diff options
Diffstat (limited to 'chapter07/src')
27 files changed, 3764 insertions, 0 deletions
diff --git a/chapter07/src/main/java/com/seaofnodes/simple/GraphVisualizer.java b/chapter07/src/main/java/com/seaofnodes/simple/GraphVisualizer.java new file mode 100644 index 00000000..ce3522bc --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/GraphVisualizer.java @@ -0,0 +1,256 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; + +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 { + + /** + * If set to true we put the control nodes in a separate cluster from + * data nodes. + */ + boolean _separateControlCluster = false; + + public GraphVisualizer(boolean separateControlCluster) { this._separateControlCluster = separateControlCluster; } + public GraphVisualizer() { this(false); } + + public String generateDotOutput(Parser 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 chapter07 {\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 + + // Preserve node input order + sb.append("\tordering=\"in\";\n"); + + // Merge multiple edges hitting the same node. Makes common shared + // nodes much prettier to look at. + sb.append("\tconcentrate=\"true\";\n"); + + // Force nested scopes to order + sb.append("\tcompound=\"true\";\n"); + + // Just the Nodes first, in a cluster no edges + nodes(sb, all); + + // Now the scopes, in a cluster no edges + scope(sb,parser._scope ); + for( ScopeNode scope : parser._xScopes ) + scope( sb, scope ); + + // Walk the Node edges + nodeEdges(sb, all); + + // Walk the active Scope edges + scopeEdges( sb, parser._scope ); + for( ScopeNode scope : parser._xScopes ) + scopeEdges( sb, scope ); + + sb.append("}\n"); + return sb.toString(); + } + + private void nodesByCluster(StringBuilder sb, boolean doCtrl, Collection<Node> all) { + if (!_separateControlCluster && doCtrl) // all nodes in 1 cluster + return; + // Just the Nodes first, in a cluster no edges + sb.append(doCtrl ? "\tsubgraph cluster_Controls {\n" : "\tsubgraph cluster_Nodes {\n"); // Magic "cluster_" in the subgraph name + for (Node n : all) { + if (n instanceof ProjNode || n instanceof ScopeNode) + continue; // Do not emit, rolled into MultiNode or Scope cluster already + if (_separateControlCluster && doCtrl && !n.isCFG()) continue; + if (_separateControlCluster && !doCtrl && n.isCFG()) continue; + sb.append("\t\t").append(n.uniqueName()).append(" [ "); + String lab = n.glabel(); + if (n instanceof MultiNode) { + // Make a box with the MultiNode on top, and all the projections on the bottom + sb.append("shape=plaintext label=<\n"); + sb.append("\t\t\t<TABLE BORDER=\"0\" CELLBORDER=\"1\" CELLSPACING=\"0\" CELLPADDING=\"4\">\n"); + sb.append("\t\t\t<TR><TD BGCOLOR=\"yellow\">").append(lab).append("</TD></TR>\n"); + sb.append("\t\t\t<TR>"); + boolean doProjTable = false; + 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.isCFG()) sb.append(" BGCOLOR=\"yellow\""); + sb.append(">").append(proj.glabel()).append("</TD>"); + } + } + if (doProjTable) { + sb.append("</TR>").append("\n"); + sb.append("\t\t\t\t</TABLE>").append("\n"); + sb.append("\t\t\t</TD>"); + } + sb.append("</TR>\n"); + sb.append("\t\t\t</TABLE>>\n\t\t"); + + } else { + // control nodes have box shape + // other nodes are ellipses, i.e. default shape + if (n.isCFG()) sb.append("shape=box style=filled fillcolor=yellow "); + else if (n instanceof PhiNode) sb.append("style=filled fillcolor=lightyellow "); + sb.append("label=\"").append(lab).append("\" "); + } + sb.append("];\n"); + } + if (!_separateControlCluster) { + // Force Region & Phis to line up + for (Node n : all) { + if (n instanceof RegionNode region) { + sb.append("\t\t{ rank=same; "); + sb.append(region).append(";"); + for (Node phi : region._outputs) + if (phi instanceof PhiNode) sb.append(phi.uniqueName()).append(";"); + sb.append("}\n"); + } + } + } + sb.append("\t}\n"); // End Node cluster + } + + private void nodes(StringBuilder sb, Collection<Node> all) { + nodesByCluster(sb, true, all); + nodesByCluster(sb, false, all); + } + + // Build a nested scope display, walking the _prev edge + private void scope( StringBuilder sb, ScopeNode scope ) { + sb.append("\tnode [shape=plaintext];\n"); + int level=1; + for( int idx = scope._scopes.size()-1; idx>=0; idx-- ) { + var syms = scope._scopes.get(idx); + String scopeName = makeScopeName(scope, level); + sb.append("\tsubgraph cluster_").append(scopeName).append(" {\n"); // Magic "cluster_" in the subgraph name + 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 + int scopeLevel = scope._scopes.size()-level; + sb.append("\t\t\t<TR><TD BGCOLOR=\"cyan\">").append(scopeLevel).append("</TD>"); + for(String name: syms.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-1 ) ); // End all Scope clusters + } + + private String makeScopeName(ScopeNode sn, int level) { return sn.uniqueName() + "_" + level; } + private String makePortName(String scopeName, String varName) { return scopeName + "_" + varName; } + + // Walk the node edges + private void nodeEdges(StringBuilder sb, Collection<Node> all) { + // All them edge labels + sb.append("\tedge [ fontname=Helvetica, fontsize=8 ];\n"); + for( Node n : all ) { + // Do not display the Constant->Start edge; + // ProjNodes handled by Multi; + // ScopeNodes are done separately + if( n instanceof ConstantNode || n instanceof ProjNode || n instanceof ScopeNode ) + continue; + for( int i=0; i<n.nIns(); i++ ) { + Node def = n.in(i); + if( n instanceof PhiNode && def instanceof RegionNode ) { + // Draw a dotted use->def edge from Phi to Region. + sb.append('\t').append(n.uniqueName()); + sb.append(" -> "); + sb.append(def.uniqueName()); + sb.append(" [style=dotted taillabel=").append(i).append("];\n"); + } else if( def != null ) { + // Most edges land here use->def + sb.append('\t').append(n.uniqueName()).append(" -> "); + if( def instanceof ProjNode proj ) { + String mname = proj.ctrl().uniqueName(); + sb.append(mname).append(":p").append(proj._idx); + } else sb.append(def.uniqueName()); + // Number edges, so we can see how they track + sb.append("[taillabel=").append(i); + // control edges are colored red + if( def.isCFG() ) + sb.append(" color=red"); + // Backedges do not add a ranking constraint + if( i==2 && (n instanceof PhiNode || n instanceof LoopNode) ) + sb.append(" constraint=false"); + sb.append("];\n"); + } + } + } + } + + // Walk the scope edges + private void scopeEdges( StringBuilder sb, ScopeNode scope ) { + sb.append("\tedge [style=dashed color=cornflowerblue];\n"); + int level=1; + for( int i = scope._scopes.size()-1; i>=0; i-- ) { + var syms = scope._scopes.get(i); + String scopeName = makeScopeName(scope, level); + for( String name : syms.keySet() ) { + int idx = syms.get(name); + Node def = scope.in(idx); + 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 HashMap<Integer, Node> all = new HashMap<>(); + for( Node n : Parser.START._outputs ) + walk(all, n); + for( Node n : parser._scope._inputs ) + walk(all, n); + return