diff options
| author | Cliff Click <cliffc@acm.org> | 2024-04-23 17:23:16 +0100 |
|---|---|---|
| committer | Cliff Click <cliffc@acm.org> | 2025-04-24 14:38:36 -0700 |
| commit | c15c5a3ef753b65f2d8a5bc253bfc8c4a1787f83 (patch) | |
| tree | e8744b1e9b83338f9409b4a1815da953d28e4237 /src/main/java | |
| parent | 489e86d923d7bc80cec353e08169b5bbeb9e0c00 (diff) | |
| download | Simple-c15c5a3ef753b65f2d8a5bc253bfc8c4a1787f83.tar.gz Simple-c15c5a3ef753b65f2d8a5bc253bfc8c4a1787f83.zip | |
Chapter 10: Structs and Memory
Co-authored-by: Thalia Archibald <thalia@archibald.dev>
Co-authored-by: Dibyendu Majumdar <mobile@majumdar.org.uk>
Co-authored-by: XmiliaH <45106915+XmiliaH@users.noreply.github.com>
Co-authored-by: tannal <tannal2409@gmail.com>
Co-authored-by: hadha <helsgithub15@gmail.com>
Co-authored-by: XmiliaH <xmilia.hermit@gmail.com>
Co-authored-by: Tamás Hadházy <85063808+Hels15@users.noreply.github.com>
Co-authored-by: RobertObkircher <robert.obkircher@gmail.com>
Co-authored-by: Robert Obkircher <robert.obkircher@gmail.com>
Diffstat (limited to 'src/main/java')
34 files changed, 1334 insertions, 359 deletions
diff --git a/src/main/java/com/seaofnodes/simple/GraphEvaluator.java b/src/main/java/com/seaofnodes/simple/GraphEvaluator.java deleted file mode 100644 index 9fc51c8e..00000000 --- a/src/main/java/com/seaofnodes/simple/GraphEvaluator.java +++ /dev/null @@ -1,181 +0,0 @@ -package com.seaofnodes.simple; - -import com.seaofnodes.simple.node.*; -import com.seaofnodes.simple.type.TypeInteger; - -import java.util.Arrays; -import java.util.BitSet; -import java.util.HashMap; - -public class GraphEvaluator { - - public enum ResultType { VALUE, FALLTHROUGH, TIMEOUT } - - public record Result(ResultType type, long value) {} - - /** - * 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 (node instanceof StartNode start) return start; - if( visit.get(node._nid) ) return null; - visit.set(node._nid); - for( Node def : node._inputs ) { - var res = findStart(visit,def); - if( res != null ) return res; - } - for( Node use : node._outputs ) { - var res = findStart(visit,use); - if( res != null ) return res; - } - return null; - } - - /** - * Find the control output from a control node - */ - private static Node findControl(Node control) { - for( Node use : control._outputs ) { - if (use.isCFG()) return use; - } - return null; - } - - /** - * Find the projection for a node - */ - private static ProjNode findProjection(Node node, int idx) { - for( Node use : node._outputs ) { - if (use instanceof ProjNode proj && proj._idx == idx) return proj; - } - return null; - } - - /** - * Cache values for phi and parameter projection nodes. - */ - private final HashMap<Node, Long> cacheValues = new HashMap<>(); - /** - * Cache for loop phis as they can depend on itself or other loop phis - */ - private long[] loopPhiCache = new long[16]; - - private GraphEvaluator() { - } - - private long div(DivNode div) { - long in2 = getValue(div.in(2)); - return in2 == 0 ? 0 : getValue(div.in(1)) / in2; - } - - /** - * Calculate the value of a node - */ - private long getValue(Node node) { - var cache = cacheValues.get(node); - if (cache != null) return cache; - return switch (node) { - case ConstantNode cons -> ((TypeInteger)cons.compute()).value(); - case AddNode add -> getValue(add.in(1)) + getValue(add.in(2)); - case BoolNode.EQ eq -> getValue(eq.in(1)) == getValue(eq.in(2)) ? 1 : 0; - case BoolNode.LE le -> getValue(le.in(1)) <= getValue(le.in(2)) ? 1 : 0; - case BoolNode.LT lt -> getValue(lt.in(1)) < getValue(lt.in(2)) ? 1 : 0; - case DivNode div -> div(div); - case MinusNode minus -> -getValue(minus.in(1)); - case MulNode mul -> getValue(mul.in(1)) * getValue(mul.in(2)); - case NotNode not -> getValue(not.in(1)) == 0 ? 1 : 0; - case SubNode sub -> getValue(sub.in(1)) - getValue(sub.in(2)); - default -> throw Utils.TODO("Unexpected node " + node); - }; - } - - /** - * Special case of latchPhis when phis can depend on phis of the same region. - */ - private void latchLoopPhis(RegionNode region, Node prev) { - int idx = Utils.find(region._inputs, prev); - assert idx > 0; - int i = 0; - for( Node use : region._outputs ) { - if (use instanceof PhiNode phi) { - var value = getValue(phi.in(idx)); - if (i == loopPhiCache.length) loopPhiCache = Arrays.copyOf(loopPhiCache, loopPhiCache.length*2); - loopPhiCache[i++] = value; - } - } - i = 0; - for( Node use : region._outputs ) { - if (use instanceof PhiNode phi) cacheValues.put(phi, loopPhiCache[i++]); - } - } - - /** - * Calculate the values of phis of the region and caches the values. The phis are not allowed to depend on other phis of the region. - */ - private void latchPhis(RegionNode region, Node prev) { - int idx = Utils.find(region._inputs, prev); - assert idx > 0; - for( Node use : region._outputs ) { - if (use instanceof PhiNode phi) { - var value = getValue(phi.in(idx)); - cacheValues.put(phi, value); - } - } - } - - /** - * Run the graph until either a return is found or the number of loop iterations are done. - */ - private Result evaluate(StartNode start, long parameter, int loops) { - var parameter1 = findProjection(start, 1); - if (parameter1 != null) cacheValues.put(parameter1, parameter); - Node control = findProjection(start, 0); - Node prev = start; - while (control != null) { - Node next; - switch (control) { - case RegionNode region -> { - if (region instanceof LoopNode && region.in(1) != prev) { - if (loops--<=0) return new Result(ResultType.TIMEOUT, 0); - latchLoopPhis(region, prev); - } else { - latchPhis(region, prev); - } - next = findControl(region); - } - case IfNode cond -> next = findProjection(cond, getValue(cond.in(1)) != 0 ? 0 : 1); - case ReturnNode ret -> { - return new Result(ResultType.VALUE, getValue(ret.in(1))); - } - case ProjNode ignored -> next = findControl(control); - default -> throw Utils.TODO("Unexpected control node " + control); - } - prev = control; - control = next; - } - return new Result(ResultType.FALLTHROUGH, 0); - } - - public static long evaluate(Node graph) { - return evaluate(graph, 0); - } - - public static long evaluate(Node graph, long parameter) { - return evaluate(graph, parameter, 1000); - } - - public static long evaluate(Node graph, long parameter, int loops) { - var res = evaluateWithResult(graph, parameter, loops); - if (res.type== ResultType.TIMEOUT) throw new RuntimeException("Timeout"); - return res.value; - } - - public static Result evaluateWithResult(Node graph, long parameter, int loops) { - var start = findStart(new BitSet(), graph); - if (start == null) return new Result(ResultType.TIMEOUT, 0); - var evaluator = new GraphEvaluator(); - return evaluator.evaluate(start, parameter, loops); - } - -} diff --git a/src/main/java/com/seaofnodes/simple/GraphVisualizer.java b/src/main/java/com/seaofnodes/simple/GraphVisualizer.java index b4d64d4c..cfe6d5cc 100644 --- a/src/main/java/com/seaofnodes/simple/GraphVisualizer.java +++ b/src/main/java/com/seaofnodes/simple/GraphVisualizer.java @@ -27,7 +27,7 @@ public class GraphVisualizer { // nodes in the graph. Collection<Node> all = findAll(stop, scope); StringBuilder sb = new StringBuilder(); - sb.append("digraph chapter09 {\n"); + sb.append("digraph chapter10 {\n"); sb.append("/*\n"); sb.append(stop._src); sb.append("\n*/\n"); @@ -39,8 +39,10 @@ public class GraphVisualizer { // 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"); + //sb.append("\tordering=\"in\";\n"); // Merge multiple edges hitting the same node. Makes common shared // nodes much prettier to look at. @@ -195,9 +197,14 @@ public class GraphVisualizer { } 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 - if( def.isCFG() ) + else if( def.isCFG() ) 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"); diff --git a/src/main/java/com/seaofnodes/simple/IRPrinter.java b/src/main/java/com/seaofnodes/simple/IRPrinter.java index c06ac9d0..f08f3208 100644 --- a/src/main/java/com/seaofnodes/simple/IRPrinter.java +++ b/src/main/java/com/seaofnodes/simple/IRPrinter.java @@ -2,14 +2,77 @@ package com.seaofnodes.simple; import com.seaofnodes.simple.node.LoopNode; import com.seaofnodes.simple.node.Node; +import com.seaofnodes.simple.node.ProjNode; import