diff options
Diffstat (limited to 'chapter05/src/main/java/com')
21 files changed, 1654 insertions, 0 deletions
diff --git a/chapter05/src/main/java/com/seaofnodes/simple/GraphVisualizer.java b/chapter05/src/main/java/com/seaofnodes/simple/GraphVisualizer.java new file mode 100644 index 00000000..f73bfd3c --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/GraphVisualizer.java @@ -0,0 +1,199 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeControl; + +import java.util.*; + +/** + * 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 { + + public String generateDotOutput(Parser parser) { + + // Since the graph has cycles, we need to create a flat list of all the + // nodes in the graph. + Collection<Node> all = findAll(parser); + StringBuilder sb = new StringBuilder(); + sb.append("digraph chapter04 {\n"); + sb.append("/*\n"); + sb.append(parser.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 + + // Just the Nodes first, in a cluster no edges + nodes(sb, all); + + // Now the scopes, in a cluster no edges + scopes(sb, parser._scope); + + // Walk the Node edges + nodeEdges(sb, all); + + // Walk the Scope edges + scopeEdges(sb, parser._scope); + + sb.append("}\n"); + return sb.toString(); + } + + + private void nodes(StringBuilder sb, Collection<Node> all) { + // Just the Nodes first, in a cluster no edges + sb.append("\tsubgraph cluster_Nodes {\n"); // Magic "cluster_" in the subgraph name + for( Node n : all ) { + if( n instanceof ProjNode ) + continue; // Do not emit, rolled into MultiNode already + sb.append("\t\t").append(n.uniqueName()).append(" [ "); + String lab = n.label(); + 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; + 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("\""); + if( proj._idx==0 ) sb.append(" BGCOLOR=\"yellow\""); + sb.append(">").append(proj.label()).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 Control ) + sb.append("shape=box style=filled fillcolor=yellow "); + sb.append("label=\"").append(lab).append("\" "); + } + sb.append("];\n"); + } + sb.append("\t}\n"); // End Node cluster + } + + private void scopes( StringBuilder sb, ScopeNode scopenode) { + sb.append("\tnode [shape=plaintext];\n"); + int level=0; + for( HashMap<String,Integer> scope : scopenode._scopes ) { + sb.append("\tsubgraph cluster_").append(level).append(" {\n"); // Magic "cluster_" in the subgraph name + String scopeName = makeScopeName(level); + 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>"); + for( String name : scope.keySet() ) + sb.append("<TD PORT=\"").append(makePortName(scopeName, name)).append("\">").append(name).append("</TD>"); + sb.append("</TR>\n"); + sb.append("\t\t\t</TABLE>>];\n"); + level++; + } + // 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( level ) ); // End all Scope clusters + } + + private String makeScopeName(int level) { return "scope" + level; } + private String makePortName(String scopeName, String varName) { return scopeName + "_" + varName; } + + private boolean isControlEdge(Node def) { + return def._type instanceof TypeControl; + } + + // Walk the node edges + private void nodeEdges(StringBuilder sb, Collection<Node> all) { + for( Node n : all ) { + if( n instanceof ConstantNode || n instanceof ProjNode ) + continue; // Do not display the Constant->Start edge; ProjNodes handled by Multi + for( Node def : n._inputs ) + if( def != null ) { + sb.append('\t').append(n.uniqueName()).append(" -> "); + if( def instanceof ProjNode proj ) { + String mname = proj.ctrl().uniqueName(); + sb.append(mname).append(":p").append(proj._idx); + } else sb.append(def.uniqueName()); + // Control edges are colored red + if( isControlEdge(def) ) + sb.append(" [color=red]"); + sb.append(";\n"); + } + } + } + + // Walk the scope edges + private void scopeEdges( StringBuilder sb, ScopeNode scopenode ) { + sb.append("\tedge [style=dashed color=cornflowerblue];\n"); + int level=0; + for( HashMap<String,Integer> scope : scopenode._scopes ) { + String scopeName = makeScopeName(level); + for( String name : scope.keySet() ) { + Node def = scopenode.in(scope.get(name)); + if( def==null ) continue; + sb.append("\t") + .append(scopeName).append(":") + .append('"').append(makePortName(scopeName, name)).append('"') // wrap port name with quotes because $ctrl is not valid unquoted + .append(" -> "); + if( def instanceof ProjNode proj ) { + String mname = proj.ctrl().uniqueName(); + sb.append(mname).append(":p").append(proj._idx); + } else sb.append(def.uniqueName()); + sb.append(";\n"); + } + level++; + } + } + + /** + * Finds all nodes in the graph. + */ + private Collection<Node> findAll(Parser parser) { + final StartNode start = Parser.START; + final