all.values(); + } + + /** + * Walk a subgraph and populate distinct nodes in the all list. + */ + private void walk(HashMap<Integer,Node> all, Node n) { + if(n == null ) return; + if (all.get(n._nid) != null) return; // Been there, done that + all.put(n._nid, n); + for (Node c : n._inputs) + walk(all, c); + for( Node c : n._outputs ) + walk(all, c); + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/IRPrinter.java b/chapter07/src/main/java/com/seaofnodes/simple/IRPrinter.java new file mode 100644 index 00000000..dc6d9f4f --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/IRPrinter.java @@ -0,0 +1,124 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.LoopNode; +import com.seaofnodes.simple.node.Node; + +import java.util.ArrayList; +import java.util.BitSet; + +public class IRPrinter { + + // Another bulk pretty-printer. Makes more effort at basic-block grouping. + public static String prettyPrint(Node node, int depth) { + // First, a Breadth First Search at a fixed depth. + BFS bfs = new BFS(node,depth); + // Convert just that set to a post-order + ArrayList<Node> rpos = new ArrayList<>(); + BitSet visit = new BitSet(); + for( int i=bfs._lim; i< bfs._bfs.size(); i++ ) + postOrd( bfs._bfs.get(i), rpos, visit, bfs._bs); + // Reverse the post-order walk + StringBuilder sb = new StringBuilder(); + boolean gap=false; + for( int i=rpos.size()-1; i>=0; i-- ) { + Node n = rpos.get(i); + if( n.isCFG() || n.isMultiHead() ) { + if( !gap ) sb.append("\n"); // Blank before multihead + n._print_line(sb); // Print head + while( --i >= 0 ) { + Node t = rpos.get(i); + if( !t.isMultiTail() ) { i++; break; } + t._print_line(sb); + } + sb.append("\n"); // Blank after multitail + gap = true; + } else { + n._print_line( sb ); + gap = false; + } + } + return sb.toString(); + } + + private static void postOrd(Node n, ArrayList<Node> rpos, BitSet visit, BitSet bfs) { + if( !bfs.get(n._nid) ) + return; // Not in the BFS visit + if( visit.get(n._nid) ) return; // Already post-order walked + visit.set(n._nid); + // First walk the CFG, then everything + if( n.isCFG() ) { + for( Node use : n._outputs ) + if( use.isCFG() && use.nOuts()>=1 && !(use._outputs.get(0) instanceof LoopNode) ) + postOrd(use, rpos,visit,bfs); + for( Node use : n._outputs ) + if( use.isCFG() ) + postOrd(use,rpos,visit,bfs); + } + for( Node use : n._outputs ) + postOrd(use, rpos,visit,bfs); + // Post-order + rpos.add(n); + } + + // Breadth-first search, broken out in a class to keep in more independent. + // Maintains a root-set of Nodes at the limit (or past by 1 if MultiHead). + public static class BFS { + // A breadth first search, plus MultiHeads for any MultiTails + public final ArrayList<Node> _bfs; + public final BitSet _bs; // Visited members by node id + public final int _depth; // Depth limit + public final int _lim; // From here to _bfs._len can be roots for a reverse search + public BFS( Node base, int d ) { + _depth = d; + _bfs = new ArrayList<>(); + _bs = new BitSet(); + + add(base); // Prime the pump + int idx=0, lim=1; // Limit is where depth counter changes + while( idx < _bfs.size() ) { // Ran out of nodes below depth + Node n = _bfs.get(idx++); + for( Node def : n._inputs ) + if( def!=null && !_bs.get(def._nid) ) + add(def); + if( idx==lim ) { // Depth counter changes at limit + if( --d < 0 ) + break; // Ran out of depth + lim = _bfs.size(); // New depth limit + } + } + // Toss things past the limit except multi-heads + while( idx < _bfs.size() ) { + Node n = _bfs.get(idx); + if( n.isMultiHead() ) idx++; + else del(idx); + } + // Root set is any node with no inputs in the visited set + lim = _bfs.size(); + for( int i=_bfs.size()-1; i>=0; i-- ) + if( !any_visited(_bfs.get(i)) ) + swap( i,--lim); + _lim = lim; + } + void swap( int x, int y ) { + if( x==y ) return; + Node tx = _bfs.get(x); + Node ty = _bfs.get(y); + _bfs.set(x,ty); + _bfs.set(y,tx); + } + void add(Node n) { + _bfs.add(n); + _bs.set(n._nid); + } + void del(int idx) { + Node n = Utils.del(_bfs, idx); + _bs.clear(n._nid); + } + boolean any_visited( Node n ) { + for( Node def : n._inputs ) + if( def!=null && _bs.get(def._nid) ) + return true; + return false; + } + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/Parser.java b/chapter07/src/main/java/com/seaofnodes/simple/Parser.java new file mode 100644 index 00000000..99594c95 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/Parser.java @@ -0,0 +1,572 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.*; + +import java.util.*; + +/** + * The Parser converts a Simple source program to the Sea of Nodes intermediate + * representation directly in one pass. There is no intermediate Abstract + * Syntax Tree structure. + * <p> + * This is a simple recursive descent parser. All lexical analysis is done here as well. + */ +public class Parser { + /** + * A Global Static, unique to each compilation. This is a public, so we + * can make constants everywhere without having to thread the StartNode + * through the entire parser and optimizer. + * <p> + * To make the compiler multithreaded, this field will have to move into a TLS. + */ + public static StartNode START; + + public StopNode STOP; + + // The Lexer. Thin wrapper over a byte[] buffer with a cursor. + private final Lexer _lexer; + + /** + * Current ScopeNode - ScopeNodes change as we parse code, but at any point of time + * there is one current ScopeNode. The reason the current ScopeNode can change is to do with how + * we handle branching. See {@link #parseIf()}. + * <p> + * Each ScopeNode contains a stack of lexical scopes, each scope is a symbol table that binds + * variable names to Nodes. The top of this stack represents current scope. + * <p> + * We keep a list of all ScopeNodes so that we can show them in graphs. + * @see #parseIf() + * @see #_xScopes + */ + public ScopeNode _scope; + + /** + * List of keywords disallowed as identifiers + */ + private final HashSet<String> KEYWORDS = new HashSet<>(){{ + add("else"); + add("false"); + add("if"); + add("int"); + add("return"); + add("true"); + add("while"); + }}; + + + /** + * We clone ScopeNodes when control flows branch; it is useful to have + * a list of all active ScopeNodes for purposes of visualization of the SoN graph + */ + public final Stack<ScopeNode> _xScopes = new Stack<>(); + + public Parser(String source, TypeInteger arg) { + Node.reset(); + _lexer = new Lexer(source); + _scope = new ScopeNode(); + START = new StartNode(new Type[]{ Type.CONTROL, arg }); + STOP = new StopNode(); + } + + public Parser(String source) { + this(source, TypeInteger.BOT); + } + + @Override + public String toString() { return _lexer.toString(); } + + String src() { return new String( _lexer._input ); } + + // Debugging utility to find a Node by index + public static Node find(int nid) { return START.find(nid); } + + private Node ctrl() { return _scope.ctrl(); } + + private Node ctrl(Node n) { return _scope.ctrl(n); } + + public StopNode parse() { return parse(false); } + public StopNode parse(boolean show) { + // 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()); + parseBlock(); + _scope.pop(); + if (!