java.util.ArrayList; import java.util.BitSet; public class IRPrinter { - // Another bulk pretty-printer. Makes more effort at basic-block grouping. + // 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<3; i++ ) + sb.append(" "); + sb.append(" [[ "); + for( Node use : n._outputs ) + sb.append(use==null ? "____ " : "%4d ".formatted(use._nid)); + int lim = 5 - Math.max(n._inputs.size(),3); + 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 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 @@ -24,16 +87,16 @@ public class IRPrinter { Node n = rpos.get(i); if( n.isCFG() || n.isMultiHead() ) { if( !gap ) sb.append("\n"); // Blank before multihead - n._printLine(sb); // Print head + printLine( n, sb, llvmFormat ); // Print head while( --i >= 0 ) { Node t = rpos.get(i); if( !t.isMultiTail() ) { i++; break; } - t._printLine(sb); + printLine( t, sb, llvmFormat ); } sb.append("\n"); // Blank after multitail gap = true; } else { - n._printLine( sb ); + printLine( n, sb, llvmFormat ); gap = false; } } diff --git a/src/main/java/com/seaofnodes/simple/IterPeeps.java b/src/main/java/com/seaofnodes/simple/IterPeeps.java index 6dafd95f..1cee1ccb 100644 --- a/src/main/java/com/seaofnodes/simple/IterPeeps.java +++ b/src/main/java/com/seaofnodes/simple/IterPeeps.java @@ -1,8 +1,6 @@ package com.seaofnodes.simple; -import com.seaofnodes.simple.node.ConstantNode; -import com.seaofnodes.simple.node.Node; -import com.seaofnodes.simple.node.StopNode; +import com.seaofnodes.simple.node.*; import java.util.ArrayList; import java.util.Arrays; @@ -90,6 +88,8 @@ public abstract class IterPeeps { n.moveDepsToWorklist(); assert progressOnList(stop); // Very expensive assert } + if( n.isUnused() && !(n instanceof StopNode) ) + n.kill(); // Just plain dead } if( show ) diff --git a/src/main/java/com/seaofnodes/simple/Parser.java b/src/main/java/com/seaofnodes/simple/Parser.java index aabdf63a..fc84c9d9 100644 --- a/src/main/java/com/seaofnodes/simple/Parser.java +++ b/src/main/java/com/seaofnodes/simple/Parser.java @@ -45,14 +45,17 @@ public class Parser { /** * List of keywords disallowed as identifiers */ - private final HashSet<String> KEYWORDS = new HashSet<>(){{ + private static final HashSet<String> KEYWORDS = new HashSet<>(){{ add("break"); add("continue"); add("else"); add("false"); add("if"); add("int"); + add("new"); + add("null"); add("return"); + add("struct"); add("true"); add("while"); }}; @@ -67,9 +70,13 @@ public class Parser { ScopeNode _continueScope; ScopeNode _breakScope; + // Mapping from a Struct name to a Struct. + public static Map<String, TypeStruct> OBJS = new HashMap<>(); + public Parser(String source, TypeInteger arg) { Node.reset(); IterPeeps.reset(); + OBJS.clear(); _lexer = new Lexer(source); _scope = new ScopeNode(); _continueScope = _breakScope = null; @@ -98,8 +105,8 @@ public class Parser { _xScopes.push(_scope); // Enter a new scope for the initial control and arguments _scope.push(); - _scope.define(ScopeNode.CTRL, new ProjNode(START, 0, ScopeNode.CTRL).peephole()); - _scope.define(ScopeNode.ARG0, new ProjNode(START, 1, ScopeNode.ARG0).peephole()); + _scope.define(ScopeNode.CTRL, Type.CONTROL , new ProjNode(START, 0, ScopeNode.CTRL).peephole()); + _scope.define(ScopeNode.ARG0, TypeInteger.BOT, new ProjNode(START, 1, ScopeNode.ARG0).peephole()); parseBlock(); _scope.pop(); _xScopes.pop(); @@ -137,19 +144,61 @@ public class Parser { * @return a {@link Node} or {@code null} */ private Node parseStatement() { - if (matchx("return") ) return parseReturn(); - else if (matchx("int")) return parseDecl(); - else if (match ("{" )) return require(parseBlock(),"}"); - else if (matchx("if" )) return parseIf(); - else if (matchx("while")) return parseWhile(); - else if (matchx("break")) return parseBreak(); + if( false ) return null; + else if (matchx("return") ) return parseReturn(); + else if (matchx("int") ) return parseDecl(TypeInteger.BOT); + else if (match ("{") ) return require(parseBlock(),"}"); + else if (matchx("if") ) return parseIf(); + else if (matchx("while") ) return parseWhile(); + 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 + else if (matchx(";") ) return null; // Empty statement + // declarations of vars with struct type are handled in parseExpressionStatement due + // to ambiguity else return parseExpressionStatement(); } /** + * Parse a struct field. + * <pre> + * int IDENTIFIER ; + * </pre> + */ + private Field parseField(String sname) { + if( matchx("int") ) // Currently only parsing "int" type fields + return require(Field.make(requireId().intern(),TypeInteger.BOT),";"); + throw errorSyntax("A field type is expected, only type 'int' is supported at present"); + } + + /** + * 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(); + if ( OBJS.containsKey(typeName)) throw errorSyntax("struct '" + typeName + "' cannot be redefined"); + ArrayList<Field> fields = new ArrayList<>(); + require("{"); + while (!peek('}') && !_lexer.isEOF()) { + Field field = parseField(typeName); + if (fields.contains(field)) throw errorSyntax("Field '" + field + "' already defined in struct '" + typeName + "'"); + fields.add(field); + } + require("}"); + // Build and install the TypeStruct + TypeStruct ts = TypeStruct.make(typeName, fields); + OBJS.put(typeName, ts); // Insert the struct name in the collection of all struct names + START.addMemProj(ts, _scope); // Insert memory edges + return parseStatement(); + } + + /** * Parses a while statement * * <pre> @@ -241,7 +290,7 @@ public class Parser { 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 + // "continue" if (toScope == null) return cur; // toScope is either the break scope, or a scope that was created here @@ -266,7 +315,7 @@ public class Parser { private Node parseIf() { require("("); // Parse predicate - var pred = require(parseExpression(), ")"); + var pred = require(parseExpression(), ")").keep(); // IfNode takes current control and predicate Node ifNode = new IfNode(ctrl(), pred).peephole(); // Setup projection nodes @@ -280,6 +329,7 @@ public class Parser { // Parse the true side ctrl(ifT.unkeep()); // set ctrl token to ifTrue projection + _scope.upcast(ifT,pred,false); // Up-cast predicate parseStatement(); // Parse true-side ScopeNode tScope = _scope; @@ -287,9 +337,11 @@ public class Parser { _scope = fScope; // Restore scope, then parse else block if any ctrl(ifF.unkeep()); // Ctrl token is now set to ifFalse projection if (matchx("else")) { + _scope.upcast(ifF,pred,true); // Up-cast predicate parseStatement(); fScope = _scope; } + pred.unkeep(); if( tScope.nIns() != ndefs || fScope.nIns() != ndefs ) throw error("Cannot define a new name on one arm of an if"); @@ -313,7 +365,7 @@ public class Parser { */ private Node parseReturn() { var expr = require(parseExpression(), ";"); - Node ret = STOP.addReturn(new ReturnNode(ctrl(), expr).peephole()); + Node ret = STOP.addReturn(new ReturnNode(ctrl(), expr, _scope).peephole()); ctrl(new ConstantNode(Type.XCONTROL).peephole()); // Kill control return ret; } @@ -328,40 +380,86 @@ public class Parser { } /** - * Parses an expression statement + * Parses an expression statement or a declaration statement where type is a struct * * <pre> - * name '=' expression ';' + * name; // Error + * type name; // Define name with default initial value + * type name = expr; // Define name with given initial value + * name = expr; // Reassign existing + * expr // Something else * </pre> * @return an expression {@link Node}, never {@code null} */ private Node parseExpressionStatement() { - var name = requireId(); - require("="); - var expr = require(parseExpression(), ";"); - if( _scope.update(name, expr)==null ) - throw error("Undefined name '" + name + "'"); + int old = _lexer._position; + Type t = type(); + String name = requireId(); + Node expr; + if( match(";") ) { // Assign a default value + // No type and no expr is an error + if( t==null ) throw errorSyntax("expression"); + expr = new ConstantNode(t.makeInit()).peephole(); + } else if( match("=") ) { // Assign "= expr;" + expr = require(parseExpression(), ";"); + } else { // Neither, so just a normal expression parse + _lexer._position = old; + return require(parseExpression(),";"); + } + + // Defining