering the nIns() count. + void popUntil(int n) { + unlock(); + while( nIns() > n ) { + Node old_def = _inputs.pop(); + if( old_def != null && // If it exists and + old_def.delUse(this) ) // If we removed the last use, the old def is now dead + old_def.kill(); // Kill old def + } + } + + /** + * Kill a Node with no <em>uses</em>, by setting all of its <em>defs</em> + * to null. This may recursively kill more Nodes, and is basically dead + * code elimination. + */ + public void kill( ) { + unlock(); + moveDepsToWorklist(); + assert isUnused(); // Has no uses, so it is dead + _type=null; // Flag as dead + while( nIns()>0 ) { // Set all inputs to null, recursively killing unused Nodes + Node old_def = _inputs.removeLast(); + if( old_def != null ) { + IterPeeps.add(old_def);// Revisit neighbor because removed use + if( old_def.delUse(this) ) // If we removed the last use, the old def is now dead + old_def.kill(); // Kill old def + } + } + assert isDead(); // Really dead now + } + + // Mostly used for asserts and printing. + public boolean isDead() { return isUnused() && nIns()==0 && _type==null; } + + // Shortcuts to stop DCE mid-parse + // Add bogus null use to keep node alive + public <N extends Node> N keep() { return addUse(null); } + // Remove bogus null. + public <N extends Node> N unkeep() { + delUse(null); + return (N)this; + } + // Test "keep" status + public boolean iskeep() { return _outputs.find(null) != -1; } + public void unkill() { + if( unkeep().isUnused() ) + kill(); + } + + + // Replace self with nnn in the graph, making 'this' go dead + public void subsume( Node nnn ) { + assert nnn!=this; + while( nOuts() > 0 ) { + Node n = _outputs.removeLast(); + n.unlock(); + int idx = n._inputs.find(this); + n._inputs.set(idx,nnn); + nnn.addUse(n); + IterPeeps.addAll(n._outputs); + } + kill(); + } + + // ------------------------------------------------------------------------ + // Graph-based optimizations + + /** + * We allow disabling peephole opt so that we can observe the + * full graph, vs the optimized graph. + */ + public static boolean _disablePeephole = false; + + /** + * Try to peephole at this node and return a better replacement Node. + * Always returns some not-null Node (often this). + */ + public final Node peephole( ) { + if (_disablePeephole) { + _type = compute(); + return this; // Peephole optimizations turned off + } + Node n = peepholeOpt(); + return n==null ? this : deadCodeElim(n.peephole()); // Cannot return null for no-progress + } + + /** + * Try to peephole at this node and return a better replacement Node if + * possible. We compute a {@link Type} and then check and replace: + * <ul> + * <li>if the Type {@link Type#isConstant}, we replace with a {@link ConstantNode}</li> + * <li>in a future chapter we will look for a + * <a href="https://en.wikipedia.org/wiki/Common_subexpression_elimination">Common Subexpression</a> + * to eliminate.</li> + * <li>we ask the Node for a better replacement. The "better replacement" + * is things like {@code (1+2)} becomes {@code 3} and {@code (1+(x+2))} becomes + * {@code (x+(1+2))}. By canonicalizing expressions we fold common addressing + * math constants, remove algebraic identities and generally simplify the + * code. </li> + * + * Unlike peephole above, this explicitly returns null for no-change, or not-null + * for a better replacement (which can be this). + * </ul> + */ + public final Node peepholeOpt( ) { + ITER_CNT++; + // Compute initial or improved Type + Type old = setType(compute()); + + // Replace constant computations from non-constants with a constant node + if( !(this instanceof ConstantNode) && !(this instanceof XCtrlNode) && _type.isHighOrConst() ) + return (_type==Type.XCONTROL ? new XCtrlNode() : new ConstantNode(_type)).peepholeOpt(); + + // Global Value Numbering + if( _hash==0 ) { + Node n = GVN.get(this); // Will set _hash as a side effect + if( n==null ) + GVN.put(this,this); // Put in table now + else { + // Because of random worklist ordering, the two equal nodes + // might have different types. Because of monotonicity, both + // types are valid. To preserve monotonicity, the resulting + // shared Node has to have the best of both types. + n.setType(n._type.join(_type)); + _hash = 0; // Clear, since it never went in the table + return deadCodeElim(n);// Return previous; does Common Subexpression Elimination + } + } + + // Ask each node for a better replacement + Node n = idealize(); + if( n != null ) // Something changed + return n; // Report progress + + if( old==_type ) ITER_NOP_CNT++; + return old==_type ? null : this; // Report progress + } + public static int ITER_CNT, ITER_NOP_CNT; + + // m is the new Node, self is the old. + // Return 'm', which may have zero uses but is alive nonetheless. + // If self has zero uses (and is not 'm'), {@link #kill} self. + private Node deadCodeElim(Node m) { + // If self is going dead and not being returned here (Nodes returned + // from peephole commonly have no uses (yet)), then kill self. + if( m != this && isUnused() && !isDead() ) { + // Killing self - and since self recursively kills self's inputs we + // might end up killing 'm', which we are returning as a live Node. + // So we add a bogus extra null output edge to stop kill(). + m.keep(); // Keep m alive + kill(); // Kill self because replacing with 'm' + m.unkeep(); // Okay to peephole m + } + return m; + } + + /** + * This function needs to be + * <a href="https://en.wikipedia.org/wiki/Monotonic_function">Monotonic</a> + * as it is part of a Monotone Analysis Framework. + * <a href="https://www.cse.psu.edu/~gxt29/teaching/cse597s21/slides/08monotoneFramework.pdf">See for example this set of slides</a>. + * <p> + * For Chapter 2, all our Types are really integer constants, and so all + * the needed properties are trivially true, and we can ignore the high + * theory. Much later on, this will become important and allow us to do + * many fancy complex optimizations trivially... because theory. + * <p> + * {@link #compute()} needs to be stand-alone, and cannot recursively call compute + * on its inputs, because programs are cyclic (have loops!) and this will just + * infinitely recurse until stack overflow. Instead, compute typically + * computes a new type from the {@link #_type} field of its inputs. + */ + public abstract Type compute(); + + // Set the type. Assert monotonic progress. + // If changing, add users to worklist. + public Type setType(Type type) { + Type old = _type; + assert old==null || type.isa(old); // Since _type not set, can just re-run this in assert in the debugger + if( old == type ) return old; + _type = type; // Set _type late for easier assert debugging + IterPeeps.addAll(_outputs); + moveDepsToWorklist(); + return old; + } + + + /** + * This function rewrites the current Node into a more "idealized" form. + * This is the bulk of our peephole rewrite rules, and we use this to + * e.g. turn arbitrary collections of adds and multiplies with mixed + * constants into a normal form that's easy for hardware to implement. + * Example: An array addressing expression: + * <pre> ary[idx+1]</pre> + * might turn into Sea-of-Nodes IR: + * <pre> (ary+12)+((idx+1) * 4)</pre> + * This expression can then be idealized into: + * <pre> ary + ((idx*4) + (12 + (1*4)))</pre> + * And more folding: + * <pre> ary + ((idx<<2) + 16)</pre> + * And during code-gen: + * <pre> MOV4 Rary,[Ridx<<2 +16] // or some such hardware-specific notation </pre> + * <p> + * {@link #idealize} has a very specific calling convention: + * <ul> + * <li>If NO change is made, return {@code null} + * <li>If ANY change is made, return not-null; this can be {@code this} + * <li>The returned Node does NOT call {@link #peephole} on itself; the {@link #peephole} call will recursively peephole it. + * <li>Any NEW nodes that are not directly returned DO call {@link #peephole}. + * </ul> + * <p> + * Examples: + * <table border="3"> + * <tr><th> before </th><th> after </th><th>return </th><th>comment </th></tr> + * <tr><td>{@code (x+5) }</td><td>{@code (x+5) }</td><td>{@code null }</td><td>No change</td></tr> + * <tr><td>{@code (5+x) }</td><td>{@code (x+5) }</td><td>{@code this }</td><td>Swapped arguments</td></tr> + * <tr><td>{@code ((x+1)+2)}</td><td>{@code (x+(1+2))}</td><td>{@code (x+_) }</td><td>Returns 2 new Nodes</td></tr> + * </table> + * + * The last entry deserves more discussion. The new Node {@code (1+2)} + * created in {@link #idealize} calls {@link #peephole} (which then folds + * into a constant). The other new Node {@code (x+3)} does not call + * peephole, because it is returned and peephole itself will recursively + * call peephole. + * <p> + * Since idealize calls peephole and peephole calls idealize, you must be + * careful that all idealizations are <em>monotonic</em>: all transforms + * remove some feature, so that the set of available transforms always + * shrinks. If you don't, you risk an infinite peephole loop! + * + * @return Either a new or changed node, or null for no changes. + */ + public abstract Node idealize(); + + + // Some of the peephole rules get complex, and search further afield than + // just the nearest neighbor. These peepholes can fail the pattern match + // on a node some distance away, and if that node ever changes we should + // retry the peephole. Track a set of Nodes dependent on `this`, and + // revisit them if `this` changes. + Ary<Node> _deps; + + /** + * Add a node to the list of dependencies. Only add it if its not an input + * or output of this node, that is, it is at least one step away. The node + * being added must benefit from this node being peepholed. + */ + Node addDep( Node dep ) { + // Running peepholes during the big assert cannot have side effects + // like adding dependencies. + if( IterPeeps.midAssert() ) return this; + if( _deps==null ) _deps = new Ary<>(Node.class); + if( _deps .find(dep) != -1 ) return this; // Already on list + if( _inputs .find(dep) != -1 ) return this; // No need for deps on immediate neighbors + if( _outputs.find(dep) != -1 ) return this; + _deps.add(dep); + return this; + } + + // Move the dependents onto a worklist, and clear for future dependents. + public void moveDepsToWorklist( ) { + if( _deps==null ) return; + IterPeeps.addAll(_deps); + _deps.clear(); + } + + + // Global Value Numbering. Hash over opcode and inputs; hits in this table + // are structurally equal. + public static final HashMap<Node,Node> GVN = new HashMap<>(); + + // Two nodes are equal if they have the same inputs and the same "opcode" + // which means the same Java class, plus same internal parts. + @Override public final boolean equals( Object o ) { + if( o==this ) return true; + if( o.getClass() != getClass() ) return false; + Node n = (Node)o; + int len = _inputs.size(); + if( len != n._inputs.size() ) return false; + for( int i=0; i<len; i++ ) + if( in(i) != n.in(i) ) + return false; + return eq(n); + } + // Subclasses add extra checks (such as ConstantNodes have same constant), + // and can assume "this!=n" and has the same Java class. + boolean eq( Node n ) { return true; } + + + // Cached hash. If zero, then not computed AND this Node is NOT in the GVN + // table - and can have its edges hacked (which will change his hash + // anyway). If Non-Zero then this Node is IN the GVN table, or is being + // probed to see if it can be inserted. His edges are "locked", because + // hacking his edges will change his hash. + int _hash; + + // If the _hash is set, then the Node is in the GVN table; remove it. + void unlock() { + if( _hash==0 ) return; + Node old = GVN.remove(this); // Pull from table + assert old==this; + _hash=0; // Out of table now + } + + + // Hash of opcode and inputs + @Override public final int hashCode() { + if( _hash != 0 ) return _hash; + int hash = hash(); + for( Node n : _inputs ) + if( n != null ) + hash = hash ^ (hash<<17) ^ (hash>>13) ^ n._nid; + if( hash==0 ) hash = 0xDEADBEEF; // Bad hash, so use some junky thing + return (_hash=hash); + } + // Subclasses add extra hash info (such as ConstantNodes constant) + int hash() { return 0; } + + // ------------------------------------------------------------------------ + // + + /** Is this Node Memory related */ + public boolean isMem() { return false; } + + /** Pinned in the schedule; these are data nodes whose input#0 is not allowed to change */ + public boolean isPinned() { return false; } + + // Semantic change to the graph (so NOT a peephole), used by the Parser. + // If any input is a float, flip to a float-flavored opcode and widen any + // non-float input. + public final Node widen() { + if( !hasFloatInput() ) return this; + Node flt = copyF(); + if( flt==null ) return this; + for( int i=1; i<nIns(); i++ ) + flt.setDef(i, in(i)._type instanceof TypeFloat ? in(i) : new ToFloatNode(in(i)).peephole()); + kill(); + return flt; + } + private boolean hasFloatInput() { + for( int i=1; i<nIns(); i++ ) + if( in(i)._type instanceof TypeFloat ) + return true; + return false; + } + Node copyF() { return null; } + + + // ------------------------------------------------------------------------ + // Peephole utilities + + // Swap inputs without letting either input go dead during the swap. + Node swap12() { + unlock(); // Hash is order dependent + Node tmp = in(1); + _inputs.set(1,in(2)); + _inputs.set(2,tmp); + return this; + } + + /** + * Does this node contain all constants? Ignores in(0), as is usually + * control. In an input is not a constant, we add dep as a dependency to + * it because dep can make progress if the input becomes a constant later. + * It is sufficient for one of the non-const inputs to have the dependency, + * so we don't bother checking the rest. + */ + boolean allCons(Node dep) { + for( int i=1; i<nIns(); i++ ) + if( !(in(i)._type.isConstant()) ) { + in(i).addDep(dep); // If in(i) becomes a constant later, will trigger some peephole + return false; + } + return true; + } + + + // Make a shallow copy (same class) of this Node, with given inputs and + // empty outputs and a new Node ID. The original inputs are ignored. + // Does not need to be implemented in isCFG() nodes. + Node copy(Node lhs, Node rhs) { throw Utils.TODO("Binary ops need to implement copy"); } + + // Report any post-optimize errors + String err() { return null; } + + /** + * Used to allow repeating tests in the same JVM. This just resets the + * Node unique id generator, and is done as part of making a new Parser. + */ + public static void reset() { + UNIQUE_ID = 1; + _disablePeephole=false; + GVN.clear(); + ITER_CNT = ITER_NOP_CNT = 0; + } + + + // Utility to walk the entire graph applying a function; return the first + // not-null result. + private static final BitSet WVISIT = new BitSet(); + final public <E> E walk( Function<Node,E> pred ) { + assert WVISIT.isEmpty(); + E rez = _walk(pred); + WVISIT.clear(); + return rez; + } + + private <E> E _walk( Function<Node,E> pred ) { + if( WVISIT.get(_nid) ) return null; // Been there, done that + WVISIT.set(_nid); + E x = pred.apply(this); + if( x != null ) return x; + for( Node def : _inputs ) if( def != null && (x = def._walk(pred)) != null ) return x; + for( Node use : _outputs ) if( use != null && (x = use._walk(pred)) != null ) return x; + return null; + } + + /** + * Debugging utility to find a Node by index + */ + public Node find(int nid) { + return walk( n -> n._nid==nid ? n : null ); + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/NotNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/NotNode.java new file mode 100644 index 00000000..664d7c7b --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/NotNode.java @@ -0,0 +1,44 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.*; +import java.util.BitSet; + +public class NotNode extends Node { + public NotNode(Node in) { super(null, in); } + + @Override public String label() { return "Not"; } + + @Override public String glabel() { return "!"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("(!"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t0 = in(1)._type; + if( t0.isHigh() ) return TypeInteger.BOOL.dual(); + switch( t0 ) { + case TypeInteger i0: return i0._max < 0 || i0._min > 0 ? TypeInteger.FALSE : (i0==TypeInteger.ZERO ? TypeInteger.TRUE : TypeInteger.BOOL); + case TypeFloat i0: return i0.isConstant() ? TypeInteger.constant(i0.value()==0 ? 1 : 0) : i0; + case TypeMemPtr p0: + // top->top, bot->bot, null->1, *void->0, not-null ptr->0, ptr/nil->bot + // If input in null then true + // If input is not null ptr then false + if( p0 == TypeMemPtr.NULLPTR ) return TypeInteger.TRUE; + if( !p0._nil ) return TypeInteger.FALSE; + return TypeInteger.BOOL; + case Type t: + if( t0.getClass() != Type.class ) + // Only doing NOT on ints and ptrs + throw Utils.TODO(); + return TypeInteger.BOOL; + } + } + + @Override + public Node idealize() { return null; } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/OrNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/OrNode.java new file mode 100644 index 00000000..b572346f --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/OrNode.java @@ -0,0 +1,65 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class OrNode extends Node { + public OrNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Or"; } + + @Override public String glabel() { return "|"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("|"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if( t1 instanceof TypeInteger i0 && + t2 instanceof TypeInteger i1 ) { + if( i0.isConstant() && i1.isConstant() ) + return TypeInteger.constant(i0.value()|i1.value()); + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // Or of 0. We do not check for (0|x) because this will already + // canonicalize to (x|0) + if( t2.isConstant() && t2 instanceof TypeInteger i && i.value()==0 ) + return lhs; + + // Move constants to RHS: con*arg becomes arg*con + if ( t1.isConstant() && !t2.isConstant() ) + return swap12(); + + // Do we have ((x | (phi cons)) | con) ? + // Do we have ((x | (phi cons)) | (phi cons)) ? + // Push constant up through the phi: x | (phi con0|con0 con1|con1...) + Node phicon = AddNode.phiCon(this,true); + if( phicon!=null ) return phicon; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new OrNode(lhs,rhs); } + @Override String err() { + if( !(in(1)._type instanceof TypeInteger) ) return "Cannot '|' " + in(1)._type; + if( !(in(2)._type instanceof TypeInteger) ) return "Cannot '|' " + in(2)._type; + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/OutNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/OutNode.java new file mode 100644 index 00000000..dbac136b --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/OutNode.java @@ -0,0 +1,7 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Ary; + +public interface OutNode { + Ary<Node> outs(); +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/PhiNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/PhiNode.java new file mode 100644 index 00000000..cb266ca3 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/PhiNode.java @@ -0,0 +1,160 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeMem; +import com.seaofnodes.simple.Utils; + +import java.util.BitSet; + +public class PhiNode extends Node { + + final String _label; + + // The Phi type we compute must stay within the domain of the Phi. + // Example Int stays Int, Ptr stays Ptr, Control stays Control, Mem stays Mem. + final Type _declaredType; + + public PhiNode(String label, Type declaredType, Node... inputs) { super(inputs); _label = label; assert declaredType!=null; _declaredType = declaredType; } + + @Override public String label() { return "Phi_"+MemOpNode.mlabel(_label); } + + @Override public String glabel() { return "φ_"+_label; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + if( !(region() instanceof RegionNode r) || r.inProgress() ) + sb.append("Z"); + sb.append("Phi("); + for( Node in : _inputs ) { + if (in == null) sb.append("____"); + else in._print0(sb, visited); + sb.append(","); + } + sb.setLength(sb.length()-1); + sb.append(")"); + return sb; + } + + public CFGNode region() { return (CFGNode)in(0); } + @Override public boolean isMultiTail() { return true; } + @Override public boolean isMem() { return _declaredType instanceof TypeMem; } + @Override public boolean isPinned() { return true; } + + @Override + public Type compute() { + if( !(region() instanceof RegionNode r) ) + return region()._type==Type.XCONTROL ? (_type instanceof TypeMem ? TypeMem.TOP : Type.TOP) : _type; + // During parsing Phis have to be computed type pessimistically. + if( r.inProgress() ) return _declaredType; + // Set type to local top of the starting type + Type t = _declaredType.lub(); + for (int i = 1; i < nIns(); i++) + // If the region's control input is live, add this as a dependency + // to the control because we can be peeped should it become dead. + if( r.in(i).addDep(this)._type != Type.XCONTROL ) + t = t.meet(in(i)._type); + return t; + } + + @Override + public Node idealize() { + if( !(region() instanceof RegionNode r ) ) + return in(1); // Input has collapse to e.g. starting control. + if( r.inProgress() || r.nIns()<=1 ) + return null; // Input is in-progress + + // If we have only a single unique input, become it. + Node live = singleUniqueInput(); + if (live != null) + return live; + + // Pull "down" a common data op. One less op in the world. One more + // Phi, but Phis do not make code. + // Phi(op(A,B),op(Q,R),op(X,Y)) becomes + // op(Phi(A,Q,X), Phi(B,R,Y)). + Node op = in(1); + if( op.nIns()==3 && op.in(0)==null && same_op() ) { + assert !(op instanceof CFGNode); + Node[] lhss = new Node[nIns()]; + Node[] rhss = new Node[nIns()]; + lhss[0] = rhss[0] = in(0); // Set Region + for( int i=1; i<nIns(); i++ ) { + lhss[i] = in(i).in(1); + rhss[i] = in(i).in(2); + } + Node phi_lhs = new PhiNode(_label, _declaredType,lhss).peephole(); + Node phi_rhs = new PhiNode(_label, _declaredType,rhss).peephole(); + return op.copy(phi_lhs,phi_rhs); + } + + // If merging Phi(N, cast(N)) - we are losing the cast JOIN effects, so just remove. + if( nIns()==3 ) { + if( in(1) instanceof CastNode cast && cast.in(1).addDep(this)==in(2) ) return in(2); + if( in(2) instanceof CastNode cast && cast.in(1).addDep(this)==in(1) ) return in(1); + } + // If merging a null-checked null and the checked value, just use the value. + // if( val ) ..; phi(Region,False=0/null,True=val); + // then replace with plain val. + if( nIns()==3 ) { + int nullx = -1; + if( in(1)._type == in(1)._type.makeInit() ) nullx = 1; + if( in(2)._type == in(2)._type.makeInit() ) nullx = 2; + if( nullx != -1 ) { + Node val = in(3-nullx); + if( r.idom(this).addDep(this) instanceof IfNode iff && iff.pred().addDep(this)==val ) { + // Must walk the idom on the null side to make sure we hit False. + CFGNode idom = (CFGNode)r.in(nullx); + while( idom.nIns() > 0 && idom.in(0) != iff ) idom = idom.idom(); + if( idom instanceof CProjNode proj && proj._idx==1 ) + return val; + } + } + } + + return null; + } + + private boolean same_op() { + for( int i=2; i<nIns(); i++ ) + if( in(1).getClass() != in(i).getClass() ) + return false; + return true; + } + + /** + * If only single unique input, return it + */ + private Node singleUniqueInput() { + if( region() instanceof LoopNode loop && loop.entry()._type == Type.XCONTROL ) + return null; // Dead entry loops just ignore and let the loop collapse + Node live = null; + for( int i=1; i<nIns(); i++ ) { + // If the region's control input is live, add this as a dependency + // to the control because we can be peeped should it become dead. + if( region().in(i).addDep(this)._type != Type.XCONTROL && in(i) != this ) + if( live == null || live == in(i) ) live = in(i); + else return null; + } + return live; + } + + @Override + boolean allCons(Node dep) { + if( !(region() instanceof RegionNode r) ) return false; + // When the region completes (is no longer in progress) the Phi can + // become a "all constants" Phi, and the "dep" might make progress. + addDep(dep); + if( r.inProgress() ) return false; + return super.allCons(dep); + } + + // True if last input is null + public final boolean inProgress() { + return in(nIns()-1) == null; + } + + // Never equal if inProgress + @Override boolean eq( Node n ) { + return !inProgress(); + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ProjNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ProjNode.java new file mode 100644 index 00000000..73c1fa15 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ProjNode.java @@ -0,0 +1,47 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeMem; +import com.seaofnodes.simple.type.TypeTuple; + +import java.util.BitSet; + +public class ProjNode extends Node { + + // Which slice of the incoming multipart value + public final int _idx; + + // Debugging label + public final String _label; + + public ProjNode(Node ctrl, int idx, String label) { + super(ctrl); + _idx = idx; + _label = label; + } + + @Override public String label() { return _label; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { return sb.append(_label); } + + @Override public CFGNode cfg0() { return in(0).cfg0(); } + + @Override public boolean isMultiTail() { return in(0).isMultiHead(); } + @Override public boolean isMem() { return _type instanceof TypeMem; } + @Override public boolean isPinned() { return true; } + + @Override + public Type compute() { + Type t = in(0)._type; + return t instanceof TypeTuple tt ? tt._types[_idx] : Type.BOTTOM; + } + + @Override public Node idealize() { return null; } + + @Override + boolean eq( Node n ) { return _idx == ((ProjNode)n)._idx; } + + @Override + int hash() { return _idx; } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ReadOnlyNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ReadOnlyNode.java new file mode 100644 index 00000000..fddcaa67 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ReadOnlyNode.java @@ -0,0 +1,29 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeMemPtr; + +import java.util.BitSet; + +/** + * Cast a pointer to read-only + */ +public class ReadOnlyNode extends Node { + public ReadOnlyNode( Node n ) { super(null,n); } + @Override public String label() { return "ReadOnly"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return in(1)._print0(sb.append("(const)"),visited); + } + @Override public Type compute() { + Type t = in(1)._type; + return t instanceof TypeMemPtr tmp ? tmp.makeRO() : t; + } + + @Override public Node idealize() { + if( in(1)._type instanceof TypeMemPtr tmp && tmp.isFinal() ) + return in(1); + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/RegionNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/RegionNode.java new file mode 100644 index 00000000..fb39af17 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/RegionNode.java @@ -0,0 +1,120 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.IterPeeps; +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.Type; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.BitSet; +import java.util.HashSet; + +public class RegionNode extends CFGNode { + + public RegionNode(Node... nodes) { super(nodes); } + + @Override + public String label() { return "Region"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return sb.append(label()); + } + + @Override public boolean isMultiHead() { return true; } + @Override public boolean blockHead() { return true; } + + @Override + public Type compute() { + if( inProgress() ) return Type.CONTROL; + Type t = Type.XCONTROL; + for (int i = 1; i < nIns(); i++) + t = t.meet(in(i)._type); + return t; + } + + @Override + public Node idealize() { + if( inProgress() ) return null; + // Delete dead paths into a Region + int path = findDeadInput(); + if( path != 0 && + // Do not delete the entry path of a loop (ok to remove the back + // edge and make the loop a single-entry Region which folds away + // the Loop). Folding the entry path confused the loop structure, + // moving the backedge to the entry point. + !(this instanceof LoopNode loop && loop.entry()==in(path)) ) { + // Cannot use the obvious output iterator here, because a Phi + // deleting an input might recursively delete *itself*. This + // shuffles the output array, and we might miss iterating an + // unrelated Phi. So on rare occasions we repeat the loop to get + // all the Phis. + int nouts = 0; + while( nouts != nOuts() ) { + nouts = nOuts(); + for( int i=0; i<nOuts(); i++ ) + if( out(i) instanceof PhiNode phi && phi.nIns()==nIns() ) { + phi.delDef(path); + IterPeeps.addAll(phi._outputs); + } + } + return isDead() ? Parser.XCTRL : delDef(path); + } + // If down to a single input, become that input + if( nIns()==2 && !hasPhi() ) + return in(1); // Collapse if no Phis; 1-input Phis will collapse on their own + + // If a CFG diamond with no merging, delete: "if( pred ) {} else {};" + if( !hasPhi() && // No Phi users, just a control user + in(1) instanceof CProjNode p1 && + in(2) instanceof CProjNode p2 && + p1.in(0).addDep(this)==p2.in(0).addDep(this) && + p1.in(0) instanceof IfNode iff ) + return iff.ctrl(); + + return null; + } + + private int findDeadInput() { + for( int i=1; i<nIns(); i++ ) + if( in(i)._type==Type.XCONTROL ) + return i; + return 0; // All inputs alive + } + + private boolean hasPhi() { + for( Node phi : _outputs ) + if( phi instanceof PhiNode ) + return true; + return false; + } + + // Immediate dominator of Region is a little more complicated. + @Override public int idepth() { + if( _idepth!=0 ) return _idepth; + int d=0; + for( Node n : _inputs ) + if( n!=null ) + d = Math.max(d,((CFGNode)n).idepth()+1); + return _idepth=d; + } + + @Override public CFGNode idom(Node dep) { + CFGNode lca = null; + // Walk the LHS & RHS idom trees in parallel until they match, or either fails. + // Because this does not cache, it can be linear in the size of the program. + for( int i=1; i<nIns(); i++ ) + lca = cfg(i)._idom(lca,dep); + return lca; + } + + // True if last input is null + public final boolean inProgress() { + return nIns()>1 && in(nIns()-1) == null; + } + + // Never equal if inProgress + @Override boolean eq( Node n ) { + return !inProgress(); + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ReturnNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ReturnNode.java new file mode 100644 index 00000000..b586a44f --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ReturnNode.java @@ -0,0 +1,50 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.*; + +import java.util.BitSet; + +/** + * The Return node has two inputs. The first input is a control node and the + * second is the data node that supplies the return value. + * <p> + * In this presentation, Return functions as a Stop node, since multiple <code>return</code> statements are not possible. + * The Stop node will be introduced in Chapter 6 when we implement <code>if</code> statements. + * <p> + * The Return's output is the value from the data node. + */ +public class ReturnNode extends CFGNode { + + public ReturnNode(Node ctrl, Node data, ScopeNode scope) { + // Add memory slices to Return, so all memory updates are live-on-exit. + super(ctrl, data); + if( scope!=null ) + for( int i=2; i<scope.mem().nIns(); i++ ) + addDef(scope.mem().in(i)); + } + + public Node ctrl() { return in(0); } + public Node expr() { return in(1); } + + @Override + public String label() { return "Return"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("return "); + expr()._print0(sb, visited); + return sb.append(";"); + } + + @Override + public Type compute() { + return TypeTuple.make(ctrl()._type,expr()._type); + } + + @Override + public Node idealize() { + if( ctrl()._type==Type.XCONTROL ) + return ctrl(); + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/RoundF32Node.java b/chapter18/src/main/java/com/seaofnodes/simple/node/RoundF32Node.java new file mode 100644 index 00000000..44d3a587 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/RoundF32Node.java @@ -0,0 +1,38 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; + +import java.util.BitSet; + +public class RoundF32Node extends Node { + public RoundF32Node(Node lhs) { super(null, lhs); } + + @Override public String label() { return "RoundF32"; } + + @Override public String glabel() { return "(f32)"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return in(1)._print0(sb.append("((f32)"), visited).append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeFloat i0 && i0.isConstant() ) + return TypeFloat.constant((float)i0.value()); + return in(1)._type; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Type t1 = lhs._type; + + // RoundF32 of float + if( t1 instanceof TypeFloat tf && tf._sz==32 ) + return lhs; + + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/SarNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/SarNode.java new file mode 100644 index 00000000..5dc26ad3 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/SarNode.java @@ -0,0 +1,61 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class SarNode extends Node { + public SarNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Sar"; } + + @Override public String glabel() { return ">>"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append(">>"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if (t1 instanceof TypeInteger i0 && + t2 instanceof TypeInteger i1) { + if( i0 == TypeInteger.ZERO ) + return TypeInteger.ZERO; + if( i0.isConstant() && i1.isConstant() ) + return TypeInteger.constant(i0.value()>>i1.value()); + if( i1.isConstant() ) { + int log = (int)i1.value(); + return TypeInteger.make(-1L<<(63-log),(1L<<(63-log))-1); + } + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t2 = rhs._type; + + // Sar of 0. + if( t2.isConstant() && t2 instanceof TypeInteger i && (i.value()&63)==0 ) + return lhs; + + // TODO: x >> 3 >> (y ? 1 : 2) ==> x >> (y ? 4 : 5) + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new SarNode(lhs,rhs); } + @Override String err() { + if( !(in(1)._type instanceof TypeInteger) ) return "Cannot '>>' " + in(1)._type; + if( !