_lexer.isEOF()) throw error("Syntax error, unexpected " + _lexer.getAnyNextToken()); + STOP.peephole(); + if( show ) showGraph(); + return STOP; + } + + + /** + * Parses a block + * + * <pre> + * '{' statements '}' + * </pre> + * Does not parse the opening or closing '{}' + * @return a {@link Node} or {@code null} + */ + private Node parseBlock() { + // Enter a new scope + _scope.push(); + while (!peek('}') && !_lexer.isEOF()) + parseStatement(); + // Exit scope + _scope.pop(); + return null; + } + + /** + * Parses a statement + * + * <pre> + * returnStatement | declStatement | blockStatement | ifStatement | expressionStatement + * </pre> + * @return a {@link Node} or {@code null} + */ + private Node parseStatement() { + if (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("#showGraph")) return require(showGraph(),";"); + else return parseExpressionStatement(); + } + + /** + * Parses a while statement + * + * <pre> + * while ( expression ) statement + * </pre> + * @return a {@link Node}, never {@code null} + */ + private Node parseWhile() { + require("("); + + // Loop region has two control inputs, the first one is the entry + // point, and second one is back edge that is set after loop is parsed + // (see end_loop() call below). Note that the absence of back edge is + // used as an indicator to switch off peepholes of the region and + // associated phis. + + ctrl(new LoopNode(ctrl(),null).peephole()); + ScopeNode head = _xScopes.push(_scope).keep(); // Save the current scope as the loop head + // Make a new Scope for the body. + _scope = _scope.dup(true); + + // Parse predicate + var pred = require(parseExpression(), ")"); + // IfNode takes current control and predicate + IfNode ifNode = (IfNode)new IfNode(ctrl(), pred).<IfNode>keep().peephole(); + // Setup projection nodes + Node ifT = new ProjNode(ifNode, 0, "True" ).peephole(); + ifNode.unkeep(); + Node ifF = new ProjNode(ifNode, 1, "False").peephole(); + // The exit scope, accounting for any side effects in the predicate + var exit = _scope.dup(); + _xScopes.push(exit); + exit.ctrl(ifF); + + // Parse the true side, which corresponds to loop body + ctrl(ifT); // set ctrl token to ifTrue projection + parseStatement(); // Parse loop body + + // The true branch loops back, so whatever is current control gets + // added to head loop as input + head.endLoop(_scope, exit); + head.unkeep().kill(); + _xScopes.pop(); + _xScopes.pop(); // Discard pushed from graph display + + // At exit the false control is the current control, and + // the scope is the exit scope after the exit test. + return (_scope = exit); + } + + /** + * Parses a statement + * + * <pre> + * if ( expression ) statement [else statement] + * </pre> + * @return a {@link Node}, never {@code null} + */ + private Node parseIf() { + require("("); + // Parse predicate + var pred = require(parseExpression(), ")"); + // IfNode takes current control and predicate + IfNode ifNode = (IfNode)new IfNode(ctrl(), pred).<IfNode>keep().peephole(); + // Setup projection nodes + Node ifT = new ProjNode(ifNode, 0, "True" ).peephole(); + ifNode.unkeep(); + Node ifF = new ProjNode(ifNode, 1, "False").peephole(); + // In if true branch, the ifT proj node becomes the ctrl + // But first clone the scope and set it as current + int ndefs = _scope.nIns(); + ScopeNode fScope = _scope.dup(); // Duplicate current scope + _xScopes.push(fScope); // For graph visualization we need all scopes + + // Parse the true side + ctrl(ifT); // set ctrl token to ifTrue projection + parseStatement(); // Parse true-side + ScopeNode tScope = _scope; + + // Parse the false side + _scope = fScope; // Restore scope, then parse else block if any + ctrl(ifF); // Ctrl token is now set to ifFalse projection + if (matchx("else")) { + parseStatement(); + fScope = _scope; + } + + if( tScope.nIns() != ndefs || fScope.nIns() != ndefs ) + throw error("Cannot define a new name on one arm of an if"); + + // Merge results + _scope = tScope; + _xScopes.pop(); // Discard pushed from graph display + + return ctrl(tScope.mergeScopes(fScope)); + } + + + /** + * Parses a return statement; "return" already parsed. + * The $ctrl edge is killed. + * + * <pre> + * 'return' expr ; + * </pre> + * @return an expression {@link Node}, never {@code null} + */ + private Node parseReturn() { + var expr = require(parseExpression(), ";"); + Node ret = STOP.addReturn(new ReturnNode(ctrl(), expr).peephole()); + ctrl(new ConstantNode(Type.XCONTROL).peephole()); // Kill control + return ret; + } + + /** + * Dumps out the node graph + * @return {@code null} + */ + private Node showGraph() { + System.out.println(new GraphVisualizer().generateDotOutput(this)); + return null; + } + + /** + * Parses an expression statement + * + * <pre> + * name '=' expression ';' + * </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 + "'"); + return expr; + } + + /** + * Parses a declStatement + * + * <pre> + * 'int' name = expression ';' + * </pre> + * @return an expression {@link Node}, never {@code null} + */ + 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 : compareExpr + * </pre> + * @return an expression {@link Node}, never {@code null} + */ + private Node parseExpression() { return parseComparison(); } + + /** + * Parse an expression of the form: + * + * <pre> + * expr : additiveExpr op additiveExpr + * </pre> + * @return an comparator expression {@link Node}, never {@code null} + */ + private Node parseComparison() { + var lhs = parseAddition(); + if (match("==")) return new BoolNode.EQ(lhs, parseComparison()).peephole(); + if (match("!=")) return new NotNode(new BoolNode.EQ(lhs, parseComparison()).peephole()).peephole(); + if (match("<" )) return new BoolNode.LT(lhs, parseComparison()).peephole(); + if (match("<=")) return new BoolNode.LE(lhs, parseComparison()).peephole(); + if (match(">" )) return new BoolNode.LT(parseComparison(), lhs).peephole(); + if (match(">=")) return new BoolNode.LE(parseComparison(), lhs).peephole(); + return lhs; + } + + /** + * Parse an additive expression + * + * <pre> + * additiveExpr : multiplicativeExpr (('+' | '-') multiplicativeExpr)* + * </pre> + * @return an add expression {@link Node}, never {@code null} + */ + 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> + * @return a multiply expression {@link Node}, never {@code null} + */ + 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> + * @return a unary expression {@link Node}, never {@code null} + */ + private Node parseUnary() { + if (match("-")) return new MinusNode(parseUnary()).peephole(); + return parsePrimary(); + } + + /** + * Parse a primary expression: + * + * <pre> + * primaryExpr : integerLiteral | Identifier | true | false | '(' expression ')' + * </pre> + * @return a primary {@link Node}, never {@code null} + */ + private Node parsePrimary() { + if( _lexer.isNumber() ) return parseIntegerLiteral(); + 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(); + String name = _lexer.matchId(); + if( name == null) throw errorSyntax("an identifier or expression"); + Node n = _scope.lookup(name); + if( n!