a new variable vs updating an old one + if( t != null ) { + if( _scope.define(name,t,expr) == null ) + throw error("Redefining name '" + name + "'"); + } else { + Node n = _scope.lookup(name); + t = _scope.lookupDeclaredType(name); + if( n==null ) + throw error("Undefined name '" + name + "'"); + _scope.update(name,expr); + } + if( !expr._type.isa(t) ) + throw error("Type " + expr._type.str() + " is not of declared type " + t.str()); return expr; } + // Parse a type-or-null + private Type type() { + int old = _lexer._position; + String tname = _lexer.matchId(); + if( tname==null ) return null; + if( tname.equals("int") ) return TypeInteger.BOT; + TypeStruct obj = OBJS.get(tname); + if( obj != null ) + return TypeMemPtr.make(obj,match("?")); + // Not a type; unwind the parse + _lexer._position = old; + return null; + } + /** * Parses a declStatement * * <pre> - * 'int' name = expression ';' + * type name = expression ';' * </pre> - * @return an expression {@link Node}, never {@code null} + * @return an expression {@link Node} */ - private Node parseDecl() { - // Type is 'int' for now + private Node parseDecl(Type t) { var name = requireId(); - require("="); - var expr = require(parseExpression(), ";"); - if( _scope.define(name,expr) == null ) + var expr = match(";") + // Assign a null value + ? new ConstantNode(t.makeInit()).peephole() + // Assign "= expr;" + : require(require("=").parseExpression(), ";"); + if( !expr._type.isa(t) ) + throw error("Type " + expr._type.str() + " is not of declared type " + t.str()); + if( _scope.define(name,t,expr) == null ) throw error("Redefining name '" + name + "'"); return expr; } + /** * Parse an expression of the form: * @@ -448,20 +546,21 @@ public class Parser { * Parse a unary minus expression. * * <pre> - * unaryExpr : ('-') unaryExpr | primaryExpr + * unaryExpr : ('-') | '!') unaryExpr | postfixExpr | primaryExpr * </pre> * @return a unary expression {@link Node}, never {@code null} */ private Node parseUnary() { if (match("-")) return new MinusNode(parseUnary()).peephole(); - return parsePrimary(); + if (match("!")) return new NotNode(parseUnary()).peephole(); + return parsePostfix(parsePrimary()); } /** * Parse a primary expression: * * <pre> - * primaryExpr : integerLiteral | Identifier | true | false | '(' expression ')' + * primaryExpr : integerLiteral | Identifier | true | false | null | new Identifier | '(' expression ')' * </pre> * @return a primary {@link Node}, never {@code null} */ @@ -470,6 +569,13 @@ public class Parser { if( match("(") ) return require(parseExpression(), ")"); if( matchx("true" ) ) return new ConstantNode(TypeInteger.constant(1)).peephole(); if( matchx("false") ) return new ConstantNode(TypeInteger.constant(0)).peephole(); + if( matchx("null" ) ) return new ConstantNode(TypeMemPtr.NULLPTR).peephole(); + if( matchx("new") ) { + String structName = requireId(); + TypeStruct obj = OBJS.get(structName); + if( obj == null) throw errorSyntax("Unknown struct type '" + structName + "'"); + return newStruct(obj); + } String name = _lexer.matchId(); if( name == null) throw errorSyntax("an identifier or expression"); Node n = _scope.lookup(name); @@ -478,6 +584,61 @@ public class Parser { } /** + * Return a NewNode but also generate instructions to initialize it. + */ + private Node newStruct( TypeStruct obj ) { + Node n = new NewNode(TypeMemPtr.make(obj), ctrl()).peephole().keep(); + Node initValue = new ConstantNode(TypeInteger.constant(0)).peephole(); + int alias = START._aliasStarts.get(obj._name); + for( Field field : obj._fields ) { + memAlias(alias, new StoreNode(field._fname, alias, memAlias(alias), n, initValue).peephole()); + alias++; + } + return n.unkeep(); + } + + // 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.lookup(memName(alias) ); } + private Node memAlias(int alias, Node st) { return _scope.update(memName(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 ] + * </pre> + */ + private Node parsePostfix(Node expr) { + if( !match(".") ) return expr; + + if( !(expr._type instanceof TypeMemPtr ptr) ) + throw error("Expected struct reference but got " + expr._type.str()); + + String name = requireId().intern(); + int idx = ptr._obj==null ? -1 : ptr._obj.find(name); + if( idx == -1 ) throw error("Accessing unknown field '" + name + "' from '" + ptr.str() + "'"); + int alias = START._aliasStarts.get(ptr._obj._name)+idx; + + if( match("=") ) { + // Disambiguate "obj.fld==x" boolean test from "obj.fld=x" field assignment + if( peek('=') ) _lexer._position--; + else { + Node val = parseExpression(); + memAlias(alias, new StoreNode(name, alias, memAlias(alias), expr, val).peephole()); + return expr; // "obj.a = expr" returns the expression while updating memory + } + } + + Type declaredType = ptr._obj._fields[idx]._type; + return parsePostfix(new LoadNode(name, alias, declaredType, memAlias(alias), expr).peephole()); + } + + /** * Parse integer literal * * <pre> @@ -497,6 +658,7 @@ public class Parser { private boolean matchx(String syntax) { return _lexer.matchx(syntax); } // 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(); } // Require and return an identifier private String requireId() { @@ -505,9 +667,11 @@ public class Parser { throw error("Expected an identifier, found '"+id+"'"); } + + // Require an exact match - private void require(String syntax) { require(null, syntax); } - private <N extends Node> N require(N n, String syntax) { + 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); } @@ -594,6 +758,8 @@ public class Parser { 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; @@ -606,10 +772,14 @@ public class Parser { return peek()==ch; } + boolean peekIsId() { + skipWhiteSpace(); + return isIdStart(peek()); + } + // Return an identifier or null String matchId() { - skipWhiteSpace(); - return isIdStart(peek()) ? parseId() : null; + return peekIsId() ? parseId() : null; } // Used for errors diff --git a/src/main/java/com/seaofnodes/simple/Utils.java b/src/main/java/com/seaofnodes/simple/Utils.java index 45f15327..4f2af769 100644 --- a/src/main/java/com/seaofnodes/simple/Utils.java +++ b/src/main/java/com/seaofnodes/simple/Utils.java @@ -36,4 +36,30 @@ public class Utils { 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); } + + public static boolean eq(String s0, String s1) { + if( s0==s1 ) return true; + assert s0==s0.intern(); + assert s1==s1.intern(); + return false; + } } diff --git a/src/main/java/com/seaofnodes/simple/node/AddNode.java b/src/main/java/com/seaofnodes/simple/node/AddNode.java index 4e30bb55..2cc0b465 100644 --- a/src/main/java/com/seaofnodes/simple/node/AddNode.java +++ b/src/main/java/com/seaofnodes/simple/node/AddNode.java @@ -132,7 +132,7 @@ public class AddNode extends Node { 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,ns).peephole(); + 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); } diff --git a/src/main/java/com/seaofnodes/simple/node/BoolNode.java b/src/main/java/com/seaofnodes/simple/node/BoolNode.java index d3fcec95..9c15f01b 100644 --- a/src/main/java/com/seaofnodes/simple/node/BoolNode.java +++ b/src/main/java/com/seaofnodes/simple/node/BoolNode.java @@ -2,6 +2,7 @@ package com.seaofnodes.simple.node; import com.seaofnodes.simple.type.Type; import com.seaofnodes.simple.type.TypeInteger; +import com.seaofnodes.simple.type.TypeMemPtr; import java.util.BitSet; @@ -44,10 +45,25 @@ abstract public class BoolNode extends Node { if( in(1)==in(2) ) return new ConstantNode(TypeInteger.constant(doOp(3,3)?1:0)); + // 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 ) + return new EQ(in(2),in(1)); + // Equals sorts by NID otherwise: non.high == non.low becomes non.low == non.high + else if( in(1)._nid > in(2)._nid ) + return new EQ(in(2),in(1)); + } + // Equals X==0 becomes a !X + if( (in(2)._type == TypeInteger.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,false); + Node phicon = AddNode.phiCon(this,this instanceof EQ); if( phicon!