(in(2)._type instanceof TypeInteger) ) return "Cannot '>>' " + in(2)._type; + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ScopeMinNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ScopeMinNode.java new file mode 100644 index 00000000..9134f9c3 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ScopeMinNode.java @@ -0,0 +1,150 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.IterPeeps; +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.*; +import java.util.*; + +import static com.seaofnodes.simple.Utils.TODO; + +/* */ +public class ScopeMinNode extends Node { + + /** The tracked fields are now complex enough to deserve a array-of-structs layout + */ + public static class Var { + public final int _idx; // index in containing scope + public final String _name; // Declared name + private Type _type; // Declared type + public final boolean _final; // Final field + public Var(int idx, String name, Type type, boolean xfinal) { + _idx = idx; + _name = name; + _type = type; + _final = xfinal; + } + public Type type() { + if( !_type.isFRef() ) return _type; + // Update self to no longer use the forward ref type + Type def = Parser.TYPES.get(((TypeMemPtr)_type)._obj._name); + return (_type=_type.meet(def)); + } + public Type lazyGLB() { + Type t = type(); + return t instanceof TypeMemPtr ? t : t.glb(); + } + @Override public String toString() { + return _type.toString()+(_final ? " ": " !")+_name; + } + } + + public ScopeMinNode() { _type = TypeMem.BOT; } + + + @Override public String label() { return "MEM"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("MEM[ "); + for( int j=2; j<nIns(); j++ ) { + sb.append(j); + sb.append(":"); + Node n = in(j); + while( n instanceof ScopeNode loop ) { + sb.append("Lazy_"); + n = loop.in(j); + } + if( n==null ) sb.append("___ "); + else n._print0(sb, visited).append(" "); + } + sb.setLength(sb.length()-1); + return sb.append("]"); + } + + + @Override public Type compute() { return TypeMem.BOT; } + + @Override public Node idealize() { return null; } + + public Node in( Var v ) { return in(v._idx); } + + Node alias( int alias ) { + return in(alias<nIns() && in(alias)!=null ? alias : 1); + } + + Node alias( int alias, Node st ) { + while( alias >= nIns() ) addDef(null); + return setDef(alias,st); + } + + + // Read or update from memory. + // A shared implementation allows us to create lazy phis both during + // lookups and updates; the lazy phi creation is part of chapter 8. + Node _mem( int alias, Node st ) { + // Memory projections are made lazily; if one does not exist + // then it must be START.proj(1) + Node old = alias(alias); + if( old instanceof ScopeNode loop ) { + ScopeMinNode loopmem = loop.mem(); + Node memdef = loopmem.alias(alias); + // Lazy phi! + old = memdef instanceof PhiNode phi && loop.ctrl()==phi.region() + // Loop already has a real Phi, use it + ? memdef + // Set real Phi in the loop head + // The phi takes its one input (no backedge yet) from a recursive + // lookup, which might have insert a Phi in every loop nest. + : loopmem.alias(alias, new PhiNode(Parser.memName(alias), TypeMem.BOT,loop.ctrl(),loopmem._mem(alias,null),null).peephole() ); + alias(alias,old); + } + // Memory projections are made lazily; expand as needed + return st==null ? old : alias(alias,st); // Not lazy, so this is the answer + } + + + void _merge(ScopeMinNode that, RegionNode r) { + int len = Math.max(nIns(),that.nIns()); + for( int i = 2; i < len; i++) + if( alias(i) != that.alias(i) ) { // No need for redundant Phis + // If we are in lazy phi mode we need to a lookup + // by name as it will trigger a phi creation + //Var v = _vars.at(i); + Node lhs = this._mem(i,null); + Node rhs = that._mem(i,null); + alias(i, new PhiNode(Parser.memName(i), TypeMem.BOT, r, lhs, rhs).peephole()); + } + } + + // Fill in the backedge of any inserted Phis + void _endLoopMem( ScopeNode scope, ScopeMinNode back, ScopeMinNode exit ) { + for( int i=2; i<back.nIns(); i++ ) { + if( back.in(i) != scope ) { + PhiNode phi = (PhiNode)in(i); + assert phi.region()==scope.ctrl() && phi.in(2)==null; + phi.setDef(2,back.in(i)); // Fill backedge + } + if( exit.alias(i) == scope ) // Replace a lazy-phi on the exit path also + exit.alias(i,in(i)); + } + } + + // Now one-time do a useless-phi removal + void _useless( ) { + for( int i=2; i<nIns(); i++ ) { + if( in(i) instanceof PhiNode phi ) { + // Do an eager useless-phi removal + Node in = phi.peephole(); + IterPeeps.addAll(phi._outputs); + phi.moveDepsToWorklist(); + if( in != phi ) { + if( !phi.iskeep() ) // Keeping phi around for parser elsewhere + phi.subsume(in); + setDef(i,in); // Set the update back into Scope + } + } + } + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ScopeNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ScopeNode.java new file mode 100644 index 00000000..86aa7665 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ScopeNode.java @@ -0,0 +1,368 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.IterPeeps; +import com.seaofnodes.simple.Ary; +import com.seaofnodes.simple.type.*; +import java.util.*; + +import static com.seaofnodes.simple.Utils.TODO; + +/** + * The Scope node is purely a parser helper - it tracks names to nodes with a + * stack of hashmaps. + */ +public class ScopeNode extends ScopeMinNode { + + /** + * The control is a name that binds to the currently active control + * node in the graph + */ + public static final String CTRL = "$ctrl"; + public static final String ARG0 = "arg"; + public static final String MEM0 = "$mem"; + + // All active/live variables in all nested scopes, all run together + public final Ary<Var> _vars; + + // Since of each nested lexical scope + public final Ary<Integer> _lexSize; + + // True if parsing inside of a constructor + public final Ary<Boolean> _inCons; + + // Extra guards; tested predicates and casted results + private final Ary<Node> _guards; + + // A new ScopeNode + public ScopeNode() { + _vars = new Ary<>(Var .class); + _lexSize= new Ary<>(Integer.class); + _inCons = new Ary<>(Boolean.class); + _guards = new Ary<>(Node .class); + } + + @Override public String label() { return "Scope"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("Scope[ "); + int j=1; + for( int i=0; i<nIns(); i++ ) { + if( j < _lexSize._len && i == _lexSize.at(j) ) { sb.append("| "); j++; } + Var v = _vars.get(i); + v.type().print(sb); + sb.append(" "); + if( v._final ) sb.append("!"); + sb.append(v._name); + sb.append("="); + Node n = in(i); + while( n instanceof ScopeNode loop ) { + sb.append("Lazy_"); + n = loop.in(i); + } + if( n==null ) sb.append("___"); + else n._print0(sb, visited); + sb.append(", "); + } + sb.setLength(sb.length()-2); + return sb.append("]"); + } + + + public Node ctrl() { return in(0); } + public ScopeMinNode mem() { return (ScopeMinNode)in(1); } + + /** + * The ctrl of a ScopeNode is always bound to the currently active + * control node in the graph, via a special name '$ctrl' that is not + * a valid identifier in the language grammar and hence cannot be + * referenced in Simple code. + * + * @param n The node to be bound to '$ctrl' + * + * @return Node that was bound + */ + public <N extends Node> N ctrl(N n) { return setDef(0,n); } + + public void push() { push(false); } + public void push(boolean inCon) { + assert _lexSize._len==_inCons._len; + _lexSize.push(_vars.size()); + _inCons.push(inCon); + } + public void pop() { + assert _lexSize._len==_inCons._len; + int n = _lexSize.pop(); + _inCons.pop(); + popUntil(n); + _vars.setLen(n); + } + + public boolean inCon() { return _inCons.last(); } + + // Find name in reverse, return an index into _vars or -1. Linear scan + // instead of hashtable, but probably doesn't matter until the scan + // typically hits many dozens of variables. + int find( String name ) { + for( int i=_vars.size()-1; i>=0; i-- ) + if( _vars.get(i)._name.equals(name) ) + return i; + return -1; + } + + /** + * Create a new variable name in the current scope + */ + public boolean define( String name, Type declaredType, boolean xfinal, Node init ) { + assert name.charAt(0)!='$' || _lexSize.size()==1; // Later scopes do not define memory + if( _lexSize._len > 1 ) + for( int i=_vars.size()-1; i>=_lexSize.last(); i-- ) + if( _vars.get(i)._name.equals(name) ) + return false; // Double define + _vars.add(new Var(nIns(),name,declaredType,xfinal)); + addDef(init); + return true; + } + + // Read from memory + public Node mem( int alias ) { return mem()._mem(alias,null); } + // Write to memory + public void mem( int alias, Node st ) { mem()._mem(alias,st); } + + + /** + * Lookup a name in all scopes starting from most deeply nested. + * + * @param name Name to be looked up + * @return null if not found, or the implementing Node + */ + public Var lookup( String name ) { + int idx = find(name); + // -1 is missed in all scopes, not found + return idx == -1 ? null : update(_vars.at(idx),null); + } + + /** + * If the name is present in any scope, then redefine else null + * + * @param name Name being redefined + * @param n The node to bind to the name + */ + public void update( String name, Node n ) { + int idx = find(name); + assert idx>=0; + update(_vars.at(idx),n); + } + + public Var update( ScopeNode.Var v, Node st ) { + Node old = in(v._idx); + if( old instanceof ScopeNode loop ) { + // Lazy Phi! + Node def = loop.in(v._idx); + old = def instanceof PhiNode phi && loop.ctrl()==phi.region() + // Loop already has a real Phi, use it + ? def + // Set real Phi in the loop head + // The phi takes its one input (no backedge yet) from a recursive + // lookup, which might have insert a Phi in every loop nest. + : loop.setDef(v._idx,new PhiNode(v._name, v.lazyGLB(), loop.ctrl(), loop.in(loop.update(v,null)._idx),null).peephole()); + setDef(v._idx,old); + } + if( st!=null ) setDef(v._idx,st); // Set new value + return v; + } + + /** + * Duplicate a ScopeNode; including all levels, up to Nodes. So this is + * neither shallow (would dup the Scope but not the internal HashMap + * tables), nor deep (would dup the Scope, the HashMap tables, but then + * also the program Nodes). + * <p> + * If the {@code loop} flag is set, the edges are filled in as the original + * Scope, as an indication of Lazy Phis at loop heads. The goal here is to + * not make Phis at loop heads for variables which are never touched in the + * loop body. + * <p> + * The new Scope is a full-fledged Node with proper use<->def edges. + */ + public ScopeNode dup() { return dup(false); } + public ScopeNode dup(boolean loop) { + ScopeNode dup = new ScopeNode(); + // Our goals are: + // 1) duplicate the name bindings of the ScopeNode across all stack levels + // 2) Make the new ScopeNode a user of all the nodes bound + // 3) Ensure that the order of defs is the same to allow easy merging + dup._vars .addAll(_vars ); + dup._lexSize.addAll(_lexSize); + dup._inCons .addAll(_inCons ); + dup._guards .addAll(_guards ); + // The dup'd guards all need dup'd keepers, to keep proper accounting + // when later removing all guards + for( Node n : _guards ) + if( !(n instanceof CFGNode) ) + n.keep(); + dup.addDef(ctrl()); // Control input is just copied + + // Memory input is a shallow copy + ScopeMinNode memdup = new ScopeMinNode(), mem = mem(); + memdup.addDef(null); + memdup.addDef(loop ? this : mem.in(1)); + for( int i=2; i<mem.nIns(); i++ ) + // For lazy phis on loops we use a sentinel + // that will trigger phi creation on update + memdup.addDef(loop ? this : mem.in(i)); + dup.addDef(memdup); + + // Copy of other inputs + for( int i=2; i<nIns(); i++ ) + // For lazy phis on loops we use a sentinel + // that will trigger phi creation on update + dup.addDef(loop ? this : in(i)); + return dup; + } + + /** + * Merges the names whose node bindings differ, by creating Phi node for such names + * The names could occur at all stack levels, but a given name can only differ in the + * innermost stack level where the name is bound. + * + * @param that The ScopeNode to be merged into this + * @return A new node representing the merge point + */ + public RegionNode mergeScopes(ScopeNode that) { + RegionNode r = (RegionNode) ctrl(new RegionNode(null,ctrl(), that.ctrl()).keep()); + mem()._merge(that.mem(),r); + this ._merge(that ,r); + that.kill(); // Kill merged scope + IterPeeps.add(r); + return r.unkeep(); + } + + private void _merge(ScopeNode that, RegionNode r) { + for( int i = 2; i < nIns(); i++) + if( in(i) != that.in(i) ) { // No need for redundant Phis + // If we are in lazy phi mode we need to a lookup + // by name as it will trigger a phi creation + Var v = _vars.at(i); + Node lhs = this.in(this.update(v,null)); + Node rhs = that.in(that.update(v,null)); + setDef(i, new PhiNode(v._name, v.type(), r, lhs, rhs).peephole()); + } + } + + // peephole the backedge scope into this loop head scope + // We set the second input to the phi from the back edge (i.e. loop body) + public void endLoop(ScopeNode back, ScopeNode exit ) { + Node ctrl = ctrl(); + assert ctrl instanceof LoopNode loop && loop.inProgress(); + ctrl.setDef(2,back.ctrl()); + + mem()._endLoopMem( this, back.mem(), exit.mem() ); + this ._endLoop ( this, back , exit ); + back.kill(); // Loop backedge is dead + // Now one-time do a useless-phi removal + mem()._useless(); + this ._useless(); + + // The exit mem's lazy default value had been the loop top, + // now it goes back to predating the loop. + exit.mem().setDef(1,mem().in(1)); + } + + // Fill in the backedge of any inserted Phis + void _endLoop( ScopeNode scope, Node back, Node exit ) { + for( int i=2; i<nIns(); i++ ) { + if( back.in(i) != scope ) { + PhiNode phi = (PhiNode)in(i); + assert phi.region()==scope.ctrl() && phi.in(2)==null; + phi.setDef(2,back.in(i)); // Fill backedge + } + if( exit.in(i) == scope ) // Replace a lazy-phi on the exit path also + exit.setDef(i,in(i)); + } + } + + + // Up-casting: using the results of an If to improve a value. + // E.g. "if( ptr ) ptr.field;" is legal because ptr is known not-null. + public void addGuards( Node ctrl, Node pred, boolean invert ) { + assert ctrl instanceof CFGNode; + _guards.add(ctrl); // Marker to distinguish 0,1,2 guards + // add pred & its cast to the normal input list, with special Vars + if( ctrl._type == Type.XCONTROL || pred==null || pred.isDead() ) + return; // Dead, do not add any guards + // Invert the If conditional + if( invert ) + pred = pred instanceof NotNode not ? not.in(1) : IterPeeps.add(new NotNode(pred).peephole()); + // This is a zero/null test. + // Compute the positive test type. + Type tnz = pred._type.nonZero(); + Type tcast = tnz.join(pred._type); + if( tcast != pred._type ) { + Node cast = new CastNode(tnz,ctrl,pred.keep()).peephole().keep(); + _guards.add(pred); + _guards.add(cast); + replace(pred,cast); + } + + // Compute the negative test type. + if( pred instanceof NotNode not ) { + Node npred = not.in(1); + Type tzero = npred._type.makeZero(); + Type tzcast= tzero.join(npred._type); + if( tzcast != npred._type ) { + Node cast = new CastNode(tzero,ctrl,npred.keep()).peephole().keep(); + _guards.add(npred); + _guards.add( cast); + replace(npred,cast); + } + } + } + + // Remove matching pred/cast pairs from this guarded region. + public void removeGuards( Node ctrl ) { + assert ctrl instanceof CFGNode; + // 0,1 or 2 guards + while( true ) { + Node g = _guards.pop(); + if( g == ctrl ) break; + if( g instanceof CFGNode ) continue; + g .unkill(); // Pop/kill cast + _guards.pop().unkill(); // Pop/kill pred + } + } + + // If we find a guarded instance of pred, replace with the upcasted version + public Node upcastGuard( Node pred ) { + // If finding an instanceof pred, replace with cast. + // Otherwise, just pred itself. + int i = _guards._len; + while( i > 0 ) { + Node cast = _guards.at(--i); + if( cast instanceof CFGNode ) continue; // Marker between guard sets + Node xpred = _guards.at(--i); + if( xpred == pred ) + return cast; + } + return pred; + } + + // Kill guards also + @Override public void kill() { + for( Node n : _guards ) + if( !(n instanceof CFGNode) ) + n.unkill(); + _guards.clear(); + super.kill(); + } + + + private Node replace( Node old, Node cast ) { + assert old!=null && old!=cast; + for( int i=0; i<nIns(); i++ ) + if( in(i)==old ) + setDef(i,cast); + return cast; + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ShlNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ShlNode.java new file mode 100644 index 00000000..6fd951e4 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ShlNode.java @@ -0,0 +1,64 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; +import java.util.BitSet; + +public class ShlNode extends Node { + public ShlNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Shl"; } + + @Override public String glabel() { return "<<"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("<<"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if (t1 instanceof TypeInteger i0 && + t2 instanceof TypeInteger i1 ) { + if( i0 == TypeInteger.ZERO ) + return TypeInteger.ZERO; + if( i0.isConstant() && i1.isConstant() ) + return TypeInteger.constant(i0.value()<<i1.value()); + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + + if( rhs._type instanceof TypeInteger shl && shl.isConstant() ) { + // Shl of 0. + if( (shl.value()&63)==0 ) + return lhs; + // (x + c) << i => (x << i) + (c << i) + if( lhs instanceof AddNode add && add.addDep(this).in(2)._type instanceof TypeInteger c && c.isConstant() && c!=TypeInteger.ZERO ) { + long sum = c.value() << shl.value(); + if( Integer.MIN_VALUE <= sum && sum <= Integer.MAX_VALUE ) + return new AddNode( new ShlNode(add.in(1),rhs).peephole(), Parser.con(sum) ); + } + } + + // TODO: x << 3 << (y ? 1 : 2) ==> x << (y ? 4 : 5) + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new ShlNode(lhs,rhs); } + @Override String err() { + if( !(in(1)._type instanceof TypeInteger) ) return "Cannot '<<' " + in(1)._type; + if( !(in(2)._type instanceof TypeInteger) ) return "Cannot '<<' " + in(2)._type; + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ShrNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ShrNode.java new file mode 100644 index 00000000..22eb45a0 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ShrNode.java @@ -0,0 +1,52 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class ShrNode extends Node { + public ShrNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Shr"; } + + @Override public String glabel() { return ">>>"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append(">>>"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if (t1 instanceof TypeInteger i0 && + t2 instanceof TypeInteger i1 ) { + if( i0 == TypeInteger.ZERO ) + return TypeInteger.ZERO; + if( i0.isConstant() && i1.isConstant() ) + return TypeInteger.constant(i0.value()>>>i1.value()); + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t2 = rhs._type; + + // Shr of 0. + if( t2.isConstant() && t2 instanceof TypeInteger i && (i.value()&63)==0 ) + return lhs; + + // TODO: x >>> 3 >>> (y ? 1 : 2) ==> x >>> (y ? 4 : 5) + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new ShrNode(lhs,rhs); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/StartNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/StartNode.java new file mode 100644 index 00000000..ab6e4931 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/StartNode.java @@ -0,0 +1,44 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.*; +import java.util.Arrays; +import java.util.BitSet; +import java.util.HashSet; +import static com.seaofnodes.simple.Utils.TODO; + +/** + * The Start node represents the start of the function. + * + * Start initially has 1 input (arg) from outside and the initial control. + * In ch10 we also add mem aliases as structs get defined; each field in struct + * adds a distinct alias to Start's tuple. + */ +public class StartNode extends LoopNode implements MultiNode { + + final Type _arg; + + public StartNode(Type arg) { super(null); _arg = arg; _type = compute(); } + + @Override public String label() { return "Start"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return sb.append(label()); + } + + @Override public boolean isMultiHead() { return true; } + @Override public boolean blockHead() { return true; } + @Override public CFGNode cfg0() { return this; } + + @Override public TypeTuple compute() { + return TypeTuple.make(Type.CONTROL,TypeMem.TOP,_arg); + } + + @Override public Node idealize() { return null; } + + // No immediate dominator, and idepth==0 + @Override public int idepth() { return 0; } + @Override public CFGNode idom(Node dep) { return null; } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/StopNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/StopNode.java new file mode 100644 index 00000000..867225cb --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/StopNode.java @@ -0,0 +1,85 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.IterPeeps; +import com.seaofnodes.simple.GlobalCodeMotion; +import com.seaofnodes.simple.GraphVisualizer; + +import java.util.BitSet; + +public class StopNode extends CFGNode { + + public final String _src; + + public StopNode(String src) { + super(); + _src = src; + } + + @Override + public String label() { + return "Stop"; + } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + if( ret()!=null ) return ret()._print0(sb, visited); + sb.append("Stop[ "); + for( Node ret : _inputs ) + ret._print0(sb, visited).append(" "); + return sb.append("]"); + } + + @Override public boolean blockHead() { return true; } + + // If a single Return, return it. + // Otherwise, null because ambiguous. + public ReturnNode ret() { + return nIns()==1 ? (ReturnNode)in(0) : null; + } + + @Override + public Type compute() { + return Type.BOTTOM; + } + + @Override + public Node idealize() { + int len = nIns(); + for( int i=0; i<nIns(); i++ ) + if( in(i)._type==Type.XCONTROL ) + delDef(i--); + if( len != nIns() ) return this; + return null; + } + + @Override public int idepth() { + if( _idepth!=0 ) return _idepth; + int d=0; + for( Node n : _inputs ) + if( n!=null ) + d = Math.max(d,((CFGNode)n).idepth()+1); + return _idepth=d; + } + @Override public CFGNode idom(Node dep) { return null; } + + public Node addReturn(Node node) { + return addDef(node); + } + + public StopNode iterate( ) { return IterPeeps.iterate(this).typeCheck().GCM(false); } + public StopNode iterate(boolean show) { return IterPeeps.iterate(this).typeCheck().GCM(show ); } + StopNode typeCheck() { + String err = walk( Node::err ); + if( err != null ) throw new RuntimeException(err); + return this; + } + StopNode GCM(boolean show) { + Parser.START.buildLoopTree(this); + if( show ) + System.out.println(new GraphVisualizer().generateDotOutput(this,null,null)); + GlobalCodeMotion.buildCFG(this); + return this; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/StoreNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/StoreNode.java new file mode 100644 index 00000000..62b49a1a --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/StoreNode.java @@ -0,0 +1,123 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.*; + +import java.util.BitSet; + +/** + * Store represents setting a value to a memory based object, in chapter 10 + * this means a field inside a struct. + */ +public class StoreNode extends MemOpNode { + + private final boolean _init; // Initializing writes are allowed to write null + + /** + * @param name The struct field we are assigning to + * @param mem The memory alias node - this is updated after a Store + * @param ptr The ptr to the struct base where we will store a value + * @param off The offset inside the struct base + * @param value Value to be stored + */ + public StoreNode(String name, int alias, Type glb, Node mem, Node ptr, Node off, Node value, boolean init) { + super(name, alias, glb, mem, ptr, off, value); + _init = init; + } + + // GraphVis DOT code and debugger labels + @Override public String label() { return "st_"+mlabel(); } + // GraphVis node-internal labels + @Override public String glabel() { return "." +_name+"="; } + @Override public boolean isMem() { return true; } + + public Node val() { return in(4); } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return sb.append(".").append(_name).append("=").append( val()).append(";"); + } + + @Override + public Type compute() { + Type val = val()._type; + TypeMem mem = (TypeMem)mem()._type; // Invariant + Type t = Type.BOTTOM; // No idea on field contents + // Same alias, lift val to the declared type and then meet into other fields + if( mem._alias == _alias ) { + // Update declared forward ref to the actual + if( _declaredType.isFRef() && val instanceof TypeMemPtr tmp && !tmp.isFRef() ) + _declaredType = tmp; + val = val.join(_declaredType); + t = val.meet(mem._t); + } + return TypeMem.make(_alias,t); + } + + @Override + public Node idealize() { + + // Simple store-after-store on same address. Should pick up the + // required init-store being stomped by a first user store. + if( mem() instanceof StoreNode st && + ptr()==st.ptr() && // Must check same object + off()==st.off() && // And same offset (could be "same alias" but this handles arrays to same index) + ptr()._type instanceof TypeMemPtr && // No bother if weird dead pointers + // Must have exactly one use of "this" or you get weird + // non-serializable memory effects in the worse case. + checkOnlyUse(st) ) { + assert _name.equals(st._name); // Equiv class aliasing is perfect + setDef(1,st.mem()); + return this; + } + + // Simple store-after-new on same address. Should pick up the + // an init-store being stomped by a first user store. + if( mem() instanceof ProjNode st && st .in(0) instanceof NewNode nnn && + ptr() instanceof ProjNode ptr && ptr.in(0) == nnn && + ptr()._type instanceof TypeMemPtr tmp && // No bother if weird dead pointers + // Cannot fold a store of a single element over the array body initializer value + !(tmp._obj.isAry() && tmp._obj._fields[1]._alias==_alias) && + // Very sad strong cutout: val has to be legal to hoist to a New + // input, which means it cannot depend on the New. Many many + // things are legal here but difficult to check without doing a + // full dominator check. Example failure: + // "struct C { C? c; }; C self = new C { c=self; }" + val()._type.isHighOrConst() && + // Must have exactly one use of "this" or you get weird + // non-serializable memory effects in the worse case. + checkOnlyUse(st) && + // Folding away a broken store + err()==null ) { + nnn.setDef(nnn.findAlias(_alias),val()); + // Must retype the NewNode + nnn ._type = nnn. compute(); + mem()._type = mem().compute(); + return st; + } + + return null; + } + + // Check that "mem" has no uses except "this" + private boolean checkOnlyUse(Node mem) { + if( mem.nOuts()==1 ) return true; + // Add deps on the other uses (can be e.g. ScopeNode mid-parse) so that + // when the other uses go away we can retry. + for( Node use : mem._outputs ) + if( use != this ) + use.addDep(this); + return false; + } + + @Override + String err() { + String err = super.err(); + if( err != null ) return err; + TypeMemPtr tmp = (TypeMemPtr)ptr()._type; + if( tmp._obj.field(_name)._final ) + return "Cannot modify final field '"+_name+"'"; + Type t = val()._type; + return _init || t.isa(_declaredType) ? null : "Cannot store "+t+" into field "+_declaredType+" "+_name; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/StructNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/StructNode.java new file mode 100644 index 00000000..db170ab1 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/StructNode.java @@ -0,0 +1,45 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.*; +import java.util.BitSet; + +/** + * Build a compound object + */ +public class StructNode extends Node { + + public TypeStruct _ts; + + @Override public String label() { return _ts==null ? "STRUCT?" : _ts.str(); } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + if( _ts==null ) return sb.append("STRUCT?"); + sb.append(_ts._name).append(" {"); + for( int i=0; i<nIns(); i++ ) { + sb.append(_ts._fields[i]._fname).append(":"); + (in(i)==null ? Type.BOTTOM : in(i)._type).print(sb); + sb.append("; "); + } + sb.setLength(sb.length()-2); + return sb.append("}"); + } + + @Override + public TypeStruct compute() { + if( _ts==null ) return TypeStruct.BOT; + Field[] fs = new Field[_ts._fields.length]; + for( int i=0; i<fs.length; i++ ) + fs[i] = _ts._fields[i].makeFrom(in(i)==null ? Type.TOP : in(i)._type); + return TypeStruct.make(_ts._name,fs); + } + + @Override + public Node idealize() { return null; } + + @Override + boolean eq(Node n) { return _ts == ((StructNode)n)._ts; } + + @Override + int hash() { return _ts==null ? 0 : _ts.hashCode(); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/SubFNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/SubFNode.java new file mode 100644 index 00000000..682930e0 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/SubFNode.java @@ -0,0 +1,44 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; + +import java.util.BitSet; + +public class SubFNode extends Node { + public SubFNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "SubF"; } + + @Override public String glabel() { return "-"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("-"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeFloat i0 && + in(2)._type instanceof TypeFloat i1) { + if (i0.isConstant() && i1.isConstant()) + return TypeFloat.constant(i0.value()-i1.value()); + } + return in(1)._type.meet(in(2)._type); + } + + @Override + public Node idealize() { + Node lhs = in(1); + Type t2 = in(2)._type; + + // Sub of 1. + if ( t2.isConstant() && t2 instanceof TypeFloat i && i.value()==0 ) + return lhs; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new SubFNode(lhs,rhs); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/SubNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/SubNode.java new file mode 100644 index 00000000..5d6c2643 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/SubNode.java @@ -0,0 +1,60 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class SubNode extends Node { + public SubNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Sub"; } + + @Override public String glabel() { return "-"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("-"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if( t1 instanceof TypeInteger i1 && + t2 instanceof TypeInteger i2 ) { + if (i1.isConstant() && i2.isConstant()) + return TypeInteger.constant(i1.value()-i2.value()); + // Fold ranges like {2-3} - {0-1} into {1-3}. + if( !AddNode.overflow(i1._min,-i2._max) && + !AddNode.overflow(i1._max,-i2._min) && + i2._min != Long.MIN_VALUE ) + return TypeInteger.make(i1._min-i2._max,i1._max-i2._min); + } + // Sub of same is 0 + if( in(1)==in(2) ) + return TypeInteger.ZERO; + + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + // x - (-y) is x+y + if( in(2) instanceof MinusNode minus ) + return new AddNode(in(1),minus.in(1)); + + // (-x) - y is -(x+y) + if( in(1) instanceof MinusNode minus ) + return new MinusNode(new AddNode(minus.in(1),in(2)).peephole()); + + return null; + } + + @Override Node copy(Node lhs, Node rhs) { return new SubNode(lhs,rhs); } + @Override Node copyF() { return new SubFNode(null,null); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/ToFloatNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/ToFloatNode.java new file mode 100644 index 00000000..1d147cf6 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/ToFloatNode.java @@ -0,0 +1,30 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeFloat; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class ToFloatNode extends Node { + public ToFloatNode(Node lhs) { super(null, lhs); } + + @Override public String label() { return "ToFloat"; } + + @Override public String glabel() { return "(flt)"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return in(1)._print0(sb.append("(flt)"), visited); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeInteger i0 && i0.isConstant() ) + return TypeFloat.constant(i0.value()); + return TypeFloat.BOT; + } + + @Override public Node idealize() { return null; } + @Override Node copy(Node lhs, Node rhs) { return new ToFloatNode(lhs); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/XCtrlNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/XCtrlNode.java new file mode 100644 index 00000000..83779dd2 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/XCtrlNode.java @@ -0,0 +1,13 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.Type; +import java.util.BitSet; + +public class XCtrlNode extends CFGNode { + public XCtrlNode( ) { super(Parser.START); } + @Override public String label() { return "Xctrl"; } + @Override StringBuilder _print1(StringBuilder sb, BitSet visited) { return sb.append("Xctrl"); } + @Override public Type compute() { return Type.XCONTROL; } + @Override public Node idealize() { return null; } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/node/XorNode.java b/chapter18/src/main/java/com/seaofnodes/simple/node/XorNode.java new file mode 100644 index 00000000..191933f9 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/node/XorNode.java @@ -0,0 +1,65 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class XorNode extends Node { + public XorNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Xor"; } + + @Override public String glabel() { return "^"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("^"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + Type t1 = in(1)._type, t2 = in(2)._type; + if( t1.isHigh() || t2.isHigh() ) + return TypeInteger.TOP; + if( t1 instanceof TypeInteger i0 && + t2 instanceof TypeInteger i1 ) { + if( i0.isConstant() && i1.isConstant() ) + return TypeInteger.constant(i0.value()^i1.value()); + } + return TypeInteger.BOT; + } + + @Override + public Node idealize() { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // Xor of 0. We do not check for (0^x) because this will already + // canonicalize to (x^0) + if( t2.isConstant() && t2 instanceof TypeInteger i && i.value()==0 ) + return lhs; + + // Move constants to RHS: con*arg becomes arg*con + if ( t1.isConstant() && !t2.isConstant() ) + return swap12(); + + // Do we have ((x ^ (phi cons)) ^ con) ? + // Do we have ((x ^ (phi cons)) ^ (phi cons)) ? + // Push constant up through the phi: x ^ (phi con0^con0 con1^con1...) + Node phicon = AddNode.phiCon(this,true); + if( phicon!