HashMap<Integer, Node> all = new HashMap<>(); + for( Node n : start._outputs ) + walk(all, n); + // Scan symbol tables + for( HashMap<String,Integer> scope : parser._scope._scopes ) + for (Integer i : scope.values()) + walk(all, parser._scope.in(i)); + 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) + if (c != null) + walk(all, c); + for (Node c : n._outputs) + if (c != null) + walk(all, c); + } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/Parser.java b/chapter05/src/main/java/com/seaofnodes/simple/Parser.java new file mode 100644 index 00000000..147515f6 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/Parser.java @@ -0,0 +1,397 @@ +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; + + private final Lexer _lexer; + + /** + * Stack of lexical scopes, each scope is a symbol table that binds + * variable names to Nodes. The top of this stack represents current scope. + */ + public ScopeNode _scope; + + public Parser(String source, TypeInteger arg) { + _lexer = new Lexer(source); + _scope = new ScopeNode(); + Node.reset(); + START = new StartNode(new Type[]{ Type.CONTROL, arg }); + START.peephole(); + } + + public Parser(String source) { + this(source, TypeInteger.BOT); + } + + String src() { return new String( _lexer._input ); } + + + + public ReturnNode parse() { + _scope.push(); + try { + _scope.define("$ctrl", new ProjNode(START, 0, "$ctrl").peephole()); + _scope.define("arg" , new ProjNode(START, 1, "arg" ).peephole()); + return (ReturnNode) parseBlock(); + } + finally { + _scope.pop(); + } + } + + /** + * Parses a block + * + * <pre> + * '{' statements '}' + * </pre> + */ + private Node parseBlock() { + // Enter a new scope + _scope.push(); + Node n = null; + while (!match("}") && !_lexer.isEOF()) { + Node n0 = parseStatement(); + if (n0 != null) n = n0; // Allow null returns from eg showGraph + } + // Exit scope + _scope.pop(); + return n; + } + + /** + * Parses a statement + * + * <pre> + * returnStatement | declStatement | blockStatement | expressionStatement + * </pre> + */ + private Node parseStatement() { + if (match("return")) return parseReturn(); + else if (match("int")) return parseDecl(); + else if (match("{")) return parseBlock(); + else if (match("#showGraph")) return showGraph(); + else return parseExpressionStatement(); + } + + /** + * Parses a return statement; "return" already parsed. + * The $ctrl edge is killed. + * + * <pre> + * 'return' expr ; + * </pre> + */ + private Node parseReturn() { + var expr = require(parseExpression(), ";"); + Node ret = new ReturnNode(_scope.lookup("$ctrl"), expr); + _scope.update("$ctrl",null); + return ret; + } + + /** + * Dumps out the node graph + */ + private Node showGraph() { + require(";"); + System.out.println(new GraphVisualizer().generateDotOutput(this)); + return null; + } + + /** + * Parses an expression statement + * + * <pre> + * name '=' expression ';' + * </pre> + */ + private Node parseExpressionStatement() { + var name = requireId(); + require("="); + var expr = require(parseExpression(), ";"); + if( _scope.update(name, expr)==null ) + throw error("Undefined name '" + name + "'"); + return expr; + } + + /** + * Parses a declStatement + * + * <pre> + * 'int' name = expression ';' + * </pre> + */ + private Node parseDecl() { + // Type is 'int' for now + var name = requireId(); + require("="); + var expr = require(parseExpression(), ";"); + if( _scope.define(name,expr) == null ) + throw error("Redefining name '" + name + "'"); + return expr; + } + + /** + * Parse an expression of the form: + * + * <pre> + * expr : additiveExpr + * </pre> + */ + private Node parseExpression() { return parseComparison(); } + + private Node parseComparison() { + var lhs = parseAddition(); + if (match("==")) return new BoolNode.EQNode(lhs, parseComparison()).peephole(); + if (match("!=")) return new BoolNode.NENode(lhs, parseComparison()).peephole(); + if (match("<" )) return new BoolNode.LTNode(lhs, parseComparison()).peephole(); + if (match("<=")) return new BoolNode.LENode(lhs, parseComparison()).peephole(); + if (match(">" )) return new BoolNode.GTNode(lhs, parseComparison()).peephole(); + if (match(">=")) return new BoolNode.GENode(lhs, parseComparison()).peephole(); + return lhs; + } + + /** + * Parse an additive expression + * + * <pre> + * additiveExpr : multiplicativeExpr (('+' | '-') multiplicativeExpr)* + * </pre> + */ + private Node parseAddition() { + var lhs = parseMultiplication(); + if (match("+")) return new AddNode(lhs, parseAddition()).peephole(); + if (match("-")) return new SubNode(lhs, parseAddition()).peephole(); + return lhs; + } + + /** + * Parse an multiplicativeExpr expression + * + * <pre> + * multiplicativeExpr : unaryExpr (('*' | '/') unaryExpr)* + * </pre> + */ + private Node parseMultiplication() { + var lhs = parseUnary(); + if (match("*")) return new MulNode(lhs, parseMultiplication()).peephole(); + if (match("/")) return new DivNode(lhs, parseMultiplication()).peephole(); + return lhs; + } + + /** + * Parse a unary minus expression. + * + * <pre> + * unaryExpr : ('-') unaryExpr | primaryExpr + * </pre> + */ + private Node parseUnary() { + if (match("-")) return new MinusNode(parseUnary()).peephole(); + return parsePrimary(); + } + + /** + * Parse a primary expression: + * + * <pre> + * primaryExpr : integerLiteral | Identifier | '(' expression ')' + * </pre> + */ + private Node parsePrimary() { + if (_lexer.isNumber()) return parseIntegerLiteral(); + if (match("(")) return require(parseExpression(), ")"); + String name = requireId(); + Node id = _scope.lookup(name); + if( id==null ) + throw error("Undefined name '" + name + "'"); + return id.peephole(); + } + + /** + * Parse integer literal + * + * <pre> + * integerLiteral: [1-9][0-9]* | [0] + * </pre> + */ + private ConstantNode parseIntegerLiteral() { + return (ConstantNode) new ConstantNode(_lexer.parseNumber()).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); } + + // Require and return an identifier + private String requireId() { + String id = _lexer.matchId(); + if (id != null) return id; + throw error("identifier"); + } + + // Require an exact match + private void require(String syntax) { require(null, syntax); } + private Node require(Node n, String syntax) { + if (match(syntax)) return n; + throw errorSyntax(syntax); + } + + RuntimeException errorSyntax(String syntax) { + return error("Syntax error, expected " + syntax + ": " + _lexer.getAnyNextToken()); + } + + 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]; + } + + 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 (isWhiteSpace()) _position++; + } + + + // 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; + } + + // Return an identifier or null + String matchId() { + skipWhiteSpace(); + return isIdStart(peek()) ? parseId() : null; + } + + // Used for errors + String getAnyNextToken() { + if (isEOF()) return ""; + if (isIdStart(peek())) return parseId(); + if (isPunctuation(peek())) return parsePunctuation(); + return String.valueOf(peek()); + } + + boolean isNumber() {return isNumber(peek());} + boolean isNumber(char ch) {return Character.isDigit(ch);} + + private Type parseNumber() { + int start = _position; + while (isNumber(nextChar())) ; + String snum = new String(_input, start, --_position - start); + if (snum.length() > 1 && snum.charAt(0) == '0') + throw error("Syntax error: integer values cannot start with '0'"); + return TypeInteger.constant(Long.parseLong(snum)); + } + + // 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; + if (isPunctuation(nextChar())) ; + return new String(_input, start, --_position - start); + } + } + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/AddNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/AddNode.java new file mode 100644 index 00000000..8b157a9c --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/AddNode.java @@ -0,0 +1,72 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.*; + +public class AddNode extends Node { + public AddNode(Node lhs, Node rhs) { + super(null, lhs, rhs); + } + + @Override + public String label() { return "Add"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + in(1)._print0(sb.append("(")); + in(2)._print0(sb.append("+")); + return sb.append(")"); + } + + + @Override + public Type compute() { + if( in(1)._type instanceof TypeInteger i0 && + in(2)._type instanceof TypeInteger i1 ) { + if (i0.isConstant() && i1.isConstant()) + return TypeInteger.constant(i0.value()+i1.value()); + return i0.meet(i1); + } + return TypeBot.BOTTOM; + } + + @Override + public Node idealize () { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // Add 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() ) { + Node tmp = in(1); // Swap inputs without letting either input go dead during the swap + _inputs.set(1,in(2)); + _inputs.set(2,tmp); + return this; + } + + // Goal: a left-spine set of adds, with constants on the rhs (which then fold). + + // Do we have (x + con1) + con2 ? + // Rotate to x +(con1 + con2) + // The constants will fold on the next peephole. + if (t2.isConstant() && lhs instanceof AddNode && lhs.in(2)._type.isConstant() ) + return new AddNode(lhs.in(1),new AddNode(lhs.in(2),rhs).peephole()); + + // Do we have x + (y + con) ? + // Swap to (x + y) + con + if (rhs instanceof AddNode add && add.in(2)._type.isConstant() ) + return