=null ) return phicon; return null; diff --git a/src/main/java/com/seaofnodes/simple/node/CastNode.java b/src/main/java/com/seaofnodes/simple/node/CastNode.java new file mode 100644 index 00000000..fec540f7 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/node/CastNode.java @@ -0,0 +1,38 @@ +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 + 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/src/main/java/com/seaofnodes/simple/node/ConstantNode.java b/src/main/java/com/seaofnodes/simple/node/ConstantNode.java index 2012a30a..e4c084d4 100644 --- a/src/main/java/com/seaofnodes/simple/node/ConstantNode.java +++ b/src/main/java/com/seaofnodes/simple/node/ConstantNode.java @@ -51,8 +51,4 @@ public class ConstantNode extends Node { @Override int hash() { return _con.hashCode(); } - - // Dead control is its own idom root - Node idom() { return null; } - } diff --git a/src/main/java/com/seaofnodes/simple/node/IfNode.java b/src/main/java/com/seaofnodes/simple/node/IfNode.java index 460dce51..1cf4ddaf 100644 --- a/src/main/java/com/seaofnodes/simple/node/IfNode.java +++ b/src/main/java/com/seaofnodes/simple/node/IfNode.java @@ -1,15 +1,16 @@ 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; public class IfNode extends MultiNode { public IfNode(Node ctrl, Node pred) { super(ctrl, pred); + IterPeeps.add(this); // Because idoms are complex, just add it } @Override diff --git a/src/main/java/com/seaofnodes/simple/node/LoadNode.java b/src/main/java/com/seaofnodes/simple/node/LoadNode.java new file mode 100644 index 00000000..53ae1096 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/node/LoadNode.java @@ -0,0 +1,78 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.Field; + +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 { + + Type _declaredType; + /** + * Load a value from a ptr.field. + * + * @param name The field we are loading + * @param memSlice The memory alias node - this is updated after a Store + * @param memPtr The ptr to the struct from where we load a field + */ + public LoadNode(String name, int alias, Type glb, Node memSlice, Node memPtr) { + super(name, alias, memSlice, memPtr, null); + _declaredType = glb; + } + + @Override + public String label() { return "Load"; } + + @Override + public String glabel() { return "."+_name; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { return sb.append(".").append(_name); } + + @Override + public Type compute() { + return _declaredType; + } + + @Override + public Node idealize() { + + // Simple Load-after-Store on same address. + if( mem() instanceof StoreNode st && + ptr() == st.ptr() ) { // Must check same object + assert Utils.eq(_name,st._name); // Equiv class aliasing is perfect + return st.val(); + } + + // 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 ) { + // 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 = new LoadNode(_name,_alias,_declaredType,memphi.in(1),ptr()).peephole(); + Node ld2 = new LoadNode(_name,_alias,_declaredType,memphi.in(2),ptr()).peephole(); + return new PhiNode(_name,_type,memphi.region(),ld1,ld2); + } + } + + return null; + } + + // Profitable if we find a matching Store on this Phi arm. + private boolean profit(PhiNode phi, int idx) { + Node px = phi.in(idx); + return px!=null && px.addDep(this) instanceof StoreNode st1 && ptr()==st1.ptr(); + } +} diff --git a/src/main/java/com/seaofnodes/simple/node/LoopNode.java b/src/main/java/com/seaofnodes/simple/node/LoopNode.java index c192bc20..ea1489c4 100644 --- a/src/main/java/com/seaofnodes/simple/node/LoopNode.java +++ b/src/main/java/com/seaofnodes/simple/node/LoopNode.java @@ -25,5 +25,7 @@ public class LoopNode extends RegionNode { return inProgress() ? null : super.idealize(); } + // Bypass Region idom, same as the default idom() using use entry in(1) instead of in(0) + @Override int idepth() { return _idepth(1); } @Override Node idom() { return entry(); } } diff --git a/src/main/java/com/seaofnodes/simple/node/MemOpNode.java b/src/main/java/com/seaofnodes/simple/node/MemOpNode.java new file mode 100644 index 00000000..08e08bbf --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/node/MemOpNode.java @@ -0,0 +1,40 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Field; +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; + + public MemOpNode(String name, int alias, Node memSlice, Node memPtr, Node value) { + super(null, memSlice, memPtr, value); + _name = name; + _alias = alias; + } + + public Node mem() { return in(1); } + public Node ptr() { return in(2); } + + @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; + return (ptr==Type.BOTTOM || (ptr instanceof TypeMemPtr tmp && tmp._nil) ) + ? "Might be null accessing '" + _name + "'" + : null; + } +} diff --git a/src/main/java/com/seaofnodes/simple/node/MinusNode.java b/src/main/java/com/seaofnodes/simple/node/MinusNode.java index dd092c9e..9b687613 100644 --- a/src/main/java/com/seaofnodes/simple/node/MinusNode.java +++ b/src/main/java/com/seaofnodes/simple/node/MinusNode.java @@ -26,5 +26,11 @@ public class MinusNode extends Node { } @Override - public Node idealize() { return null; } + public Node idealize() { + // -(-x) is x + if( in(1) instanceof MinusNode minus ) + return minus.in(1); + + return null; + } } diff --git a/src/main/java/com/seaofnodes/simple/node/NewNode.java b/src/main/java/com/seaofnodes/simple/node/NewNode.java new file mode 100644 index 00000000..352689b5 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/node/NewNode.java @@ -0,0 +1,40 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeMemPtr; + +import java.util.BitSet; + +public class NewNode extends Node { + + TypeMemPtr _ptr; + + public NewNode(TypeMemPtr ptr, Node ctrl) { + super(ctrl); + this._ptr = ptr; + } + + @Override + public String label() { return "new"; } + + @Override + public String glabel() { return "new " + _ptr._obj._name; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("new "); + return sb.append(_ptr._obj.str()); + } + + @Override + public Type compute() { return _ptr; } + + @Override + public Node idealize() { return null; } + + @Override + boolean eq(Node n) { return this == n; } + + @Override + int hash() { return _ptr.hashCode(); } +} diff --git a/src/main/java/com/seaofnodes/simple/node/Node.java b/src/main/java/com/seaofnodes/simple/node/Node.java index 5eb9c076..bb698860 100644 --- a/src/main/java/com/seaofnodes/simple/node/Node.java +++ b/src/main/java/com/seaofnodes/simple/node/Node.java @@ -51,15 +51,6 @@ public abstract class Node { /** - * 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>} - */ - int _idepth; - - /** * 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. @@ -81,7 +72,11 @@ public abstract class Node { public abstract String label(); // Unique label for graph visualization, e.g. "Add12" or "Region30" or "EQ99" - public String uniqueName() { return label() + _nid; } + 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(); } @@ -118,31 +113,6 @@ public abstract class Node { // Every Node implements this; a partial-line recursive print abstract StringBuilder _print1(StringBuilder sb, BitSet visited); - - // 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 void _printLine(StringBuilder sb ) { - sb.append("%4d %-7.7s ".formatted(_nid,label())); - if( _inputs==null ) { - sb.append("DEAD\n"); - return; - } - for( Node def : _inputs ) - sb.append(def==null ? "____ " : "%4d ".formatted(def._nid)); - for( int i = _inputs.size(); i<3; i++ ) - sb.append(" "); - sb.append(" [[ "); - for( Node use : _outputs ) - sb.append(use==null ? "____ " : "%4d ".formatted(use._nid)); - int lim = 5 - Math.max(_inputs.size(),3); - for( int i = _outputs.size(); i<lim; i++ ) - sb.append(" "); - sb.append(" ]] "); - if( _type!= null ) _type._print(sb); - sb.append("\n"); - } - public String p(int depth) { return IRPrinter.prettyPrint(this,depth); } public boolean isMultiHead() { return false; } @@ -167,6 +137,8 @@ public abstract class Node { public boolean isCFG() { return false; } + public boolean isMem() { return false; } + /** * 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 @@ -197,6 +169,7 @@ public abstract class Node { old_def.kill(); // Kill old def // Set the new_def over the old (killed) edge _inputs.set(idx,new_def); + moveDepsToWorklist(); // Return self for easy flow-coding return new_def; } @@ -283,7 +256,12 @@ public abstract class Node { // 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; } + public <N extends Node> N unkeep() { + delUse(null); + return (N)this; + } + // Test "keep" status + public boolean iskeep() { return Utils.find(_outputs,null) != -1; } // Replace self with nnn in the graph, making 'this' go dead @@ -345,7 +323,7 @@ public abstract class Node { Type old = setType(compute()); // Replace constant computations from non-constants with a constant node - if (!