=null ) return phicon; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new XorNode(lhs,rhs); } + @Override String err() { + if( !(in(1)._type instanceof TypeInteger) ) return "Cannot '^' " + in(1)._type; + if( !(in(2)._type instanceof TypeInteger) ) return "Cannot '^' " + in(2)._type; + return null; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/Field.java b/chapter18/src/main/java/com/seaofnodes/simple/type/Field.java new file mode 100644 index 00000000..349c1fb0 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/Field.java @@ -0,0 +1,77 @@ +package com.seaofnodes.simple.type; + +import com.seaofnodes.simple.Utils; +import java.util.ArrayList; + +/** + * Represents a field in a struct. This is not a Type in the type system. + */ +public class Field extends Type { + + // The pair {fieldName,type} uniquely identifies a field. + + // Field name + public final String _fname; + // Type of the field + public final Type _type; + // Unique memory alias, not sensibly part of a "type" but very convenient here. + public final int _alias; + // Field must be written to exactly once, no more, no less + public final boolean _final; + + private Field(String fname, Type type, int alias, boolean xfinal ) { + super(TFLD); + _fname = fname; + _type = type; + _alias = alias; + _final = xfinal; + } + // Make with existing alias + public static Field make( String fname, Type type, int alias, boolean xfinal ) { + return new Field(fname,type,alias,xfinal).intern(); + } + public Field makeFrom( Type type ) { + return type == _type ? this : new Field(_fname,type,_alias,_final).intern(); + } + @Override public Field makeRO() { return _final ? this : make(_fname,_type.makeRO(),_alias,true); } + @Override public boolean isFinal() { return _final && _type.isFinal(); } + + public static final Field TEST = make("test",TypeInteger.ZERO,-2,false); + public static void gather(ArrayList<Type> ts) { ts.add(TEST); } + + @Override Field xmeet( Type that ) { + Field fld = (Field)that; // Invariant + assert _fname.equals(fld._fname); + assert _alias==fld._alias; + return make(_fname,_type.meet(fld._type),_alias,_final | fld._final); + } + + @Override + public Field dual() { return make(_fname,_type.dual(),_alias,!_final); } + + @Override public Field glb() { + Type glb = _type.glb(); + return glb==_type ? this : make(_fname,glb,_alias,_final); + } + + @Override public Field lub() { + Type lub = _type.lub(); + return lub==_type ? this : make(_fname,lub,_alias,_final); + } + + // Override in subclasses + int hash() { return _fname.hashCode() ^ _type.hashCode() ^ _alias ^ (_final ? 1024 : 0); } + + boolean eq(Type t) { + Field f = (Field)t; + return _fname.equals(f._fname) && _type==f._type && _alias==f._alias && _final==f._final; + } + + + @Override + public StringBuilder print( StringBuilder sb ) { + return _type.print(sb.append(_final?"":"!").append(_fname).append(":").append(_alias).append(" : ")); + } + + @Override public String str() { return _fname; } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/Type.java b/chapter18/src/main/java/com/seaofnodes/simple/type/Type.java new file mode 100644 index 00000000..4ebb2b6d --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/Type.java @@ -0,0 +1,218 @@ +package com.seaofnodes.simple.type; + +import com.seaofnodes.simple.Utils; + +import java.util.ArrayList; +import java.util.HashMap; + +/** + * These types are part of a Monotone Analysis Framework, + * @see <a href="https://www.cse.psu.edu/~gxt29/teaching/cse597s21/slides/08monotoneFramework.pdf">see for example this set of slides</a>. + * <p> + * The types form a lattice; @see <a href="https://en.wikipedia.org/wiki/Lattice_(order)">a symmetric complete bounded (ranked) lattice.</a> + * <p> + * This wild lattice theory will be needed later to allow us to easily beef up + * the analysis and optimization of the Simple compiler... but we don't need it + * now, just know that it is coming along in a later Chapter. + * <p>g + * One of the fun things here is that while the theory is deep and subtle, the + * actual implementation is darn near trivial and is generally really obvious + * what we're doing with it. Right now, it's just simple integer math to do + * simple constant folding e.g. 1+2 == 3 stuff. + */ + +public class Type { + static final HashMap<Type,Type> INTERN = new HashMap<>(); + + // ---------------------------------------------------------- + // Simple types are implemented fully here. "Simple" means: the code and + // type hierarchy are simple, not that the Type is conceptually simple. + static final byte TBOT = 0; // Bottom (ALL) + static final byte TTOP = 1; // Top (ANY) + static final byte TCTRL = 2; // Ctrl flow bottom + static final byte TXCTRL = 3; // Ctrl flow top (mini-lattice: any-xctrl-ctrl-all) + static final byte TSIMPLE = 4; // End of the Simple Types + static final byte TINT = 5; // All Integers; see TypeInteger + static final byte TFLT = 6; // All Integers; see TypeInteger + static final byte TTUPLE = 7; // Tuples; finite collections of unrelated Types, kept in parallel + static final byte TMEM = 8; // All memory (alias 0) or A slice of memory - with specific alias + static final byte TMEMPTR = 9; // Memory pointer type + static final byte TSTRUCT =10; // Structs; tuples with named fields + static final byte TFLD =11; // Fields into struct + static final byte TARRAY =12; // Array + + public final byte _type; + + public boolean is_simple() { return _type < TSIMPLE; } + private static final String[] STRS = new String[]{"Bot","Top","Ctrl","~Ctrl"}; + protected Type(byte type) { _type = type; } + + public static final Type BOTTOM = new Type( TBOT ).intern(); // ALL + public static final Type TOP = new Type( TTOP ).intern(); // ANY + public static final Type CONTROL = new Type( TCTRL ).intern(); // Ctrl + public static final Type XCONTROL = new Type( TXCTRL ).intern(); // ~Ctrl + public static Type[] gather() { + ArrayList<Type> ts = new ArrayList<>(); + ts.add(BOTTOM); + ts.add(CONTROL); + Field.gather(ts); + TypeInteger.gather(ts); + TypeFloat.gather(ts); + TypeMem.gather(ts); + TypeMemPtr.gather(ts); + TypeStruct.gather(ts); + TypeTuple.gather(ts); + int sz = ts.size(); + for( int i = 0; i < sz; i++ ) + ts.add(ts.get(i).dual()); + return ts.toArray(new Type[ts.size()]); + } + + // Is high or on the lattice centerline. + public boolean isHigh () { return _type==TTOP || _type==TXCTRL; } + public boolean isHighOrConst() { return _type==TTOP || _type==TXCTRL; } + + // Strict constant values, things on the lattice centerline. + // Excludes both high and low values + public boolean isConstant() { return false; } + + /** + * Display Type name in a format that's good for IR printer + */ + public StringBuilder typeName( StringBuilder sb) { return print(sb); } + + + // ---------------------------------------------------------- + + // Notes on Type interning: At the moment it is not easy to reset the + // interned types because we hold static references to several types and + // these are scattered around. This means the INTERN cache will retain all + // types from every run of the Parser. For this to work correctly types + // must be rigorous about defining when they are the same. Also types need + // to be immutable once defined. The rationale for interning is + // *correctness* with cyclic type definitions. Simple structural recursive + // checks go exponential with merely sharing, but with cycles they will + // stack overflow and crash. Intering means we do not need to have sharing + // checks with every type compare, only during interning. + + // Factory method which interns "this" + public <T extends Type> T intern() { + T nnn = (T)INTERN.get(this); + if( nnn==null ) + INTERN.put(nnn=(T)this,this); + return nnn; + } + + private int _hash; // Hash cache; not-zero when set. + @Override + public final int hashCode() { + if( _hash!=0 ) return _hash; + _hash = hash(); + if( _hash==0 ) _hash = 0xDEADBEEF; // Bad hash from subclass; use some junk thing + return _hash; + } + // Override in subclasses + int hash() { return _type; } + + @Override + public final boolean equals( Object o ) { + if( o==this ) return true; + if( !(o instanceof Type t)) return false; + if( _type != t._type ) return false; + return eq(t); + } + // Overridden in subclasses; subclass can assume "this!=t" and java classes are same + boolean eq(Type t) { return true; } + + + // ---------------------------------------------------------- + public final Type meet(Type t) { + // Shortcut for the self case + if( t == this ) return this; + // Same-type is always safe in the subclasses + if( _type==t._type ) return xmeet(t); + // Reverse; xmeet 2nd arg is never "is_simple" and never equal to "this". + if( is_simple() ) return this.xmeet(t ); + if( t.is_simple() ) return t .xmeet(this); + return Type.BOTTOM; // Mixing 2 unrelated types + } + + // Compute meet right now. Overridden in subclasses. + // Handle cases where 'this.is_simple()' and unequal to 't'. + // Subclassed xmeet calls can assert that '!t.is_simple()'. + Type xmeet(Type t) { + assert is_simple(); // Should be overridden in subclass + // ANY meet anything is thing; thing meet ALL is ALL + if( _type==TBOT || t._type==TTOP ) return this; + if( _type==TTOP || t._type==TBOT ) return t; + // 'this' is {TCTRL,TXCTRL} + if( !t.is_simple() ) return BOTTOM; + // 't' is {TCTRL,TXCTRL} + return _type==TCTRL || t._type==TCTRL ? CONTROL : XCONTROL; + } + + public Type dual() { + return switch( _type ) { + case TBOT -> TOP; + case TTOP -> BOTTOM; + case TCTRL -> XCONTROL; + case TXCTRL -> CONTROL; + default -> throw Utils.TODO(); // Should not reach here + }; + } + + // ---------------------------------------------------------- + // Our lattice is defined with a MEET and a DUAL. + // JOIN is dual of meet of both duals. + public final Type join(Type t) { + if( this==t ) return this; + return dual().meet(t.dual()).dual(); + } + + // True if this "isa" t; e.g. 17 isa TypeInteger.BOT + public boolean isa( Type t ) { return meet(t)==t; } + + /** Compute greatest lower bound in the lattice */ + public Type glb() { return _type==TCTRL ? CONTROL : BOTTOM; } + /** Compute least upper bound in the lattice */ + public Type lub() { return _type==TCTRL ? XCONTROL : TOP; } + + // Make an initial/default version of this type. Typically, 0 for integers + // and null for nullable pointers. + public Type makeInit() { return this; } + // Make a zero version of this type, 0 for integers and null for pointers. + public Type makeZero() { return null; } + // Make a non-zero version of this type, if possible. Integers attempt to + // exclude zero from their range and pointers become not-null. + public Type nonZero() { return glb(); } + + // Is forward-reference + public boolean isFRef() { return false; } + + // All reachable struct Fields are final + public boolean isFinal() { return true; } + + // Make all reachable struct Fields final + public Type makeRO() { return this; } + + // ---------------------------------------------------------- + + // Size in bits to hold an instance of this type. + // Sizes are expected to be between 1 and 64 bits. + // Size 0 means this either takes no space (such as a known-zero field) + // or isn't a scalar to be stored in memory. + public int log_size() { throw Utils.TODO(); } + + // ---------------------------------------------------------- + // Useful in the debugger, which calls toString everywhere. + // This is a more verbose dev-friendly print. + @Override + public final String toString() { + return print(new StringBuilder()).toString(); + } + + public StringBuilder print(StringBuilder sb) { return is_simple() ? sb.append(STRS[_type]) : sb;} + + // This is used by error messages, and is a shorted print. + public String str() { return STRS[_type]; } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/TypeFloat.java b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeFloat.java new file mode 100644 index 00000000..f85abbed --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeFloat.java @@ -0,0 +1,120 @@ +package com.seaofnodes.simple.type; + +import java.util.ArrayList; + +/** + * Float Type + */ +public class TypeFloat extends Type { + + public final static TypeFloat TOP = make((byte)-64, 0); + public final static TypeFloat T32 = make((byte)-32, 0); + public final static TypeFloat ZERO= make((byte) 0, 0); + public final static TypeFloat B32 = make((byte) 32, 0); + public final static TypeFloat BOT = make((byte) 64, 0); + + /** +/-64 for double; +/-32 for float, or 0 for constants */ + public final byte _sz; + + /** + * The constant value or 0 + */ + public final double _con; + + private TypeFloat(byte sz, double con) { + super(TFLT); + _sz = sz ; + _con = con; + } + private static TypeFloat make(byte sz, double con) { + return new TypeFloat(sz,con).intern(); + } + + public static TypeFloat constant(double con) { return make((byte)0, con); } + + public static void gather(ArrayList<Type> ts) { ts.add(ZERO); ts.add(BOT); ts.add(B32); ts.add(constant(3.141592653589793)); } + + // FIXME this display format is problematic + // In visualizer '#' gets prepended if its a constant + @Override + public StringBuilder print(StringBuilder sb) { + if( this==TOP ) return sb.append("FltTop"); + if( this==T32 ) return sb.append("F32Top"); + if( this==B32 ) return sb.append("F32Bot"); + if( this==BOT ) return sb.append("FltBot"); + return sb.append(_con); + } + + @Override public String str() { + if( this==TOP ) return "~flt"; + if( this==T32 ) return "~f32"; + if( this==B32 ) return "f32"; + if( this==BOT ) return "flt"; + return ""+_con+(isF32() ? "f" : ""); + } + + /** + * Display Type name in a format that's good for IR printer + */ + @Override + public StringBuilder typeName(StringBuilder sb) { + if( this==TOP ) return sb.append("FltTop"); + if( this==T32 ) return sb.append("F32Top"); + if( this==B32 ) return sb.append("F32Bot"); + if( this==BOT ) return sb.append("FltBot"); + return sb.append(isF32() ? "F32" : "Flt"); + } + + boolean isF32() { return ((float)_con)==_con; } + @Override public boolean isHigh() { return _sz< 0; } + @Override public boolean isHighOrConst() { return _sz<=0; } + @Override public boolean isConstant() { return _sz==0; } + + @Override public int log_size() { + int sz = _sz==0 ? (isF32() ? 32 : 64) : Math.abs(_sz); + return _sz==32 ? 2 : 3; + } + + public double value() { return _con; } + + @Override + public Type xmeet(Type other) { + // Invariant from caller: 'this' != 'other' and same class (TypeFloat) + TypeFloat i = (TypeFloat)other; // Contract + // Larger size in i1, smaller in i0 + TypeFloat i0 = _sz < i._sz ? this : i; + TypeFloat i1 = _sz < i._sz ? i : this; + + if( i1._sz== 64 ) return BOT; + if( i0._sz==-64 ) return i1; + if( i1._sz== 32 ) + return i0._sz==0 && !i0.isF32() ? BOT : B32; + if( i1._sz!= 0 ) return i1; + // i1 is a constant + if( i0._sz==-32 ) + return i1.isF32() ? i1 : BOT; + // Since both are constants, and are never equals (contract) unequals + // constants fall to bottom + return i0.isF32() && i1.isF32() ? B32 : BOT; + } + + @Override + public Type dual() { + if( _sz==0 ) return this; // Constants are a self-dual + return make((byte)-_sz,0); + } + + @Override public Type glb() { return BOT; } + @Override public Type lub() { return TOP; } + @Override public TypeFloat makeInit() { return ZERO; } + @Override public TypeFloat makeZero() { return ZERO; } + + @Override + int hash() { return (int)(Double.hashCode(_con) ^ _sz); } + @Override + public boolean eq( Type t ) { + TypeFloat i = (TypeFloat)t; // Contract + return _con==i._con && _sz==i._sz; + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/TypeInteger.java b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeInteger.java new file mode 100644 index 00000000..b2979d7b --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeInteger.java @@ -0,0 +1,133 @@ +package com.seaofnodes.simple.type; + +import com.seaofnodes.simple.Utils; +import java.util.ArrayList; + +/** + * Integer Type + */ +public class TypeInteger extends Type { + + public final static TypeInteger TOP = make(false, 0); + public final static TypeInteger BOT = make(false, 1); + public final static TypeInteger ZERO= make(0,0); + public final static TypeInteger U1 = make(0,1); + public final static TypeInteger BOOL= U1; + public final static TypeInteger FALSE=ZERO; + public final static TypeInteger TRUE= make(1,1); + public final static TypeInteger I8 = make(-128,127); + public final static TypeInteger I16 = make(-32768,32767); + public final static TypeInteger I32 = make(-1L<<31,(1L<<31)-1); + + public final static TypeInteger U8 = make(0,255); + public final static TypeInteger U16 = make(0,65535); + public final static TypeInteger U32 = make(0,(1L<<32)-1); + + /** + * Describes an integer *range* - everything from min to max; both min and + * max are inclusive. If min==max, this is a constant. + * + * If min <= max, this is a below center (towards bottom). + * If min > max, this is an above center (towards top). + */ + public final long _min, _max; + + private TypeInteger(long min, long max) { super(TINT); _min = min; _max = max; } + public static TypeInteger make(long lo, long hi) { return new TypeInteger(lo,hi).intern(); } + public static TypeInteger make(boolean is_con, long con) { + return make(is_con ? con : (con==0 ? Long.MAX_VALUE : Long.MIN_VALUE), + is_con ? con : (con==0 ? Long.MIN_VALUE : Long.MAX_VALUE)); + } + + public static TypeInteger constant(long con) { return make(true, con); } + + public static void gather(ArrayList<Type> ts) { ts.add(ZERO); ts.add(BOT); ts.add(U1); ts.add(U8); } + + // FIXME this display format is problematic + // In visualizer '#' gets prepended if its a constant + @Override + public StringBuilder print(StringBuilder sb) { return sb.append(str()); } + + @Override public String str() { + if( this==TOP ) return "~int"; + if( this==BOT ) return "int"; + if( this==BOOL) return ("bool"); + if( this==I8 ) return ("i8"); + if( this==I16 ) return ("i16"); + if( this==I32 ) return ("i32"); + if( this==U8 ) return ("u8"); + if( this==U16 ) return ("u16"); + if( this==U32 ) return ("u32"); + if( isConstant() ) return ""+_min; + return "["+_min+"-"+_max+"]"; + } + + /** + * Display Type name in a format that's good for IR printer + */ + @Override + public StringBuilder typeName(StringBuilder sb) { + if( this==TOP ) return sb.append("IntTop"); + if( this==BOT ) return sb.append("IntBot"); + return sb.append("Int"); + } + + @Override public boolean isHigh () { return _min > _max; } + @Override public boolean isHighOrConst() { return _min >= _max; } + @Override public boolean isConstant () { return _min == _max; } + + @Override public int log_size() { + if( this==I8 || this==U8 || this==BOOL ) return 0; // 1<<0 == 1 bytes + if( this==I16 || this==U16 ) return 1; // 1<<1 == 2 bytes + if( this==I32 || this==U32 ) return 2; // 1<<2 == 4 bytes + if( this==BOT ) return 3; // 1<<3 == 8 bytes + if( isHighOrConst() ) return 0; + throw Utils.TODO(); + } + + public long value() { assert isConstant(); return _min; } + + // AND-mask of forced zeros. e.g. unsigned types will return their mask; + // u8 will return 0xFF. But also a range of 16-18 (0x10-0x12) will return + // 0x13 - no value in the range {16,17,18} will allow bit 0x04 to be set. + public long mask() { + if( isHigh() ) return 0; + if( isConstant() ) return _min; + //if( _min<0 ) return -1L; + //if( _max==Long.MAX_VALUE ) return -1L; + // Those bit positions which differ min to max + long x = _min ^ _max; + // Highest '1' bit in the differ set. Since the range is from min to + // max, all values below here are possible. + long ff1 = Long.highestOneBit(x); + // Make a all-1's mask from ff1, and set over the same bits (either min + // or max is ok). + long mask = _min | (ff1-1) | ff1; + return mask; + } + + @Override + public Type xmeet(Type other) { + // Invariant from caller: 'this' != 'other' and same class (TypeInteger) + TypeInteger i = (TypeInteger)other; // Contract + return make(Math.min(_min,i._min), Math.max(_max,i._max)); + } + + @Override public TypeInteger dual() { return make(_max,_min); } + @Override public TypeInteger glb() { return BOT; } + @Override public TypeInteger lub() { return TOP; } + @Override public TypeInteger makeInit() { return ZERO; } + @Override public TypeInteger makeZero() { return ZERO; } + @Override public TypeInteger nonZero() { + if( isHigh() ) return this; + if( _min==0 ) return make(1,Math.max(_max,1)); // specifically good on BOOL + if( _max==0 ) return make(_min,-1); + return this; + } + @Override int hash() { return (int)((_min ^ (_min>>32)) *(_max ^ (_max>>32))); } + @Override + public boolean eq( Type t ) { + TypeInteger i = (TypeInteger)t; // Contract + return _min==i._min && _max==i._max; + } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/TypeMem.java b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeMem.java new file mode 100644 index 00000000..33c6a8ce --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeMem.java @@ -0,0 +1,67 @@ +package com.seaofnodes.simple.type; + +import com.seaofnodes.simple.Utils; +import java.lang.Long; +import java.util.BitSet; +import java.util.ArrayList; + + +/** + * Represents a slice of memory corresponding to a set of aliases + */ +public class TypeMem extends Type { + + // Which slice of memory? + // 0 means TOP, no slice. + // -1 means BOT, all memory. + // N means slice#N. + public final int _alias; + public final Type _t; // Memory contents, some scalar type + + private TypeMem(int alias, Type t) { super(TMEM); _alias = alias; _t = t; } + + public static TypeMem make(int alias, Type t) { return new TypeMem(alias,t).intern(); } + public static final TypeMem TOP = make(-1, Type.TOP ); + public static final TypeMem BOT = make(-1, Type.BOTTOM); + + public static void gather(ArrayList<Type> ts) { ts.add(make(1,TypeInteger.ZERO)); ts.add(BOT); } + + @Override + TypeMem xmeet(Type t) { + TypeMem that = (TypeMem) t; // Invariant: TypeMem and unequal + if( this==TOP ) return that; + if( that==TOP ) return this; + if( this==BOT ) return BOT; + if( that==BOT ) return BOT; + int alias = _alias==that._alias ? _alias : -1; + Type mt = _t.meet(that._t); + return make(alias,mt); + } + + @Override + public Type dual() { + return make(_alias,_t.dual()); + } + + @Override public Type glb() { return make(_alias,_t.glb()); } + @Override public Type lub() { return make(_alias,_t.lub()); } + + @Override + int hash() { return 9876543 + _alias + _t.hashCode(); } + + @Override + boolean eq(Type t) { + TypeMem that = (TypeMem) t; // Invariant + return _alias == that._alias && _t == that._t; + } + + @Override + public StringBuilder print(StringBuilder sb) { + sb.append("MEM#"); + if( _alias== 0 ) return sb.append("TOP"); + if( _alias==-1 ) return sb.append("BOT"); + return _t.print(sb.append(_alias).append(":")); + } + + @Override public String str() { return toString(); } +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/TypeMemPtr.java b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeMemPtr.java new file mode 100644 index 00000000..786a7be5 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeMemPtr.java @@ -0,0 +1,98 @@ +package com.seaofnodes.simple.type; + +import java.util.ArrayList; + +/** + * Represents a Pointer to memory. + * + * Null is generic pointer to non-existent memory. + * *void is a non-Null pointer to all possible refs, both structs and arrays. + * Pointers can be to specific struct and array types, or a union with Null. + * The distinguished *$BOT ptr represents union of *void and Null. + * The distinguished *$TOP ptr represents the dual of *$BOT. + */ +public class TypeMemPtr extends Type { + // A TypeMemPtr is pair (obj,nil) + // where obj is a TypeStruct, possibly TypeStruct.BOT + // where nil is an explicit null is allowed or not + + // Examples: + // (Person,false) - a not-nil Person + // (Person,true ) - a Person or a nil + // (BOT ,false) - a not-nil void* (unspecified struct) + // (TOP ,true ) - a nil + + public final TypeStruct _obj; + public final boolean _nil; + + private TypeMemPtr(TypeStruct obj, boolean nil) { + super(TMEMPTR); + assert obj!=null; + _obj = obj; + _nil = nil; + } + public static TypeMemPtr make(TypeStruct obj, boolean nil) { return new TypeMemPtr(obj, nil).intern(); } + public static TypeMemPtr make(TypeStruct obj) { return make(obj, false); } + public TypeMemPtr makeFrom(TypeStruct obj) { return obj==_obj ? this : make(obj, _nil); } + public TypeMemPtr makeFrom(boolean nil) { return nil==_nil ? this : make(_obj, nil); } + @Override public TypeMemPtr makeRO() { return makeFrom(_obj.makeRO()); } + @Override public boolean isFinal() { return _obj.isFinal(); } + + // An abstract pointer, pointing to either a Struct or an Array. + // Can also be null or not. + public static TypeMemPtr BOT = make(TypeStruct.BOT,true); + public static TypeMemPtr TOP = BOT.dual(); + // An abstract null (can be Struct or Array) or not-null C void* + public static TypeMemPtr NULLPTR = make(TypeStruct.TOP,true); + public static TypeMemPtr VOIDPTR = NULLPTR.dual(); // A bottom mix of not-null ptrs, like C's void* but not null + + public static TypeMemPtr TEST= make(TypeStruct.TEST,false); + public static void gather(ArrayList<Type> ts) { ts.add(NULLPTR); ts.add(BOT); ts.add(TEST); } + + @Override + Type xmeet(Type t) { + TypeMemPtr that = (TypeMemPtr) t; + return TypeMemPtr.make((TypeStruct)_obj.meet(that._obj), _nil | that._nil); + } + + @Override + public TypeMemPtr dual() { return TypeMemPtr.make(_obj.dual(), !_nil); } + + @Override public TypeMemPtr glb() { return make(_obj.glb(),true ); } + @Override public TypeMemPtr lub() { return make(_obj.lub(),false); } + // Is forward-reference + @Override public boolean isFRef() { return _obj.isFRef(); } + @Override public Type makeInit() { return _nil ? NULLPTR : Type.TOP; } + @Override public Type makeZero() { return NULLPTR; } + @Override public Type nonZero() { return VOIDPTR; } + + @Override public boolean isHigh() { return this==TOP; } + @Override public boolean isConstant() { return this==NULLPTR; } + @Override public boolean isHighOrConst() { return this==TOP || this==NULLPTR; } + + @Override public int log_size() { return 2; } // (1<<2)==4-byte pointers + + @Override + int hash() { return _obj.hashCode() ^ (_nil ? 1024 : 0); } + + @Override + boolean eq(Type t) { + TypeMemPtr ptr = (TypeMemPtr)t; // Invariant + return _obj == ptr._obj && _nil == ptr._nil; + } + + // [void,name,MANY]*[,?] + @Override + public StringBuilder print(StringBuilder sb) { + if( this== NULLPTR) return sb.append("null"); + if( this== VOIDPTR) return sb.append("*void"); + return _obj.print(sb.append("*")).append(_nil ? "?" : ""); + } + + @Override public String str() { + if( this== NULLPTR) return "null"; + if( this== VOIDPTR) return "*void"; + return "*"+_obj.str()+(_nil ? "?" : ""); + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/TypeStruct.java b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeStruct.java new file mode 100644 index 00000000..b3dbcad0 --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeStruct.java @@ -0,0 +1,256 @@ +package com.seaofnodes.simple.type; + +import com.seaofnodes.simple.Utils; +import java.util.ArrayList; + +/** + * Represents a struct type. + */ +public class TypeStruct extends Type { + + // A Struct has a name and a set of fields; the fields themselves have + // names, types and aliases. The name has no semantic meaning, but is + // useful for debugging. Briefly during parsing a Struct can be a + // forward-ref; in this case the _fields array is null. + + // Its illegal to attempt to load a field from a forward-ref struct. + + // Example: "int rez = new S.x; struct S { int x; } return rez;" // Error, S not defined + // Rewrite: "struct S { int x; } int rez = new S.x; return rez;" // Ok, no forward ref + // + // During the normal optimization run, struct types "bottom out" at further + // struct references, so we don't have to handle e.g. cyclic types. The + // "bottom out" is again the forward-ref struct. + public final String _name; + public final Field[] _fields; + + TypeStruct(String name, Field[] fields) { + super(TSTRUCT); + _name = name; + _fields = fields; + } + + // All fields directly listed + public static TypeStruct make(String name, Field... fields) { return new TypeStruct(name, fields).intern(); } + public static final TypeStruct TOP = make("$TOP",new Field[0]); + public static final TypeStruct BOT = make("$BOT",new Field[0]); + public static final TypeStruct TEST = make("test",new Field[]{Field.TEST}); + // Forward-ref version + public static TypeStruct makeFRef(String name) { return make(name, (Field[])null); } + // Make a read-only version + @Override public TypeStruct makeRO() { + if( isFinal() ) return this; + Field[] flds = new Field[_fields.length]; + for( int i=0; i<flds.length; i++ ) + flds[i] = _fields[i].makeRO(); + return make(_name,flds); + } + + // Array + public static TypeStruct makeAry(TypeInteger len, int lenAlias, Type body, int bodyAlias) { + assert !(body instanceof TypeMemPtr tmp && !tmp._nil); + return make("[" + body.str() + "]", + Field.make("#" ,len , lenAlias,true ), + Field.make("[]",body,bodyAlias,false)); + } + + // A pair of self-cyclic types + private static final TypeStruct S1F = makeFRef("S1"); + private static final TypeStruct S2F = makeFRef("S2"); + public static final TypeStruct S1 = make("S1", Field.make("a", TypeInteger.BOT, -1, false), Field.make("s2",TypeMemPtr.make(S2F,false),-2, false) ); + private static final TypeStruct S2 = make("S2", Field.make("b", TypeFloat .BOT, -3, false), Field.make("s1",TypeMemPtr.make(S1F,false),-4, false) ); + + private static final TypeStruct ARY = makeAry(TypeInteger.BOT,-1,TypeFloat.BOT,-2); + + public static void gather(ArrayList<Type> ts) { ts.add(TEST); ts.add(BOT); ts.add(S1); ts.add(S2); ts.add(ARY); } + + // Find field index by name + public int find(String fname) { + for( int i=0; i<_fields.length; i++ ) + if( _fields[i]._fname.equals(fname) ) + return i; + return -1; + } + public Field field(String fname) { + int idx = find(fname); + return idx== -1 ? null : _fields[idx]; + } + + // Find field index by alias + public int findAlias( int alias ) { + for( int i=0; i<_fields.length; i++ ) + if( _fields[i]._alias==alias ) + return i; + return -1; + } + + + @Override + Type xmeet(Type t) { + TypeStruct that = (TypeStruct) t; + if( this==TOP ) return that; + if( that==TOP ) return this; + if( this==BOT ) return BOT; + if( that==BOT ) return BOT; + + // Within the same compilation unit, struct names are unique. If the + // names differ, its different structs. Across many compilation units, + // structs with the same name but different field layouts can be + // interned... which begs the question: + // "What is the meet of structs from two different compilation units?" + // And the answer is: "don't ask". + if( !_name.equals(that._name) ) + return BOT; // It's a struct; that's about all we know + if( this._fields==null ) return that; + if( that._fields==null ) return this; + if( _fields.length != that._fields.length ) return BOT; + // Just do field meets + Field[] flds = new Field[_fields.length]; + for( int i=0; i<_fields.length; i++ ) { + Field f0 = _fields[i], f1 = that._fields[i]; + if( !f0._fname.equals(f1._fname) || f0._alias != f1._alias ) + return BOT; + flds[i] = (Field)f0.meet(f1); + } + return make(_name,flds); + } + + @Override + public TypeStruct dual() { + if( this==TOP ) return BOT; + if( this==BOT ) return TOP; + if( _fields == null ) return this; + Field[] flds = new Field[_fields.length]; + for( int i=0; i<_fields.length; i++ ) + flds[i] = _fields[i].dual(); + return make(_name,flds); + } + + // Keeps the same struct, but lower-bounds all fields. + @Override public TypeStruct glb() { + if( _glb() ) return this; + // Need to glb each field + Field[] flds = new Field[_fields.length]; + for( int i=0; i<_fields.length; i++ ) + flds[i] = _fields[i].glb(); + return make(_name,flds); + } + private boolean _glb() { + if( _fields!=null ) + for( Field f : _fields ) + if( f.glb() != f ) + return false; + return true; + } + @Override public TypeStruct lub() { + if( _lub() ) return this; + // Need to glb each field + Field[] flds = new Field[_fields.length]; + for( int i=0; i<_fields.length; i++ ) + flds[i] = _fields[i].lub(); + return make(_name,flds); + } + private boolean _lub() { + if( _fields!=null ) + for( Field f : _fields ) + if( f.lub() != f ) + return false; + return true; + } + + + // Is forward-reference + @Override public boolean isFRef() { return _fields==null; } + // All fields are final + @Override public boolean isFinal() { + if( _fields==null ) return true; + for( Field fld : _fields ) + if( !fld.isFinal() ) + return false; + return true; + } + + @Override + boolean eq(Type t) { + TypeStruct ts = (TypeStruct)t; // Invariant + if( !_name.equals(ts._name) ) + return false; + if( _fields == ts._fields ) return true; + if( _fields==null || ts._fields==null ) return false; + if( _fields.length!