=null ) return n; + throw error("Undefined name '" + name + "'"); + } + + /** + * 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); } + // Match must be "exact", not be followed by more id letters + 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); } + + // Require and return an identifier + private String requireId() { + String id = _lexer.matchId(); + if (id != null && !KEYWORDS.contains(id) ) return id; + throw error("Expected an identifier, found '"+id+"'"); + } + + // 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; + } + + boolean matchx(String syntax) { + if( !match(syntax) ) return false; + if( !isIdLetter(peek()) ) return true; + _position -= syntax.length(); + return false; + } + + private boolean peek(char ch) { + skipWhiteSpace(); + return peek()==ch; + } + + // 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; + return new String(_input, start, 1); + } + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/Utils.java b/chapter07/src/main/java/com/seaofnodes/simple/Utils.java new file mode 100644 index 00000000..4d663c25 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/Utils.java @@ -0,0 +1,39 @@ +package com.seaofnodes.simple; + +import java.util.ArrayList; + +public class Utils { + public static RuntimeException TODO() { return TODO("Not yet implemented"); } + public static RuntimeException TODO(String msg) { return new RuntimeException(msg); } + + /** + * Fast, constant-time, element removal. Does not preserve order + * + * @param array ArrayList to modify + * @param i element to be removed + * @return element removed + */ + public static <E> E del(ArrayList<E> array, int i) { + if ( i >= 0 && i < array.size() ) { + E tmp = array.get(i); + E last = array.removeLast(); + if (i < array.size()) array.set(i, last); + return tmp; + } + return null; + } + + /** + * Search a list for an element by reference + * + * @param ary List to search in + * @param x Object to be searched + * @return >= 0 on success, -1 on failure + */ + public static <E> int find( ArrayList<E> ary, E x ) { + for( int i=0; i<ary.size(); i++ ) + if( ary.get(i)==x ) + return i; + return -1; + } +}
\ No newline at end of file diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/AddNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/AddNode.java new file mode 100644 index 00000000..85d7b20e --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/AddNode.java @@ -0,0 +1,158 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.*; + +import java.util.BitSet; + +public class AddNode extends Node { + public AddNode(Node lhs, Node rhs) { + super(null, lhs, rhs); + } + + @Override public String label() { return "Add"; } + + @Override public String glabel() { return "+"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("+"), visited); + return sb.append(")"); + } + + + @Override + public Type compute() { + 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 Type.BOTTOM; + } + + @Override + public Node idealize () { + Node lhs = in(1); + Node rhs = in(2); + Type t1 = lhs._type; + Type t2 = rhs._type; + + // Already handled by peephole constant folding + assert !(t1.isConstant() && t2.isConstant()); + + // Add of 0. We do not check for (0+x) because this will already + // canonicalize to (x+0) + if( t2 instanceof TypeInteger i && i.value()==0 ) + return lhs; + + // Add of same to a multiply by 2 + if( lhs==rhs ) + return new MulNode(lhs,new ConstantNode(TypeInteger.constant(2)).peephole()); + + // Goal: a left-spine set of adds, with constants on the rhs (which then fold). + + // Move non-adds to RHS + if( !(lhs instanceof AddNode) && rhs instanceof AddNode ) + return swap12(); + + // Now we might see (add add non) or (add non non) or (add add add) but never (add non add) + + // Do we have x + (y + z) ? + // Swap to (x + y) + z + // Rotate (add add add) to remove the add on RHS + if( rhs instanceof AddNode add ) + return new AddNode(new AddNode(lhs,add.in(1)).peephole(), add.in(2)); + + // Now we might see (add add non) or (add non non) but never (add non add) nor (add add add) + if( !(lhs instanceof AddNode) ) + // Rotate; look for (add (phi cons) con/(phi cons)) + return spline_cmp(lhs,rhs) ? swap12() : phiCon(this,true); + + // Now we only see (add add non) + + // Do we have (x + con1) + con2? + // Replace with (x + (con1+con2) which then fold the constants + if( lhs.in(2)._type.isConstant() && t2.isConstant() ) + return new AddNode(lhs.in(1),new AddNode(lhs.in(2),rhs).peephole()); + + + // Do we have ((x + (phi cons)) + con) ? + // Do we have ((x + (phi cons)) + (phi cons)) ? + // Push constant up through the phi: x + (phi con0+con0 con1+con1...) + Node phicon = phiCon(this,true); + if( phicon!=null ) return phicon; + + // Now we sort along the spline via rotates, to gather similar things together. + + // Do we rotate (x + y) + z + // into (x + z) + y ? + if( spline_cmp(lhs.in(2),rhs) ) + return new AddNode(new AddNode(lhs.in(1),rhs).peephole(),lhs.in(2)); + + return null; + } + + // Rotation is only valid for associative ops, e.g. Add, Mul, And, Or. + // Do we have ((phi cons)|(x + (phi cons)) + con|(phi cons)) ? + // Push constant up through the phi: x + (phi con0+con0 con1+con1...) + static Node phiCon(Node op, boolean rotate) { + Node lhs = op.in(1); + Node rhs = op.in(2); + // LHS is either a Phi of constants, or another op with Phi of constants + PhiNode lphi = pcon(lhs); + if( rotate && lphi==null && lhs.nIns() > 2 ) { + // Only valid to rotate constants if both are same associative ops + if( lhs.getClass() != op.getClass() ) return null; + lphi = pcon(lhs.in(2)); // Will rotate with the Phi push + } + if( lphi==null ) return null; + + // RHS is a constant or a Phi of constants + if( !(rhs instanceof ConstantNode con) && pcon(rhs)==null ) + return null; + + // If both are Phis, must be same Region + if( rhs instanceof PhiNode && lphi.in(0) != rhs.in(0) ) + return null; + + // Note that this is the exact reverse of Phi pulling a common op down + // to reduce total op-count. We don't get in an endless push-up + // push-down peephole cycle because the constants all fold first. + Node[] ns = new Node[lphi.nIns()]; + ns[0] = lphi.in(0); + // Push constant up through the phi: x + (phi con0+con0 con1+con1...) + for( int i=1; i<ns.length; i++ ) + ns[i] = op.copy(lphi.in(i), rhs instanceof PhiNode ? rhs.in(i) : rhs).peephole(); + String label = lphi._label + (rhs instanceof PhiNode rphi ? rphi._label : ""); + Node phi = new PhiNode(label,ns).peephole(); + // Rotate needs another op, otherwise just the phi + return lhs==lphi ? phi : op.copy(lhs.in(1),phi); + } + + static PhiNode pcon(Node op) { + return op instanceof PhiNode phi && phi.all_cons() ? phi : null; + } + + // Compare two off-spline nodes and decide what order they should be in. + // Do we rotate ((x + hi) + lo) into ((x + lo) + hi) ? + // Generally constants always go right, then Phi-of-constants, then muls, then others. + // Ties with in a category sort by node ID. + // TRUE if swapping hi and lo. + static boolean spline_cmp( Node hi, Node lo ) { + if( lo._type.isConstant() ) return false; + if( hi._type.isConstant() ) return true ; + + if( lo instanceof PhiNode && lo.all_cons() ) return false; + if( hi instanceof PhiNode && hi.all_cons() ) return true ; + + if( lo instanceof PhiNode && !