new AddNode(new AddNode(lhs,add.in(1)).peephole(), add.in(2)); + + // Add of same to a multiply by 2 + if( lhs==rhs ) + return new MulNode(lhs,new ConstantNode(TypeInteger.constant(2)).peephole()); + + return null; + } + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/BoolNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/BoolNode.java new file mode 100644 index 00000000..b0e0bf42 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/BoolNode.java @@ -0,0 +1,53 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; +import 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 op(); } + + @Override + StringBuilder _print1(StringBuilder sb) { + in(1)._print0(sb.append("(")); + in(2)._print0(sb.append(op())); + return sb.append(")"); + } + + @Override + public Type compute() { + if( in(1)._type instanceof TypeInteger i0 && + in(2)._type instanceof TypeInteger i1 ) { + if (i0.isConstant() && i1.isConstant()) + return TypeInteger.constant(doOp(i0.value(), i1.value()) ? 1 : 0); + return i0.meet(i1); + } + return TypeBot.BOTTOM; + } + + abstract boolean doOp(long lhs, long rhs); + + @Override + public Node idealize() { + // Compare of same + if( in(1)==in(2) ) + return new ConstantNode(TypeInteger.constant(doOp(3,3)?1:0)); + + return null; + } + + public static class EQNode extends BoolNode { public EQNode(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return "=="; } boolean doOp(long lhs, long rhs) { return lhs == rhs; } } + public static class NENode extends BoolNode { public NENode(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return "!="; } boolean doOp(long lhs, long rhs) { return lhs != rhs; } } + public static class LTNode extends BoolNode { public LTNode(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return "<" ; } boolean doOp(long lhs, long rhs) { return lhs < rhs; } } + public static class LENode extends BoolNode { public LENode(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return "<="; } boolean doOp(long lhs, long rhs) { return lhs <= rhs; } } + public static class GTNode extends BoolNode { public GTNode(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return ">" ; } boolean doOp(long lhs, long rhs) { return lhs > rhs; } } + public static class GENode extends BoolNode { public GENode(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return ">="; } boolean doOp(long lhs, long rhs) { return lhs >= rhs; } } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/ConstantNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/ConstantNode.java new file mode 100644 index 00000000..ec85bf1f --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/ConstantNode.java @@ -0,0 +1,42 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.Type; + +/** + * 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) { + return _con._print(sb); + } + + @Override + public Type compute() { return _con; } + + @Override + public Node idealize() { return null; } + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/Control.java b/chapter05/src/main/java/com/seaofnodes/simple/node/Control.java new file mode 100644 index 00000000..48cf2b7a --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/Control.java @@ -0,0 +1,9 @@ +package com.seaofnodes.simple.node; + + +/** + * Control interface is a marker interface to be implemented + * by Control nodes. + */ +public interface Control { +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/DivNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/DivNode.java new file mode 100644 index 00000000..22167a87 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/DivNode.java @@ -0,0 +1,38 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; +import com.seaofnodes.simple.type.TypeInteger; + +public class DivNode extends Node { + public DivNode(Node lhs, Node rhs) { + super(null, lhs, rhs); + } + + @Override + public String label() { return "Div"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + in(1)._print0(sb.append("(")); + in(2)._print0(sb.append("/")); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeInteger i0 && + in(2)._type instanceof TypeInteger i1) { + if (i0.isConstant() && i1.isConstant()) { + if (i1.value() == 0) + throw new IllegalArgumentException("Divide by zero"); + return TypeInteger.constant(i0.value()/i1.value()); + } + return i0.meet(i1); + } + return TypeBot.BOTTOM; + } + + @Override + public Node idealize() { return null; } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/MinusNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/MinusNode.java new file mode 100644 index 00000000..04084d0f --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/MinusNode.java @@ -0,0 +1,30 