=ts._fields.length ) + return false; + for( int i = 0; i < _fields.length; i++ ) + if( _fields[i] != ts._fields[i] ) + return false; + return true; + } + + @Override + int hash() { + long hash = _name.hashCode(); + if( _fields != null ) + for( Field f : _fields ) + hash = Utils.rot(hash,13) ^ f.hashCode(); + return Utils.fold(hash); + } + + @Override + public StringBuilder print(StringBuilder sb) { + sb.append(_name); + if( _fields == null ) return sb; // Forward reference struct, just print the name + sb.append(" {"); + for( Field f : _fields ) + f._type.print(sb).append(f._final ? " " : " !").append(f._fname).append("; "); + return sb.append("}"); + } + + @Override public String str() { return _name; } + + + public boolean isAry() { return _fields.length==2 && _fields[1]._fname.equals("[]"); } + + public int aryBase() { + assert isAry(); + if( _offs==null ) _offs = offsets(); + return _offs[1]; + } + public int aryScale() { + assert isAry(); + return _fields[1]._type.log_size(); + } + + + // Field offsets as packed byte offsets + private int[] _offs; // Lazily computed and not part of the type semantics + public int offset(int idx) { + if( _offs==null ) _offs = offsets(); + return _offs[idx]; + } + private int[] offsets() { // Field byte offsets + // Compute a layout for a collection of fields + assert _fields != null; // No forward refs + // Compute a layout + int[] cnts = new int[4]; // Count of fields at log field size + for( Field f : _fields ) + cnts[f._type.log_size()]++; // Log size is 0(byte), 1(i16/u16), 2(i32/f32), 3(i64/dbl) + int off = 0, idx = 0; // Base common struct fields go here, e.g. Mark/Klass + // Compute offsets to the start of each power-of-2 aligned fields. + int[] offs = new int[4]; + for( int i=3; i>=0; i-- ) { + offs[i] = off; + off += cnts[i]<<i; + } + // Assign offsets to all fields. + // Really a hidden radix sort. + _offs = new int[_fields.length+1]; + for( Field f : _fields ) { + int log = f._type.log_size(); + _offs[idx++] = offs[log]; // Field offset + offs[log] += 1<<log; // Next field offset at same alignment + cnts[log]--; // Count down, should be all zero at end + } + _offs[_fields.length] = (off+7)& ~7; // Round out to max alignment + return _offs; + } + +} diff --git a/chapter18/src/main/java/com/seaofnodes/simple/type/TypeTuple.java b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeTuple.java new file mode 100644 index 00000000..a34c64db --- /dev/null +++ b/chapter18/src/main/java/com/seaofnodes/simple/type/TypeTuple.java @@ -0,0 +1,95 @@ +package com.seaofnodes.simple.type; + +import java.util.ArrayList; + +public class TypeTuple extends Type { + + public final Type[] _types; + + private TypeTuple(Type[] types) { super(TTUPLE); _types = types; } + public static TypeTuple make(Type... types) { return new TypeTuple(types).intern(); } + + private static final TypeTuple TEST = make(TypeInteger.BOT,TypeMemPtr.TEST); + public static final TypeTuple START = make(Type.CONTROL,TypeMem.TOP,TypeInteger.BOT); + public static void gather(ArrayList<Type> ts) { ts.add(TEST); ts.add(START); } + + @Override + Type xmeet(Type other) { + TypeTuple tt = (TypeTuple)other; // contract from xmeet + if( _types.length != tt._types.length ) + return BOTTOM; + Type[] ts = new Type[_types.length]; + for( int i=0; i<_types.length; i++ ) + ts[i] = _types[i].meet(tt._types[i]); + return make(ts); + } + + @Override public Type dual() { + Type[] ts = new Type[_types.length]; + for( int i=0; i<_types.length; i++ ) + ts[i] = _types[i].dual(); + return make(ts); + } + + @Override + public Type glb() { + Type[] ts = new Type[_types.length]; + for( int i=0; i<_types.length; i++ ) + ts[i] = _types[i].glb(); + return make(ts); + } + + @Override public StringBuilder print(StringBuilder sb) { + sb.append("[ "); + for( Type t : _types ) + t.print(sb).append(", "); + sb.setLength(sb.length()-2); + sb.append("]"); + return sb; + } + + @Override public String str() { + StringBuilder sb = new StringBuilder(); + sb.append("[ "); + for( Type t : _types ) + sb.append(t.str()).append(", "); + sb.setLength(sb.length()-2); + return sb.append("]").toString(); + } + + /** + * Display Type name in a format that's good for IR printer + */ + @Override + public StringBuilder typeName(StringBuilder sb) { + sb.append("["); + for( Type t : _types ) + t.typeName(sb).append(","); + sb.setLength(sb.length()-1); + return sb.append("]"); + } + + public static final TypeTuple IF_BOTH = make(new Type[]{Type. CONTROL,Type. CONTROL}); + public static final TypeTuple IF_NEITHER = make(new Type[]{Type.XCONTROL,Type.XCONTROL}); + public static final TypeTuple IF_TRUE = make(new Type[]{Type. CONTROL,Type.XCONTROL}); + public static final TypeTuple IF_FALSE = make(new Type[]{Type.XCONTROL,Type. CONTROL}); + + @Override + int hash() { + int sum = 0; + for( Type type : _types ) sum ^= type.hashCode(); + return sum; + } + + @Override + boolean eq( Type t ) { + TypeTuple tt = (TypeTuple)t; // Contract + if( _types.length != tt._types.length ) return false; + for( int i=0; i<_types.length; i++ ) + if( _types[i]!=tt._types[i] ) + return false; + return true; + } + + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/BrainFuckTest.java b/chapter18/src/test/java/com/seaofnodes/simple/BrainFuckTest.java new file mode 100644 index 00000000..88d79215 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/BrainFuckTest.java @@ -0,0 +1,72 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; +import org.junit.Ignore; + +import java.nio.charset.StandardCharsets; + +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class BrainFuckTest { + + @Test + public void testBrainfuck() { + var program = "++++++++[>++++[>++>+++>+++>+<<<<-]>+>+>->>+[<]<-]>>.>---.+++++++..+++.>>.<-.<.+++.------.--------.>>+.>++.".getBytes(StandardCharsets.UTF_8); + var encoded = new StringBuilder("u8[] !program = new u8[").append(program.length).append("];"); + for (int i = 0; i < program.length; i++) { + int value = program[i] & 0xFF; + encoded.append("program[").append(i).append("] = ").append(value).append(";"); + } + + Parser parser = new Parser( + encoded + """ +var d = 0; +u8[] !output = new u8[0]; +u8[] !data = new u8[100]; + +for( int pc = 0; pc < program#; pc++ ) { + var command = program[pc]; + if (command == 62) { + d++; + } else if (command == 60) { + d--; + } else if (command == 43) { + data[d]++; + } else if (command == 45) { + data[d]--; + } else if (command == 46) { + // Output a byte; increase the output array size + var old = output; + output = new u8[output# + 1]; + for( var i = 0; i < old#; i++ ) + output[i] = old[i]; + output[old#] = data[d]; // Add the extra byte on the end + } else if (command == 44) { + data[d] = 42; + } else if (command == 91) { + if (data[d] == 0) { + for( var d = 1; d > 0; ) { + command = program[++pc]; + if (command == 91) d++; + if (command == 93) d--; + } + } + } else if (command == 93) { + if (data[d]) { + for( var d = 1; d > 0; ) { + command = program[--pc]; + if (command == 93) d++; + if (command == 91) d--; + } + } + } +} +return output; + """); + StopNode stop = parser.parse(false).iterate(false); + assertEquals("Hello World!\n", Evaluator.evaluate(stop, 0, 10000).toString()); + } +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter01Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter01Test.java new file mode 100644 index 00000000..f7524c17 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter01Test.java @@ -0,0 +1,100 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter01Test { + + @Test + public void testSimpleProgram() { + Parser parser = new Parser("return 1;"); + StopNode stop = parser.parse(); + StartNode start = Parser.START; + ReturnNode ret = (ReturnNode)stop.in(0); + + assertTrue(ret.ctrl() instanceof CProjNode); + Node expr = ret.expr(); + if( expr instanceof ConstantNode con ) { + assertEquals(start,con.in(0)); + assertEquals(TypeInteger.constant(1), con._type); + } else { + fail(); + } + } + + @Test + public void testZero() { + Parser parser = new Parser("return 0;"); + parser.parse(); + StartNode start = Parser.START; + for( Node use : start._outputs ) + if( use instanceof ConstantNode con && con._type instanceof TypeInteger ) + assertEquals(TypeInteger.constant(0),con._type); + } + + @Test + public void testBad1() { + try { + new Parser("ret").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'ret'",e.getMessage()); + } + } + + @Test + public void testBad2() { + try { + new Parser("return 0123;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error: integer values cannot start with '0'",e.getMessage()); + } + } + + @Test + public void testNotBad3() { + // this test used to fail in chapter 1 + assertEquals("return 12;", new Parser("return - -12;").parse().print()); + } + + @Test + public void testBad4() { + try { + new Parser("return 100").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected ;: ",e.getMessage()); + } + } + + @Test + public void testNotBad5() { + // this test used to fail in chapter 1 + assertEquals("return -100;", new Parser("return -100;").parse().print()); + } + + @Test + public void testBad6() { + try { + new Parser("return100").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'return100'",e.getMessage()); + } + } + + @Test + public void testBad7() { + try { + new Parser("return 1;}").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, unexpected }",e.getMessage()); + } + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter02Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter02Test.java new file mode 100644 index 00000000..75ee0b70 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter02Test.java @@ -0,0 +1,62 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter02Test { + + @Test + public void testParseGrammar() { + Parser parser = new Parser("return 1+2*3+-5;"); + Node._disablePeephole = true; // disable peephole so we can observe full graph + StopNode ret = parser.parse(); + assertEquals("return ((1+(2*3))+(-5));", ret.print()); + Node._disablePeephole = false; + } + + @Test + public void testAddPeephole() { + Parser parser = new Parser("return 1+2;"); + StopNode ret = parser.parse(); + assertEquals("return 3;", ret.print()); + } + + @Test + public void testSubPeephole() { + Parser parser = new Parser("return 1-2;"); + StopNode ret = parser.parse(); + assertEquals("return -1;", ret.print()); + } + + @Test + public void testMulPeephole() { + Parser parser = new Parser("return 2*3;"); + StopNode ret = parser.parse(); + assertEquals("return 6;", ret.print()); + } + + @Test + public void testDivPeephole() { + Parser parser = new Parser("return 6/3;"); + StopNode ret = parser.parse(); + assertEquals("return 2;", ret.print()); + } + + @Test + public void testMinusPeephole() { + Parser parser = new Parser("return 6/-3;"); + StopNode ret = parser.parse(); + assertEquals("return -2;", ret.print()); + } + + @Test + public void testExample() { + Parser parser = new Parser("return 1+2*3+-5;"); + StopNode ret = parser.parse(); + assertEquals("return 2;", ret.print()); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter03Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter03Test.java new file mode 100644 index 00000000..4525918c --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter03Test.java @@ -0,0 +1,68 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter03Test { + + @Test + public void testVarDecl() { + Parser parser = new Parser("int a=1; return a;"); + StopNode ret = parser.parse(); + assertEquals("return 1;", ret.print()); + } + + @Test + public void testVarAdd() { + Parser parser = new Parser("int a=1; int b=2; return a+b;"); + StopNode ret = parser.parse(); + assertEquals("return 3;", ret.print()); + } + + @Test + public void testVarScope() { + Parser parser = new Parser("int a=1; int b=2; int c=0; { int b=3; c=a+b; } return c;"); + StopNode ret = parser.parse(); + assertEquals("return 4;", ret.print()); + } + + @Test + public void testVarScopeNoPeephole() { + Parser parser = new Parser("int a=1; int b=2; int !c=0; { int b=3; c=a+b; } return c; "); + Node._disablePeephole = true; + StopNode ret = parser.parse(); + Node._disablePeephole = false; + assertEquals("return (1+3);", ret.print()); + } + + @Test + public void testVarDist() { + Parser parser = new Parser("int x0=1; int y0=2; int x1=3; int y1=4; return (x0-x1)*(x0-x1) + (y0-y1)*(y0-y1); "); + StopNode ret = parser.parse(); + assertEquals("return 8;", ret.print()); + } + + @Test + public void testSelfAssign() { + try { + new Parser("int a=a; return a;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'a'",e.getMessage()); + } + } + + @Test + public void testBad1() { + try { + new Parser("int a=1; int b=2; int !c=0; { int b=3; c=a+b;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected }: ",e.getMessage()); + } + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter04Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter04Test.java new file mode 100644 index 00000000..24612fee --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter04Test.java @@ -0,0 +1,128 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter04Test { + + @Test + public void testPeephole() { + Parser parser = new Parser("return 1+arg+2; "); + StopNode ret = parser.parse(); + assertEquals("return (arg+3);", ret.print()); + } + + @Test + public void testPeephole2() { + Parser parser = new Parser("return (1+arg)+2;"); + StopNode ret = parser.parse(); + assertEquals("return (arg+3);", ret.print()); + } + + @Test + public void testAdd0() { + Parser parser = new Parser("return 0+arg;"); + StopNode ret = parser.parse(); + assertEquals("return arg;", ret.print()); + } + + @Test + public void testAddAddMul() { + Parser parser = new Parser("return arg+0+arg;"); + StopNode ret = parser.parse(); + assertEquals("return (arg*2);", ret.print()); + } + + @Test + public void testPeephole3() { + Parser parser = new Parser("return 1+arg+2+arg+3; "); + StopNode ret = parser.parse(); + assertEquals("return ((arg*2)+6);", ret.print()); + } + + @Test + public void testMul1() { + Parser parser = new Parser("return 1*arg;"); + StopNode ret = parser.parse(); + assertEquals("return arg;", ret.print()); + } + + @Test + public void testVarArg() { + Parser parser = new Parser("return arg; "); + StopNode stop = parser.parse(); + ReturnNode ret = stop.ret(); + assertTrue(ret.in(0) instanceof CProjNode); + assertTrue(ret.in(1) instanceof ProjNode); + } + + @Test + public void testConstantArg() { + Parser parser = new Parser("return arg; ", TypeInteger.constant(2)); + StopNode ret = parser.parse(); + assertEquals("return 2;", ret.print()); + } + + @Test + public void testCompEq() { + Parser parser = new Parser("return 3==3; "); + StopNode ret = parser.parse(); + assertEquals("return 1;", ret.print()); + } + + @Test + public void testCompEq2() { + Parser parser = new Parser("return 3==4; "); + StopNode ret = parser.parse(); + assertEquals("return 0;", ret.print()); + } + + @Test + public void testCompNEq() { + Parser parser = new Parser("return 3!=3; "); + StopNode ret = parser.parse(); + assertEquals("return 0;", ret.print()); + } + + @Test + public void testCompNEq2() { + Parser parser = new Parser("return 3!=4; "); + StopNode ret = parser.parse(); + assertEquals("return 1;", ret.print()); + } + + @Test + public void testBug1() { + Parser parser = new Parser("int a=arg+1; int !b=a; b=1; return a+2; "); + StopNode ret = parser.parse(); + assertEquals("return (arg+3);", ret.print()); + } + + @Test + public void testBug2() { + Parser parser = new Parser("int !a=arg+1; a=a; return a; "); + StopNode ret = parser.parse(); + assertEquals("return (arg+1);", ret.print()); + } + + @Test + public void testBug3() { + try { + new Parser("inta=1; return a;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'inta'",e.getMessage()); + } + } + + @Test + public void testBug4() { + Parser parser = new Parser("return -arg;"); + StopNode ret = parser.parse(); + assertEquals("return (-arg);", ret.print()); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter05Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter05Test.java new file mode 100644 index 00000000..9afb8f28 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter05Test.java @@ -0,0 +1,212 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter05Test { + + @Test + public void testIfStmt() { + Parser parser = new Parser( +""" +int a = 1; +if (arg == 1) + a = arg+2; +else { + a = arg-3; +} +return a; +"""); + StopNode ret = parser.parse().iterate(); + assertEquals("return Phi(Region,(arg+2),(arg-3));", ret.toString()); + } + + @Test + public void testTest() { + Parser parser = new Parser( +""" +int c = 3; +int b = 2; +if (arg == 1) { + b = 3; + c = 4; +} +return c;""", TypeInteger.BOT); + StopNode ret = parser.parse().iterate(); + assertEquals("return Phi(Region,4,3);", ret.toString()); + } + + @Test + public void testReturn2() { + Parser parser = new Parser( +""" +if( arg==1 ) + return 3; +else + return 4; +""", TypeInteger.BOT); + StopNode stop = parser.parse(); + assertEquals("Stop[ return 3; return 4; ]", stop.toString()); + } + + @Test + public void testIfMergeB() { + Parser parser = new Parser( +""" +int a=arg+1; +int b=0; +if( arg==1 ) + b=a; +else + b=a+1; +return a+b;"""); + StopNode ret = parser.parse().iterate(); + assertEquals("return ((arg*2)+Phi(Region,2,3));", ret.toString()); + } + + @Test + public void testIfMerge2() { + Parser parser = new Parser( +""" +int a=arg+1; +int b=arg+2; +if( arg==1 ) + b=b+a; +else + a=b+1; +return a+b;"""); + StopNode ret = parser.parse().iterate(); + assertEquals("return ((Phi(Region,(arg*2),arg)+arg)+Phi(Region,4,5));", ret.toString()); + } + + @Test + public void testMerge3() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( arg==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.BOT); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,Phi(Region,2,3),Phi(Region,4,5));", stop.toString()); + } + + @Test + public void testMerge4() { + Parser parser = new Parser( +""" +int a=0; +int b=0; +if( arg ) + a=1; +if( arg==0 ) + b=2; +return arg+a+b; +""", TypeInteger.BOT); + StopNode stop = parser.parse(); + assertEquals("return ((arg+Phi(Region,1,0))+Phi(Region,2,0));", stop.toString()); + } + + @Test + public void testMerge5() { + Parser parser = new Parser( +""" +int a=arg==2; +if( arg==1 ) +{ + a=arg==3; +} +return a;"""); + StopNode ret = parser.parse().iterate(); + assertEquals("return (arg==Phi(Region,3,2));", ret.toString()); + } + + @Test + public void testTrue() { + StopNode stop = new Parser("return true;").parse(); + assertEquals("return 1;",stop.toString()); + } + + @Test + public void testHalfDef() { + try { + new Parser("if( arg==1 ) int b=2; return b;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Cannot define a new name on one arm of an if",e.getMessage()); + } + } + + @Test + public void testHalfDef2() { + try { + new Parser("if( arg==1 ) { int b=2; } else { int b=3; } return b;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'b'",e.getMessage()); + } + } + + @Test + public void testRegress1() { + try { + new Parser("if(arg==2) int a=1; else int b=2; return a;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Cannot define a new name on one arm of an if",e.getMessage()); + } + } + + + @Test + public void testBadNum() { + try { + new Parser("return 1-;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected an identifier or expression: ;",e.getMessage()); + } + } + + @Test + public void testKeyword1() { + try { + new Parser("int true=0; return true;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Expected an identifier, found 'true'",e.getMessage()); + } + } + + @Test + public void testKeyword2() { + try { + new Parser("int else=arg; if(else) else=2; else else=1; return else;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Expected an identifier, found 'else'",e.getMessage()); + } + } + + @Test + public void testKeyword3() { + try { + new Parser("int a=1; ififif(arg)inta=2;return a;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'ififif'",e.getMessage()); + } + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter06Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter06Test.java new file mode 100644 index 00000000..50c0580d --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter06Test.java @@ -0,0 +1,294 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter06Test { + + @Test + public void testPeepholeReturn() { + Parser parser = new Parser( +""" +if( true ) return 2; +return 1; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 2;", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + @Test + public void testPeepholeRotate() { + Parser parser = new Parser( +""" +int a = 1; +if (arg) + a = 2; +return (arg < a) < 3; // Because (arg < a) is a bool/uint1/[0-1], its always less than 3 +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + } + + @Test + public void testPeepholeCFG() { + Parser parser = new Parser( +""" +int a=1; +if( true ) + a=2; +else + a=3; +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 2;", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + @Test + public void testIfIf() { + Parser parser = new Parser( +""" +int a=1; +if( arg!=1 ) + a=2; +else + a=3; +int b=4; +if( a==2 ) + b=42; +else + b=5; +return b;""", TypeInteger.BOT); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,42,5);", stop.toString()); + } + + @Test + public void testIfArgIf() { + Parser parser = new Parser( +""" +int a=1; +if( 1==1 ) + a=2; +else + a=3; +int b=4; +if( arg==2 ) + b=a; +else + b=5; +return b;""", TypeInteger.BOT); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,2,5);", stop.toString()); + } + + @Test + public void testMerge3With2() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( arg==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.constant(2)); + StopNode stop = parser.parse(); + assertEquals("return 5;", stop.toString()); + } + + @Test + public void testMerge3With1() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( arg==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.constant(1)); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3;", stop.toString()); + } + + @Test + public void testMerge3Peephole() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( 1==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.BOT); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,3,Phi(Region,4,5));", stop.toString()); + } + + @Test + public void testMerge3Peephole1() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( 1==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.constant(1)); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3;", stop.toString()); + } + + @Test + public void testMerge3Peephole3() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( 1==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.constant(3)); + StopNode stop = parser.parse().iterate(); + assertEquals("return 4;", stop.toString()); + } + + @Test + public void testDemo1NonConst() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +if( arg ) { + a = 2; + if( arg ) { b = 2; } + else b = 3; +} +return a+b; +"""); + StopNode ret = parser.parse().iterate(); + assertEquals("return Phi(Region,4,1);", ret.toString()); + } + + + @Test + public void testDemo1True() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +if( arg ) { + a = 2; + if( arg ) { b = 2; } + else b = 3; +} +return a+b; +""", TypeInteger.constant(1)); + StopNode ret = parser.parse().iterate(); + assertEquals("return 4;", ret.toString()); + } + + @Test + public void testDemo1False() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +if( arg ) { + a = 2; + if( arg ) { b = 2; } + else b = 3; +} +return a+b; +""", TypeInteger.constant(0)); + StopNode ret = parser.parse().iterate(); + assertEquals("return 1;", ret.toString()); + } + + @Test + public void testDemo2NonConst() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +int c = 0; +if( arg ) { + a = 1; + if( arg==2 ) { c=2; } else { c=3; } + if( arg ) { b = 2; } + else b = 3; +} +return a+b+c; +"""); + StopNode ret = parser.parse().iterate(); + assertEquals("return (Phi(Region,Phi(Region,2,3),0)+Phi(Region,3,1));", ret.toString()); + } + + + @Test + public void testDemo2True() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +int c = 0; +if( arg ) { + a = 1; + if( arg==2 ) { c=2; } else { c=3; } + if( arg ) { b = 2; } + else b = 3; +} +return a+b+c; +""", TypeInteger.constant(1)); + StopNode ret = parser.parse().iterate(); + assertEquals("return 6;", ret.toString()); + } + + @Test + public void testDemo2arg2() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +int c = 0; +if( arg ) { + a = 1; + if( arg==2 ) { c=2; } else { c=3; } + if( arg ) { b = 2; } + else b = 3; +} +return a+b+c; +""", TypeInteger.constant(2)); + StopNode ret = parser.parse().iterate(); + assertEquals("return 5;", ret.toString()); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter07Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter07Test.java new file mode 100644 index 00000000..355bbba4 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter07Test.java @@ -0,0 +1,233 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter07Test { + + @Test + public void testExample() { + Parser parser = new Parser( +""" +while(arg < 10) { + arg = arg + 1; +} +return arg; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop,arg,(Phi_arg+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + Node._disablePeephole = false; + } + + @Test + public void testRegression() { + Parser parser = new Parser( +""" +int a = 1; +if(arg){}else{ + while(a < 10) { + a = a + 1; + } +} +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,1,Phi(Loop,1,(Phi_a+1)));", stop.toString()); + } + + @Test + public void testWhileNested() { + Parser parser = new Parser( +""" +int sum = 0; +int i = 0; +while(i < arg) { + i = i + 1; + int j = 0; + while( j < arg ) { + sum = sum + j; + j = j + 1; + } +} +return sum; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,Phi(Loop,Phi_sum,(Phi_sum+Phi(Loop,0,(Phi_j+1)))));", stop.toString()); + } + + @Test + public void testWhileScope() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + if (a == 2) a = 3; + else b = 4; +} +return b; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop,2,Phi(Region,Phi_b,4));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + Node._disablePeephole = false; + } + + @Test + public void testWhileNestedIfAndInc() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + if (a == 2) a = 3; + else b = 4; + b = b + 1; + a = a + 1; +} +return b; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,2,(Phi(Region,Phi_b,4)+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + + @Test + public void testWhile() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + a = a + 1; + a = a + 2; +} +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop,1,((Phi_a+1)+2));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + Node._disablePeephole = false; + } + + @Test + public void testWhilePeep() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + a = a + 1; + a = a + 2; +} +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,1,(Phi_a+3));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + @Test + public void testWhile2() { + Parser parser = new Parser( +""" +int a = 1; +while(arg) a = 2; +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop,1,2);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + Node._disablePeephole = false; + } + + @Test + public void testWhile2Peep() { + Parser parser = new Parser( +""" +int a = 1; +while(arg) a = 2; +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,1,2);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + @Test + public void testWhile3() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop,1,((Phi_a+1)+2));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + Node._disablePeephole = false; + } + + @Test + public void testWhile3Peep() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,1,(Phi_a+3));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + @Test + public void testWhile4() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(); + assertEquals("return Phi(Loop,1,((Phi_a+1)+2));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + Node._disablePeephole = false; + } + + @Test + public void testWhile4Peep() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,1,(Phi_a+3));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter08Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter08Test.java new file mode 100644 index 00000000..bb3bd674 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter08Test.java @@ -0,0 +1,208 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.*; +import org.junit.Assert; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter08Test { + + @Test + public void testEx6() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + break; + if (arg == 6) + break; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,Phi(Region,Phi(Loop,arg,(Phi_arg+1)),Add),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + Assert.assertEquals(5L, Evaluator.evaluate(stop, 1)); + Assert.assertEquals(10L, Evaluator.evaluate(stop, 6)); + } + + + @Test + public void testEx5() { + Parser parser = new Parser( + """ +int a = 1; +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; + if (arg == 7) + continue; + a = a + 1; +} +return a; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,1,Phi(Region,Phi_a,(Phi_a+1)));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + + @Test + public void testEx4() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; + if (arg == 6) + break; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,Phi(Loop,arg,(Phi_arg+1)),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + } + + @Test + public void testEx3() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 6) + break; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,Phi(Loop,arg,(Phi_arg+1)),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + } + + + @Test + public void testEx2() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; + if (arg == 6) + continue; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,arg,(Phi_arg+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + + @Test + public void testEx1() { + Parser parser = new Parser( + """ +while(arg < 10) { + arg = arg + 1; + if (arg == 5) + continue; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,arg,(Phi_arg+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode); + } + + @Test + public void testRegress1() { + Parser parser = new Parser( + """ +while( arg < 10 ) { + int a = arg+2; + if( a > 4 ) + break; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return arg;", stop.toString()); + } + + @Test + public void testRegress2() { + Parser parser = new Parser("if(1) return 0; else while(arg>- -arg) arg=arg+1; return 0;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testBreakOutsideLoop() { + try { + new Parser(""" +if(arg <= 10) { + break; + arg = arg + 1; +} +return arg; +""").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("No active loop for a break or continue",e.getMessage()); + } + } + + @Test + public void testRegress3() { + Parser parser = new Parser(""" +while(arg < 10) { + break; +} +return arg; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return arg;", stop.toString()); + } + + @Test + public void testRegress4() { + Parser parser = new Parser(""" +int a = 1; +while(arg < 10) { + a = a + 1; + if (arg > 2) { + int a = 17; + break; + } +} +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,Phi(Loop,1,(Phi_a+1)),Add);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof RegionNode); + } + + @Test + public void testRegress5() { + Parser parser = new Parser(""" +int a = 1; +while(1) { + a = a + 1; + if (a<10) continue; + break; +} +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (Phi(Loop,1,Add)+1);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof CProjNode prj && prj._idx==1 ); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter09Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter09Test.java new file mode 100644 index 00000000..c31afcd6 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter09Test.java @@ -0,0 +1,301 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Assert; +import org.junit.Test; +import org.junit.Ignore; + +import static org.junit.Assert.*; + +public class Chapter09Test { + + @Test + @Ignore + public void testJig() { + Parser parser = new Parser(""" +int v0=0; +arg=0; +while(v0) { + while(1) if(arg*arg*0==0) {} + while(0) {} + arg=1; +} +return 0; + """); + StopNode stop = parser.parse().iterate(); + } + + @Test + public void testGVN1() { + Parser parser = new Parser( + """ +int x = arg + arg; +if(arg < 10) { + return arg + arg; +} +else { + x = x + 1; +} +return x; + """); + StopNode stop = parser.parse(); + assertEquals("Stop[ return (arg*2); return (Mul+1); ]", stop.toString()); + Assert.assertEquals(2L, Evaluator.evaluate(stop, 1)); + Assert.assertEquals(23L, Evaluator.evaluate(stop, 11)); + } + + @Test + public void testGVN2() { + Parser parser = new Parser( + """ +return arg*arg-arg*arg; + """); + StopNode stop = parser.parse(); + assertEquals("return 0;", stop.toString()); + Assert.assertEquals(0L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testWorklist1() { + Parser parser = new Parser( + """ +int step = 1; +while (arg < 10) { + arg = arg + step + 1; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,arg,(Phi_arg+2));", stop.toString()); + Assert.assertEquals(11L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testWorklist2() { + Parser parser = new Parser( + """ +int cond = 0; +int one = 1; +while (arg < 10) { + if (cond) one = 2; + arg = arg + one*3 + 1; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,arg,(Phi_arg+4));", stop.toString()); + Assert.assertEquals(13L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testWorklist3() { + Parser parser = new Parser( + """ +int v1 = 0; +int v2 = 0; +int v3 = 0; +int v4 = 0; +int v5 = 0; +int v6 = 0; +int v7 = 0; +int v8 = 0; +while (arg) { + if (v1) v2 = 1; + if (v2) v3 = 1; + if (v3) v4 = 1; + if (v4) v5 = 1; + if (v5) v6 = 1; + if (v6) v7 = 1; + if (v7) v8 = 1; + arg = arg + v8 + 1; +} +return arg; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testRegionPeepBug() { + Parser parser = new Parser( + """ +int v0=0; +int v1=0; +while(v1+arg) { + arg=0; + int v2=v0; + while(arg+1) {} + v0=1; + v1=v2; +} + """); + StopNode stop = parser.parse().iterate(); + assertEquals("Stop[ return 0; return 0; ]", stop.toString()); + } + + @Test + public void testWhile0() { + Parser parser = new Parser("while(0) continue; if(0) arg=0;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testWhile1() { + Parser parser = new Parser(""" +if(0) while(0) { + int arg=arg; + while(0) {} +} +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + + @Test + public void testPrecedence() { + Parser parser = new Parser("return 3-1+2;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 4;", stop.toString()); + } + + @Test + public void testSwap2() { + Parser parser = new Parser("return 1+(1+1);"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3;", stop.toString()); + } + + + @Test + public void testFuzz0() { + Parser parser = new Parser(""" +int one = 1; +int a = 0; +int zero = 0; +while(arg) { + a = -(one + a + 2); + arg = arg + 1; + one = one + zero; +} +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(-(Phi_a+3)));", stop.toString()); + } + + @Test + public void testFuzz1() { + Parser parser = new Parser(""" +while(1) {} +while(arg) break; +while(arg) arg=0; +arg=0; +int v0=0!