(this instanceof ConstantNode) && _type.isHighOrConst() ) + if( !(this instanceof ConstantNode) && _type.isHighOrConst() ) return new ConstantNode(_type).peepholeOpt(); // Global Value Numbering @@ -380,7 +358,7 @@ public abstract class Node { 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() ) { + 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(). @@ -478,9 +456,9 @@ public abstract class Node { ArrayList<Node> _deps; /** - * Add a node to the list o 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. + * 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 @@ -567,14 +545,11 @@ public abstract class Node { } /** - * 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. + * 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++ ) @@ -585,19 +560,29 @@ public abstract class Node { return true; } - // Return the immediate dominator of this Node and compute dom tree depth. - Node idom() { - Node idom = in(0); - if( idom._idepth==0 ) idom.idom(); // Recursively set _idepth - if( _idepth==0 ) _idepth = idom._idepth+1; - return idom; - } + + /** + * Immediate dominator tree depth, used to approximate a real IDOM depth + * 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; // IDOM depth approx; Zero is unset; non-zero is cached legit + final int _idepth(int idx) { return _idepth==0 ? (_idepth=in(idx).idepth()+1) : _idepth; } + int idepth() { return _idepth(0); } + + // Return the immediate dominator of this Node. + Node idom() { return in(0); } // 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. diff --git a/src/main/java/com/seaofnodes/simple/node/NotNode.java b/src/main/java/com/seaofnodes/simple/node/NotNode.java index 7a520fec..05e44eb0 100644 --- a/src/main/java/com/seaofnodes/simple/node/NotNode.java +++ b/src/main/java/com/seaofnodes/simple/node/NotNode.java @@ -1,8 +1,7 @@ package com.seaofnodes.simple.node; -import com.seaofnodes.simple.type.Type; -import com.seaofnodes.simple.type.TypeInteger; - +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.*; import java.util.BitSet; public class NotNode extends Node { @@ -20,9 +19,24 @@ public class NotNode extends Node { @Override public Type compute() { - if( in(1)._type instanceof TypeInteger i0 ) + Type t0 = in(1)._type; + switch( t0 ) { + case TypeInteger i0: return i0.isConstant() ? TypeInteger.constant(i0.value()==0 ? 1 : 0) : i0; - return TypeInteger.TOP.meet(in(1)._type); + 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.TOP ) return TypeInteger.TOP; + if( p0 == TypeMemPtr.NULLPTR ) return TypeInteger.constant(1); + if( !p0._nil ) return TypeInteger.constant(0); + return TypeInteger.BOT; + case Type t: + if( t0.getClass() != Type.class ) + // Only doing NOT on ints and ptrs + throw Utils.TODO(); + return t0==Type.TOP ? Type.TOP : Type.BOTTOM; + } } @Override diff --git a/src/main/java/com/seaofnodes/simple/node/PhiNode.java b/src/main/java/com/seaofnodes/simple/node/PhiNode.java index ec4c6ad3..dd67bd06 100644 --- a/src/main/java/com/seaofnodes/simple/node/PhiNode.java +++ b/src/main/java/com/seaofnodes/simple/node/PhiNode.java @@ -1,6 +1,8 @@ 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; @@ -8,7 +10,11 @@ public class PhiNode extends Node { final String _label; - public PhiNode(String label, Node... inputs) { super(inputs); _label = 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_"+_label; } @@ -31,17 +37,21 @@ public class PhiNode extends Node { Node region() { return in(0); } @Override public boolean isMultiTail() { return true; } + @Override + public boolean isMem() { return _declaredType instanceof TypeMem; } @Override public Type compute() { if( !(region() instanceof RegionNode r) ) return region()._type==Type.XCONTROL ? Type.TOP : _type; - if( r.inProgress() ) return Type.BOTTOM; - Type t = Type.TOP; + // 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.glb().dual(); 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 && in(i) != this ) + if( r.in(i).addDep(this)._type != Type.XCONTROL ) t = t.meet(in(i)._type); return t; } @@ -71,11 +81,35 @@ public class PhiNode extends Node { lhss[i] = in(i).in(1); rhss[i] = in(i).in(2); } - Node phi_lhs = new PhiNode(_label,lhss).peephole(); - Node phi_rhs = new PhiNode(_label,rhss).peephole(); + 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( region().idom() instanceof IfNode iff && iff.pred().addDep(this)==val ) { + // Must walk the idom on the null side to make sure we hit False. + Node idom = region().in(nullx); + while( idom.in(0) != iff ) idom = idom.idom(); + if( idom instanceof ProjNode proj && proj._idx==1 ) + return val; + } + } + } + return null; } diff --git a/src/main/java/com/seaofnodes/simple/node/ProjNode.java b/src/main/java/com/seaofnodes/simple/node/ProjNode.java index 0ed9441d..735fcdf3 100644 --- a/src/main/java/com/seaofnodes/simple/node/ProjNode.java +++ b/src/main/java/com/seaofnodes/simple/node/ProjNode.java @@ -1,6 +1,7 @@ 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; @@ -27,6 +28,7 @@ public class ProjNode extends Node { @Override public boolean isCFG() { return _idx==0 || ctrl() instanceof IfNode; } @Override public boolean isMultiTail() { return in(0).isMultiHead(); } + @Override public boolean isMem() { return _type instanceof TypeMem; } public MultiNode ctrl() { return (MultiNode)in(0); } @@ -38,8 +40,14 @@ public class ProjNode extends Node { @Override public Node idealize() { - if( ctrl()._type instanceof TypeTuple tt && tt._types[1-_idx]==Type.XCONTROL ) // Only true for IfNodes - return ctrl().in(0); // We become our input control + if ( ctrl() instanceof IfNode iff ) { + if ( iff._type instanceof TypeTuple tt && tt._types[1 - _idx] == Type.XCONTROL ) + return iff.in(0); // We become our input control + + // Flip a negating if-test, to remove the not + if( iff.pred().addDep(this) instanceof NotNode not ) + return new ProjNode((MultiNode)new IfNode(iff.ctrl(),not.in(1)).peephole(),1-_idx,_idx==0 ? "False" : "True"); + } return null; } diff --git a/src/main/java/com/seaofnodes/simple/node/RegionNode.java b/src/main/java/com/seaofnodes/simple/node/RegionNode.java index c949c2b2..42501118 100644 --- a/src/main/java/com/seaofnodes/simple/node/RegionNode.java +++ b/src/main/java/com/seaofnodes/simple/node/RegionNode.java @@ -35,6 +35,7 @@ public class RegionNode extends Node { @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 @@ -51,17 +52,25 @@ public class RegionNode extends Node { while( nouts != nOuts() ) { nouts = nOuts(); for( int i=0; i<nOuts(); i++ ) - if( out(i) instanceof PhiNode phi && phi.nIns()==nIns() ) + if( out(i) instanceof PhiNode phi && phi.nIns()==nIns() ) { phi.delDef(path); + IterPeeps.addAll(phi._outputs); + } } - _idom = null; // Clear idom cache return isDead() ? new ConstantNode(Type.XCONTROL) : delDef(path); } // If down to a single input, become that input - if( nIns()==2 && !hasPhi() ) { - _idom = null; // Clear idom cache + 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 ProjNode p1 && + in(2) instanceof ProjNode p2 && + p1.in(0)==p2.in(0) && + p1.in(0) instanceof IfNode iff ) + return iff.ctrl(); + return null; } @@ -80,26 +89,28 @@ public class RegionNode extends Node { } // Immediate dominator of Region is a little more complicated. - private Node _idom; // Immediate dominator cache + @Override int idepth() { + if( _idepth!=0 ) return _idepth; + int d=0; + for( Node n : _inputs ) + if( n!=null ) + d = Math.max(d,n.idepth()); + return _idepth=d; + } + @Override Node idom() { - if( _idom != null ) { - if( _idom.isDead() ) _idom=null; - else return _idom; // Return cached copy - } if( nIns()==2 ) return in(1); // 1-input is that one input if( nIns()!