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; +import com.seaofnodes.simple.type.TypeInteger; + +public class MinusNode extends Node { + public MinusNode(Node in) { + super(null, in); + } + + @Override + public String label() { return "Minus"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + in(1)._print0(sb.append("(-")); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeInteger i0) + return TypeInteger.constant(-i0.value()); + return TypeBot.BOTTOM; + } + + @Override + public Node idealize() { return null; } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/MulNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/MulNode.java new file mode 100644 index 00000000..e3e83b38 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/MulNode.java @@ -0,0 +1,55 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; +import com.seaofnodes.simple.type.TypeInteger; + +public class MulNode extends Node { + public MulNode(Node lhs, Node rhs) { + super(null, lhs, rhs); + } + + @Override + public String label() { return "Mul"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + in(1)._print0(sb.append("(")); + in(2)._print0(sb.append("*")); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeInteger i0 && + in(2)._type instanceof TypeInteger i1) { + if (i0.isConstant() && i1.isConstant()) + return TypeInteger.constant(i0.value()*i1.value()); + return i0.meet(i1); + } + return TypeBot.BOTTOM; + } + + @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() ) { + Node tmp = in(1); // Swap inputs without letting either input go dead during the swap + _inputs.set(1,in(2)); + _inputs.set(2,tmp); + return this; + } + + return null; + } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/MultiNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/MultiNode.java new file mode 100644 index 00000000..e517c3d5 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/MultiNode.java @@ -0,0 +1,13 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; + +public abstract class MultiNode extends Node { + + public MultiNode(Node... inputs) { + super(inputs); + } + + // Return the ProjNode with the idx + abstract ProjNode proj(int idx); +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/Node.java b/chapter05/src/main/java/com/seaofnodes/simple/node/Node.java new file mode 100644 index 00000000..8d698d1b --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/Node.java @@ -0,0 +1,343 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; + +import java.util.ArrayList; +import java.util.Collections; + +/** + * 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 { + + /** + * 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 Control node. + * @see Control + */ + public final ArrayList<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 ArrayList<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 multi-threaded, 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; + + protected Node(Node... inputs) { + _nid = UNIQUE_ID++; // allocate unique dense ID + _inputs = new ArrayList<>(); + Collections.addAll(_inputs,inputs); + _outputs = new ArrayList<>(); + for( Node n : _inputs ) + if( n != null ) + n._outputs.add( this ); + } + + public abstract String label(); + + public String uniqueName() { return label() + _nid; } + + @Override + public final String toString() { + // TODO: This needs a lot of work + return print(); + } + + // This is a *deep* print. This version will fail on cycles, which we will + // correct later when we can parse programs with loops. 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()).toString(); + } + // This is the common print: check for DEAD and print "DEAD" else call the + // per-Node print1. + final StringBuilder _print0(StringBuilder sb) { + return isDead() + ? sb.append(uniqueName()).append(":DEAD") + : _print1(sb); + } + // Every Node implements this. + abstract StringBuilder _print1(StringBuilder sb); + + + /** + * 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 int nIns() { return _inputs.size(); } + + /** + * Gets the ith output node + * @param i Offset of the output node + * @return Output node (not null) + */ + public Node out(int i) { return _outputs.get(i); } + + public int nOuts() { return _outputs.size(); } + + public boolean isUnused() { return nOuts() == 0; } + + /** + * 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 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> + * </ul> + */ + public final Node peephole( ) { + // Compute initial or improved Type + Type type = _type = compute(); + + if (_disablePeephole) + return this; // Peephole optimizations turned off + + // Replace constant computations from non-constants with a constant node + if (!