=0<-0; +return -0+0+0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + + @Test + public void testFuzz2() { + Parser parser = new Parser("return 0+-0;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testFuzz3() { + Parser parser = new Parser("int v0=0; while(0==69) while(v0) return 0;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testFuzz4() { + Parser parser = new Parser(""" +while(1) { + arg=0<=0; + if(1<0) while(arg==-0) arg=arg-arg; +} +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testFuzz5() { + Parser parser = new Parser(""" +{ + int v0=0; + while(1) + int v1=0--0; + while(v0) + break; + while(-v0) { + while(0+0+v0) continue; + break; + } + if(-0!=-0+0+v0) while(0+0+0+0) + break; +} +return 0!=0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testFuzz6() { + Parser parser = new Parser( +""" +int v0=0; +while(0==1) while(v0) + v0=1+v0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testFuzz7() { + Parser parser = new Parser(""" +while(1) {} +int v0=0; +while(v0) + {} +int v1=0; +while(1) + v1=1; +return v1+v0; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testFuzz8() { + Parser parser = new Parser("while(arg) arg = arg - 1; return arg;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testMeet() { + Type t1 = Type.TOP; + Type t2 = TypeInteger.TOP; + Assert.assertEquals(TypeInteger.TOP, t1.meet(t2)); + Assert.assertEquals(TypeInteger.TOP, t2.meet(t1)); + t1 = Type.BOTTOM; + t2 = TypeInteger.BOT; + Assert.assertEquals(Type.BOTTOM, t1.meet(t2)); + Assert.assertEquals(Type.BOTTOM, t2.meet(t1)); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter10Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter10Test.java new file mode 100644 index 00000000..d41c83d8 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter10Test.java @@ -0,0 +1,399 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class Chapter10Test { + + @Test + public void testFuzzer() { + Parser parser = new Parser( +""" +int a = arg/3; +int b = arg*5; +int x = arg*7; +int y = arg/11; +int p; int g; int h; +if( (arg/13)==0 ) { + p = x + y; + g = x; + h = y; +} else { + p = a + b; + g = a; + h = b; +} +int r = g+h; +return p-r; +"""); + StopNode stop = parser.parse(false).iterate(false); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testStruct() { + Parser parser = new Parser(""" +struct Bar { + int a; + int b; +}; +struct Foo { + int x; +}; +Foo? foo = null; +Bar !bar = new Bar; +bar.a = 1; +bar.a = 2; +return bar.a; +"""); + StopNode stop = parser.parse(false).iterate(); + assertEquals("return 2;", stop.toString()); + } + + @Test + public void testExample() { + Parser parser = new Parser(""" +struct Vector2D { int x; int y; }; +Vector2D !v = new Vector2D; +v.x = 1; +if (arg) + v.y = 2; +else + v.y = 3; +return v; +"""); + StopNode stop = parser.parse(false).iterate(); + assertEquals("return Vector2D;", stop.toString()); + } + + @Test + public void testBug() { + Parser parser = new Parser(""" +struct s0 { + int v0; +}; +s0? v1=null; +int v3=v1.zAicm; +"""); + try { parser.parse(); fail(); } + catch( Exception e ) { assertEquals("Accessing unknown field 'zAicm' from 'null'",e.getMessage()); } + } + + @Test + public void testBug2() { + Parser parser = new Parser(""" +struct s0 { int v0; }; +arg=0+new s0.0; +"""); + try { parser.parse(); fail(); } + catch( Exception e ) { assertEquals("Expected an identifier, found 'null'",e.getMessage()); } + } + + @Test + public void testLoop() { + Parser parser = new Parser(""" +struct Bar { int a; }; +Bar !bar = new Bar; +while (arg) { + bar.a = bar.a + 2; + arg = arg + 1; +} +return bar.a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(Phi_a+2));", stop.toString()); + } + + @Test + public void testIf() { + Parser parser = new Parser(""" +struct Bar { int a; }; +Bar !bar = new Bar; +if (arg) bar = null; +bar.a = 1; +return bar.a; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Type null is not of declared type *Bar",e.getMessage()); } + } + + @Test + public void testIf2() { + Parser parser = new Parser(""" +struct Bar { int a; }; +Bar? !bar = null; +if (arg) bar = new Bar; +bar.a = 1; +return bar.a; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Might be null accessing 'a'",e.getMessage()); } + } + + @Test + public void testIf3() { + Parser parser = new Parser(""" +struct Bar { int a; }; +Bar bar = null; +if (arg) bar = null; +bar.a = 1; +return bar.a; +"""); + try { parser.parse(); fail(); } + catch( Exception e ) { assertEquals("Type null is not of declared type *Bar", e.getMessage()); } + } + + @Test + public void testIfOrNull() { + Parser parser = new Parser(""" +struct Bar { int a; }; +Bar? !bar = new Bar; +if (arg) bar = null; +if( bar ) bar.a = 1; +return bar; +"""); + StopNode stop = parser.parse(false).iterate(); + assertEquals("return Phi(Region,(*void)Phi(Region,null,Bar),null);", stop.toString()); + } + + @Test + public void testIfOrNull2() { + Parser parser = new Parser( +""" +struct Bar { int a; }; +Bar? !bar = new Bar; +if (arg) bar = null; +int rez = 3; +if( !bar ) rez=4; +else bar.a = 1; +return rez; +"""); + StopNode stop = parser.parse(false).iterate(); + assertEquals("return Phi(Region,4,3);", stop.toString()); + } + + @Test + public void testWhileWithNullInside() { + Parser parser = new Parser(""" +struct s0 {int v0;}; +s0? !v0 = new s0; +int ret = 0; +while(arg) { + ret = v0.v0; + v0 = null; + arg = arg - 1; +} +return ret; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { + assertEquals("Might be null accessing 'v0'", e.getMessage()); } + } + + @Test + public void testRedeclareStruct() { + Parser parser = new Parser(""" +struct s0 { + int v0; +}; +s0? v1=new s0; +s0? v1; +v1=new s0; +"""); + try { parser.parse(); fail(); } + catch( Exception e ) { assertEquals("Redefining name 'v1'", e.getMessage()); } + } + + @Test + public void testIter() { + // Build and use an iterator + Parser parser = new Parser( +""" +struct Iter { + int x; + int len; +}; +Iter !i = new Iter; +i.len = arg; +int sum=0; +while( i.x < i.len ) { + sum = sum + i.x; + i.x = i.x + 1; +} +return sum; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(Phi(Loop,0,(Phi_x+1))+Phi_sum));", stop.toString()); + } + + + @Test + public void test1() { + Parser parser = new Parser(""" +struct s0 {int v0;}; +s0 !ret = new s0; +while(arg) { + s0 !v0 = new s0; + v0.v0 = arg; + arg = arg-1; + if (arg==5) ret=v0; + +} +return ret; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,s0,Phi(Region,s0,Phi_ret));", stop.toString()); + } + + @Test + public void test2() { + Parser parser = new Parser(""" +struct s0 {int v0;}; +s0 !ret = new s0; +s0 !v0 = new s0; +while(arg) { + v0.v0 = arg; + arg = arg-1; + if (arg==5) ret=v0; + +} +return ret; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,s0,Phi(Region,s0,Phi_ret));", stop.toString()); + } + + + @Test + public void test3() { + Parser parser = new Parser(""" +struct s0 {int v0;}; +s0 !ret = new s0; +while(arg < 10) { + s0 !v0 = new s0; + if (arg == 5) ret=v0; + arg = arg + 1; +} +return ret; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,s0,Phi(Region,s0,Phi_ret));", stop.toString()); + } + + @Test + public void testBug3() { + Parser parser = new Parser(""" +struct s0 { int f0; }; +return new s0; +int v0=null.f0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return s0;", stop.toString()); + assertEquals("Obj<s0>{f0=0}", Evaluator.evaluate(stop, 0).toString()); + } + + @Test + public void testBug4() { + Parser parser = new Parser(""" +if(0) { + while(0) if(arg) continue; + int v0=0; + while(1) { + int arg=-arg; + v0=arg; + } +} + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testBug5() { + Parser parser = new Parser(""" +struct s0 { + int f0; +}; +if(0) return 0; +else return new s0; +if(new s0.f0) return 0; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return s0;", stop.toString()); + } + + @Test + public void testBug6MissedWorklist() { + Parser parser = new Parser(""" +while(0) {} +int v4=0; +while(0<arg) { + v4=v4+1; + while(1) v4=-v4; + while(0) arg=-1; +} +return 0; + """); + StopNode stop = parser.parse().iterate(); + } + + @Test + public void testBug7() { + Parser parser = new Parser(""" +struct s0 { int f0; }; +s0 v0 = new s0; +while(v0.f0) {} +s0 v1 = v0; +return v1; + """); + StopNode stop = parser.parse().iterate(); + assertEquals("return (const)s0;", stop.toString()); + } + + + @Test + public void testBug8() { + Parser parser = new Parser(""" +int v2=0; +while(0) +while(0) {} +{ + { + { + int v36=0; + { + while(0) { + { + while(-v2) { + { + while(v36) { + while(v2) return 0; + break; + } } + if(-v2) break; + } + } + } + } + } } +} +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testBug9() { + Parser parser = new Parser(""" +int v0=arg==0; +while(v0) continue; +return 0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter11Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter11Test.java new file mode 100644 index 00000000..613b979b --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter11Test.java @@ -0,0 +1,553 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; + + +import static org.junit.Assert.assertEquals; + +public class Chapter11Test { + + // A placeholder test used to rapidly rotate through fuzzer produced issues + @Test + public void testFuzzer() { + Parser parser = new Parser( +""" +while(---- -arg) { + while(-arg) { + while(-----arg*---0) { + int N=--false==false<--arg; + while(N<-4==N) { + N=N+N; + } + } + { + int kzEl_r7EYz=3*----0!=-arg<(37*--97!=0/arg==arg)<=-(--arg!=0); + while(kzEl_r7EYz<---1) { + kzEl_r7EYz=kzEl_r7EYz+kzEl_r7EYz*arg>=24; + if(7) continue; + kzEl_r7EYz=false; + if(-kzEl_r7EYz+arg<-3) continue; + else { + while(kzEl_r7EYz) continue; + arg=----3; + kzEl_r7EYz=-(-----arg*1>-kzEl_r7EYz); + int v2uF_4ba=9; + } + } + } + int pjcp7rv=arg; + { + int m2ya3=--arg-pjcp7rv; + while(m2ya3<-----pjcp7rv>=pjcp7rv+--pjcp7rv!=---pjcp7rv!=-arg<---(-m2ya3)>m2ya3<=-----true>14!=--m2ya3) { + m2ya3=m2ya3+-(--0<=false<pjcp7rv/arg<=-true); + while((--m2ya3)<--arg<-----arg*false!=arg<pjcp7rv*arg) { + pjcp7rv=-3+-arg; + break; + } + while(-3) { + while(67+0-61) m2ya3=m2ya3; + if(----pjcp7rv==---(---arg)) pjcp7rv=0!=-23; + else pjcp7rv=----89; + while(m2ya3!=m2ya3<pjcp7rv) m2ya3=1; + while(--arg<=pjcp7rv) pjcp7rv=-32<=-m2ya3+62; + } + break; + } + } + { + int arg=-1<-9!=(-arg>=-pjcp7rv>=arg<=arg); + while(arg<-arg) { + arg=arg+--arg; + { + while((--93)--pjcp7rv*-pjcp7rv+arg) arg=0-(6>=(--(---41/(0))!=--pjcp7rv)>=---2*33); + pjcp7rv=11; + int c=pjcp7rv; + if(--107) break; + else break; + } + } + } + pjcp7rv=pjcp7rv; + int aR0Wkua=-pjcp7rv==pjcp7rv; + { + if(-0!=-0) while(-true) break; + else { + while(aR0Wkua) pjcp7rv=-0/pjcp7rv; + pjcp7rv=pjcp7rv; + } + } + } + if(-arg) { + { + int Isdlt0fr91=0!=arg; + while(Isdlt0fr91<-Isdlt0fr91==-Isdlt0fr91+true) { + Isdlt0fr91=Isdlt0fr91+-1!=true; + if(-arg) if(--arg<=Isdlt0fr91) Isdlt0fr91=-Isdlt0fr91; + int i=---arg<---arg!=--40; + { + int jVX43Ln4Dm=-(6)==-Isdlt0fr91/----0; + while(jVX43Ln4Dm<--(3-3)) { + jVX43Ln4Dm=jVX43Ln4Dm+-0<25; + i=24<--(jVX43Ln4Dm); + } + } + i=(arg!=----false>=7); + int Te=5>-arg; + break; + } + } + arg=arg!=--true/arg; + { + int UX=arg; + while(UX<-3*arg) { + UX=UX+arg/-1; + arg=-3--(-UX- -47<arg==--arg==arg)/arg- -UX>=-arg; + if(---12) while(-UX) break; + break; + } + } + continue; + } + if(arg) arg=--0; + else if(1) continue; + int DtTlhjYq=19==arg; + { + arg=--DtTlhjYq<=(DtTlhjYq/---DtTlhjYq<=-DtTlhjYq); + if(---arg) continue; + else { + int Zsl=40; + while(Zsl<--Zsl--false>((Zsl))==Zsl!=--DtTlhjYq-DtTlhjYq-DtTlhjYq) { + Zsl=Zsl+arg; + } + } + if((arg)) if(-DtTlhjYq) { + } + else while(((2)==3*arg/DtTlhjYq)<=0==---arg) return false; + else { + int lwbF=arg>=0; + while(lwbF<57) { + lwbF=lwbF+--(-arg+lwbF)>=-2>=arg!=arg; + arg=----0+0; + while(49) break; + if(true) DtTlhjYq=-----arg; + DtTlhjYq=0!=-----(0); + } + } + arg=---arg!=DtTlhjYq/--0; + DtTlhjYq=-DtTlhjYq/(--arg<arg); + if(32) { + int q=-DtTlhjYq; + while(q<arg*(0*q)/0) { + q=q+DtTlhjYq; + DtTlhjYq=arg; + } + } + else if(--arg) if(15) break; + else arg=0==arg<=-55>DtTlhjYq; + else { + } + DtTlhjYq=-0; + { + while((0)<-arg) DtTlhjYq=-DtTlhjYq; + } + if(30/--(arg)>=0) DtTlhjYq=-0>=arg; + else { + int Y2wcIQJ=--DtTlhjYq*---11; + if(arg==arg) { + Y2wcIQJ=-----Y2wcIQJ; + Y2wcIQJ=Y2wcIQJ<7; + if(DtTlhjYq) arg=arg; + else break; + while(-arg!=-31==(false<=-15>=-DtTlhjYq+--6*-----Y2wcIQJ<=---arg!=-Y2wcIQJ<=---0<-arg*--Y2wcIQJ)) DtTlhjYq=arg!=3; + } + continue; + } + arg=DtTlhjYq; + arg=--3/(---arg)>=80>=-DtTlhjYq<=DtTlhjYq; + arg=51+---(-true)!=arg!=----1==-DtTlhjYq; + if(11<=arg) if((arg)+79<32+(-arg)) continue; + else if(true==DtTlhjYq) break; + break; + } +} +if(arg!=62==arg) { + while(---arg) { + { + int bhmDacPM=arg/arg; + while(bhmDacPM<arg) { + bhmDacPM=bhmDacPM+80*((-bhmDacPM)/---bhmDacPM>1)<bhmDacPM-2!=7; + arg=-0; + arg=bhmDacPM>=-arg+-arg; + break; + } + } + int arg=true; + arg=arg<=arg; + { + int KlC=30; + while(KlC<-2) { + KlC=KlC+-1!=25<=-KlC>KlC>----0; + int Ij=arg>=-arg<=---10; + { + int LAbgurVa2R=-arg!=Ij; + while(LAbgurVa2R<-true) { + LAbgurVa2R=LAbgurVa2R+Ij; + KlC=-LAbgurVa2R; + Ij=42*(-Ij>true); + while(Ij) arg=KlC; + KlC=-----7>-(--KlC<--7)==-LAbgurVa2R; + } + } + int a=Ij<=-KlC; + if(Ij) { + int r1W=a!=-false; + } + else { + arg=56>=Ij; + while(54) break; + arg=8>=-(a<--Ij)/a>=-a-KlC; + } + int Yt_T=KlC; + arg=KlC; + } + } + if(----false/--arg/12+-----0) if(-9+-arg) while(arg!=(arg)) arg=--1>=-71-arg!=---(--arg*11+102)/--arg; + else if(----arg) continue; + if(-arg-arg) { + arg=-(-arg)*--(-3)<(-7==-arg----arg); + { + int arg=arg; + while(arg<-0>arg==-arg-(-arg>1+11)) { + arg=arg+6-arg!=--0>---30>=---arg<=arg/(3)+---arg; + } + } + arg=-arg+arg; + arg=--47+-arg<1>arg*(-arg==-arg- -0>3); + arg=(----arg)!=arg+--59; + arg=- -4+arg==-(arg)-arg; + } + else { + while(--true-----true*-25+-18>arg>=-----(-arg)---13) { + arg=-0+--true<false; + continue; + } + arg=true<=arg; + break; + } + arg=arg*22<--(0+-arg); + { + continue; + } + } + arg=1*---((3<=true)==---2); + arg=7+-(-1); + return arg+--true; +} +else { + int o3ypEsewxM=-(---arg); + int vzXB=(-(---11<=--o3ypEsewxM>=--0))<=-0/-arg; + int L=-arg; + int B4mHcrf=---vzXB; + int oZWGdzZl=-o3ypEsewxM; + int K6tQqa1=11; + while(0!=--L) { + int sdZfTM=vzXB*true+K6tQqa1; + while(sdZfTM<false) { + sdZfTM=sdZfTM+arg; + sdZfTM=oZWGdzZl; + K6tQqa1=-K6tQqa1; + arg=---K6tQqa1; + while((3+-K6tQqa1)<oZWGdzZl) { + if(-----(-1)) sdZfTM=-false; + {} + } + K6tQqa1=vzXB!=-(B4mHcrf+-7>false); + sdZfTM=vzXB; + } + } + L=false; + while(31) B4mHcrf=arg; + oZWGdzZl=-0<--oZWGdzZl<=--2; + if(K6tQqa1>=20<=46) { + if(-1+-L) if(oZWGdzZl) { + int wmhv=-----0; + } + int arg=0; + o3ypEsewxM=---(oZWGdzZl); + return -oZWGdzZl/0; + } + else if(arg) { + int yKk5=B4mHcrf>=4>K6tQqa1<-B4mHcrf/o3ypEsewxM; + return -K6tQqa1; + } + else { + if(---0) { + {} + {} + } + return o3ypEsewxM; + } +} +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("Stop[ return 9; return 0; return 0; return 0; return 0; ]", stop.toString()); + } + + + @Test + public void testPrimes() { + Parser parser = new Parser( +""" +if( arg < 2 ) return 0; +int primeCount = 1; +int prime = 3; +while( prime <= arg ) { + int isPrime = 1; + // Check for even case, so the next loop need only check odds + if( (prime/2)*2 == prime ) + continue; + // Check odds up to sqrt of prime + int j = 3; + while( j*j <= prime ) { + if( (prime/j)*j == prime ) { + isPrime = 0; + break; + } + j = j + 2; + } + if( isPrime ) + primeCount = primeCount + 1; + prime = prime + 2; +} +return primeCount; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("Stop[ return 0; return Phi(Loop,1,Phi(Region,Phi_primeCount,Phi(Region,(Phi_primeCount+1),Phi_primeCount))); ]", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 1)); // No primes 1 or below + assertEquals(1L, Evaluator.evaluate(stop, 2)); // 2 + assertEquals(2L, Evaluator.evaluate(stop, 3)); // 2, 3 + assertEquals(2L, Evaluator.evaluate(stop, 4)); // 2, 3 + assertEquals(3L, Evaluator.evaluate(stop, 5)); // 2, 3, 5 + assertEquals(4L, Evaluator.evaluate(stop, 10)); // 2, 3, 5, 7 + } + + @Test + public void testAntiDeps1() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v=new S; +v.f = 2; +int i=new S.f; +i=v.f; +if (arg) v.f=1; +return i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 2;", stop.toString()); + assertEquals(2L, Evaluator.evaluate(stop, 0)); + assertEquals(2L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testAntiDeps2() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v = new S; +v.f = arg; +S !t = new S; +int i = 0; +if (arg) { + if (arg+1) v = t; + i = v.f; +} else { + v.f = 2; +} +return i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,.f,0);", stop.toString()); + } + + @Test + public void testAntiDeps3() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v0 = new S; +S? v1; +if (arg) v1 = new S; +if (v1) { + v0.f = v1.f; +} else { + v0.f = 2; +} +return v0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return S;", stop.toString()); + } + + + @Test + public void testAntiDeps4() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v = new S; +v.f = arg; +S t = new S; +int i = v.f; +if (arg+1) arg= 0; +while (arg) v.f = 2; +return i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return arg;", stop.toString()); + } + + @Test + public void testAntiDeps5() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v = new S; +while(1) { + while(arg+1) { arg=arg-1; } + if (arg) break; + v.f = 2; +} +return v; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return S;", stop.toString()); + } + + @Test + public void testAntiDeps6() { + Parser parser = new Parser( +""" +struct s { int v; }; +s !ptr=new s; +while( -arg ) + ptr = new s; +while(1) + arg = arg+ptr.v; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testAntiDeps7() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v = new S; +S t = new S; +int i = v.f; +while (arg) { + v.f = arg; + arg = arg-1; +} +return i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testAntiDeps8() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v = new S; +S t = new S; +while(arg) { + arg=arg-1; + int f = v.f; + v.f = 2; + if (arg) arg = f; + else v.f = 3; +} +return arg; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testAntiDeps9() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v = new S; +S t = new S; +if (arg) { + v.f=2; + int i=t.f; + v.f=i; +} +return v; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return S;", stop.toString()); + } + + @Test + public void testExample2() { + Parser parser = new Parser( +""" +struct S { int f; }; +S !v = new S; +int i = arg; +while (arg > 0) { + int j = i/3; + if (arg == 5) + v.f = j; + arg = arg - 1; +} +return v; + """); + StopNode stop = parser.parse().iterate(); + //assertEquals("return new S;", stop.toString()); + } + + @Test + public void testScheduleUse() { + Parser parser = new Parser( +""" +int v0=0; +while(0>=0) { + u1 v1=0; + v1=v0; + if(v1*0) + v0=-v1; +} +return 0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testLoopCarriedDep() { + Parser parser = new Parser( +""" +u32 v0=0; +{ + int v1=0; + while(v1) { + v1=1>>>v0!=0; + v0=v1/0; + } +} +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter12Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter12Test.java new file mode 100644 index 00000000..a70a5f33 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter12Test.java @@ -0,0 +1,62 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Ignore; +import org.junit.Test; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class Chapter12Test { + @Test + public void testJig() { + Parser parser = new Parser( +""" +return 3.14; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3.14;", stop.toString()); + assertEquals(3.14, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testFloat() { + Parser parser = new Parser( +""" +return 3.14; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3.14;", stop.toString()); + assertEquals(3.14, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testSquareRoot() { + Parser parser = new Parser( +""" +flt guess = arg; +while( 1 ) { + flt next = (arg/guess + guess)/2; + if( next == guess ) break; + guess = next; +} +return guess; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,(flt)arg,(((ToFloat/Phi_guess)+Phi_guess)/2.0));", stop.toString()); + assertEquals(3.0, Evaluator.evaluate(stop, 9)); + assertEquals(1.414213562373095, Evaluator.evaluate(stop, 2)); + } + + @Test + public void testFPOps() { + Parser parser = new Parser( +""" +flt x = arg; +return x+1==x; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return ((flt)arg==(ToFloat+1.0));", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 1)); + } +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter13Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter13Test.java new file mode 100644 index 00000000..30d9b147 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter13Test.java @@ -0,0 +1,183 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class Chapter13Test { + @Test + public void testJig() { + Parser parser = new Parser( +""" +return 3.14; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3.14;", stop.toString()); + assertEquals(3.14, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testLinkedList0() { + Parser parser = new Parser( +""" +struct LLI { LLI? next; int i; }; +LLI? !head = null; +while( arg ) { + LLI !x = new LLI; + x.next = head; + x.i = arg; + head = x; + arg = arg-1; +} +return head.next.i; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Might be null accessing 'i'",e.getMessage()); } + } + + @Test + public void testLinkedList1() { + Parser parser = new Parser( +""" +struct LLI { LLI? next; int i; }; +LLI? !head = null; +while( arg ) { + LLI !x = new LLI; + x.next = head; + x.i = arg; + head = x; + arg = arg-1; +} +if( !head ) return 0; +LLI? next = head.next; +if( next==null ) return 1; +return next.i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("Stop[ return 0; return 1; return .i; ]", stop.toString()); + assertEquals(2L, Evaluator.evaluate(stop, 3)); + } + + @Test + public void testCoRecur() { + Parser parser = new Parser( +""" +struct int0 { int i; flt0? f; }; +struct flt0 { flt f; int0? i; }; +int0 !i0 = new int0; +i0.i = 17; +flt0 !f0 = new flt0; +f0.f = 3.14; +i0.f = f0; +f0.i = i0; +return f0.i.f.i.i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 17;", stop.toString()); + } + + @Test + public void testNullRef0() { + Parser parser = new Parser( +""" +struct N { N? next; int i; }; +N n = new N; +return n.next; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return null;", stop.toString()); + } + + @Test + public void testNullRef1() { + Parser parser = new Parser( +""" +struct M { int m; }; +struct N { M next; int i; }; +N n = new N { next = new M; }; +return n.next; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (const)M;", stop.toString()); + } + + @Test + public void testNullRef2() { + Parser parser = new Parser( +""" +struct M { int m; }; +struct N { M next; int i; }; +N n = new N { next = null; } +return n.next; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Type null is not of declared type *M",e.getMessage()); } + } + + @Test + public void testNullRef3() { + Parser parser = new Parser( +""" +struct N { N? next; int i; }; +N !n = new N; +n.i = 3.14; +return n.i; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Type 3.14 is not of declared type int",e.getMessage()); } + } + + @Test + public void testEmpty() { + Parser parser = new Parser( +""" +struct S{}; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testForwardRef0() { + Parser parser = new Parser( +""" +struct S1 { S2? s; }; +return new S2; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Unknown struct type 'S2'",e.getMessage()); } + } + + @Test + public void testForwardRef1() { + Parser parser = new Parser( +""" +struct S1 { S2? s; }; +struct S2 { int x; }; +return new S1.s=new S2; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return S2;", stop.toString()); + } + + @Test + public void testcheckNull() { + Parser parser = new Parser( +""" +struct I {int i;}; +struct P { I? pi; }; +P !p1 = new P; +P p2 = new P; +p2.pi = new I; +p2.pi.i = 2; +if (arg) p1 = new P; +return p1.pi.i + 1; +"""); + try { parser.parse(false).iterate(); fail(); } + catch( Exception e ) { assertEquals("Might be null accessing 'i'",e.getMessage()); } + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter14Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter14Test.java new file mode 100644 index 00000000..23c82358 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter14Test.java @@ -0,0 +1,227 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; + +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class Chapter14Test { + + @Test + public void testJig() { + Parser parser = new Parser( +""" +return 3.14; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3.14;", stop.toString()); + assertEquals(3.14, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testRange() { + Parser parser = new Parser( +""" +int b; +if( arg ) b=1; else b=0; +int c = 99; +if( b < 0 ) c = -1; +if( b > 2 ) c = 1; +return c; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 99;", stop.toString()); + assertEquals(99L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testU8() { + Parser parser = new Parser( +""" +u8 b = 123; +b = b + 456;// Truncate +return b; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 67;", stop.toString()); + assertEquals(67L, Evaluator.evaluate(stop, 0)); + } + + + @Test + public void testU8While() { + Parser parser = new Parser( +""" +u8 b = 123; +while( b ) b = b + 456;// Truncate +return b; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testU1() { + Parser parser = new Parser( +""" +bool b = 123; +b = b + 456;// Truncate +u1 c = b; // No more truncate needed +return c; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testAnd() { + Parser parser = new Parser( +""" +int b = 123; +b = b+456 & 31; // Precedence +return b; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3;", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testRefLoad() { + Parser parser = new Parser( +""" +struct Foo { u1 b; }; +Foo !f = new Foo; +f.b = 123; +return f.b; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testSigned() { + Parser parser = new Parser( +""" +i8 b = 255; // Chopped +return b; // Sign extend +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return -1;", stop.toString()); + assertEquals(-1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testI8() { + Parser parser = new Parser( +""" +i8 b = arg; +b = b + 1;// Truncate +return b; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (((((arg<<56)>>56)+1)<<56)>>56);", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + assertEquals(-128L, Evaluator.evaluate(stop, 127)); + } + + @Test + public void testMask() { + Parser parser = new Parser( +""" +u16 mask = (1<<16)-1; // AND mask +int c = 123456789 & mask; +return c; // +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 52501;", stop.toString()); + assertEquals(52501L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testOr() { + Parser parser = new Parser( +""" +return (arg | 123 ^ 456) >>> 1; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (((arg|123)^456)>>>1);", stop.toString()); + assertEquals(217L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testMaskFloat() { + Parser parser = new Parser( +""" +flt f = arg; +arg = f & 0; +return arg; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot '&' FltBot",e.getMessage()); } + } + + @Test + public void testCloneAnd() { + Parser parser = new Parser(""" +int v0=0; +u32 v1 = 1&(1<<arg)&(1<<arg); +while(arg) v1=-v0; +while(v1) break; +return v1; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (Phi(Loop,((1<<arg)&1),0)&Phi(Loop,Shl,4294967295));", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testAndHigh() { + Parser parser = new Parser(""" +int v0=0; +if(0&0>>>0) { + while(0) { + u8 v1=0; + v0=0>>>0; + v1=arg; + while(v1+0) {} + } +} +return v0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testTypes() { + Parser parser = new Parser( +""" +i8 xi8 = 123456789; if( xi8 != 21 ) return -8; +i16 xi16 = 123456789; if( xi16 != -13035 ) return -16; +i32 xi32 = 123456789; if( xi32 != 123456789 ) return -32; +i64 xi64 = 123456789; if( xi64 != 123456789 ) return -64; +int xint = 123456789; if( xint != 123456789 ) return -64; + +u1 ui1 = 123456789; if( ui1 != 1 ) return 1; +u8 ui8 = 123456789; if( ui8 != 21 ) return 8; +u16 ui16 = 123456789; if( ui16 != 52501 ) return 16; +u32 ui32 = 123456789; if( ui32 != 123456789 ) return 32; + +flt fflt = 3.141592653589793; if( fflt != 3.141592653589793 ) return 3; +f64 ff64 = 3.141592653589793; if( ff64 != 3.141592653589793 ) return 3; +f32 ff32 = 3.141592653589793; if( ff32 != 3.1415927410125732) return 5; + +return 0; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter15Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter15Test.java new file mode 100644 index 00000000..4e2682dc --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter15Test.java @@ -0,0 +1,387 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; +import org.junit.Ignore; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class Chapter15Test { + + @Test + public void testJig() { + Parser parser = new Parser( +""" +return 3.14; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3.14;", stop.toString()); + assertEquals(3.14, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testCyclic() { + Parser parser = new Parser( +""" +struct C { C? l; }; +C !c = new C; +c.l = c; +return c; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return C;", stop.toString()); + assertEquals("Obj<C>@1{l=obj@1}", Evaluator.evaluate(stop, 0).toString()); + } + + @Test + public void testSafetyCheck() { + Parser parser = new Parser( +""" +u8[] old = new u8[0]; +u8[] !output = new u8[1]; +int i = 0; +while (i < old#) { + output[i] = old[i]; + i = i + 1; +} +output[i] = 1; +return output; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return [u8];", stop.toString()); + assertEquals("\u0001", Evaluator.evaluate(stop, 0).toString()); + } + + @Test + public void testBasic1() { + Parser parser = new Parser( +""" +int[] is = new int[2]; +return is[1]; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testBasic2() { + Parser parser = new Parser( +""" +int[] is = new int[2]; +int[] is2 = new int[2]; +return is[1]; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testBasic3() { + Parser parser = new Parser( +""" +int[] !a = new int[2]; +a[0] = 1; +a[1] = 2; +return a[0]; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testBasic4() { + Parser parser = new Parser( +""" +struct A { int i; }; +A?[] !a = new A?[2]; +return a; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return [*A?];", stop.toString()); + assertEquals("Obj<[*A?]>{#=2,[]=[null,null]}", Evaluator.evaluate(stop, 0).toString()); + } + + @Test + public void testBasic5() { + Parser parser = new Parser( +""" +struct S { int x; flt y; }; +// A new S +S !s = new S; s.x=99; s.y = 3.14; + +// Double-d array of Ss. Fill in one row. +S?[]?[] !iss = new S?[]?[2]; +iss[0] = new S?[7]; +iss[0][2] = s; + +// Now pull out the filled-in value, with null checks +flt rez; +S?[]? is = iss[arg]; +if( !is ) rez = 1.2; +else { + S? i = is[2]; + if( !i ) rez = 2.3; + else rez = i.y; +} +return rez; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,1.2,Phi(Region,2.3,3.14));", stop.toString()); + assertEquals(3.14, Evaluator.evaluate(stop, 0)); + assertEquals(1.2 , Evaluator.evaluate(stop, 1)); + } + + @Test + public void testBasic6() { + Parser parser = new Parser( +""" +struct S { int x; flt y; }; +// A new S +S !s = new S; s.x=99; s.y = 3.14; + +// Double-d array of Ss. Fill in one row. +S?[]?[] iss = new S?[]?[2]; +iss[0] = new S?[7]; +iss[0][2] = s; + +// Now pull out the filled-in value, with null checks +flt rez = 1.2; +if( iss[arg] ) + if( iss[arg][2] ) + rez = iss[arg][2].y; +return rez; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Might be null accessing 'y'",e.getMessage()); } + } + + @Test + public void testTree() { + Parser parser = new Parser( +""" +// Can we define a forward-reference array? +struct Tree { Tree?[]? _kids; }; +Tree !root = new Tree; +root._kids = new Tree?[2]; // NO BANG SO ARRAY IS OF IMMUTABLE TREES???? +root._kids[0] = new Tree; +return root; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Tree;", stop.toString()); + assertEquals("Obj<Tree>{_kids=Obj<[*Tree?]>{#=2,[]=[Obj<Tree>{_kids=null},null]}}", Evaluator.evaluate(stop, 0).toString()); + } + + @Test + public void testNestedStructAddMemProj() { + Parser parser = new Parser( +""" +struct S { int a; int[] b; }; +return 0; +"""); + StopNode stop = parser.parse(); + assertEquals("return 0;", stop.toString()); + } + + @Test + public void testRollingSum() { + Parser parser = new Parser( +""" +int[] !ary = new int[arg]; +// Fill [0,1,2,3,4,...] +int i=0; +while( i < ary# ) { + ary[i] = i; + i = i+1; +} +// Fill [0,1,3,6,10,...] +i=0; +while( i < ary# - 1 ) { + ary[i+1] = ary[i+1] + ary[i]; + i = i+1; +} +return ary[1] * 1000 + ary[3]; // 1 * 1000 + 6 +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (.[]+(.