=3 ) return null; // Fails for anything other than 2-inputs - // Walk the LHS & RHS idom trees in parallel until they match, or either fails - Node lhs = in(1).idom(); - Node rhs = in(2).idom(); + // 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. + Node lhs = in(1); + Node rhs = in(2); while( lhs != rhs ) { if( lhs==null || rhs==null ) return null; - var comp = lhs._idepth - rhs._idepth; + var comp = lhs.idepth() - rhs.idepth(); if( comp >= 0 ) lhs = lhs.idom(); if( comp <= 0 ) rhs = rhs.idom(); } - if( lhs==null ) return null; - _idepth = lhs._idepth+1; - if( !IterPeeps.midAssert() ) _idom=lhs; return lhs; } diff --git a/src/main/java/com/seaofnodes/simple/node/ReturnNode.java b/src/main/java/com/seaofnodes/simple/node/ReturnNode.java index 922a3649..92bda5bf 100644 --- a/src/main/java/com/seaofnodes/simple/node/ReturnNode.java +++ b/src/main/java/com/seaofnodes/simple/node/ReturnNode.java @@ -15,8 +15,15 @@ import java.util.BitSet; */ public class ReturnNode extends Node { - public ReturnNode(Node ctrl, Node data) { + public ReturnNode(Node ctrl, Node data, ScopeNode scope) { super(ctrl, data); + // We lookup memory slices by the naming convention that they start with $ + // We could also use implicit knowledge that all memory projects are at offset >= 2 + String[] names = scope.reverseNames(); + for (String name: names) { + if (!name.equals("$ctrl") && name.startsWith("$")) + addDef(scope.lookup(name)); + } } public Node ctrl() { return in(0); } @@ -27,7 +34,9 @@ public class ReturnNode extends Node { @Override StringBuilder _print1(StringBuilder sb, BitSet visited) { - return expr()._print0(sb.append("return "), visited).append(";"); + sb.append("return "); + expr()._print0(sb, visited); + return sb.append(";"); } @Override public boolean isCFG() { return true; } diff --git a/src/main/java/com/seaofnodes/simple/node/ScopeNode.java b/src/main/java/com/seaofnodes/simple/node/ScopeNode.java index 3abea54d..843ce733 100644 --- a/src/main/java/com/seaofnodes/simple/node/ScopeNode.java +++ b/src/main/java/com/seaofnodes/simple/node/ScopeNode.java @@ -2,6 +2,8 @@ package com.seaofnodes.simple.node; import com.seaofnodes.simple.IterPeeps; import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.TypeMemPtr; import java.util.*; @@ -23,10 +25,16 @@ public class ScopeNode extends Node { */ public final Stack<HashMap<String, Integer>> _scopes; + /** + * Tracks declared types for every name + */ + public Stack<HashMap<String, Type>> _types; + // A new ScopeNode public ScopeNode() { _scopes = new Stack<>(); + _types = new Stack<>(); _type = Type.BOTTOM; } @@ -69,14 +77,15 @@ public class ScopeNode extends Node { @Override public Node idealize() { return null; } - public void push() { _scopes.push(new HashMap<>()); } - public void pop() { popN(_scopes.pop().size()); } + public void push() { _scopes.push(new HashMap<>()); _types.push(new HashMap<>()); } + public void pop() { popN(_scopes.pop().size()); _types.pop(); } /** * Create a new name in the current scope */ - public Node define( String name, Node n ) { + public Node define( String name, Type declaredType, Node n ) { HashMap<String,Integer> syms = _scopes.lastElement(); + _types.lastElement().put(name,declaredType); if( syms.put(name,nIns()) != null ) return null; // Double define return addDef(n); @@ -97,7 +106,7 @@ public class ScopeNode extends Node { public Node update( String name, Node n ) { return update(name,n,_scopes.size()-1); } /** * Both recursive lookup and update. - * + * <p> * A shared implementation allows us to create lazy phis both during * lookups and updates; the lazy phi creation is part of chapter 8. * @@ -120,12 +129,21 @@ public class ScopeNode extends Node { // 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(idx,new PhiNode(name,loop.ctrl(),loop.update(name,null,nestingLevel),null).peephole()); + : loop.setDef(idx,new PhiNode(name, lookupDeclaredType(name),loop.ctrl(),loop.update(name,null,nestingLevel),null).peephole()); setDef(idx,old); } return n==null ? old : setDef(idx,n); // Not lazy, so this is the answer } + // Return declared type + public Type lookupDeclaredType( String name ) { + for( int i=_types.size(); i>0; i-- ) { + Type t = _types.get(i-1).get(name); + if( t != null ) return t; + } + return null; + } + public Node ctrl() { return in(0); } /** @@ -162,8 +180,10 @@ public class ScopeNode extends Node { // 3) Ensure that the order of defs is the same to allow easy merging for( HashMap<String,Integer> syms : _scopes ) dup._scopes.push(new HashMap<>(syms)); + for( HashMap<String,Type> ts : _types ) + dup._types.push(ts); // Types don't change, just keep stacks aligned - dup.addDef(ctrl()); // Control input is just copied + dup.addDef(ctrl()); // Control input is just copied for( int i=1; i<nIns(); i++ ) // For lazy phis on loops we use a sentinel // that will trigger phi creation on update @@ -187,8 +207,9 @@ public class ScopeNode extends Node { 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 - setDef(i, new PhiNode(ns[i], r, this.lookup(ns[i]), that.lookup(ns[i])).peephole()); + setDef(i, new PhiNode(ns[i], this.lookupDeclaredType(ns[i]), r, this.lookup(ns[i]), that.lookup(ns[i])).peephole()); that.kill(); // Kill merged scope + IterPeeps.add(r); return r.unkeep().peephole(); } @@ -216,11 +237,61 @@ public class ScopeNode extends Node { IterPeeps.addAll(phi._outputs); phi.moveDepsToWorklist(); if( in != phi ) { - phi.subsume(in); + if( !phi.iskeep() ) // Keeping phi around for parser elsewhere + phi.subsume(in); setDef(i,in); // Set the update back into Scope } } } } + + + // 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. + + // This Scope looks for direct variable uses, or certain simple + // combinations, and replaces the variable with the upcast variant. + public Node upcast( Node ctrl, Node pred, boolean invert ) { + if( ctrl._type==Type.XCONTROL ) return null; + // Invert the If conditional + if( invert ) + pred = pred instanceof NotNode not ? not.in(1) : IterPeeps.add(new NotNode(pred).peephole()); + + // Direct use of a value as predicate. This is a zero/null test. + if( Utils.find(_inputs, pred) != -1 ) { + if( !(pred._type instanceof TypeMemPtr tmp) ) + // Must be an `int`, since int and ptr are the only two value types + // being tested. No representation for a generic not-null int, so no upcast. + return null; + if( tmp.isa(TypeMemPtr.VOIDPTR) ) + return null; // Already not-null, no reason to upcast + // Upcast the ptr to not-null ptr, and replace in scope + return replace(pred,new CastNode(TypeMemPtr.VOIDPTR,ctrl,pred).peephole()); + } + + if( pred instanceof NotNode not ) { + // Direct use of a !value as predicate. This is a zero/null test. + if( Utils.find(_inputs, not.in(1)) != -1 ) { + Type tinit = not.in(1)._type.makeInit(); + if( not.in(1)._type.isa(tinit) ) return null; // Already zero/null, no reason to upcast + return replace(not.in(1), new ConstantNode(tinit).peephole()); + } + } + // Apr/9/2024: Attempted to replace X with Y if guarded by a test of + // X==Y. This didn't seem to help very much, or at least in the test + // cases seen so far was a very minor help. + + // No upcast + return null; + } + + 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/src/main/java/com/seaofnodes/simple/node/StartNode.java b/src/main/java/com/seaofnodes/simple/node/StartNode.java index e399138b..4b7e02a8 100644 --- a/src/main/java/com/seaofnodes/simple/node/StartNode.java +++ b/src/main/java/com/seaofnodes/simple/node/StartNode.java @@ -1,25 +1,58 @@ package com.seaofnodes.simple.node; -import com.seaofnodes.simple.type.Type; -import com.seaofnodes.simple.type.TypeTuple; - +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.