(this instanceof ConstantNode) && type.isConstant()) + return deadCodeElim(new ConstantNode(type).peephole()); + + // Future chapter: Global Value Numbering goes here + + // Ask each node for a better replacement + Node n = idealize(); + if( n != null ) // Something changed + // Recursively optimize + return deadCodeElim(n.peephole()); + + return this; // No progress + } + + // 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() ) { + // 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.addUse(null); // Add bogus null use to keep m alive + kill(); // Kill self because replacing with 'm' + m.delUse(null); // Remove bogus null. + } + return m; + } + + + /** + * 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 this for flow coding + */ + Node set_def(int idx, Node new_def ) { + Node old_def = in(idx); + if( old_def == new_def ) return this; // No change + 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 + // Set the new_def over the old (killed) edge + _inputs.set(idx,new_def); + // If new def is not null, add the corresponding def->use edge + if( new_def != null ) + new_def._outputs.add(this); + // Return self for easy flow-coding + return this; + } + + /** + * 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 + */ + Node add_def(Node new_def) { + // 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._outputs.add(this); + return new_def; + } + + + // Breaks the edge invariants, used temporarily + private void addUse(Node n) { _outputs.add(n); } + + // 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. + private boolean delUse( Node use ) { + ArrayList<Node> outs = _outputs; + int lidx = outs.size()-1; // Last index + // This 1-line hack compresses an element out of an ArrayList + // without having to copy the contents. The last element is + // stuffed over the deleted element, and then the size is reduced. + outs.set(outs.indexOf(use),outs.get(lidx)); + outs.remove(lidx); // Reduce ArrayList size without copying anything + return lidx==0; + } + + // Shortcut for "popping" n nodes. A "pop" is basically a + // set_def(last,null) followed by lowering the nIns() count. + void pop_n(int n) { + for( int i=0; i<n; i++ ) { + Node old_def = _inputs.remove(_inputs.size()-1); + 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. This function is co-recursive with {@link #pop_n}. + */ + public void kill( ) { + assert isUnused(); // Has no uses, so it is dead + pop_n(nIns()); // Set all inputs to null, recursively killing unused Nodes + _type=null; // Flag as dead + assert isDead(); // Really dead now + } + + // Mostly used for asserts and printing. + boolean isDead() { return isUnused() && nIns()==0 && _type==null; } + + /** + * 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> + * compute() needs to be stand-alone, and cannot recursively call compute + * on its inputs 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(); + + /** + * 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,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(); + + /** + * 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; } + + /* + * hashCode and equals implementation to be added in later chapter. + */ + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/ProjNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/ProjNode.java new file mode 100644 index 00000000..be37c514 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/ProjNode.java @@ -0,0 +1,39 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; +import com.seaofnodes.simple.type.TypeTuple; + +public class ProjNode extends Node { + + // Which slice of the incoming multi-part value + public final int _idx; + + // Debugging label + public final String _label; + + public ProjNode(MultiNode ctrl, int idx, String label) { + super(ctrl); + _idx = idx; + _label = label; + } + + @Override + public String label() { return _label; } + + @Override + StringBuilder _print1(StringBuilder sb) { return sb.append("Proj_" +_nid); } + + public MultiNode ctrl() { return (MultiNode)in(0); } + + @Override + public Type compute() { + Type t = ctrl()._type; + return t instanceof TypeTuple tt ? tt._types[_idx] : TypeBot.BOTTOM; + } + + @Override + public Node idealize() { + return null; + } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/ReturnNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/ReturnNode.java new file mode 100644 index 00000000..c94115bb --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/ReturnNode.java @@ -0,0 +1,40 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; + +/** + * 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 Node implements Control { + + public ReturnNode(Node ctrl, Node