[]*1000));", stop.toString()); + assertEquals(1006L, Evaluator.evaluate(stop, 4)); + } + + @Test + public void sieveOEratosthenes() { + Parser parser = new Parser( +""" +int[] !ary = new int[arg], !primes = new int[arg]; +int nprimes = 0, p=2; +// Find primes while p^2 < arg +while( p*p < arg ) { + // skip marked non-primes + while( ary[p]==1 ) p = p + 1; + // p is now a prime + primes[nprimes] = p; nprimes = nprimes + 1; + // Mark out the rest non-primes + int i = p + p; + while( i < ary# ) { + ary[i] = 1; + i = i + p; + } + p = p + 1; +} +// Now just collect the remaining primes, no more marking +while( p < arg ) { + if( ary[p] == 0 ) { + primes[nprimes] = p; nprimes = nprimes + 1; + } + p = p + 1; +} +// Copy/shrink the result array +int[] !rez = new int[nprimes]; +int j = 0; +while( j < nprimes ) { + rez[j] = primes[j]; + j = j + 1; +} +return rez; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return [int];", stop.toString()); + Evaluator.Obj obj = (Evaluator.Obj)Evaluator.evaluate(stop, 20); + assertEquals("[int] {int #; int ![]; }",obj.struct().toString()); + long nprimes = (Long)obj.fields()[0]; + long[] primes = new long[]{2,3,5,7,11,13,17,19}; + for( int i=0; i<nprimes; i++ ) + assertEquals(primes[i],(long)(Long)obj.fields()[i+1]); + } + + @Test + public void testNewNodeInit() { + Parser parser = new Parser( +""" +struct S {int i; flt f;}; +S !s1 = new S; +S !s2 = new S; +s2.i = 3; +s2.f = 2.0; +if (arg) s1 = new S; +return s1.i + s1.f; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return ((flt).i+.f);", stop.toString()); + assertEquals(0.0, Evaluator.evaluate(stop, 0)); + } + + + @Test + public void testBad0() { + Parser parser = new Parser( +""" +return new flt; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot allocate a flt",e.getMessage()); } + } + + @Test + public void testBad1() { + Parser parser = new Parser( +""" +int is = new int[2]; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Type *[int] is not of declared type int",e.getMessage()); } + } + + @Test + public void testBad2() { + Parser parser = new Parser( +""" +int[] is = new int[3.14]; +return is[1]; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot allocate an array with length 3.14",e.getMessage()); } + } + + @Test + public void testBad3() { + Parser parser = new Parser( +""" +int[] is = new int[arg]; +return is[1]; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 4)); + try { Evaluator.evaluate(stop,0); } + catch( ArrayIndexOutOfBoundsException e ) { assertEquals("Array index 1 out of bounds for array length 0",e.getMessage()); } + try { Evaluator.evaluate(stop,-1); } + catch( NegativeArraySizeException e ) { assertEquals("-1",e.getMessage()); } + } + + @Test + public void testProgress() { + Parser parser = new Parser(""" +i8 v1=0&0; +u8 v2=0; +byte v4=0; +if(0) {} +while(v2<0) { + v4=0-v1; + break; +} +int v5=0&0; +while(v5+(0&0)) { + int v7=0&0; + while(v7) + v4=0>>>v5; + while(v1) + return 0; +} +return v1; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testSharpNot() { + Parser parser = new Parser( +""" +if(0>>0) {} +while(0) {} +u32 v7=0; +int v8=0; +while(0<--1>>>---(v7*0==v8)) {} +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } + + + @Test + public void testProgress2() { + Parser parser = new Parser( +""" +if(1) {} +else { + while(arg>>>0&0>>>0) {} + byte v3=0>>>0; + while(0) {} + int v7=0>>>0; + while(v7<0>>>0) { + while(0+v7<=0) if(1) arg=-12; + if(arg) { + v3=arg+v3+0; + arg=0; + } + } +} +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + } +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter16Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter16Test.java new file mode 100644 index 00000000..5450824a --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter16Test.java @@ -0,0 +1,260 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class Chapter16Test { + + @Test + public void testJig() { + Parser parser = new Parser( +""" +return 3.14; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3.14;", stop.toString()); + assertEquals(3.14, Evaluator.evaluate(stop, 0)); + } + + + @Test + public void testMulti0() { + Parser parser = new Parser( +""" +int x, y; +return x+y; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + @Test + public void testMulti1() { + Parser parser = new Parser( +""" +int x=2, y=x+1; +return x+y; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 5;", stop.toString()); + assertEquals(5L, Evaluator.evaluate(stop, 0)); + } + +// @Test +// public void testFinal0() { +// Parser parser = new Parser( +//""" +//int !x=2; +//x=3; +//return x; +//"""); +// try { parser.parse().iterate(); fail(); } +// catch( Exception e ) { assertEquals("Cannot reassign final 'x'",e.getMessage()); } +// } + + @Test + public void testFinal1() { + Parser parser = new Parser( +""" +int x=2, y=3; +if( arg ) { int x = y; x = x*x; y=x; } // Shadow final x +return y; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,9,3);", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 0)); + assertEquals(9L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testConstruct0() { + Parser parser = new Parser(""" +struct X { int x=3; }; +X z = new X; +return z.x; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3;", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testConstruct1() { + Parser parser = new Parser(""" +struct X { int !x; }; +X z = new X { x=3; }; +return z.x; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 3;", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testConstruct2() { + Parser parser = new Parser(""" +struct X { int x=3; }; +X z = new X { x = 4; }; +return z.x; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 4;", stop.toString()); + assertEquals(4L, Evaluator.evaluate(stop, 0)); + } + + + @Test + public void testStructFinal0() { + Parser parser = new Parser(""" +struct Point { int !x, !y; }; +Point p = new Point { x=3; y=4; }; +return p; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (const)Point;", stop.toString()); + assertEquals("Obj<Point>{x=3,y=4}", Evaluator.evaluate(stop, 0).toString()); + } + + @Test + public void testStructFinal1() { + Parser parser = new Parser(""" +struct Point { int x=3, y=4; }; +Point p = new Point { x=5; y=6; }; +p.x++; +return p; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot modify final field 'x'",e.getMessage()); } + } + + @Test + public void testStructFinal2() { + Parser parser = new Parser(""" +struct Point { int x=3, y=4; }; +Point p = new Point; +p.x++; +return p; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot modify final field 'x'",e.getMessage()); } + } + + @Test + public void testStructFinal3() { + Parser parser = new Parser(""" +struct Point { var x; var y; }; +Point p = new Point; +p.x++; +return p; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("'Point' is not fully initialized, field 'x' needs to be set in a constructor",e.getMessage()); } + } + + @Test + public void testStructFinal4() { + Parser parser = new Parser(""" +struct Point { val x=3; val y=4; }; +Point p = new Point; +p.x++; +return p; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot reassign final 'x'",e.getMessage()); } + } + + @Test + public void testStructFinal5() { + Parser parser = new Parser(""" +struct Point { var x=3; var y=4; }; +Point !p = new Point; +p.x++; +return p; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Point;", stop.toString()); + assertEquals("Obj<Point>{x=4,y=4}", Evaluator.evaluate(stop, 0).toString()); + } + + // Same as the Chapter13 test with the same name, but using the new + // constructor syntax + @Test + public void testLinkedList1() { + Parser parser = new Parser( +""" +struct LLI { LLI? next; int i; }; +LLI? !head = null; +while( arg ) { + head = new LLI { next=head; i=arg; }; + arg = arg-1; +} +if( !head ) return 0; +LLI? next = head.next; +if( !next ) return 1; +return next.i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("Stop[ return 0; return 1; return .i; ]", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + assertEquals(1L, Evaluator.evaluate(stop, 1)); + assertEquals(2L, Evaluator.evaluate(stop, 3)); + } + + @Test + public void testLinkedList2() { + Parser parser = new Parser( +""" +struct LLI { LLI? next; int i; }; +LLI? !head = null; +while( arg ) { + head = new LLI { + next=head; + // Any old code in the constructor + int !tmp=arg; + while( arg > 10 ) { + tmp = tmp + arg; + arg = arg - 1; + } + i=tmp; + }; + arg = arg-1; +} +if( !head ) return 0; +LLI? next = head.next; +if( !next ) return 1; +return next.i; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("Stop[ return 0; return 1; return .i; ]", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + assertEquals(1L, Evaluator.evaluate(stop, 1)); + assertEquals(2L, Evaluator.evaluate(stop, 11)); + } + + @Test + public void testSquare() { + Parser parser = new Parser( +""" +struct Square { + flt !side = arg; + // Newtons approximation to the square root, computed in a constructor. + // The actual allocation will copy in this result as the initial + // value for 'diag'. + flt !diag = arg*arg/2; + while( 1 ) { + flt next = (side/diag + diag)/2; + if( next == diag ) break; + diag = next; + } +}; +return new Square; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Square;", stop.toString()); + assertEquals("Obj<Square>{side=3.0,diag=1.7320508075688772}", Evaluator.evaluate(stop, 3).toString()); + assertEquals("Obj<Square>{side=4.0,diag=2.0}", Evaluator.evaluate(stop, 4).toString()); + } +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/Chapter17Test.java b/chapter18/src/test/java/com/seaofnodes/simple/Chapter17Test.java new file mode 100644 index 00000000..4a7e959a --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/Chapter17Test.java @@ -0,0 +1,505 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Test; +import org.junit.Ignore; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.fail; + +public class Chapter17Test { + + @Test + public void testJig() { + Parser parser = new Parser(""" +int i = 0; +i=i=1; +return i; + //return 3.14; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + + // --------------------------------------------------------------- + @Test + public void testInc0() { + Parser parser = new Parser(""" +return arg++; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return arg;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testInc1() { + Parser parser = new Parser(""" +return arg+++arg++; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return ((arg*2)+1);", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testInc2() { + Parser parser = new Parser(""" +// -(arg--)-(arg--) +return -arg---arg--; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (-((arg*2)+-1));", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testInc3() { + Parser parser = new Parser(""" +int[] !xs = new int[arg]; +xs[0]++; +xs[1]++; +return xs[0]; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 2)); + } + + @Test + public void testInc4() { + Parser parser = new Parser(""" +u8[] !xs = new u8[1]; +xs[0]--; +return xs[0]; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 255;", stop.toString()); + assertEquals(255L, Evaluator.evaluate(stop, 2)); + } + + @Test + public void testInc5() { + Parser parser = new Parser(""" +struct S { u16 x; }; +S !s = new S; +s.x--; +return s.x; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 65535;", stop.toString()); + assertEquals(65535L, Evaluator.evaluate(stop, 2)); + } + + @Test + public void testInc6() { + Parser parser = new Parser("return --arg;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return (arg+-1);", stop.toString()); + assertEquals(-1L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testInc7() { + Parser parser = new Parser("u8 x=0; return --x;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 255;", stop.toString()); + assertEquals(255L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testInc8() { + Parser parser = new Parser("int x; x+=2; return x+=3;"); + StopNode stop = parser.parse().iterate(); + assertEquals("return 5;", stop.toString()); + assertEquals(5L, Evaluator.evaluate(stop, 0)); + } + + // --------------------------------------------------------------- + @Test public void testVar0() { + Parser parser = new Parser("var d; return d;"); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Syntax error, expected =expression: ;",e.getMessage()); } + } + + @Test public void testVar1() { + Parser parser = new Parser("val d; return d;"); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Syntax error, expected =expression: ;",e.getMessage()); } + } + + @Test public void testVar2() { + Parser parser = new Parser("int x; x=3; x++; return x; // Ok, no initializer so x is mutable "); + StopNode stop = parser.parse().iterate(); + assertEquals("return 4;", stop.toString()); + assertEquals(4L, Evaluator.evaluate(stop, 0)); + } + + @Test public void testVar3() { + Parser parser = new Parser("int x=3; x++; return x; // Ok, primitive so x is mutable despite initializer "); + StopNode stop = parser.parse().iterate(); + assertEquals("return 4;", stop.toString()); + assertEquals(4L, Evaluator.evaluate(stop, 0)); + } + + @Test public void testVar4() { + Parser parser = new Parser("struct S{int x;}; S s; s=new S; s.x++; return s.x; // Ok, no initializer so x is mutable "); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test public void testVar5() { + Parser parser = new Parser("struct S{int x;}; S s; s=new S{x=3;}; s.x++; return s.x; // Ok, no initializer so x is mutable "); + StopNode stop = parser.parse().iterate(); + assertEquals("return 4;", stop.toString()); + assertEquals(4L, Evaluator.evaluate(stop, 0)); + } + + @Test public void testVar6() { + Parser parser = new Parser("struct S{int x;}; S s=new S; s.x++; return s.x; // Error initializer so x is immutable "); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot modify final field 'x'",e.getMessage()); } + } + + @Test public void testVar7() { + Parser parser = new Parser("struct S{int x;}; S s=new S{x=3;}; s.x++; return s.x; // Error initializer so x is immutable "); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot modify final field 'x'",e.getMessage()); } + } + + @Test public void testVar8() { + Parser parser = new Parser("struct S{int x;}; S !s=new S; s.x++; return s.x; // Ok, has '!' so s.x is mutable "); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test public void testVar9() { + Parser parser = new Parser("struct S{int x;}; var s=new S; s.x++; return s.x; // Ok, has var so s.x is mutable "); + StopNode stop = parser.parse().iterate(); + assertEquals("return 1;", stop.toString()); + assertEquals(1L, Evaluator.evaluate(stop, 0)); + } + + @Test public void testVar10() { + Parser parser = new Parser("struct S{int x;}; val s=new S; s.x++; return s.x; // Error, has val so x is immutable "); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot modify final field 'x'",e.getMessage()); } + } + + @Test public void testVar11() { + Parser parser = new Parser(""" +struct Bar { int x; }; +Bar !bar = new Bar; +bar.x = 3; // Ok, bar is mutable + +struct Foo { Bar? !bar; int y; }; +Foo !foo = new Foo { bar = bar; }; +foo.bar = bar; // Ok foo is mutable +foo.bar.x++; // Ok foo and foo.bar and foo.bar.x are all mutable + +val xfoo = foo; // Throw away mutability +xfoo.bar.x++; // Error, cannot mutate through xfoo + """); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot modify final field 'x'",e.getMessage()); } + } + + @Test public void testVar12() { + Parser parser = new Parser(""" +struct Bar { int x; }; +Bar !bar = new Bar; +bar.x = 3; // Ok, bar is mutable + +struct Foo { Bar? !bar; int y; }; +Foo !foo = new Foo; +foo.bar = bar; // Ok bar is mutable +foo.bar.x++; // Ok foo and foo.bar and foo.bar.x are all mutable + +val xfoo = foo; // Throw away mutability +int x4 = xfoo.bar.x; // Ok to read through xfoo, gets 4 +foo.bar.x++; // Bumps to 5 +int x5 = xfoo.bar.x; // Ok to read through xfoo, gets 5 +return x4*10+x5; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 45;", stop.toString()); + assertEquals(45L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testVar13() { + Parser parser = new Parser(""" +int i,i++; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Redefining name 'i'",e.getMessage()); } + } + + + @Test + public void testVar14() { + Parser parser = new Parser(""" +struct B {}; +struct A { B b; }; +A x = new A { + return b; // read before init + b = new B; +}; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Cannot read uninitialized field 'b'",e.getMessage()); } + } + + @Test + public void testVar15() { + Parser parser = new Parser(""" +struct B {}; +struct A { B b; }; +return new A { + if (arg) b = new B; // Constructor ends with partial init of b +}.b; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("'A' is not fully initialized, field 'b' needs to be set in a constructor",e.getMessage()); } + } + + // --------------------------------------------------------------- + @Test + public void testTrinary0() { + Parser parser = new Parser(""" +return arg ? 1 : 2; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,1,2);", stop.toString()); + assertEquals(2L, Evaluator.evaluate(stop, 0)); + assertEquals(1L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testTrinary1() { + Parser parser = new Parser(""" +return arg ? 0 : arg; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return 0;", stop.toString()); + assertEquals(0L, Evaluator.evaluate(stop, 0)); + } + + @Test + public void testTrinary2() { + Parser parser = new Parser(""" +struct Bar { int x; }; +var b = arg ? new Bar : null; +return b ? b.x++ + b.x++ : -1; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,1,-1);", stop.toString()); + assertEquals(-1L, Evaluator.evaluate(stop, 0)); + assertEquals( 1L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testTrinary3() { + Parser parser = new Parser(""" +struct Bar { int x; }; +var b = arg ? new Bar; +return b ? b.x++ + b.x++ : -1; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,1,-1);", stop.toString()); + assertEquals(-1L, Evaluator.evaluate(stop, 0)); + assertEquals( 1L, Evaluator.evaluate(stop, 1)); + } + + @Test + public void testTrinary4() { + // This test case will benefit from an unzipping transformation + Parser parser = new Parser(""" +struct Bar { Bar? next; int x; }; +var b = arg ? new Bar { next = (arg==2) ? new Bar{x=2;}; x=1; }; +return b ? b.next ? b.next.x : b.x; // parses "b ? (b.next ? b.next.x : b.x) : 0" +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,Phi(Region,.x,.x),0);", stop.toString()); + assertEquals( 0L, Evaluator.evaluate(stop, 0)); + assertEquals( 1L, Evaluator.evaluate(stop, 1)); + assertEquals( 2L, Evaluator.evaluate(stop, 2)); + } + + @Test + public void testTrinary5() { + Parser parser = new Parser(""" +flt f=arg?1:1.2; +return f; // missing widening +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Region,1.0,1.2);", stop.toString()); + assertEquals(1.2, Evaluator.evaluate(stop, 0)); + } + + // --------------------------------------------------------------- + @Test + public void testFor0() { + Parser parser = new Parser(""" +int sum=0; +for( int i=0; i<arg; i++ ) + sum += i; +return sum; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(Phi_sum+Phi(Loop,0,(Phi_i+1))));", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 3)); + assertEquals(45L, Evaluator.evaluate(stop, 10)); + } + @Test + public void testFor1() { + Parser parser = new Parser(""" +int sum=0, i=0; +for( ; i<arg; i++ ) + sum += i; +return sum; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(Phi_sum+Phi(Loop,0,(Phi_i+1))));", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 3)); + assertEquals(45L, Evaluator.evaluate(stop, 10)); + } + @Test + public void testFor2() { + Parser parser = new Parser(""" +int sum=0; +for( int i=0; ; i++ ) { + if( i>=arg ) break; + sum += i; +} +return sum; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(Phi_sum+Phi(Loop,0,(Phi_i+1))));", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 3)); + assertEquals(45L, Evaluator.evaluate(stop, 10)); + } + @Test + public void testFor3() { + Parser parser = new Parser(""" +int sum=0; +for( int i=0; i<arg; ) + sum += i++; +return sum; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(Phi_sum+Phi(Loop,0,(Phi_i+1))));", stop.toString()); + assertEquals(3L, Evaluator.evaluate(stop, 3)); + assertEquals(45L, Evaluator.evaluate(stop, 10)); + } + @Test + public void testFor4() { + Parser parser = new Parser(""" +int sum=0; +for( int i=0; i<arg; i++ ) + sum += i; +return i; +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Undefined name 'i'",e.getMessage()); } + } + @Test + public void testFor5() { + Parser parser = new Parser(""" +for(;;arg++;) {} +"""); + try { parser.parse().iterate(); fail(); } + catch( Exception e ) { assertEquals("Syntax error, expected Unexpected code after expression: ;",e.getMessage()); } + } + + + + // --------------------------------------------------------------- + @Test + public void testForward0() { + Parser parser = new Parser(""" +struct A{ + B? f1; + B? f2; +}; +return new A; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return A;", stop.toString()); + assertEquals("Obj<A>{f1=null,f2=null}", Evaluator.evaluate(stop).toString()); + } + + @Test + public void testForward1() { + Parser parser = new Parser(""" +struct A{ + B?[]? nil_array_of_b; + B?[] not_array_of_b = new B?[0]; +}; +return new A.not_array_of_b; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return (const)[*B?];", stop.toString()); + assertEquals("Obj<[*B?]>{#=0,[]=[]}", Evaluator.evaluate(stop).toString()); + } + + // --------------------------------------------------------------- + @Test + public void testLinkedList2() { + Parser parser = new Parser(""" +struct LLI { LLI? next; int i; }; +LLI? !head = null; +while( arg-- ) + head = new LLI { next=head; i=arg; }; +int sum=0; +var ptr = head; // A read-only ptr, to be assigned from read-only next fields +for( ; ptr; ptr = ptr.next ) + sum += ptr.i; +return sum; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return Phi(Loop,0,(Phi_sum+.i));", stop.toString()); + assertEquals(45L, Evaluator.evaluate(stop, 10)); + } + + @Test + public void sieveOfEratosthenes() { + Parser parser = new Parser( +""" +var ary = new bool[arg], primes = new int[arg]; +var nprimes=0, p=0; +// Find primes while p^2 < arg +for( p=2; p*p < arg; p++ ) { + // skip marked non-primes + while( ary[p] ) p++; + // p is now a prime + primes[nprimes++] = p; + // Mark out the rest non-primes + for( int i = p + p; i < ary#; i += p ) + ary[i] = true; +} +// Now just collect the remaining primes, no more marking +for( ; p < arg; p++ ) + if( !ary[p] ) + primes[nprimes++] = p; +// Copy/shrink the result array +var !rez = new int[nprimes]; +for( int j=0; j<nprimes; j++ ) + rez[j] = primes[j]; +return rez; +"""); + StopNode stop = parser.parse().iterate(); + assertEquals("return [int];", stop.toString()); + Evaluator.Obj obj = (Evaluator.Obj)Evaluator.evaluate(stop, 20); + assertEquals("[int] {int #; int ![]; }",obj.struct().toString()); + long nprimes = (Long)obj.fields()[0]; + long[] primes = new long[]{2,3,5,7,11,13,17,19}; + for( int i=0; i<nprimes; i++ ) + assertEquals(primes[i],(long)(Long)obj.fields()[i+1]); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/FuzzerWrap.java b/chapter18/src/test/java/com/seaofnodes/simple/FuzzerWrap.java new file mode 100644 index 00000000..eaeed8e2 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/FuzzerWrap.java @@ -0,0 +1,43 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.fuzzer.Fuzzer; +import java.util.Random; +import org.junit.Ignore; +import org.junit.Test; +import static org.junit.Assert.assertTrue; + +/** + * To use the fuzzer run the <code>fuzzPeeps</code> methods. + * This can be done from IntelliJ Gui or remove the `@Ignore` annotation and start the test case from the command line + * via <code>mvn clean test -Dtest=com.seaofnodes.simple.Fuzzer08Test#fuzzPeeps</code> + */ +public class FuzzerWrap { + + @Ignore + @Test + public void fuzzPeeps() { + var fuzzer = new Fuzzer(); + for (int i=0; i<1000000; i++) + fuzzer.fuzzPeeps(i); + assertTrue(fuzzer.noExceptions()); + } + + + @Test + public void fuzzPeepsSmall() { + Random R = new Random(System.currentTimeMillis()); + var fuzzer = new Fuzzer(); + for (int i=0; i<100; i++) + fuzzer.fuzzPeeps(R.nextLong()); + assertTrue(fuzzer.noExceptions()); + } + + @Test + @Ignore + public void fuzzPeepTiming() { + var fuzzer = new Fuzzer(); + int max_nid=0; + for (int i=0; i<1000000; i++) + max_nid = fuzzer.fuzzPeepTiming(i, max_nid); + } +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/SchedulerTest.java b/chapter18/src/test/java/com/seaofnodes/simple/SchedulerTest.java new file mode 100644 index 00000000..c67217af --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/SchedulerTest.java @@ -0,0 +1,74 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.StopNode; +import org.junit.Assert; +import org.junit.Ignore; +import org.junit.Test; + +import static org.junit.Assert.assertEquals; + +public class SchedulerTest { + + private static void assertObj(Object obj, String name, Object... fields) { + assertEquals(Evaluator.Obj.class, obj.getClass()); + var o = (Evaluator.Obj)obj; + assertEquals(name, o.struct()._name); + Assert.assertArrayEquals(fields, o.fields()); + } + + @Test + @Ignore + public void testJig() { + Parser parser = new Parser(""" +struct S { + int f; +} +S !v=new S; +v.f = 2; +int i=v.f; +if (arg) v.f=1; +return i; +"""); + StopNode._disablePeephole = true; + StopNode stop = parser.parse();//.iterate(); + var eval = new Evaluator(stop); + assertEquals(2L, eval.evaluate(1, 10)); + } + + @Test + public void testStoreInIf() { + Parser parser = new Parser(""" +struct S { + int f; +}; +S !v0=new S; +if(arg) v0.f=1; +return v0; +"""); + StopNode stop = parser.parse().iterate(); + var eval = new Evaluator(stop); + assertObj(eval.evaluate(0, 10), "S", 0L); + assertObj(eval.evaluate(1, 10), "S", 1L); + } + + @Test + public void testStoreInIf2() { + Parser parser = new Parser(""" +struct S { + int f; +}; +S !v=new S; +v.f = 2; +int i=new S.f; +i=v.f; +if (arg) v.f=1; +return i; +"""); + StopNode stop = parser.parse().iterate(); + var eval = new Evaluator(stop); + assertEquals(2L, eval.evaluate(0, 10)); + assertEquals(2L, eval.evaluate(1, 10)); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/TypeTest.java b/chapter18/src/test/java/com/seaofnodes/simple/TypeTest.java new file mode 100644 index 00000000..1cb97cf6 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/TypeTest.java @@ -0,0 +1,157 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.type.*; +import org.junit.Assert; +import org.junit.Ignore; +import org.junit.Test; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertSame; + +public class TypeTest { + + // Test basic properties and GLB + @Test + public void testTypeAdHoc() { + TypeStruct s1 = TypeStruct.make("s1", new Field[]{ + Field.make("a", TypeInteger.BOT,-1, false), + Field.make("b", TypeInteger.BOT,-2, false) }); + TypeStruct s2 = TypeStruct.make("s2", new Field[]{ + Field.make("a", TypeInteger.BOT,-3, false), + Field.make("b", TypeInteger.BOT,-4, false) }); + Assert.assertEquals(s1, s1.glb()); + Assert.assertNotEquals(s1, s1.dual()); + Assert.assertEquals(s1.makeRO(), s1.dual().glb()); + + TypeMem m1 = TypeMem.make(1,TypeInteger.ZERO); + TypeMem m2 = TypeMem.make(2,TypeInteger.U16); + TypeMem m3 = TypeMem.make(3,TypeFloat.BOT); + TypeMem m4 = TypeMem.make(4,TypeInteger.BOT); + + Assert.assertNotEquals(m1, m2); + Assert.assertNotEquals(m2, m3); + Assert.assertNotEquals(m3, m4); + + Assert.assertEquals(TypeStruct.BOT, s1.meet(s2)); + Assert.assertEquals(TypeMem.make(-1,TypeInteger.U16), m1.meet(m2)); + Assert.assertEquals(TypeMem .BOT, m2.meet(m3)); + Assert.assertEquals(TypeMem .BOT, m3.meet(m4)); + + Assert.assertEquals(TypeMem.make(1,TypeInteger.BOT), m1.glb()); + Assert.assertEquals(TypeMem.make(1,TypeInteger.ZERO), m1.dual()); + Assert.assertEquals(m4.dual(), m4.glb().dual()); + + TypeMemPtr ptr1 = TypeMemPtr.make(s1); + Assert.assertEquals(s1, ptr1._obj); + TypeMemPtr ptr2 = TypeMemPtr.make(s2); + Assert.assertEquals(s2, ptr2._obj); + + TypeMemPtr ptr1nil = TypeMemPtr.make(s1, true); + Assert.assertEquals(s1, ptr1nil._obj); + Assert.assertTrue(ptr1nil._nil); + Assert.assertFalse(ptr1nil._obj==null); + TypeMemPtr ptr2nil = TypeMemPtr.make(s2, true); + Assert.assertEquals(s2, ptr2nil._obj); + + Assert.assertNotEquals(ptr1, ptr2); + Assert.assertNotEquals(ptr1, ptr1.glb()); + Assert.assertEquals(ptr1nil, ptr1.glb()); + + Assert.assertEquals(ptr1, ptr1.dual().dual()); + Assert.assertEquals(ptr1.glb().makeRO(), ptr1.dual().glb()); + Assert.assertEquals(TypeMemPtr.make(TypeStruct.BOT,true), ptr1.meet(ptr2nil)); + Assert.assertEquals(ptr1.glb(), ptr1.meet(TypeMemPtr.NULLPTR)); + + TypeMemPtr TOP = TypeMemPtr.TOP; + TypeMemPtr BOT = TypeMemPtr.make(TypeStruct.BOT,true ); + TypeMemPtr PTR = TypeMemPtr.make(TypeStruct.BOT,false); + TypeMemPtr NULL = TypeMemPtr.NULLPTR; + Type PTR_meet_NULL = NULL.meet(PTR); + Assert.assertEquals(BOT, PTR_meet_NULL); + Type ptr1_meet_ptr2 = ptr1.meet(ptr2); + Assert.assertEquals(PTR, ptr1_meet_ptr2); + Type NULL_join_ptr1 = NULL.join(ptr1); + Assert.assertEquals(TOP, NULL_join_ptr1); + Type NULL_join_PTR = PTR.join(NULL); + Assert.assertEquals(TOP, NULL_join_PTR); + Type ptr1_dual = ptr1.dual(); + Type nullableptr1_dual = ptr1nil.dual(); + } + + // Test theoretical properties. + // This is a symmetric complete bounded (ranked) lattice. + // Also, the meet is commutative and associative. + // The lattice has a dual (symmetric), and join is ~(~x meet ~y). + // See https://en.wikipedia.org/wiki/Lattice_(order). + @Test + public void testLatticeTheory() { + Type[] ts = Type.gather(); + + // Confirm commutative & complete + for( Type t0 : ts ) + for( Type t1 : ts ) { + check_commute (t0,t1); + check_symmetric(t0,t1); + } + + // Confirm associative + for( Type t0 : ts ) + for( Type t1 : ts ) + for( Type t2 : ts ) + assoc(t0,t1,t2); + + // Confirm symmetry. If A isa B, then A.join(C) isa B.join(C) + for( Type t0 : ts ) + for( Type t1 : ts ) + if( t0.isa(t1) ) + for( Type t2 : ts ) { + Type t02 = t0.join(t2); + Type t12 = t1.join(t2); + Type mt = t02.meet(t12); + assertSame(mt,t12); + } + } + + // By design in meet, args are already flipped to order _type, which forces + // symmetry for things with badly ordered _type fields. The question is + // still interesting for other orders. + private static void check_commute( Type t0, Type t1 ) { + if( t0==t1 ) return; + if( t0.is_simple() && !t1.is_simple() ) return; // By design, flipped the only allowed order + Type mta = t0.meet(t1); + Type mtb = t1.meet(t0); // Reverse args and try again + assertSame(mta,mtb); + } + + // A & B = MT + // Expect: ~A & ~MT == ~A + // Expect: ~B & ~MT == ~B + private static void check_symmetric( Type t0, Type t1 ) { + if( t1==t0 ) return; + Type mt = t0.meet(t1); + Type dm = mt.dual(); + Type d0 = t0.dual(); + Type d1 = t1.dual(); + Type ta = dm.meet(d1); + Type tb = dm.meet(d0); + assertSame(ta,d1); + assertSame(tb,d0); + } + + private static void assoc( Type t0, Type t1, Type t2 ) { + Type t01 = t0 .meet(t1 ); + Type t12 = t1 .meet(t2 ); + Type t01_2 = t01.meet(t2 ); + Type t0_12 = t0 .meet(t12); + assertSame(t01_2,t0_12); + } + + // Test cyclic types and meets + @Test + public void testCyclic0() { + Type d0 = TypeStruct.S1.dual(); + Type d1 = d0.dual(); + assertSame(TypeStruct.S1,d1); + } + + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/evaluator/Evaluator.java b/chapter18/src/test/java/com/seaofnodes/simple/evaluator/Evaluator.java new file mode 100644 index 00000000..72f84fa2 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/evaluator/Evaluator.java @@ -0,0 +1,378 @@ +package com.seaofnodes.simple.evaluator; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.*; + +import java.lang.invoke.MethodHandle; +import java.lang.invoke.MethodHandles; +import java.util.