(hi instanceof PhiNode) ) return true; + if( hi instanceof PhiNode && !(lo instanceof PhiNode) ) return false; + + // Same category of "others" + return lo._nid > hi._nid; + } + + @Override Node copy(Node lhs, Node rhs) { return new AddNode(lhs,rhs); } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/BoolNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/BoolNode.java new file mode 100644 index 00000000..d65fbf14 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/BoolNode.java @@ -0,0 +1,60 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +abstract public class BoolNode extends Node { + + public BoolNode(Node lhs, Node rhs) { + super(null, lhs, rhs); + } + + abstract String op(); // String opcode name + + @Override + public String label() { return getClass().getSimpleName(); } + + @Override + public String glabel() { return op(); } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append(op()), visited); + return sb.append(")"); + } + + @Override + public 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 Type.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)); + + // 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); + if( phicon!=null ) return phicon; + + return null; + } + + public static class EQ extends BoolNode { public EQ(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return "=="; } boolean doOp(long lhs, long rhs) { return lhs == rhs; } Node copy(Node lhs, Node rhs) { return new EQ(lhs,rhs); } } + public static class LT extends BoolNode { public LT(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return "<" ; } boolean doOp(long lhs, long rhs) { return lhs < rhs; } Node copy(Node lhs, Node rhs) { return new LT(lhs,rhs); } } + public static class LE extends BoolNode { public LE(Node lhs, Node rhs) { super(lhs,rhs); } String op() { return "<="; } boolean doOp(long lhs, long rhs) { return lhs <= rhs; } Node copy(Node lhs, Node rhs) { return new LE(lhs,rhs); } } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/ConstantNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/ConstantNode.java new file mode 100644 index 00000000..0e13d2f2 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/ConstantNode.java @@ -0,0 +1,45 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Parser; +import com.seaofnodes.simple.type.Type; + +import java.util.BitSet; + +/** + * A Constant node represents a constant value. At present, the only constants + * that we allow are integer literals; therefore Constants contain an integer + * value. As we add other types of constants, we will refactor how we represent + * Constants. + * <p> + * Constants have no semantic inputs. However, we set Start as an input to + * Constants to enable a forward graph walk. This edge carries no semantic + * meaning, and it is present <em>solely</em> to allow visitation. + * <p> + * The Constant's value is the value stored in it. + */ +public class ConstantNode extends Node { + Type _con; + public ConstantNode( Type type ) { + super(Parser.START); + _con = type; + } + + @Override + public String label() { return ""+_con; } + + @Override + public String uniqueName() { return "Con_" + _nid; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return _con._print(sb); + } + + @Override public boolean isMultiTail() { return true; } + + @Override + public Type compute() { return _con; } + + @Override + public Node idealize() { return null; } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/DivNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/DivNode.java new file mode 100644 index 00000000..b0e12547 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/DivNode.java @@ -0,0 +1,39 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class DivNode extends Node { + public DivNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Div"; } + + @Override public String glabel() { return "//"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("/"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeInteger i0 && + in(2)._type instanceof TypeInteger i1) { + if (i0.isConstant() && i1.isConstant()) + return i1.value() == 0 + ? TypeInteger.ZERO + : TypeInteger.constant(i0.value()/i1.value()); + return i0.meet(i1); + } + return Type.BOTTOM; + } + + @Override + public Node idealize() { return null; } + + @Override Node copy(Node lhs, Node rhs) { return new DivNode(lhs,rhs); } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/IfNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/IfNode.java new file mode 100644 index 00000000..e573010d --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/IfNode.java @@ -0,0 +1,58 @@ +package com.seaofnodes.simple.node; + +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); + } + + @Override + public String label() { return "If"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("if( "); + return in(1)._print0(sb, visited).append(" )"); + } + + @Override public boolean isCFG() { return true; } + @Override public boolean isMultiHead() { return true; } + + public Node ctrl() { return in(0); } + public Node pred() { return in(1); } + + @Override + public Type compute() { + // If the If node is not reachable then neither is any following Proj + if (ctrl()._type != Type.CONTROL && ctrl()._type != Type.BOTTOM ) + return TypeTuple.IF_NEITHER; + // If constant is 0 then false branch is reachable + // Else true branch is reachable + if (pred()._type instanceof TypeInteger ti && ti.isConstant()) { + if (ti.value() == 0) return TypeTuple.IF_FALSE; + else return TypeTuple.IF_TRUE; + } + + // Hunt up the immediate dominator tree. If we find an identical if + // test on either the true or false branch, then this test matches. + for( Node dom = idom(), prior=this; dom!