data) { + super(ctrl, data); + } + + public Node ctrl() { return in(0); } + public Node expr() { return in(1); } + + @Override + public String label() { return "Return"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + return expr()._print0(sb.append("return ")).append(";"); + } + + + @Override + public Type compute() { + return expr().compute(); + } + + @Override + public Node idealize() { return null; } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/ScopeNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/ScopeNode.java new file mode 100644 index 00000000..8bd81e82 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/ScopeNode.java @@ -0,0 +1,88 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.TypeBot; + +import java.util.*; + +/** + * The Scope node is a purely parser helper - it tracks names to nodes with a + * stack of scopes. + */ +public class ScopeNode extends Node { + + /** + * Stack of lexical scopes, each scope is a symbol table + * that binds variable names to Nodes. + * The top of this stack represents current scope. + */ + public final Stack<HashMap<String, Integer>> _scopes = new Stack<>(); + + @Override + public String label() { return "Scope"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + for( HashMap<String,Integer> scope : _scopes ) { + sb.append("["); + boolean first=true; + for( String name : scope.keySet() ) { + if( !first ) sb.append(", "); + first=false; + sb.append(name).append(":"); + Node n = in(scope.get(name)); + if( n==null ) sb.append("null"); + else n._print0(sb); + } + sb.append("]"); + } + return sb; + } + + @Override + public TypeBot compute() { return TypeBot.BOTTOM; } + + @Override + public Node idealize() { return null; } + + // Add an empty lexical scope + public void push() { + _scopes.push(new HashMap<>()); + } + + // Remove the current lexical scope, killing all unused nodes. + public void pop() { + HashMap<String,Integer> scope = _scopes.pop(); + pop_n(scope.size()); + } + + // Create a new name in the current scope + public Node define( String name, Node n ) { + HashMap<String,Integer> scope = _scopes.lastElement(); + if( scope.put(name,nIns()) != null ) + return null; // Double define + return add_def(n); + } + + // Lookup a name in all scopes + public Node lookup(String name) { + for (int i = _scopes.size() - 1; i >= 0; i--) { + var idx = _scopes.get(i).get(name); + if (idx != null) return in(idx); + } + return null; + } + + + // If the name is present in any scope, then redefine + public Node update(String name, Node n) { + for (int i = _scopes.size() - 1; i >= 0; i--) { + HashMap<String, Integer> scope = _scopes.get(i); + Integer idx = scope.get(name); + if (idx != null) // Found prior def + return set_def(idx,n); // Update def in scope + } + return null; + } + + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/StartNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/StartNode.java new file mode 100644 index 00000000..b59e3375 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/StartNode.java @@ -0,0 +1,46 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; +import com.seaofnodes.simple.type.TypeTuple; + +/** + * 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. + */ +public class StartNode extends MultiNode implements Control { + + final TypeTuple _args; + + public StartNode(Type[] args) { + super(); + _args = new TypeTuple(args); + } + + @Override + public String label() { return "Start"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + return sb.append(label()); + } + + @Override + public TypeTuple compute() { return _args; } + + @Override + public Node idealize() { return null; } + + + @Override + public ProjNode proj( int idx ) { + for( Node proj : _outputs ) + if( ((ProjNode)proj)._idx==idx ) + return (ProjNode)proj; + return null; + } + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/node/SubNode.java b/chapter05/src/main/java/com/seaofnodes/simple/node/SubNode.java new file mode 100644 index 00000000..e5939e1b --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/node/SubNode.java @@ -0,0 +1,42 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeBot; +import com.seaofnodes.simple.type.TypeInteger; + +public class SubNode extends Node { + public SubNode(Node lhs, Node rhs) { + super(null, lhs, rhs); + } + + @Override + public String label() { return "Sub"; } + + @Override + StringBuilder _print1(StringBuilder sb) { + in(1)._print0(sb.append("(")); + in(2)._print0(sb.append("-")); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeInteger i0 && + in(2)._type instanceof TypeInteger i1) { + if (i0.isConstant() && i1.isConstant()) + return TypeInteger.constant(i0.value()-i1.value()); + return