*; + +public class Evaluator { + + private static final Object MEMORY = new Object(); + + public record Obj(TypeStruct struct, Object[] fields) { + private void init(IdentityHashMap<Obj, Integer> objs) { + var oid = objs.get(this); + if (oid != null) { + if (oid != 0) objs.put(this, 0); + return; + } + objs.put(this, -1); + for (var obj : fields) { + if (obj instanceof Obj o) o.init(objs); + } + } + private static int p(StringBuilder sb, IdentityHashMap<Obj, Integer> objs, int id, String indentation, String step, String sep, Object obj) { + if (obj instanceof Obj o) return o.p(sb, objs, id, indentation, step, sep); + sb.append(obj); + return id; + } + private int p(StringBuilder sb, IdentityHashMap<Obj, Integer> objs, int id, String indentation, String step, String sep) { + var cid = objs.get(this); + assert cid != null; + if (cid > 0) { + sb.append("obj@").append(cid); + return id; + } + if (struct._name.equals("[u8]")) { + sb.append('"'); + for (int i=struct._fields.length-1; i<fields.length; i++) { + var v = fields[i]; + if (v == null) v = 0; + assert v instanceof Number; + var n = ((Number)v).byteValue() & 0xFF; + if (n >= 0x20 && n < 0x80) { + if (n == 0x22 || n == 0x5C) sb.append("\\"); + sb.append((char)n); + } else { + sb.append("\\x").append("0123456789abcdef".charAt(n >> 4)).append("0123456789abcdef".charAt(n & 0xF)); + } + } + sb.append('"'); + return id; + } + sb.append("Obj<").append(struct._name).append(">"); + if (cid == 0) { + cid = id++; + objs.put(this, cid); + sb.append("@").append(cid); + } + sb.append("{"); + if (struct._fields.length == 0) { + assert !struct.isAry(); + sb.append("}"); + return id; + } + String nextIndent = indentation + step; + int e = struct._fields.length - 1; + for(int i=0; i<e; i++) { + sb.append(nextIndent).append(struct._fields[i]._fname).append("="); + id = p(sb, objs, id, nextIndent, step, sep, fields[i]); + sb.append(sep); + } + sb.append(nextIndent).append(struct._fields[e]._fname).append("="); + if (struct.isAry()) { + sb.append("["); + if (fields.length > e) { + String innerIndent = nextIndent + step; + sb.append(innerIndent); + id = p(sb, objs, id, nextIndent, step, sep, fields[e]); + for (int i = e+1; i < fields.length; i++) { + sb.append(sep).append(innerIndent); + id = p(sb, objs, id, nextIndent, step, sep, fields[i]); + } + sb.append(nextIndent); + } + sb.append("]"); + } else { + id = p(sb, objs, id, nextIndent, step, sep, fields[e]); + } + sb.append(indentation).append("}"); + return id; + } + private StringBuilder p(StringBuilder sb, String indentation, String step, String sep) { + var objs = new IdentityHashMap<Obj, Integer>(); + init(objs); + p(sb, objs, 1, indentation, step, sep); + return sb; + } + @Override + public String toString() { + if (struct._name.equals("[u8]")) { + var sb = new StringBuilder(); + for (int i=struct._fields.length-1; i<fields.length; i++) { + var v = fields[i]; + if (v == null) v = 0; + assert v instanceof Number; + var n = ((Number)v).byteValue() & 0xFF; + sb.append((char)n); + } + return sb.toString(); + } + return p(new StringBuilder(), "", "", ",").toString(); + } + public String pretty() { + return p(new StringBuilder(), "\n", " ", "").toString(); + } + } + + private static int getFieldIndex(TypeStruct struct, MemOpNode memop, long off) { + int idx = struct.find(memop._name); + if( idx >= 0 ) return idx; + throw new AssertionError("Field "+memop._name+" not found in struct " + struct._name); + } + + public enum Status { + TIMEOUT, + FALLTHROUGH + } + + /** + * Find the start node from some node in the graph or null if there is no start node + */ + private static StartNode findStart(BitSet visit, Node node) { + if (node == null) return null; + if( visit.get(node._nid) ) return null; + visit.set(node._nid); + StartNode start = node instanceof StartNode ? (StartNode) node : null; + for( Node def : node._inputs ) { + var res = findStart(visit,def); + if( res != null ) start = res; + } + for( Node use : node._outputs ) { + var res = findStart(visit,use); + if( res != null ) start = res; + } + return start; + } + + private final Object[] values; + private final ArrayList<Object> phiCache = new ArrayList<>(); + private final StartNode start; + private final Scheduler.Block startBlock; + + public Evaluator(Node graph) { + var visited = new BitSet(); + this.start = findStart(visited, graph); + if (this.start == null) { + this.values = null; + this.startBlock = null; + return; + } + this.startBlock = Scheduler.schedule(this.start); + this.values = new Object[visited.length()]; + } + + private long div(DivNode div) { + long in2 = vall(div.in(2)); + return in2 == 0 ? 0 : vall(div.in(1)) / in2; + } + private double div(DivFNode div) { + double in2 = vald(div.in(2)); + return in2 == 0 ? 0 : vald(div.in(1)) / in2; + } + + private static long offToIdx(long off, TypeStruct t) { + off -= t.aryBase(); + int scale = t.aryScale(); + long mask = (1L << scale)-1; + assert (off & mask) == 0; + return off>>scale; + } + + private Object alloc(NewNode alloc) { + TypeStruct type = alloc._ptr._obj; + Object[] body=null; + int num; + if( type.isAry() ) { + long sz = (Long)val(alloc.in(1)); + long n = offToIdx(sz, type); + if( n < 0 ) + throw new NegativeArraySizeException(""+n); + body = new Object[(int)n+1]; // Array body + var elem = type._fields[1]._type; + if (elem instanceof TypeInteger) { + for (int i=0; i<n; i++) body[i+1] = 0L; + } else if (elem instanceof TypeFloat) { + for (int i = 0; i < n; i++) body[i+1] = 0D; + } else { + assert elem instanceof TypeMemPtr; + } + // Length value + body[0] = vall(alloc.in(2+2)); + } else { + body = new Object[num = type._fields.length]; + for (int i=0; i<num; i++) + body[i] = val(alloc.in(2+i+num)); + } + Object[] mems = new Object[type._fields.length+2]; + // mems[0] is control + mems[1] = new Obj(type,body); // the ref + // mems[2+...] are memory aliases + return mems; + } + + private Object load(LoadNode load) { + var from = (Obj)val(load.ptr()); + var off = vall(load.off()); + var idx = getFieldIndex(from.struct, load, (Long)off); + if( idx==from.struct._fields.length-1 && from.struct.isAry() ) { + long len = from.fields.length - from.struct._fields.length + 1; + long i = offToIdx(off, from.struct); + if( i < 0 || i >= len ) + throw new ArrayIndexOutOfBoundsException("Array index out of bounds " + i + " < " + len); + return from.fields[(int)i+from.struct._fields.length-1]; + + } else + return from.fields[idx]; + } + + private Object store(StoreNode store) { + var to = (Obj)val(store.ptr()); + var off = vall(store.off()); + var val = val(store.val()); + var idx = getFieldIndex(to.struct, store, (Long)off); + if( idx==to.struct._fields.length-1 && to.struct.isAry() ) { + long len = to.fields.length - to.struct._fields.length + 1; + long i = offToIdx(off, to.struct); + if( i < 0 || i >= len ) + throw new RuntimeException("Array index out of bounds " + off + " <= " + len); + to.fields[(int)i+to.struct._fields.length-1] = val; + } else + to.fields[idx] = val; + return null; + } + + private static boolean isTrue(Object obj) { + if (obj == null) return false; + if (obj instanceof Number n) return n.longValue() != 0; + return true; + } + + private Object val(Node node) { + return values[node._nid]; + } + + private long vall(Node node) { + var v = val(node); + if (v instanceof Number n) return n.longValue(); + throw new AssertionError("Not a long " + v); + } + private double vald(Node node) { + var v = val(node); + if (v instanceof Number n) return n.doubleValue(); + throw new AssertionError("Not a double " + v); + } + + private Object cons(ConstantNode cons) { + var type = cons.compute(); + if (type instanceof TypeInteger i) return i.value(); + if (type instanceof TypeFloat i) return i.value(); + assert type instanceof TypeMemPtr; + return null; + } + + private Object exec(Node node) { + return switch (node) { + case ConstantNode cons -> cons(cons); + case AddNode add -> vall(add.in(1)) + vall(add.in(2)); + case AddFNode add -> vald(add.in(1)) + vald(add.in(2)); + case BoolNode.EQF eq -> vald(eq.in(1)) == vald(eq.in(2)) ? 1L : 0L; + case BoolNode.LEF le -> vald(le.in(1)) <= vald(le.in(2)) ? 1L : 0L; + case BoolNode.LTF lt -> vald(lt.in(1)) < vald(lt.in(2)) ? 1L : 0L; + case BoolNode.EQ eq -> Objects.equals(val(eq.in(1)), val(eq.in(2))) ? 1L : 0L; + case BoolNode.LE le -> vall(le.in(1)) <= vall(le.in(2)) ? 1L : 0L; + case BoolNode.LT lt -> vall(lt.in(1)) < vall(lt.in(2)) ? 1L : 0L; + case DivNode div -> div(div); + case DivFNode div -> div(div); + case MinusNode minus -> -vall(minus.in(1)); + case MinusFNode minus -> -vald(minus.in(1)); + case MulNode mul -> vall(mul.in(1)) * vall(mul.in(2)); + case MulFNode mul -> vald(mul.in(1)) * vald(mul.in(2)); + case NotNode not -> isTrue(val(not.in(1))) ? 0L : 1L; + case SubNode sub -> vall(sub.in(1)) - vall(sub.in(2)); + case SubFNode sub -> vald(sub.in(1)) - vald(sub.in(2)); + case ShlNode shl -> vall(shl.in(1)) << vall(shl.in(2)); + case ShrNode shr -> vall(shr.in(1)) >>> vall(shr.in(2)); + case SarNode sar -> vall(sar.in(1)) >> vall(sar.in(2)); + case AndNode and -> vall(and.in(1)) & vall(and.in(2)); + case OrNode or -> vall(or .in(1)) | vall(or .in(2)); + case XorNode xor -> vall(xor.in(1)) ^ vall(xor.in(2)); + case CastNode cast -> val(cast.in(1)); + case ToFloatNode cast -> (double)vall(cast.in(1)); + case LoadNode load -> load(load); + case StoreNode store -> store(store); + case NewNode alloc -> alloc(alloc); + case CProjNode cproj -> ((Object[])val(cproj.ctrl()))[cproj._idx]; + case ProjNode proj -> ((Object[])val( proj.in(0) ))[ proj._idx]; + case ScopeMinNode mem -> null; + case ReadOnlyNode ro -> val(ro.in(1)); + default -> throw new AssertionError("Unexpected node " + node); + }; + } + + /** + * Run the graph until either a return is found or the number of loop iterations are done. + */ + public Object evaluate(long parameter, int loops) { + if (start == null) return Status.TIMEOUT; + var s = new Object[start.compute()._types.length]; + s[1] = MEMORY; + s[2] = parameter; + values[start._nid] = s; + int i=0; + Scheduler.Block block = this.startBlock; + for(;;) { + for(; i<block.nodes().length;i++) values[block.nodes()[i]._nid] = exec(block.nodes()[i]); + i=0; + switch (block.exit()) { + case null: + return Status.FALLTHROUGH; + case ReturnNode ret: + return val(ret.in(1)); + case IfNode ifn: + block = block.next()[isTrue(val(ifn.in(1))) ? 0 : 1]; + if (block == null) return Status.FALLTHROUGH; + break; + case RegionNode region: + if (loops-- <= 0) return Status.TIMEOUT; + int exit = block.exitId(); + assert exit > 0 && region.nIns() > exit; + block = block.next()[0]; + assert block != null; + for (; i < block.nodes().length; i++) { + if (!(block.nodes()[i] instanceof PhiNode)) break; + phiCache.add(val(block.nodes()[i].in(exit))); + } + for (i=0; i<phiCache.size(); i++) { + values[block.nodes()[i]._nid] = phiCache.get(i); + } + phiCache.clear(); + break; + default: + throw Utils.TODO("Unexpected control node " + block.exit()); + } + } + } + + public static Object evaluate(StopNode graph) { + return evaluate(graph, 0); + } + + public static Object evaluate(StopNode graph, long parameter) { + return evaluate(graph, parameter, 1000); + } + + public static Object evaluate(StopNode graph, long parameter, int loops) { + var res = evaluateWithResult(graph, parameter, loops); + if (res == Status.TIMEOUT) throw new RuntimeException("Timeout"); + return res; + } + + public static Object evaluateWithResult(StopNode graph, long parameter, int loops) { + return new Evaluator(graph).evaluate(parameter, loops); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/evaluator/Scheduler.java b/chapter18/src/test/java/com/seaofnodes/simple/evaluator/Scheduler.java new file mode 100644 index 00000000..06169e2c --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/evaluator/Scheduler.java @@ -0,0 +1,599 @@ +package com.seaofnodes.simple.evaluator; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.Type; + +import java.util.*; + +/** + * A late scheduler for test cases. + * <br> + * <br> + * This scheduler is used for tests and is not the final scheduler. + * <br> + * <br> + * The scheduler schedules not as late as possible. Since it is just for test cases this is fine. + * A better scheduler will try to place nodes outside of loops. Due to the schedule late strategy + * this scheduler might place initialization code in loops. + * <br> + * We schedule late here since memory edges have some implicit information. There can only be one + * memory edge (for a field) at a time. However, before <code>if</code> statements this might split. + * When scheduling early a store might be moved out of the loop but then there are two edges alive. + * The one through the store node and the adjacent one. This is an invalid schedule and instead of + * handling this case a late scheduler does not have this problem as memory edges are combined + * through phi nodes. + * <br> + * <br> + * A bit about this scheduler. It first discovers all alive nodes and allocates side data for them. + * Then the control flow graph is build. Then, all phis are placed and finally all the remaining nodes + * in an order where a node is placed when all alive uses are placed. Finally, the output is produced. + */ +public class Scheduler { + + /** + * A basic block with a schedule of the containing nodes. + * + * @param nodes The nodes in the final schedule of this block + * @param exit The exit node of this block. + * @param exitId In case the next block is a region this gives the entry id into the region. + * @param next The next blocks. + */ + public record Block(Node[] nodes, Node exit, int exitId, Block[] next) {} + + /** + * Definition of a block in the building process. + */ + private static class BasicBlock { + + /** + * Dominator of this block + */ + final BasicBlock dom; + /** + * Id of this block where <code>a.depth < b.depth</code> means that a is before b or + * both are in different branches. + */ + final int depth; + /** + * Previous blocks + */ + final BasicBlock[] prev; + /** + * Entry to this block + */ + final Node entry; + /** + * Schedules node in reverse order. + */ + final ArrayList<Node> reverseSchedule = new ArrayList<>(); + + /** + * Initialize the block. + * @param entry The node that started this block + * @param depth The depth of this node. All previous nodes need to have a lower value. + * @param prev The previous blocks. + */ + BasicBlock(Node entry, int depth, BasicBlock... prev) { + BasicBlock dom = null; + int max = -1; + for(var bb: prev) { + max = Math.max(max, bb.depth); + dom = dom==null?bb:dom(dom, bb); + } + assert depth > max; + this.dom = dom; + this.depth = depth; + this.entry = entry; + this.prev = prev; + } + + } + + /** + * Ancillary data for nodes used during the scheduling process. + */ + private static class NodeData { + + /** + * The node this ancillary data is used for. + */ + final Node node; + + /** + * Number of alive users not yet scheduled. + */ + int users = 1; + + /** + * Block into which the node should be placed so far. + * This will be updated with every placed use. + */ + BasicBlock block; + + /** + * Initialize ancillary data for a node + * @param node The node this ancillary data is associated with. + */ + NodeData(Node node) { + this.node = node; + } + + } + + /** + * Ancillary data for nodes. + */ + private final IdentityHashMap<Node, NodeData> data = new IdentityHashMap<>(); + /** + * List of nodes which can be placed since all users are placed. + */ + private final Stack<NodeData> scheduleQueue = new Stack<>(); + + /** + * Get the ancillary data for an alive node. + * @param node The node for which the ancillary data is requested. + * @return The ancillary data for the node. + */ + NodeData d(Node node) { + return od(node).orElseThrow(AssertionError::new); + } + + /** + * Get the ancillary data for a potentially dead node. + * @param node The node for which the ancillary data is requested. + * @return The ancillary data for the node an alive node or + * <code>Optional.empty()</code> for <code>null</code> or dead nodes. + */ + Optional<NodeData> od(Node node) { + return Optional.ofNullable(data.get(node)); + } + + /** + * Checks a node for validity + * @param data The node to check. + * @return true if all placed inputs are before this node. + */ + private boolean isValid(NodeData data) { + return data.node._inputs.stream() + .map(i->i==null?null:d(i)) + .map(d->d==null||d.users>0?null:d.block) + .allMatch(d->d==null||dom(d, data.block)==d); + } + + /** + * Checks that node is not XCtrl. + * @param node The node to check. + * @return true if the node is not XCtrl. + */ + private static boolean isNotXCtrl(Node node) { + return !(node instanceof ConstantNode c && c.compute() == Type.XCONTROL) && !(node instanceof XCtrlNode); + } + + /** + * Return the dominator of <code>a</code> and <code>b</code> + * @param a Block a + * @param b Block b + * @return The dominator of <code>a</code> and <code>b</code> + */ + private static BasicBlock dom(BasicBlock a, BasicBlock b) { + while (a!=b) { + if (a.depth >= b.depth) a=a.dom; + if (b.depth > a.depth) b=b.dom; + } + return a; + } + + /** + * Return if a is before b. + * @param a Block a + * @param b Block b + * @return true is a is before b. + */ + private static boolean isBefore(BasicBlock a, BasicBlock b) { + while (b.depth > a.depth) { + while (b.dom.depth > a.depth) b = b.dom; + for (int i=0; i<b.prev.length-1; i++) { + if (isBefore(a, b.prev[i])) return true; + } + b = b.prev[b.prev.length-1]; + } + return a == b; + } + + /** + * Is node placed during the control flow graph build. + * @param data Node to check. + * @return true if node is placed during the control flow graph build. + */ + private static boolean isPinnedNode(NodeData data) { + return data.node instanceof CFGNode || data.node instanceof PhiNode; + } + + /** + * Refine placement of a node. + * @param data The node to refine. + * @param block The block before the node should be scheduled. + */ + private void refinePlacement(NodeData data, BasicBlock block) { + assert !isPinnedNode(data); + data.block = data.block == null ? block : dom(data.block, block); + assert isValid(data); + } + + /** + * Refine placement if before is happening before data + * @param data The node for which the placement should be refined. + * @param before The node before which the data node should be placed. + */ + private void optionalRefinePlacement(NodeData data, Node before) { + od(before).ifPresent(d->{ + // before might be in a different branch. So check this case with isBefore + // and only refine the placement if it is not in a different branch. + if (isBefore(d.block, data.block)) refinePlacement(data, d.block); + }); + } + + /** + * Schedule all nodes not yet scheduled. + */ + private void doSchedule() { + while (!scheduleQueue.isEmpty()) { + var data = scheduleQueue.pop(); + assert !isPinnedNode(data); + + assert data.block != null; + assert data.users == 0; + + if (data.node instanceof LoadNode l) { + assert isValid(data); + // Handle anti-deps of load nodes. + // At this point all anti-dep nodes are scheduled, + // but they did not refine the placement + // so do that now. + var mem = l.in(1); + for(var out : mem._outputs) { + if (out instanceof PhiNode p) { + var r = p.in(0); + for (int i = 1; i < p.nIns(); i++) { + if (p.in(i) == mem) optionalRefinePlacement(data, r.in(i)); + } + } else if (!(out instanceof LoadNode)) { + optionalRefinePlacement(data, out); + } + } + } + + assert isValid(data); + data.block.reverseSchedule.add(data.node); + + for(var in:data.node._inputs) { + if (in!=null) update(d(in), data.block); + } + if (data.node instanceof StoreNode s) { + // Store nodes have anti-deps to load nodes. + // So decrease the uses of these loads when the store is placed. + for (var out: s.in(1)._outputs) { + if (out instanceof LoadNode) od(out).ifPresent(this::decUsers); + } + } + } + + // Now all nodes should be placed and have a block assigned + assert this.data.values().stream().noneMatch(d->d.block==null); + } + + /** + * Decrement the not-yet-placed users of a block. + * @param data The node for which the users should be decremented. + */ + private void decUsers(NodeData data) { + assert data.users > 0; + if (--data.users == 0) { + assert data.block != null; + assert isValid(data); + + // When all users are gone this node can be scheduled. + scheduleQueue.push(data); + } + } + + /** + * Update the placement of a node + * @param data The node to update + * @param block The block before which the node should happen. + */ + private void update(NodeData data, BasicBlock block) { + assert block != null; + if (data.users == 0) { + assert isPinnedNode(data); + return; + } + refinePlacement(data, block); + decUsers(data); + } + + /** + * Checks if a CFG node is ready to be placed. This is used for regions joining branches. + * @param node The CFG node to check + * @return true if all parents of a CFG node are placed. + */ + private boolean isCFGNodeReady(Node node) { + if (node instanceof LoopNode l) { + assert d(l.in(1)).block != null; + } else if (node instanceof RegionNode r) { + for(int i=1; i<r.nIns(); i++) { + if (od(r.in(i)).map(d->d.block==null).orElse(false)) return false; + } + } else if (node instanceof XCtrlNode) { + return false; + } else { + assert d(node.in(0)).block != null; + } + return true; + } + + /** + * Schedule all phi nodes. + * @param phiQueue List of all the phi nodes to schedule. + */ + private void schedulePhis(Stack<NodeData> phiQueue) { + while(!phiQueue.empty()) { + var data = phiQueue.pop(); + var phi = (PhiNode) data.node; + var r = phi.in(0); + data.block = d(r).block; + for(int i=1; i<phi.nIns(); i++) { + var in = phi.in(i); + od(r.in(i)).ifPresent(d->update(d(in), d.block)); + } + } + } + + /** + * Build the control flow graph. + * @param start The start node. + */ + private void doBuildCTF(StartNode start) { + var queue = new Stack<NodeData>(); + var phiQueue = new Stack<NodeData>(); + queue.push(d(start)); + int depth = 0; + while (!queue.isEmpty()) { + var data = queue.pop(); + var node = data.node; + assert node instanceof CFGNode; + BasicBlock block; + switch (node) { + case StartNode s: + block = new BasicBlock(s, depth++); + break; + case LoopNode l: + block = new BasicBlock(l, depth++, d(l.in(1)).block); + break; + case RegionNode r: + var prev = new ArrayList<BasicBlock>(); + for(int i=1; i<r.nIns(); i++) { + od(r.in(i)).ifPresent(d->prev.add(d.block)); + } + block = new BasicBlock(r, depth++, prev.toArray(BasicBlock[]::new)); + break; + case IfNode i: + block = d(i.in(0)).block; + break; + case ReturnNode r: + block = d(r.in(0)).block; + break; + default: + block = new BasicBlock(node, depth++, d(node.in(0)).block); + } + data.block = block; + if (node instanceof RegionNode r) { + // Regions might have phis which need to be scheduled. + // Put them on a list for later scheduling. + for (var out:r._outputs) { + if (out instanceof PhiNode p) { + var d = this.data.get(p); + if (d!=null) { + d.users=0; + phiQueue.push(d); + } + } + } + } + if (!(node instanceof ReturnNode)) + for (Node n : node._outputs) + if(n instanceof CFGNode && isCFGNodeReady(n) && d(n).block == null) + queue.push(d(n)); + var b = block; + for(var in:data.node._inputs) od(in).ifPresent(d->update(d, b)); + } + + // Schedule all phi nodes. + schedulePhis(phiQueue); + } + + /** + * Mark a node alive and create ancillary data for it. + * @param queue List into which this node should be placed if it needs to be visited. + * @param node Node which should be marked alive. + * @param cfg If this node is a CFG node. + */ + private void markAlive(Stack<NodeData> queue, Node node, boolean cfg) { + var nd = od(node).orElse(null); + if (nd != null) { + // Node was already visited, just increase the users. + if (nd.users>0) nd.users++; + return; + } + assert node instanceof CFGNode == cfg; + assert isNotXCtrl(node); + nd = new NodeData(node); + if (cfg) nd.users=0; + data.put(node, nd); + queue.push(nd); + } + + /** + * Mark all alive nodes. + * First all CFG nodes are marked, then all other nodes. + * @param node THe start node. + */ + private void doMarkAlive(Node node) { + var cfgQueue = new Stack<NodeData>(); + var dataQueue = new Stack<NodeData>(); + var mem = new Stack<NodeData>(); + markAlive(cfgQueue, node, true); + // Mark all CFG nodes. + while (!cfgQueue.isEmpty()) { + var data = cfgQueue.pop(); + node = data.node; + assert node instanceof CFGNode; + if (!(node instanceof ReturnNode)) { + for (var out : node._outputs) if (out!=null && out instanceof CFGNode && isNotXCtrl(out)) markAlive(cfgQueue, out, true); + } + for (var in : node._inputs) if(in!=null && !(in instanceof CFGNode) && isNotXCtrl(in)) markAlive(dataQueue, in, false); + } + // Mark all other nodes. + while (!dataQueue.isEmpty()) { + var data = dataQueue.pop(); + node = data.node; + assert !(node instanceof CFGNode); + if (node instanceof PhiNode phi) { + var r = phi.in(0); + for (int i=1; i<phi.nIns(); i++) { + if (od(r.in(i)).isPresent()) markAlive(dataQueue, phi.in(i), false); + } + } else { + for (var in : node._inputs) if (in != null && !(in instanceof CFGNode)) markAlive(dataQueue, in, false); + } + if (node instanceof StoreNode) mem.push(data); + } + // Handle store nodes and increase load with an anti-dep to the store. + while (!mem.isEmpty()) { + var data = mem.pop(); + node = data.node; + for(var out:node.in(1)._outputs) { + if (out instanceof LoadNode) od(out).ifPresent(d->d.users++); + } + } + } + + /** + * Helper function to append the nodes of a block to an array of nodes + * @param arr The array the nodes of a block should be appended to. + * @param node A potentially separator node + * @param block The block from which the nodes should be appended. + * @return The combined new array. + */ + private static Node[] appendNodes(Node[] arr, Node node, BasicBlock block) { + var idx = arr.length; + arr = Arrays.copyOf(arr, arr.length+block.reverseSchedule.size()+(node==null?0:1)); + if (node != null) arr[idx++] = node; + for(int i=block.reverseSchedule.size()-1;i>=0;i--) { + arr[idx++] = block.reverseSchedule.get(i); + } + return arr; + } + + /** + * Find the CFG output of a node + * @param node The node + * @return THe CFG output of the node. + */ + private static Node findSingleCFGOut(Node node) { + if (node instanceof StartNode) { + for(var n:node._outputs) if (n instanceof CProjNode p && p._idx==0) return p; + return null; + } + assert node._outputs.stream().filter(x -> x instanceof CFGNode).limit(2).count()<=1; + for(var n:node._outputs) if(n instanceof CFGNode) return n; + return null; + } + + /** + * Build the final data structure after all the scheduling happened. + * @param start The start node + * @return The final schedule. + */ + private Block build(Node start) { + var blocks = new IdentityHashMap<Node, Block>(); + var queue = new Stack<NodeData>(); + queue.push(d(start)); + + // Visit all CFG nodes and create blocks for them. + // This can combine blocks. + while(!queue.isEmpty()) { + var data = queue.pop(); + var first = data.node; + Node prev; + var last = first; + Node[] arr = new Node[0]; + if (first instanceof RegionNode) { + var nodes = new ArrayList<Node>(); + for(var out: first._outputs) { + if (out instanceof PhiNode) { + if(od(out).isPresent()) nodes.add(out); + } + } + arr = nodes.toArray(arr); + } + arr = appendNodes(arr, null, data.block); + assert !(first instanceof IfNode); + for(;;) { + prev = last; + last = findSingleCFGOut(last); + if (last == null) break; + if (last instanceof RegionNode) { + if (blocks.get(last) == null && last != first) + queue.push(d(last)); + break; + } + if (last instanceof ReturnNode) break; + if (last instanceof IfNode if_) { + for(var out:if_._outputs) if (out instanceof CFGNode && blocks.get(out) == null) queue.push(d(out)); + break; + } + data = d(last); + arr = appendNodes(arr, data.node, data.block); + } + blocks.put(first, switch(last) { + case null -> new Block(arr, null, -1, new Block[0]); + case IfNode i -> new Block(arr, i, -1, new Block[2]); + case RegionNode r -> new Block(arr, r, r._inputs.find(prev), new Block[1]); + case ReturnNode r -> new Block(arr, r, -1, new Block[0]); + default -> throw new AssertionError("Unexpected block exit node"); + }); + } + // Update the next pointer of all blocks. + for (var block: blocks.values()) { + switch(block.exit) { + case null: break; + case IfNode i: + for(var out:i._outputs) if (out instanceof CProjNode p) block.next[p._idx] = blocks.get(p); + break; + case RegionNode r: + block.next[0] = blocks.get(r); + break; + default: + assert block.exit instanceof ReturnNode; + } + } + // And return the block for the start node. + return blocks.get(start); + } + + /** + * Create a schedule for the program reachable from start. + * @param start The start node + * @return The final schedule. + */ + public static Scheduler.Block schedule(StartNode start) { + var scheduler = new Scheduler(); + scheduler.doMarkAlive(start); + scheduler.doBuildCTF(start); + scheduler.doSchedule(); + return scheduler.build(start); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/Fuzzer.java b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/Fuzzer.java new file mode 100644 index 00000000..51e39cd0 --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/Fuzzer.java @@ -0,0 +1,185 @@ +package com.seaofnodes.simple.fuzzer; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.evaluator.Evaluator; +import com.seaofnodes.simple.node.Node; +import com.seaofnodes.simple.node.StopNode; + +import java.util.ArrayList; +import java.util.Objects; +import java.util.Random; +import java.util.function.Consumer; + +/** + * Implementation of the fuzzer. + * Random testcases are generated using the ScriptGenerator. + * This will generate a script similar to how the parser parses it but instead of parsing it will + * randomly choose a variation the parser would parse and generate it. + * These scripts are the parsed by the parser and all exceptions are caught and filtered + * to only show one occurrence of one problem. This includes script which generate different + * results when the compiled graph with and without peeps is executed. + * To aid debugging scripts that cause errors are then reduced by applying rules and checking + * that the same issue persists. + */ +public class Fuzzer { + + private static final int EVAL_TIMEOUT = 1000; + + /** + * List of exceptions already encountered. + * This is used to filter new exceptions and discard them if they are already found. + */ + private final ArrayList<Throwable> exceptions = new ArrayList<>(); + + /** + * Filter and record an exception in a script. + * @param e The exception caused by the script + * @param script The script causing the exception + * @param reproducer Reproducer which should be used to reproduce the test case. + */ + private void recordException(Throwable e, String script, Consumer<String> reproducer, long seed) { + for (var ex : exceptions) { + if (FuzzerUtils.isExceptionFromSameCause(ex, e)) return; + } + exceptions.add(e); + System.out.println("========== Stack =========="); + e.printStackTrace(System.out); + System.out.println("========== Seed =========="); + System.out.println(seed); + System.out.println("========== Code ==========="); + System.out.println(script); + System.out.println("========= Reduced ========="); + System.out.println(Reducer.reduce(script, e, reproducer)); + System.out.println("==========================="); + System.out.flush(); + } + + private static boolean neq(Object a, Object b) { + if (Objects.equals(a, b)) return false; + if (a instanceof Evaluator.Obj ea && b instanceof Evaluator.Obj eb) { + if (ea.struct() != eb.struct()) return true; + for(int i=0;i<ea.fields().length;i++) { + if (neq(ea.fields()[i], eb.fields()[i])) return true; + } + return false; + } + return true; + } + + /** + * Check that two graphs result in the same output when supplied with a value + * @param e1 Evaluator for the first graph + * @param e2 Evaluator for the second graph + * @param in The input value to both graphs to test for an equal output + */ + private static void checkGraphs(Evaluator e1, Evaluator e2, long in) { + var r1 = e1.evaluate(in, EVAL_TIMEOUT); + var r2 = e2.evaluate(in, EVAL_TIMEOUT); + if (r1 == Evaluator.Status.TIMEOUT || r2 == Evaluator.Status.TIMEOUT) return; + if (neq(r1, r2)) + throw new RuntimeException("Different calculations values " + r1 + " vs " + r2); + } + + /** + * Run checks for script. Compile the script with peeps enabled and disabled. + * Check that exceptions raised in the parser by both methods are the same and only happens if the script may be invalid. + * If the script was successfully parsed check that both version behave the same. + * @param script The script to test + * @param valid If the script is definitely valid. If not some exceptions may be suppressed. + */ + private static void runCheck(String script, boolean valid) { + StopNode stop1; + try { + stop1 = FuzzerUtils.parse(script, false); + } catch (RuntimeException e1) { + try { + FuzzerUtils.parse(script, true); + } catch (RuntimeException e2) { + if (FuzzerUtils.isExceptionFromSameCause(e1, e2)) { + if (!valid || e1.getClass() == RuntimeException.class) return; + } else { + e1.addSuppressed(e2); + } + } + throw e1; + } + var stop2 = FuzzerUtils.parse(script, true); + var e1 = new Evaluator(stop1); + var e2 = new Evaluator(stop2); + checkGraphs(e1, e2, 0); + checkGraphs(e1, e2, 1); + checkGraphs(e1, e2, 10); + } + + /** + * Check that the script does not result in exceptions. + * @param script The script to test. + * @param valid If the script is valid or if it might contain syntax errors. + */ + private void check(String script, boolean valid, long seed) { + try { + runCheck(script, valid); + } catch (Throwable e) { + recordException(e, script, s->runCheck(s, valid), seed); + } + } + + /** + * Run one test with the given seed, and check for peephole counts. + * @param seed The seed to use for generating this test case + */ + public int fuzzPeepTiming(long seed, int max_nids) { + var rand = new Random(seed); + var sb = new StringBuilder(); + new ScriptGenerator(rand, sb, true).genProgram(); + try { + var parser = new Parser(sb.toString()); + + var stop = parser.parse(); + int parse_peeps= Node.ITER_CNT; + int parse_nops = Node.ITER_NOP_CNT; + double parse_nop_ratio = (double)parse_nops/parse_peeps; + int nids = Node.UID(); + if( nids <= max_nids ) return max_nids; + + double parse_peeps_per_node = (double)parse_peeps/nids; + + stop.iterate(); + int iter_peeps= Node.ITER_CNT; + int iter_nops = Node.ITER_NOP_CNT; + double iter_nop_ratio = (double)iter_nops/iter_peeps; + double iter_peeps_per_node = (double)iter_peeps/nids; + + System.out.printf("%6d | Parsing: peeps: %5d, nops: %5d, ratio: %5.3f, last UID: %5d ps/node: %5.3f | Iter: peeps: %6d, nops: %6d, ratio: %5.3f, ps/node: %5.3f\n", + seed, + parse_peeps,parse_nops,parse_nop_ratio,nids,parse_peeps_per_node, + iter_peeps , iter_nops, iter_nop_ratio, iter_peeps_per_node); + return nids; + } catch (Throwable e) { + // ignore exceptions, let the normal fullPeeps catch and reduce, + // we're interested in valid program optimizations + } + return max_nids; + } + + + /** + * Run one test with the given seed. + * @param seed The seed to use for generating this test case + */ + public void fuzzPeeps(long seed) { + var rand = new Random(seed); + var sb = new StringBuilder(); + var valid = new ScriptGenerator(rand, sb, true).genProgram(); + check(sb.toString(), valid, seed); + } + + + /** + * Check that no exceptions happened. + * @return true if no exception happened + */ + public boolean noExceptions() { + return exceptions.isEmpty(); + } +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/FuzzerUtils.java b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/FuzzerUtils.java new file mode 100644 index 00000000..18ef069a --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/FuzzerUtils.java @@ -0,0 +1,140 @@ +package com.seaofnodes.simple.fuzzer; + +import com.seaofnodes.simple.IterPeeps; +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.node.Node; +import com.seaofnodes.simple.node.StopNode; + +import java.io.OutputStream; +import java.io.PrintStream; +import java.lang.invoke.MethodHandle; +import java.lang.invoke.MethodHandles; +import java.lang.reflect.Field; +import java.util.BitSet; + +/** + * Some utilities for the fuzzer. + */ +class FuzzerUtils { + + /** + * Get the val of a private field + */ + @SuppressWarnings("unchecked") + public static <T> T getFieldValue(Object obj, String name) throws NoSuchFieldException, IllegalAccessException { + return (T) (obj instanceof Class<?