*; +import java.util.Arrays; import java.util.BitSet; +import java.util.HashMap; /** - * The Start node represents the start of the function. For now, we do not - * have any inputs to Start because our function does not yet accept - * parameters. When we add parameters the value of Start will be a tuple, and - * will require Projections to extract the values. We discuss this in detail - * in Chapter 9: Functions and Calls. + * 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 MultiNode { - final TypeTuple _args; + // This field is NOT final, because the tuple expands as we add memory aliases + TypeTuple _args; + + // The alias number of the first field in the struct. + // + public final HashMap<String,Integer> _aliasStarts; + public StartNode(Type[] args) { super(); _args = TypeTuple.make(args); _type = _args; + _aliasStarts = new HashMap<>(); + } + + /** + * Creates a projection for each of the struct's fields, using the field alias + * as the key. + */ + public void addMemProj( TypeStruct ts, ScopeNode scope) { + int len = _args._types.length; + _aliasStarts.put(ts._name,len); + + // resize the tuple's type array to include all fields of the struct + int max = len + ts._fields.length; + Type[] args = Arrays.copyOf(_args._types, max); + + // The new members of the tuple get a mem type with an alias + for( int alias = len; alias < max; alias++ ) + args[alias] = TypeMem.make(alias); + _type = _args = TypeTuple.make(args); + // For each of the fields we now add a mem projection. Note that the + // alias matches the slot of the field in the tuple + for( int alias = len; alias < max; alias++ ) { + String name = Parser.memName(alias); + Node n = new ProjNode(this, alias, name).peephole(); + scope.define(name, args[alias], n); + } } @Override @@ -40,7 +73,6 @@ public class StartNode extends MultiNode { public Node idealize() { return null; } // No immediate dominator, and idepth==0 - @Override - Node idom() { return null; } - + @Override int idepth() { return 0; } + @Override Node idom() { return null; } } diff --git a/src/main/java/com/seaofnodes/simple/node/StopNode.java b/src/main/java/com/seaofnodes/simple/node/StopNode.java index 602feffc..3b5a7ce3 100644 --- a/src/main/java/com/seaofnodes/simple/node/StopNode.java +++ b/src/main/java/com/seaofnodes/simple/node/StopNode.java @@ -51,10 +51,17 @@ public class StopNode extends Node { return null; } + @Override public Node idom() { return null; } + public Node addReturn(Node node) { return addDef(node); } - public StopNode iterate( ) { return IterPeeps.iterate(this,false); } - public StopNode iterate(boolean show) { return IterPeeps.iterate(this,show ); } + public StopNode iterate( ) { return IterPeeps.iterate(this,false).typeCheck(); } + public StopNode iterate(boolean show) { return IterPeeps.iterate(this,show ).typeCheck(); } + StopNode typeCheck() { + String err = walk( Node::err ); + if( err != null ) throw new RuntimeException(err); + return this; + } } diff --git a/src/main/java/com/seaofnodes/simple/node/StoreNode.java b/src/main/java/com/seaofnodes/simple/node/StoreNode.java new file mode 100644 index 00000000..8d264601 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/node/StoreNode.java @@ -0,0 +1,70 @@ +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 { + + /** + * @param name The struct field we are assigning to + * @param memSlice The memory alias node - this is updated after a Store + * @param memPtr The ptr to the struct where we will store a value + * @param value Value to be stored + */ + public StoreNode(String name, int alias, Node memSlice, Node memPtr, Node value) { + super(name, alias, memSlice, memPtr, value); + } + + @Override + public String label() { return "Store"; } + @Override + public String glabel() { return "."+_name+" ="; } + @Override + public boolean isMem() { return true; } + public Node val() { return in(3); } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return sb.append(".").append(_name).append("=").append( val()).append(";"); + } + + @Override + public Type compute() { return TypeMem.make(_alias); } + + @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 + 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. + st.checkNoUseBeyond(this) ) { + assert Utils.eq(_name,st._name); // Equiv class aliasing is perfect + setDef(1,st.mem()); + return this; + } + + return null; + } + + // Check that `this` has no uses beyond `that` + private boolean checkNoUseBeyond(Node that) { + if( 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 : _outputs ) + if( use != that ) + use.addDep(that); + return false; + } + +} diff --git a/src/main/java/com/seaofnodes/simple/node/SubNode.java b/src/main/java/com/seaofnodes/simple/node/SubNode.java index f661be14..b87115cd 100644 --- a/src/main/java/com/seaofnodes/simple/node/SubNode.java +++ b/src/main/java/com/seaofnodes/simple/node/SubNode.java @@ -35,6 +35,14 @@ public class SubNode extends Node { @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; } diff --git a/src/main/java/com/seaofnodes/simple/type/Field.java b/src/main/java/com/seaofnodes/simple/type/Field.java new file mode 100644 index 00000000..56626482 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/type/Field.java @@ -0,0 +1,60 @@ +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; + + private Field(String fname, Type type ) { + super(TFLD); + _fname = fname; + _type = type; + } + // Make with existing alias + public static Field make( String fname, Type type ) { + return new Field(fname,type).intern(); + } + + public static final Field TEST = make("test",TypeInteger.ZERO); + 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); + return make(_fname,_type.meet(fld._type)); + } + + @Override + public Field dual() { return make(_fname,_type.dual()); } + + @Override + public Field glb() { + return make(_fname,_type.glb()); + } + + // Override in subclasses + int hash() { return _fname.hashCode() ^ _type.hashCode(); } + + boolean eq(Type t) { + Field f = (Field)t; + return Utils.eq(_fname,f._fname) && _type==f._type; + } + + + @Override + public StringBuilder _print( StringBuilder sb ) { + return _type._print(sb.append(_fname).append(":")); + } + + @Override public String str() { return _fname; } +} diff --git a/src/main/java/com/seaofnodes/simple/type/Type.java b/src/main/java/com/seaofnodes/simple/type/Type.java index d0265e83..aa0ba1ea 100644 --- a/src/main/java/com/seaofnodes/simple/type/Type.java +++ b/src/main/java/com/seaofnodes/simple/type/Type.java @@ -2,6 +2,7 @@ package com.seaofnodes.simple.type; import com.seaofnodes.simple.Utils; +import java.util.ArrayList; import java.util.HashMap; /** @@ -33,6 +34,10 @@ public class Type { static final byte TSIMPLE = 4; // End of the Simple Types static final byte TINT = 5; // All Integers; see TypeInteger static final byte TTUPLE = 6; // Tuples; finite collections of unrelated Types, kept in parallel + static final byte TMEM = 7; // All memory (alias 0) or A slice of memory - with specific alias + static final byte TMEMPTR = 8; // Memory pointer type + static final byte TSTRUCT = 9; // Structs; tuples with named fields + static final byte TFLD =10; // Fields into struct public final byte _type; @@ -44,6 +49,21 @@ public class Type { 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); + 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 isHighOrConst() { return _type==TTOP || _type==TXCTRL; } @@ -52,12 +72,26 @@ public class Type { // Excludes both high and low values public boolean isConstant() { return false; } - public StringBuilder _print(StringBuilder sb) {return is_simple() ? sb.append(STRS[_type]) : sb;} + /** + * Display Type name in a format that's good for IR printer + */ + public StringBuilder typeName( StringBuilder sb) { return _print(sb); } + + public Type makeInit() { return null; } // ---------------------------------------------------------- + // 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 performance. + // Factory method which interns "this" - protected <T extends Type> T intern() { + public <T extends Type> T intern() { T nnn = (T)INTERN.get(this); if( nnn==null ) INTERN.put(nnn=(T)this,this); @@ -95,13 +129,13 @@ public class Type { // 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 xmeet(t); // Mixing 2 unrelated types + 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()'. - protected Type xmeet(Type t) { + 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; @@ -112,17 +146,6 @@ public class Type { return _type==TCTRL || t._type==TCTRL ? CONTROL : XCONTROL; } - // True if this "isa" t; e.g. 17 isa TypeInteger.BOT - public boolean isa( Type t ) { return meet(t)==t; } - - // ---------------------------------------------------------- - // 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(); - } - public Type dual() { return switch( _type ) { case TBOT -> TOP; @@ -134,8 +157,31 @@ public class Type { } // ---------------------------------------------------------- + // 