i0.meet(i1); + } + return TypeBot.BOTTOM; + } + + @Override + public Node idealize() { + // Sub of same is 0 + if( in(1)==in(2) ) + return new ConstantNode(TypeInteger.constant(0)); + + return null; + } + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/type/Type.java b/chapter05/src/main/java/com/seaofnodes/simple/type/Type.java new file mode 100644 index 00000000..d9567dc8 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/type/Type.java @@ -0,0 +1,30 @@ +package com.seaofnodes.simple.type; + + +/** + * 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 abstract class Type { + + public static final TypeControl CONTROL = new TypeControl(); + + public boolean isConstant() { return false; } + + public abstract StringBuilder _print(StringBuilder sb); + + public Type meet(Type other) { return TypeBot.BOTTOM; } + +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/type/TypeBot.java b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeBot.java new file mode 100644 index 00000000..a5709448 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeBot.java @@ -0,0 +1,19 @@ +package com.seaofnodes.simple.type; + +import java.lang.StringBuilder; + +public class TypeBot extends Type { + + public static final TypeBot BOTTOM = new TypeBot(); + + @Override + public String toString() { return "Bottom"; } + + @Override + public Type meet(Type other) { + return BOTTOM; + } + + @Override + public StringBuilder _print(StringBuilder sb) { return sb.append(toString()); } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/type/TypeControl.java b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeControl.java new file mode 100644 index 00000000..0130ffd0 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeControl.java @@ -0,0 +1,16 @@ +package com.seaofnodes.simple.type; + +public class TypeControl extends Type { + + public static final TypeControl CONTROL = new TypeControl(); + + @Override + public StringBuilder _print(StringBuilder sb) { + return sb.append(toString()); + } + + @Override + public String toString() { + return "Control"; + } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/type/TypeInteger.java b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeInteger.java new file mode 100644 index 00000000..e23840e0 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeInteger.java @@ -0,0 +1,63 @@ +package com.seaofnodes.simple.type; + +/** + * Integer Type + */ +public class TypeInteger extends Type { + + public final static TypeInteger TOP = new TypeInteger(false, 0); + public final static TypeInteger BOT = new TypeInteger(false, 1); + + private final boolean _is_con; + + /** + * The constant value or + * if not constant then 0=bottom, 1=top. + */ + private final long _con; + + public TypeInteger(boolean is_con, long con) { _is_con = is_con; _con = con; } + + public static TypeInteger constant(long con) { return new TypeInteger(true, con); } + + public boolean isTop() { return !_is_con && _con==0; } + public boolean isBot() { return !_is_con && _con==1; } + + @Override + public String toString() { + return _print(new StringBuilder()).toString(); + } + + @Override + public StringBuilder _print(StringBuilder sb) { + if (isTop()) return sb.append("IntTop"); + if (isBot()) return sb.append("IntBot"); + return sb.append(_con); + } + + @Override + public boolean isConstant() { return _is_con; } + + public long value() { return _con; } + + @Override + public Type meet(Type other) { + if( this==other ) return this; + if (!(other instanceof TypeInteger i)) return super.meet(other); + // BOT wins + if ( isBot() ) return this; + if ( i.isBot() ) return i ; + // TOP loses + if ( i.isTop() ) return this; + if ( isTop() ) return i ; + assert isConstant() && i.isConstant(); + return _con==i._con ? this : TypeInteger.BOT; + } + + @Override + public boolean equals( Object o ) { + if( o==this ) return true; + if( !(o instanceof TypeInteger i) ) return false; + return _con==i._con && _is_con==i._is_con; + } +} diff --git a/chapter05/src/main/java/com/seaofnodes/simple/type/TypeTuple.java b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeTuple.java new file mode 100644 index 00000000..ef87a415 --- /dev/null +++ b/chapter05/src/main/java/com/seaofnodes/simple/type/TypeTuple.java @@ -0,0 +1,20 @@ +package com.seaofnodes.simple.type; + +public class TypeTuple extends Type { + + public final Type[] _types; + + public TypeTuple(Type[] _types) { + this._types = _types; + } + + @Override + public Type meet(Type other) { + throw new UnsupportedOperationException("Meet on Tuple Type not yet implemented"); + } + + @Override + public StringBuilder _print(StringBuilder sb) { + return sb; + } +} |