=null; prior=dom, dom = dom.idom() ) + if( dom instanceof IfNode iff && iff.pred()==pred() ) + return prior instanceof ProjNode proj + // Repeated test, dominated on one side. Test result is the same. + ? (proj._idx==0 ? TypeTuple.IF_TRUE : TypeTuple.IF_FALSE) + : null; // Repeated test not dominated on one side + + return TypeTuple.IF_BOTH; + } + + @Override + public Node idealize() { + return null; + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/LoopNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/LoopNode.java new file mode 100644 index 00000000..eaf19199 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/LoopNode.java @@ -0,0 +1,35 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; + +import java.util.BitSet; + +public class LoopNode extends RegionNode { + + public LoopNode( Node entry, Node back) { super(null,entry,back); } + + Node entry() { return in(1); } + Node back () { return in(2); } + + @Override + public String label() { return "Loop"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return sb.append("Loop").append(_nid); + } + + @Override + public Type compute() { + return inProgress() ? Type.CONTROL : super.compute(); + } + + @Override + public Node idealize() { + return inProgress() ? null : super.idealize(); + } + + @Override Node idom() { return entry(); } + + @Override public boolean inProgress() { return back()==null; } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/MinusNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/MinusNode.java new file mode 100644 index 00000000..8a96693d --- /dev/null +++ b/chapter07/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.TypeInteger; + +import java.util.BitSet; + +public class MinusNode extends Node { + public MinusNode(Node in) { super(null, in); } + + @Override public String label() { return "Minus"; } + + @Override public String glabel() { return "-"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("(-"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if (in(1)._type instanceof TypeInteger i0) + return i0.isConstant() ? TypeInteger.constant(-i0.value()) : i0; + return Type.BOTTOM; + } + + @Override + public Node idealize() { return null; } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/MulNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/MulNode.java new file mode 100644 index 00000000..70e6c0db --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/MulNode.java @@ -0,0 +1,58 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class MulNode extends Node { + public MulNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Mul"; } + + @Override public String glabel() { return "*"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("*"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + 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 Type.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() ) + return swap12(); + + // Do we have ((x * (phi cons)) * con) ? + // Do we have ((x * (phi cons)) * (phi cons)) ? + // Push constant up through the phi: x * (phi con0*con0 con1*con1...) + Node phicon = AddNode.phiCon(this,true); + if( phicon!=null ) return phicon; + + return null; + } + @Override Node copy(Node lhs, Node rhs) { return new MulNode(lhs,rhs); } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/MultiNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/MultiNode.java new file mode 100644 index 00000000..81c90f68 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/MultiNode.java @@ -0,0 +1,7 @@ +package com.seaofnodes.simple.node; + +public abstract class MultiNode extends Node { + + public MultiNode(Node... inputs) { super(inputs); } + +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/Node.java b/chapter07/src/main/java/com/seaofnodes/simple/node/Node.java new file mode 100644 index 00000000..fcc8df85 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/Node.java @@ -0,0 +1,467 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.Type; + +import java.util.*; + +/** + * 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 {@link #isCFG} node. + */ + 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; + + + /** + * 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. + * */ + 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.addUse( this ); + } + + // Easy reading label for debugger, e.g. "Add" or "Region" or "EQ" + public abstract String label(); + + // Unique label for graph visualization, e.g. "Add12" or "Region30" or "EQ99" + public String uniqueName() { return label() + _nid; } + + // Graphical label, e.g. "+" or "Region" or "==" + public String glabel() { return label(); } + + + // ------------------------------------------------------------------------ + + // Debugger Printing. + + // {@code toString} is what you get in the debugger. It has to print 1 + // line (because this is what a debugger typically displays by default) and + // has to be robust with broken graph/nodes. + @Override + public final String toString() { return print(); } + + // This is a *deep* print. 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(), new BitSet()).toString(); + } + // This is the common print: check for repeats, check for DEAD and print + // "DEAD" else call the per-Node print1. + final StringBuilder _print0(StringBuilder sb, BitSet visited) { + if (visited.get(_nid)) + return sb.append(label()); + visited.set(_nid); + return isDead() + ? sb.append(uniqueName()).append(":DEAD") + : _print1(sb, visited); + } + // Every Node implements this; a partial-line recursive print + abstract StringBuilder _print1(StringBuilder sb, BitSet visited); + + + // 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 _print_line( 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("%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 boolean isMultiHead() { return false; } + public boolean isMultiTail() { return false; } + + // ------------------------------------------------------------------------ + // Graph Node & Edge manipulation + + /** + * Gets the ith input node + * @param i Offset of the input node + * @return Input node or null + */ + public Node in(int i) { return _inputs.get(i); } + + public int nIns() { return _inputs.size(); } + + public Node out(int i) { return _outputs.get(i); } + + public int nOuts() { return _outputs.size(); } + + public boolean isUnused() { return nOuts() == 0; } + + public boolean isCFG() { 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 + * <em>def</em> go dead. This function is co-recursive with {@link #kill}. + * <p> + + * This method is the normal path for altering a Node, because it does the + * proper default edge maintenance. It also <em>immediately</em> kills + * Nodes that lose their last use; at times care must be taken to avoid + * killing Nodes that are being used without having an output Node. This + * definitely happens in the middle of recursive {@link #peephole} calls. + * + * @param idx which def to set + * @param new_def the new definition + * @return new_def for flow coding + */ + Node set_def(int idx, Node new_def ) { + Node old_def = in(idx); + if( old_def == new_def ) return this; // No change + // If new def is not null, add the corresponding def->use edge + // This needs to happen before removing the old node's def->use edge as + // the new_def might get killed if the old node kills it recursively. + if( new_def != null ) + new_def.addUse(this); + 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); + // Return self for easy flow-coding + return new_def; + } + + // Remove the numbered input, compressing the inputs in-place. This + // shuffles the order deterministically - which is suitable for Region and + // Phi, but not for every Node. + void delDef(int idx) { + Node old_def = in(idx); + 