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 ? XCONTROL : BOTTOM; } + + // ---------------------------------------------------------- + // 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/src/main/java/com/seaofnodes/simple/type/TypeInteger.java b/src/main/java/com/seaofnodes/simple/type/TypeInteger.java index ba045603..f2a93a3a 100644 --- a/src/main/java/com/seaofnodes/simple/type/TypeInteger.java +++ b/src/main/java/com/seaofnodes/simple/type/TypeInteger.java @@ -1,5 +1,7 @@ package com.seaofnodes.simple.type; +import java.util.ArrayList; + /** * Integer Type */ @@ -28,6 +30,10 @@ public class TypeInteger extends Type { public static TypeInteger constant(long con) { return make(true, con); } + public static void gather(ArrayList<Type> ts) { ts.add(ZERO); ts.add(BOT); } + + // 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("IntTop"); @@ -35,6 +41,22 @@ public class TypeInteger extends Type { return sb.append(_con); } + @Override public String str() { + if( this==TOP ) return "~int"; + if( this==BOT ) return "int"; + return ""+_con; + } + + /** + * 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 isHighOrConst() { return _is_con || _con==0; } @@ -65,6 +87,11 @@ public class TypeInteger extends Type { } @Override + public Type glb() { return BOT; } + + @Override public TypeInteger makeInit() { return ZERO; } + + @Override int hash() { return (int)(_con ^ (_is_con ? 0 : 0x4000)); } @Override public boolean eq( Type t ) { diff --git a/src/main/java/com/seaofnodes/simple/type/TypeMem.java b/src/main/java/com/seaofnodes/simple/type/TypeMem.java new file mode 100644 index 00000000..198d49ee --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/type/TypeMem.java @@ -0,0 +1,64 @@ +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. + private final int _alias; + + private TypeMem(int alias) { super(TMEM); _alias = alias; } + + public static TypeMem make(int alias) { return new TypeMem(alias).intern(); } + public static final TypeMem TOP = make( 0); + public static final TypeMem BOT = make(-1); + + + public static void gather(ArrayList<Type> ts) { ts.add(make(1)); ts.add(BOT); } + + @Override + TypeMem xmeet(Type t) { + TypeMem that = (TypeMem) t; // Invariant: TypeMem and unequal + return _alias==0 ? that : (that._alias==0 ? this : BOT); + } + + @Override + public Type dual() { + if( _alias== 0 ) return BOT; + if( _alias==-1 ) return TOP; + return this; + } + + @Override + public Type glb() { return TypeMem.BOT; } + + @Override + int hash() { return 9876543 + _alias; } + + @Override + boolean eq(Type t) { + TypeMem that = (TypeMem) t; // Invariant + return _alias == that._alias; + } + + @Override + public StringBuilder _print(StringBuilder sb) { + return sb.append("MEM#").append( switch(_alias) { + case 0 -> "TOP"; + case -1 -> "BOT"; + default -> ""+_alias; + }); + } + + @Override public String str() { return _print(new StringBuilder()).toString(); } +} diff --git a/src/main/java/com/seaofnodes/simple/type/TypeMemPtr.java b/src/main/java/com/seaofnodes/simple/type/TypeMemPtr.java new file mode 100644 index 00000000..9392da20 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/type/TypeMemPtr.java @@ -0,0 +1,78 @@ +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 structs. + * Pointers can be to specific struct 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 one of + // (null,TypeStruct). + // where nil is one of + // (true,false) meaning an explicit null is allowed or not + + public final TypeStruct _obj; // null, a TypeStruct, or sentinel TypeStruct.MANY + public final boolean _nil; + + private TypeMemPtr(TypeStruct obj, boolean nil) { + super(TMEMPTR); + _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 TypeMemPtr.make(obj, false); } + + public static final TypeMemPtr BOT = make(TypeStruct.BOT,true); + public static final TypeMemPtr TOP = BOT.dual(); + public static final TypeMemPtr NULLPTR = make(TypeStruct.TOP,true); + public static final TypeMemPtr VOIDPTR = NULLPTR.dual(); // A bottom mix of not-null ptrs, like C's void* but not null + public static final 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==null ? null : _obj.dual(), !_nil); } + + @Override + public Type glb() { + if( _obj==null ) return BOT; + return make(_obj.glb(),true); + } + @Override public TypeMemPtr makeInit() { return NULLPTR; } + + @Override + int hash() { return (_obj==null ? 0xDEADBEEF : _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/src/main/java/com/seaofnodes/simple/type/TypeStruct.java b/src/main/java/com/seaofnodes/simple/type/TypeStruct.java new file mode 100644 index 00000000..29102675 --- /dev/null +++ b/src/main/java/com/seaofnodes/simple/type/TypeStruct.java @@ -0,0 +1,121 @@ +package com.seaofnodes.simple.type; + +import com.seaofnodes.simple.Utils; +import java.util.ArrayList; + +/** + * Represents a struct type. + */ +public class TypeStruct extends Type { + + // For now in terms of the lattice + // a struct type just stays as is + + public final String _name; + public final Field[] _fields; + + private TypeStruct(String name, Field[] fields) { + super(Type.TSTRUCT); + _name = name; + _fields = fields; + } + + public static TypeStruct make(String name, Field[] fields) { return new TypeStruct(name, fields).intern(); } + public static TypeStruct make(String name, ArrayList<Field> fields) { return make(name,fields.toArray(new Field[fields.size()])); } + + 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}); + public static void gather(ArrayList<Type> ts) { ts.add(TEST); ts.add(BOT); } + + public int find(String fname) { + for( int i=0; i<_fields.length; i++ ) + if( _fields[i]._fname.equals(fname) ) + 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 + // Now all fields should be the same, so just do field meets + assert _fields.length == that._fields.length; + Field[] flds = new Field[_fields.length]; + for( int i=0; i<_fields.length; i++ ) + flds[i] = (Field)_fields[i].meet(that._fields[i]); + return make(_name,flds); + } + + @Override + public TypeStruct dual() { + if( this==TOP ) return BOT; + if( this==BOT ) return TOP; + 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() { + for( Field f : _fields ) + if( f.glb() != f ) + return false; + return true; + } + + @Override + boolean eq(Type t) { + TypeStruct ts = (TypeStruct)t; // Invariant + if( !_name.equals(ts._name) ) + 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(); + for( Field f : _fields ) hash = Utils.rot(hash,13) ^ f.hashCode(); + return Utils.fold(hash); + } + + @Override + public StringBuilder _print(StringBuilder sb) { + sb.append(_name).append(" {\n"); + for( Field f : _fields ) { + sb.append(" ").append(f._fname).append(":"); + f._type._print(sb); + sb.append(";\n"); + } + return sb.append("}"); + } + + @Override public String str() { return _name; } +} diff --git a/src/main/java/com/seaofnodes/simple/type/TypeTuple.java b/src/main/java/com/seaofnodes/simple/type/TypeTuple.java index e82ea00b..d57f6c98 100644 --- a/src/main/java/com/seaofnodes/simple/type/TypeTuple.java +++ b/src/main/java/com/seaofnodes/simple/type/TypeTuple.java @@ -1,5 +1,7 @@ package com.seaofnodes.simple.type; +import java.util.ArrayList; + public class TypeTuple extends Type { public final Type[] _types; @@ -7,8 +9,11 @@ public class TypeTuple extends Type { private TypeTuple(Type[] types) { super(TTUPLE); _types = types; } public static TypeTuple make(Type... types) { return new TypeTuple(types).intern(); } + private static TypeTuple TEST = make(TypeInteger.BOT,TypeMemPtr.TEST); + public static void gather(ArrayList<Type> ts) { ts.add(TEST); } + @Override - public Type xmeet(Type other) { + Type xmeet(Type other) { TypeTuple tt = (TypeTuple)other; // contract from xmeet assert _types.length == tt._types.length; Type[] ts = new Type[_types.length]; @@ -25,6 +30,14 @@ public class TypeTuple extends Type { } @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 ) @@ -34,6 +47,21 @@ public class TypeTuple extends Type { return sb; } + @Override public String str() { return _print(new StringBuilder()).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); + sb.append("]"); + return sb; + } + 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}); |