> clz ? getField(clz, name).get(null) : getField(obj.getClass(), name).get(obj)); + } + + /** + * Get access to a private field + */ + public static Field getField(Class<?> clz, String name) throws NoSuchFieldException { + var field = clz.getDeclaredField(name); + try { + field.setAccessible(true); + } catch (Throwable e) { + // Intentionally left empty + } + return field; + } + + /** + * Try to rethrow an exception or create a runtime exception and throw it. + */ + public static RuntimeException rethrow(Throwable e) { + if (e instanceof RuntimeException re) return re; + if (e instanceof Error er) throw er; + return new RuntimeException(e); + } + + /** + * Copy of Node.WVISIST + * Used to clear as exceptions might happen in the walk and left this bitset not cleared + */ + private static final BitSet NodeWalkVisit; + + /** + * Write access to Iterate.MID_ASSERT + * Exception could happen mid assert and left this at true. Used to reset to false prior to parsing. + */ + private static final MethodHandle set_MID_ASSERT; + + /** + * Some problems might trigger debug output. Suppress this output with a null print stream during fuzzing. + */ + public static final PrintStream NULL_PRINT_STREAM = new PrintStream(OutputStream.nullOutputStream()); + + static { + try { + NodeWalkVisit = getFieldValue(Node.class, "WVISIT"); + set_MID_ASSERT = MethodHandles.lookup().unreflectSetter(getField( IterPeeps.class, "MID_ASSERT")); + } catch (Exception e) { + throw new ExceptionInInitializerError(e); + } + } + + /** + * Check that the messages are similar. + */ + private static boolean similarMessages(String a, String b) { + if (a == null || b == null) return true; + a = a.replaceAll("'\\w+'", "'normalized'").replaceAll("variable \\w+", "variable normalized"); + b = b.replaceAll("'\\w+'", "'normalized'").replaceAll("variable \\w+", "variable normalized"); + return a.equals(b); + } + + /** + * Check if both stack traces have the same first entry. Empty stack traces can happen with NPE optimization + * and allow the other to be any stack trace. + */ + private static boolean sameStackTraceOrigin(StackTraceElement[] a, StackTraceElement[] b) { + if (a == null || a.length == 0 || b == null || b.length == 0) return true; // One or both stack traces are missing. + return a[0].equals(b[0]); + } + + /** + * Checks if two exceptions are caused by the same problem. + */ + public static boolean isExceptionFromSameCause(Throwable a, Throwable b) { + if (a == null || b == null) return a == b; // Handle the null case + if (a.getClass() != b.getClass()) return false; // Different classes + if (!similarMessages(a.getMessage(), b.getMessage())) return false; // Different messages. Null is allowed as wildcard + var s1 = a.getStackTrace(); + var s2 = b.getStackTrace(); + if (!sameStackTraceOrigin(s1, s2)) return false; // Different stack trace origins + if (!isExceptionFromSameCause(a.getCause(), b.getCause())) return false; // Different causes + var o1 = a.getSuppressed(); + var o2 = b.getSuppressed(); + if (o1 == null || o2 == null || o1.length != o2.length) return o1 == o2; // Different suppression + for (int i=0; i<o1.length; i++) { + if (!isExceptionFromSameCause(o1[i], o2[i])) return false; // Different suppression + } + return true; + } + + /** + * Parse script with peepholes enabled or disabled + */ + public static StopNode parse(String script, boolean runPeeps) { + var err = System.err; + var out = System.out; + try { + System.setErr(NULL_PRINT_STREAM); + System.setOut(NULL_PRINT_STREAM); + try { + set_MID_ASSERT.invokeExact(false); + } catch (Throwable e) { + throw rethrow(e); + } + var parser = new Parser(script); + Node._disablePeephole = !runPeeps; + var stop = parser.parse(); + return runPeeps ? stop.iterate() : stop; + } finally { + NodeWalkVisit.clear(); + System.setErr(err); + System.setOut(out); + } + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/Reducer.java b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/Reducer.java new file mode 100644 index 00000000..3731b40c --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/Reducer.java @@ -0,0 +1,176 @@ +package com.seaofnodes.simple.fuzzer; + +import java.util.Arrays; +import java.util.function.BiConsumer; +import java.util.function.Consumer; +import java.util.function.Predicate; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +/** + * This class is used to reduce test cases created by the fuzzer. + * It applies rewrite rules to the test case and checks that the + * test still produces the same exception. + * This is done in a fixpoint iteration until every rewrite produces + * no or a different exception. + */ +public class Reducer { + + private interface Replacer extends BiConsumer<StringBuilder, Matcher> {} + + /** + * Holder for the rewrite rules + */ + private record Replace(Pattern pattern, boolean iterate, Replacer... replacements) { + Replace(Pattern p, Object... replacements) { + this(p, replacements[0] == Boolean.TRUE, Arrays.stream(replacements).filter(o->!(o instanceof Boolean)).map(Replace::from).toArray(Replacer[]::new)); + } + private static Replacer from(Object o) { + if (o instanceof Replacer r) return r; + if (o instanceof Integer i) return (s, m)->s.append(m.group(i)); + if (o instanceof String r) return (s, m)->s.append(r); + throw new IllegalArgumentException(); + } + } + + /** + * List of rewrite rules. + */ + private static final Replace[] REPLACEMENTS = { + new Replace(Pattern.compile("\\b(?:[^\\W0]|\\w\\w+)\\b"), "0", "1"), + new Replace(Pattern.compile("(?<=\\n|^)[^\\n]+(?=\\n|$)"), true, ""), + new Replace(Pattern.compile("(?<=[+\\-*/<>=(])--"), ""), + new Replace(Pattern.compile("\\b--"), "+"), + new Replace(Pattern.compile("-"), ""), + new Replace(Pattern.compile("\\b\\+-"), "-"), + new Replace(Pattern.compile("(?<![+\\-*/<>=])(?:-|\\*|/|>=|<=|>|<|!=|==)(?![+\\-*/<>=])"), "+"), + new Replace(Pattern.compile("\\{((?:[^{}]|\\{})+)(?:\\n[ \\t]*)?}"), "", "{}", 1), + new Replace(Pattern.compile("(?<=\\n|^)([ \\t]*)\\{\\n(.*?)\\n\\1}", Pattern.DOTALL), 2), + new Replace(Pattern.compile("\\(([^()]+)\\)"), 1), + new Replace(Pattern.compile("\\d+\\+"), ""), + new Replace(Pattern.compile("\\+\\d+"), ""), + new Replace(Pattern.compile("\\n\\n+"), "\n"), + new Replace(Pattern.compile("^\\n+|\\n+$"), ""), + new Replace(Pattern.compile("else *"), ""), + new Replace(Pattern.compile("\\bif\\([^()]+\\) *"), ""), + new Replace(Pattern.compile("\\bwhile\\([^()]+\\) *"), ""), + new Replace(Pattern.compile("\\bstruct \\w+ \\{[^{}]*}"), "") + }; + + /** + * Predicate to test if the reduced script generates the same error. + */ + private final Predicate<String> tester; + + /** + * Create a reducer with a test function. + * @param tester Test function which returns true when the same issue is found in the script. + */ + private Reducer(Predicate<String> tester) { + this.tester = tester; + } + + /** + * Rewrites the script with one rewrite rule. + */ + private String doReplacement(String script, Pattern pattern, Replacer[] replacements) { + var matcher = pattern.matcher(script); + var sb = new StringBuilder(); + var last = 0; + var skip = 0; + outer: + while (matcher.find(last + skip)) { + sb.append(script, last, matcher.start()); + last = matcher.end(); + skip = last == matcher.start() ? 1 : 0; + var pos = sb.length(); + for (var replacement : replacements) { + replacement.accept(sb, matcher); + var tail = sb.length(); + sb.append(script, last, script.length()); + if (tester.test(sb.toString())) { + sb.setLength(tail); + continue outer; + } + sb.setLength(pos); + } + last = matcher.start(); + skip = 1; + } + sb.append(script, last, script.length()); + return sb.toString(); + } + + /** + * Clean up variable names from the random ones generated by the fuzzer. + */ + private String cleanVariables(String script) { + var matcher = Pattern.compile("\\b([0-9a-zA-Z_]+) ([0-9a-zA-Z_]+)").matcher(script); + int[] num = {0, 0}; + while (matcher.find()) { + var type = matcher.group(1); + var var = matcher.group(2); + if (type.equals("new")) continue; + String prefix = "v"; + int t = 0; + if (type.equals("struct")) { + t = 1; + prefix = "s"; + } + if (var.matches(prefix+"\\d+")) continue; + while (script.contains(prefix+num[t])) num[t]++; + var n = script.replaceAll("\\b"+var+"\\b", prefix + num[t]); + if (tester.test(n)) { + script = n; + } + } + return script; + } + + /** + * Run all rewrite rules once. + */ + private String doAllReplacements(String script) { + for (var replace: REPLACEMENTS) { + String old; + do { + old = script; + script = doReplacement(script, replace.pattern, replace.replacements); + } while (replace.iterate && !old.equals(script)); + } + return script; + } + + /** + * Reduce the script to a minimal version which produces the same problem with a test function. + * @param tester Test function which returns true when the same issue is found in the script. + */ + public static String reduce(String script, Predicate<String> tester) { + var reducer = new Reducer(tester); + String old; + do { + old = script; + script = reducer.doAllReplacements(script); + script = reducer.cleanVariables(script); + } while (!script.equals(old)); + return script; + } + + /** + * Reduce the script to a minimal version which produces the same problem with a reproducer. + * @param ex The exception originally caused by the script + * @param reproducer Test function which throws an exception which will be checked against ex. + */ + public static String reduce(String script, Throwable ex, Consumer<String> reproducer) { + return reduce(script, s->{ + Throwable nex = null; + try { + reproducer.accept(s); + } catch (Throwable e) { + nex = e; + } + return FuzzerUtils.isExceptionFromSameCause(nex, ex); + }); + } + +} diff --git a/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/ScriptGenerator.java b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/ScriptGenerator.java new file mode 100644 index 00000000..d3cbb0ee --- /dev/null +++ b/chapter18/src/test/java/com/seaofnodes/simple/fuzzer/ScriptGenerator.java @@ -0,0 +1,880 @@ +package com.seaofnodes.simple.fuzzer; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.node.ScopeNode; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.ArrayList; +import java.util.HashSet; +import java.util.List; +import java.util.Random; +import java.util.function.Predicate; + +/** + * Generate a pseudo random script. + * This generator will generate the same script for two random number generators initialized with the same seed. + * To generate valid code it implements the parser but instead of parsing it emits the statements and expressions. + * It is guaranteed to terminate. + */ +public class ScriptGenerator { + + private static final int MAX_STATEMENTS_PER_BLOCK = 5; + private static final int MAX_BINARY_EXPRESSIONS_PER_EXPRESSION = 10; + private static final int MAX_UNARY_EXPRESSIONS_PER_EXPRESSION = 6; + private static final int MAX_NAME_LENGTH = 10; + private static final int MAX_BLOCK_DEPTH = 4; + private static final int MAX_EXPRESSION_DEPTH = 10; + private static final int MAX_SUFFIX_RECURSIVE_DEPTH = 10; + + /** + * Number of spaces per indentation + */ + private static final int INDENTATION = 4; + /** + * Valid characters for identifiers. The last 10 are not valid for the first character. + */ + private static final String VAR_CHARS = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_0123456789"; + /** + * List of keywords not valid for identifiers. + */ + private static final HashSet<String> KEYWORDS; + + static { + try { + KEYWORDS = FuzzerUtils.getFieldValue(new Parser(""), "KEYWORDS"); + } catch (Throwable e) { + throw new ExceptionInInitializerError(e); + } + } + + /** + * Flag for a statement that it does not pass on control flow to the next statement. + */ + private static final int FLAG_STOP = 0x01; + /** + * Flag for a statement that it contains a final if statement without an else branch. + */ + private static final int FLAG_IF_WITHOUT_ELSE = 0x02; + /** + * Binary operators. + */ + private static final String[] BINARY_OP = {"==", "!=", "<", "<=", ">", ">=", "+", "-", "*", "/", "&", ">>", ">>>", "<<"}; + /** + * Unary operators. + */ + private static final String[] UNARY_OP = {"-"}; + + private static class Type { + final String name; + Type(String name) {this.name=name;} + boolean isa(Type other) { return this == other; } + } + + private static class TypeStruct extends Type { + record Field (String name, Type type, TypeStruct struct) {} + Field[] fields; + final TypeNullable nullable = new TypeNullable(this); + TypeStruct(String name) { + super(name); + } + boolean isa(Type other) { return this == other || other == nullable; } + } + + private static class TypeNullable extends Type { + + final Type base; + + TypeNullable(Type base) { + super(base.name+"?"); + this.base = base; + } + + } + + private static final Type TYPE_FLT = new Type("flt"); + + private static class TypeInt extends Type { + + TypeInt(String name) { + super(name); + } + + @Override + boolean isa(Type other) { + return super.isa(other) || other == TYPE_FLT || other instanceof TypeInt; + } + } + + private static final List<TypeInt> INTTYPES = new ArrayList<>(); + + static { + new Parser("", TypeInteger.BOT); + for( var e : Parser.defaultTypes().entrySet() ) { + if( e.getValue() instanceof TypeInteger ) { + INTTYPES.add(new TypeInt(e.getKey())); + } + } + } + + private static final Type TYPE_INT = INTTYPES.stream().filter(t->t.name.equals("int")).findAny().get(); + private static final Type TYPE_BOOL = INTTYPES.stream().filter(t->t.name.equals("bool")).findAny().get(); + + private static class Variable { + final String name; + final Type declared; + final Variable shadowing; + Type type; + boolean shadowed = false; + + Variable(String name, Type type, Variable var) { + this.name = name; + this.declared = type; + this.type = type; + this.shadowing = var; + } + } + + /** + * The random number generator used for random decisions. + */ + private final Random random; + /** + * Indentation depth. + */ + private int indentation = 0; + /** + * Output string builder + */ + private final StringBuilder sb; + /** + * Number of nested loops + */ + private int loopDepth = 0; + /** + * Current scope start in the variables list. + */ + private int currScopeStart = 0; + /** + * The depth of blocks allowed. + */ + private int depth = MAX_BLOCK_DEPTH; + /** + * The depth of expressions allowed. + */ + private int exprDepth = MAX_EXPRESSION_DEPTH; + /** + * Current variables in scope. + */ + private final ArrayList<Variable> variables = new ArrayList<>(); + /** + * All defined structs. + */ + private final ArrayList<TypeStruct> structs = new ArrayList<>(); + /** + * All forward declared structs + */ + private final ArrayList<TypeStruct> forwardStructs = new ArrayList<>(); + /** + * Allow to declare structs. + */ + private boolean allowStructs = true; + /** + * If this needs to generate valid scripts or is also allowed to generate invalid ones. + */ + private boolean generateValid; + /** + * If this script might be invalid. + */ + private boolean maybeInvalid = false; + + + /** + * + * @param random the random number generator. + * @param sb the script will be written to this string builder. + * @param generateValid if the script should be guaranteed valid or if it is allowed to contain bugs. + */ + public ScriptGenerator(Random random, StringBuilder sb, boolean generateValid) { + this.random = random; + this.sb = sb; + this.generateValid = generateValid; + } + + /** + * Random number with log distribution + * @param max The maximum value + * @return A random number in the range [0, max) with higher numbers being more uncommon. + */ + private int randLog(int max) { + max--; + int n = 1<<max; + var num = random.nextInt(n); + for (int i=max-1; i>=0; i--) { + if ((num & (1<<i))!=0) return max-i-1; + } + return max; + } + + /** + * Helper function to print indentation. + * @return sb for chaining + */ + private StringBuilder printIndentation() { + return sb.repeat(' ', indentation); + } + + /** + * Generate a random name for variables. This might be invalid when it is a keyword. + * @return The random name generated + */ + private StringBuilder getRandomName() { + int len = random.nextInt(MAX_NAME_LENGTH) + 1; + StringBuilder sb = new StringBuilder(len); + sb.append(VAR_CHARS.charAt(random.nextInt(VAR_CHARS.length()-10))); + for (int i=1; i<len; i++) + sb.append(VAR_CHARS.charAt(random.nextInt(VAR_CHARS.length()))); + return sb; + } + + /** + * Should invalid code be generated? + * @return True if invalid code should be generated + */ + private boolean generateInvalid() { + if (generateValid || random.nextInt(1000)>2) return false; + maybeInvalid = true; + return true; + } + + /** + * Lookup a variable by name + * @param name name of the variable + * @return The index of the variable in variables or -1 + */ + private int lookup(String name) { + for (int i=variables.size()-1; i>=0; i--) { + if (variables.get(i).name.equals(name)) return i; + } + return -1; + } + + /** + * Lookup a variable by name + * @param name name of the variable + * @return THe variable of null if not found + */ + private Variable lookupVar(String name) { + int idx = lookup(name); + return idx == -1 ? null : variables.get(idx); + } + + /** + * Add a variable to the current scope + * @param name The name of the variable + * @param type The declared type of the variable + */ + private void addVariable(String name, Type type) { + var old = lookupVar(name); + variables.add(new Variable(name, type, old)); + if (old != null) old.shadowed = true; + } + + /** + * Pop variables to level to + * @param to Level until which variables should be popped + */ + private void popVariables(int to) { + while (variables.size() > to) { + var v = variables.removeLast(); + if (v.shadowing != null) v.shadowing.shadowed = false; + } + } + + /** + * Get a random visible variable patching pred + * @param pred The predicate the variable needs to match + * @return A random visible variable matching pred or null if no variable mached pred. + */ + private Variable findVisibleVariablesMatching(Predicate<Variable> pred) { + int num=0; + for (var v:variables) { + if (!v.shadowed && pred.test(v)) num++; + } + if (num == 0) return null; + num = random.nextInt(num); + for (var v:variables) { + if (!v.shadowed && pred.test(v) && num-- == 0) return v; + } + throw new AssertionError(); + } + + /** + * Get a structure by name + * @param name Name of the structure + * @return The structure of null + */ + private TypeStruct getStruct(String name) { + for (var s:structs) { + if (s.name.equals(name)) return s; + } + for (var s:forwardStructs) if (s.name.equals(name)) return s; + return null; + } + + /** + * Generate a variable name. This might be new random name or a name from an outer scope. + * If the program is allowed to be invalid this can return keywords and already used variable names in the current scope. + * @return The variable name. + */ + private String getVarName() { + if (currScopeStart > 0 && random.nextInt(10) > 7) { + // Use a variable outside the current scope. + var v = variables.get(random.nextInt(currScopeStart)); + if (lookup(v.name) < currScopeStart) return v.name; + if (!generateValid) { + maybeInvalid = true; + return v.name; + } + } + // Generate a new random variable name + StringBuilder sb = getRandomName(); + var v = sb.toString(); + if (!generateValid && (KEYWORDS.contains(v) || lookup(v) >= currScopeStart)) { + maybeInvalid = true; + return v; + } + while (KEYWORDS.contains(v) || lookup(v) >= currScopeStart) { + sb.append(VAR_CHARS.charAt(random.nextInt(VAR_CHARS.length()))); + v = sb.toString(); + } + return v; + } + + private <T> T randFromList(List<T> list) { + return list.get(random.nextInt(list.size())); + } + + /** + * Get a random structure name + * @return A random structure name + */ + private String getStructName() { + if (!structs.isEmpty() && generateInvalid()) return randFromList(structs).name; + if (!forwardStructs.isEmpty() && generateInvalid()) return randFromList(forwardStructs).name; + + // Generate a new random struct name + StringBuilder sb = getRandomName(); + var v = sb.toString(); + if (!generateValid && (KEYWORDS.contains(v) || getStruct(v) != null)) { + maybeInvalid = true; + return v; + } + while (KEYWORDS.contains(v) || getStruct(v) != null) { + sb.append(VAR_CHARS.charAt(random.nextInt(VAR_CHARS.length()))); + v = sb.toString(); + } + return v; + } + + public TypeInt getIntType() { + return randFromList(INTTYPES); + } + + /** + * Get a random type + * @return A random type + */ + private Type getType(boolean allowForward) { + int t = random.nextInt(10); + if( t<5 || structs.isEmpty() ) return getIntType(); + if( t<7 ) return TYPE_FLT; + if (allowForward && random.nextInt(10)==0) { + int i=random.nextInt(forwardStructs.size()+1); + if (i>0) return forwardStructs.get(i-1).nullable; + var name = getStructName(); + var struct = new TypeStruct(name); + forwardStructs.add(struct); + return struct.nullable; + } + TypeStruct struct = randFromList(structs); + if (random.nextBoolean()) return struct.nullable; + return struct; + } + + private Type getType() { + return getType(false); + } + + /** + * Generates a program and writes it into the string builder supplied in the constructor. + * @return If the program is allowed to be invalid returns if something potentially invalid was generated. + */ + public boolean genProgram() { + var oldGenerateValid = generateValid; + if (!generateValid && random.nextBoolean()) generateValid = true; + this.maybeInvalid = false; + addVariable(ScopeNode.ARG0, TYPE_INT); + currScopeStart = variables.size(); + if ((genStatements() & FLAG_STOP) == 0) { + if (generateValid || random.nextInt(10)<7) { + genReturn(); + } else { + this.maybeInvalid = true; + } + } + generateValid = oldGenerateValid; + return !this.maybeInvalid; + } + + /** + * Generate a list of statements. + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the last statement generated + */ + public int genStatements() { + var num = random.nextInt(MAX_STATEMENTS_PER_BLOCK * (depth+1)); + for (int i=0; i<num; i++) { + printIndentation(); + var stop = genStatement(); + sb.append("\n"); + if ((stop & FLAG_STOP) != 0) return stop; + } + return 0; + } + + /** + * Generate a single statement + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the generated statement + */ + public int genStatement() { + return switch (random.nextInt(12)) { + case 0 -> allowStructs || generateInvalid() ? genStruct() : genAssignment(); + case 1 -> genBlock(); + case 2 -> genIf(); + case 3 -> genCountedLoop(); + case 4 -> genWhile(); + case 5, 6 -> genDecl(); + case 7, 8, 9 -> genAssignment(); + case 10 -> genNullCheck(); + default -> genExit(); + }; + } + + /** + * Generate a new structure + * @return 0 + */ + public int genStruct() { + int idx = random.nextInt(forwardStructs.size()+10); + TypeStruct struct; + if (idx < 10) { + var name = getStructName(); + struct = new TypeStruct(name); + forwardStructs.add(struct); + } else { + struct = forwardStructs.get(idx-10); + } + var fields = new TypeStruct.Field[generateInvalid() ? 0 : random.nextInt(10)]; + sb.append("struct ").append(struct.name).append(" {\n"); + indentation += INDENTATION; + for (int i=0; i<fields.length; i++) { + var fieldName = getRandomName(); + var type = getType(true); + printIndentation().append(type.name).append(" ").append(fieldName).append(";\n"); + fields[i] = new TypeStruct.Field(fieldName.toString(), type, struct); + } + indentation -= INDENTATION; + printIndentation().append("}"); + struct.fields = fields; + forwardStructs.remove(struct); + structs.add(struct); + return 0; + } + + /** + * Generate a statement for if, else and while blocks. + * This is special since it disallows declarations and prefers to generate blocks. + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the generated statement + */ + public int genStatementBlock() { + var oldAllowStructs = allowStructs; + allowStructs = false; + indentation += INDENTATION; + int res; + if (depth == 0) { + res = random.nextBoolean() ? genAssignment() : genExit(); + } else { + depth--; + res = switch (random.nextInt(12)) { + case 1, 2, 3, 4, 5 -> { + depth++; + indentation -= INDENTATION; + var ret = genBlock(); + indentation += INDENTATION; + depth--; + yield ret; + } + case 6 -> genIf(); + case 7 -> genCountedLoop(); + case 8 -> genWhile(); + case 9 -> genAssignment(); + case 10 -> genNullCheck(); + default -> genExit(); + }; + depth++; + } + indentation -= INDENTATION; + allowStructs = oldAllowStructs; + return res; + } + + /** + * Generate an exit. This can be return or break and continue when in a loop. + * @return FLAG_STOP + */ + public int genExit() { + if (loopDepth == 0 && generateValid) return genReturn(); + return switch (random.nextInt(7)) { + case 0,1,2 -> { + if (loopDepth == 0) maybeInvalid = true; + sb.append("continue;"); + yield FLAG_STOP; + } + case 3,4,5 -> { + if (loopDepth == 0) maybeInvalid = true; + sb.append("break;"); + yield FLAG_STOP; + } + default -> genReturn(); + }; + } + + /** + * Generate a block statement. After a certain depth only empty blocks are generated to ensure termination of the generator. + * @return flag FLAG_STOP for the generated statement + */ + public int genBlock() { + if (depth == 0) { + sb.append("{}"); + return 0; + } + var oldAllowStructs = allowStructs; + var oldCSS = currScopeStart; + allowStructs = false; + currScopeStart = variables.size(); + depth--; + sb.append("{\n"); + indentation += INDENTATION; + var stop = genStatements(); + indentation -= INDENTATION; + printIndentation().append("}"); + popVariables(currScopeStart); + depth++; + currScopeStart = oldCSS; + allowStructs = oldAllowStructs; + return stop & ~FLAG_IF_WITHOUT_ELSE; + } + + /** + * Generate an if statement with an optional else block. + * @return flags FLAG_STOP and FLAG_IF_WITHOUT_ELSE for the generated statement + */ + public int genIf() { + sb.append("if("); + genExpression(TYPE_BOOL, true); + sb.append(") "); + var stop = genStatementBlock(); + if ((stop & FLAG_IF_WITHOUT_ELSE) == 0 && random.nextInt(10) > 3) { + sb.append("\n"); + printIndentation().append("else "); + stop &= genStatementBlock(); + } else { + stop = FLAG_IF_WITHOUT_ELSE; + } + return stop; + } + + /** + * Generate a block with a null check + * if (nullable) { handle_nullable_as_non_nullable; } + */ + public int genNullCheck() { + var v = findVisibleVariablesMatching(va->va.declared instanceof TypeNullable); + if (v == null) return genIf(); + var n = (TypeNullable)v.declared; + boolean negate = random.nextBoolean(); + sb.append("if("); + if (negate) sb.append("!"); + sb.append(v.name).append(")"); + if (!negate) v.type = n.base; + var stop = genStatementBlock(); + v.type = n; + if ((stop & FLAG_IF_WITHOUT_ELSE) == 0 && random.nextInt(10) > 3) { + sb.append("\n"); + printIndentation().append("else "); + if (negate) v.type = n.base; + stop &= genStatementBlock(); + v.type = n; + } else { + stop = FLAG_IF_WITHOUT_ELSE; + } + return stop; + } + + /** + * Generate a while loop. + * @return 0 + */ + public int genWhile() { + sb.append("while("); + genExpression(TYPE_BOOL, true); + sb.append(") "); + loopDepth++; + genStatementBlock(); + loopDepth--; + return 0; + } + + /** + * Generate a counted loop of the form + * <code> + * { + * int varname = start_expr; + * while (varname < end_expr) loop_body; + * } + * </code> + * @return 0 + */ + public int genCountedLoop() { + if (depth == 0) return genWhile(); + var oldCSS = currScopeStart; + currScopeStart = variables.size(); + sb.append("{\n"); + indentation += INDENTATION; + String name = getVarName(); + printIndentation().append("int ").append(name).append("="); + genExpression(TYPE_INT, true); + sb.append(";\n"); + addVariable(name, TYPE_INT); + printIndentation().append("while(").append(name).append("<"); + genExpression(TYPE_INT, true); + sb.append(") {\n"); + indentation += INDENTATION; + depth--; + loopDepth++; + printIndentation().append(name).append("=").append(name).append("+"); + genExpression(TYPE_INT, true); + sb.append(";\n"); + genStatements(); + loopDepth--; + depth++; + indentation -= INDENTATION; + printIndentation().append("}\n"); + indentation -= INDENTATION; + printIndentation().append("}"); + popVariables(currScopeStart); + currScopeStart = oldCSS; + return 0; + } + + /** + * Generate a declaration statement. + * @return 0 + */ + public int genDecl() { + var type = getType(); + var name = getVarName(); + sb.append(generateInvalid() ? getRandomName() : type.name).append(" ").append(name); + if (!(type instanceof TypeNullable) || random.nextBoolean()) { + sb.append("="); + genExpression(type, true); + } + sb.append(";"); + addVariable(name, type); + return 0; + } + + /** + * Generate an assignment statement. + * @return 0 + */ + public int genAssignment() { + Type type; + Type declared; + if (generateInvalid()) { + sb.append(getRandomName()); + type = getType(); + declared = type; + } else { + var v = findVisibleVariablesMatching(va->true); + if (v == null) return genDecl(); + sb.append(v.name); + type = v.type; + declared = v.declared; + } + if (generateInvalid()) { + var name = getRandomName(); + sb.append(".").append(name); + declared = getType(); + } else if (type instanceof TypeStruct s && s.fields.length > 0 && random.nextBoolean()) { + var field = s.fields[random.nextInt(s.fields.length)]; + sb.append(".").append(field.name); + declared = field.type; + } + sb.append("="); + genExpression(declared, true); + sb.append(";"); + return 0; + } + + /** + * Generate a return statement. + * @return FLAG_STOP + */ + public int genReturn() { + var type = getType(); + sb.append("return "); + genExpression(type, true); + sb.append(";"); + return FLAG_STOP; + } + + /** + * Generate a binary expression. + * This method does not care about operator precedence. + */ + public void genExpression(Type type, boolean change) { + if (change && generateInvalid()) type = getType(); + if (!(type instanceof TypeInt) && type != TYPE_FLT) { + genUnary(type, false); + return; + } + var num = randLog(MAX_BINARY_EXPRESSIONS_PER_EXPRESSION); + while(num-->0) { + genUnary(type, false); + sb.append(BINARY_OP[random.nextInt(BINARY_OP.length)]); + } + genUnary(type, false); + } + + /** + * Generate a unary expression. + */ + public void genUnary(Type type, boolean change) { + if (change && generateInvalid()) type = getType(); + if (!(type instanceof TypeInt) && type != TYPE_FLT) { + genSuffix(type, false); + return; + } + var num = randLog(MAX_UNARY_EXPRESSIONS_PER_EXPRESSION); + while(num-->0) { + sb.append(UNARY_OP[random.nextInt(UNARY_OP.length)]); + } + genSuffix(type, false); + } + + public TypeStruct.Field getField(Type type) { + int n=0; + for (var s: structs) { + for (var f: s.fields) { + if (f.type.isa(type)) n++; + } + } + if (n==0) return null; + n = random.nextInt(n); + for (var s: structs) { + for (var f: s.fields) { + if (f.type.isa(type)) if (n--==0) return f; + } + } + throw new AssertionError(); + } + + /** + * Generate + */ + public void genSuffix(Type type, boolean change) { + genSuffixRecursive(type, change, MAX_SUFFIX_RECURSIVE_DEPTH); + } + + public void genSuffixRecursive(Type type, boolean change, int depth) { + if (change && generateInvalid()) type = getType(); + if (depth > 0 && random.nextBoolean()) { + if (generateInvalid()) { + var field = getRandomName(); + var t = getType(); + genSuffixRecursive(t, true, depth-1); + sb.append(".").append(field); + return; + } else { + var field = getField(type); + if (field != null) { + genSuffixRecursive(field.struct, true, depth-1); + sb.append(".").append(field.name); + return; + } + } + } + genPrimary(type, false); + } + + /** + * Generate a primary expression. + */ + public void genPrimary(Type type, boolean change) { + if (change && generateInvalid()) type = getType(); + var rand = random.nextInt(10); + if (rand == 0 && exprDepth != 0) { + sb.append("("); + exprDepth--; + genExpression(type, false); + exprDepth++; + sb.append(")"); + } else if (rand < 6) { + genVariable(type); + } else { + genConst(type); + } + } + + /** + * Generate a constant. + */ + public void genConst(Type type) { + if (generateInvalid()) type = getType(); + if (type instanceof TypeInt || (type == TYPE_FLT && random.nextBoolean())) { + var rand = random.nextInt(10); + switch (rand) { + case 0 -> sb.append("true"); + case 1 -> sb.append("false"); + default -> sb.append(random.nextInt(1<<(rand-2))); + } + } else if (type == TYPE_FLT) { + sb.append(random.nextFloat()); + } else if (type instanceof TypeNullable n) { + if ((n.base instanceof TypeStruct s && s.fields == null) || random.nextBoolean()) { + sb.append("null"); + } else { + sb.append("new ").append(generateInvalid() ? getRandomName() : n.base.name); + } + } else { + sb.append("new ").append(generateInvalid() ? getRandomName() : type.name); + } + } + + /** + * Generate a variable. If there are none generate a number instead. + * If the program is allowed to be invalid a random name can be generated in some cases. + */ + public void genVariable(Type type) { + if (generateInvalid()) { + sb.append(getRandomName()); + return; + } + if (generateInvalid()) type = getType(); + var t = type; + var v = findVisibleVariablesMatching(va->va.type.isa(t)); + if (v == null) genConst(type); + else sb.append(v.name); + } + +} @@ -36,6 +36,7 @@ <module>chapter15</module> <module>chapter16</module> <module>chapter17</module> + <module>chapter18</module> <module>transpile-tests</module> </modules> |