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 + Utils.del(_inputs, idx); + } + + /** + * Add a new def to an existing Node. Keep the edges correct by + * adding the corresponding <em>def->use</em> edge. + * + * @param new_def the new definition, appended to the end of existing definitions + * @return new_def for flow coding + */ + public Node 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.addUse(this); + return new_def; + } + + // Breaks the edge invariants, used temporarily + protected <N extends Node> N addUse(Node n) { _outputs.add(n); return (N)this; } + + // Remove node 'use' from 'def's (i.e. our) output list, by compressing the list in-place. + // Return true if the output list is empty afterward. + // Error is 'use' does not exist; ok for 'use' to be null. + protected boolean delUse( Node use ) { + Utils.del(_outputs, Utils.find(_outputs, use)); + return _outputs.size() == 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.removeLast(); + 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; } + + // Shortcuts to stop DCE mid-parse + // Add bogus null use to keep node alive + public <N extends Node> N keep() { return addUse(null); } + // Remove bogus null. + public <N extends Node> N unkeep() { delUse(null); return (N)this; } + + + // Replace self with nnn in the graph, making 'this' go dead + void subsume( Node nnn ) { + assert nnn!=this; + while( nOuts() > 0 ) { + Node n = _outputs.removeLast(); + int idx = Utils.find(n._inputs, this); + n._inputs.set(idx,nnn); + nnn.addUse(n); + } + kill(); + } + + // ------------------------------------------------------------------------ + // Graph-based optimizations + + /** + * We allow disabling peephole opt so that we can observe the + * full graph, vs the optimized graph. + */ + public static boolean _disablePeephole = false; + + /** + * Try to peephole at this node and return a better replacement Node 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.keep(); // Keep m alive + kill(); // Kill self because replacing with 'm' + m.unkeep(); // Okay to peephole m + } + return m; + } + + /** + * This function needs to be + * <a href="https://en.wikipedia.org/wiki/Monotonic_function">Monotonic</a> + * as it is part of a Monotone Analysis Framework. + * <a href="https://www.cse.psu.edu/~gxt29/teaching/cse597s21/slides/08monotoneFramework.pdf">See for example this set of slides</a>. + * <p> + * For Chapter 2, all our Types are really integer constants, and so all + * the needed properties are trivially true, and we can ignore the high + * theory. Much later on, this will become important and allow us to do + * many fancy complex optimizations trivially... because theory. + * <p> + * 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(); + + + // ------------------------------------------------------------------------ + // Peephole utilities + + // Swap inputs without letting either input go dead during the swap. + Node swap12() { + Node tmp = in(1); + _inputs.set(1,in(2)); + _inputs.set(2,tmp); + return this; + } + + // does this node contain all constants? + // Ignores in(0), as is usually control. + boolean all_cons() { + for( int i=1; i<nIns(); i++ ) + if( !(in(i)._type.isConstant()) ) + return false; + 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; + } + + // 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"); } + + /** + * Used to allow repeating tests in the same JVM. This just resets the + * Node unique id generator, and is done as part of making a new Parser. + */ + public static void reset() { UNIQUE_ID = 1; _disablePeephole=false; } + + /** + * Debugging utility to find a Node by index + */ + public Node find(int nid) { return _find(new BitSet(),nid); } + private Node _find(BitSet visit, int nid) { + if( _nid==nid ) return this; + if( visit.get(_nid) ) return null; + visit.set(_nid); + for( Node def : _inputs ) + if( def!=null ) { + Node rez = def._find(visit,nid); + if( rez != null ) return rez; + } + for( Node use : _outputs ) { + Node rez = use._find(visit,nid); + if( rez != null ) return rez; + } + return null; + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/NotNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/NotNode.java new file mode 100644 index 00000000..04e6c75b --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/NotNode.java @@ -0,0 +1,30 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class NotNode extends Node { + public NotNode(Node in) { super(null, in); } + + @Override public String label() { return "Not"; } + + @Override public String glabel() { return "!"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("(!"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + if( in(1)._type instanceof TypeInteger i0 ) + return i0.isConstant() ? TypeInteger.constant(i0.value()==0 ? 1 : 0) : i0; + return Type.BOTTOM; + } + + @Override + public Node idealize() { return null; } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/PhiNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/PhiNode.java new file mode 100644 index 00000000..202dbe37 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/PhiNode.java @@ -0,0 +1,101 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; + +import java.util.BitSet; + +public class PhiNode extends Node { + + final String _label; + + public PhiNode(String label, Node... inputs) { super(inputs); _label = label; } + + @Override public String label() { return "Phi_"+_label; } + + @Override public String glabel() { return "φ_"+_label; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + if( region().inProgress() ) + sb.append("Z"); + sb.append("Phi("); + for( Node in : _inputs ) { + if (in == null) sb.append("____"); + else in._print0(sb, visited); + sb.append(","); + } + sb.setLength(sb.length()-1); + sb.append(")"); + return sb; + } + + RegionNode region() { return (RegionNode)in(0); } + @Override public boolean isMultiTail() { return true; } + + @Override + public Type compute() { + if( !(region() instanceof RegionNode r) || r.inProgress() ) + return Type.BOTTOM; + Type t = Type.TOP; + for (int i = 1; i < nIns(); i++) + t = t.meet(in(i)._type); + return t; + } + + @Override + public Node idealize() { + if( !(region() instanceof RegionNode r ) || r.inProgress() ) + return null; + + // If we have only a single unique input, become it. + Node live = singleUniqueInput(); + if (live != null) + return live; + + // Pull "down" a common data op. One less op in the world. One more + // Phi, but Phis do not make code. + // Phi(op(A,B),op(Q,R),op(X,Y)) becomes + // op(Phi(A,Q,X), Phi(B,R,Y)). + Node op = in(1); + if( op.nIns()==3 && op.in(0)==null && !op.isCFG() && same_op() ) { + Node[] lhss = new Node[nIns()]; + Node[] rhss = new Node[nIns()]; + lhss[0] = rhss[0] = in(0); // Set Region + for( int i=1; i<nIns(); i++ ) { + lhss[i] = in(i).in(1); + rhss[i] = in(i).in(2); + } + Node phi_lhs = new PhiNode(_label,lhss).peephole(); + Node phi_rhs = new PhiNode(_label,rhss).peephole(); + return op.copy(phi_lhs,phi_rhs); + } + + return null; + } + + private boolean same_op() { + for( int i=2; i<nIns(); i++ ) + if( in(1).getClass() != in(i).getClass() ) + return false; + return true; + } + + /** + * If only single unique input, return it + */ + private Node singleUniqueInput() { + Node live = null; + for( int i=1; i<nIns(); i++ ) + if( region().in(i)._type != Type.XCONTROL && in(i) != this ) + if( live == null || live == in(i) ) live = in(i); + else return null; + return live; + } + + @Override + boolean all_cons() { + if( !(region() instanceof RegionNode r) || r.inProgress() ) + return false; + return super.all_cons(); + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/ProjNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/ProjNode.java new file mode 100644 index 00000000..79ba9d13 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/ProjNode.java @@ -0,0 +1,49 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeTuple; + +import java.util.BitSet; + +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, BitSet visited) { return sb.append(_label); } + + @Override public boolean isCFG() { return _idx==0 || ctrl() instanceof IfNode; } + @Override public boolean isMultiTail() { return in(0).isMultiHead(); } + + public MultiNode ctrl() { return (MultiNode)in(0); } + + @Override + public Type compute() { + Type t = ctrl()._type; + return t instanceof TypeTuple tt ? tt._types[_idx] : Type.BOTTOM; + } + + @Override + public Node idealize() { + if( ctrl()._type instanceof TypeTuple tt ) { + if( tt._types[_idx]==Type.XCONTROL ) + return new ConstantNode(Type.XCONTROL).peephole(); // We are dead + if( tt._types[1-_idx]==Type.XCONTROL ) // Only true for IfNodes + return ctrl().in(0); // We become our input control + } + return null; + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/RegionNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/RegionNode.java new file mode 100644 index 00000000..3b793758 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/RegionNode.java @@ -0,0 +1,81 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.Utils; +import com.seaofnodes.simple.type.Type; + +import java.util.Collection; +import java.util.BitSet; + +public class RegionNode extends Node { + public RegionNode(Node... inputs) { super(inputs); } + + @Override + public String label() { return "Region"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return sb.append(label()).append(_nid); + } + + @Override public boolean isCFG() { return true; } + @Override public boolean isMultiHead() { return true; } + + @Override + public Type compute() { + Type t = Type.XCONTROL; + for (int i = 1; i < nIns(); i++) + t = t.meet(in(i)._type); + return t; + } + + @Override + public Node idealize() { + int path = findDeadInput(); + if( path != 0 ) { + for( Node phi : _outputs ) + if( phi instanceof PhiNode ) + phi.delDef(path); + delDef(path); + + // If down to a single input, become that input - but also make all + // Phis an identity on *their* single input. + if( nIns()==2 ) { + for( Node phi : _outputs ) + if( phi instanceof PhiNode ) + // Currently does not happen, because no loops + throw Utils.TODO(); + return in(1); + } + return this; + } + return null; + } + + private int findDeadInput() { + for( int i=1; i<nIns(); i++ ) + if( in(i)._type==Type.XCONTROL ) + return i; + return 0; // All inputs alive + } + + // Immediate dominator of Region is a little more complicated. + private Node _idom; // Immediate dominator cache + @Override Node idom() { + if( _idom != null ) return _idom; // Return cached copy + 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(); + while( lhs != rhs ) { + if( lhs==null || rhs==null ) return null; + 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; + return (_idom=lhs); + } + + public boolean inProgress() { return false; } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/ReturnNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/ReturnNode.java new file mode 100644 index 00000000..4dea773a --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/ReturnNode.java @@ -0,0 +1,46 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.*; + +import java.util.BitSet; + +/** + * The Return node has two inputs. The first input is a control node and the + * second is the data node that supplies the return value. + * <p> + * In this presentation, Return functions as a Stop node, since multiple <code>return</code> statements are not possible. + * The Stop node will be introduced in Chapter 6 when we implement <code>if</code> statements. + * <p> + * The Return's output is the value from the data node. + */ +public class ReturnNode extends Node { + + 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, BitSet visited) { + return expr()._print0(sb.append("return "), visited).append(";"); + } + + @Override public boolean isCFG() { return true; } + + @Override + public Type compute() { + return new TypeTuple(ctrl()._type,expr()._type); + } + + @Override + public Node idealize() { + if( ctrl()._type==Type.XCONTROL ) + return ctrl(); + return null; + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/ScopeNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/ScopeNode.java new file mode 100644 index 00000000..cc6af152 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/ScopeNode.java @@ -0,0 +1,169 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; + +import java.util.*; + +/** + * The Scope node is purely a parser helper - it tracks names to nodes with a + * stack of scopes. + */ +public class ScopeNode extends Node { + + /** + * The control is a name that binds to the currently active control + * node in the graph + */ + public static final String CTRL = "$ctrl"; + public static final String ARG0 = "arg"; + + /** + * Names for every input edge + */ + public final Stack<HashMap<String, Integer>> _scopes; + + + // A new ScopeNode + public ScopeNode() { + _scopes = new Stack<>(); + _type = Type.BOTTOM; + } + + + @Override public String label() { return "Scope"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + sb.append("Scope[ "); + String[] names = reverse_names(); + for( int j=0; j<nIns(); j++ ) { + sb.append(names[j]).append(":"); + Node n = in(j); + n._print0(sb, visited).append(" "); + } + sb.setLength(sb.length()-1); + return sb.append("]"); + } + + // Expensive... + public String[] reverse_names() { + String[] names = new String[nIns()]; + for( HashMap<String,Integer> syms : _scopes ) + for( String name : syms.keySet() ) + names[syms.get(name)] = name; + return names; + } + + @Override public Type compute() { return Type.BOTTOM; } + + @Override public Node idealize() { return null; } + + public void push() { _scopes.push(new HashMap<>()); } + public void pop() { pop_n(_scopes.pop().size()); } + + // Create a new name in the current scope + public Node define( String name, Node n ) { + HashMap<String,Integer> syms = _scopes.lastElement(); + if( syms.put(name,nIns()) != null ) + return null; // Double define + return add_def(n); + } + + // Lookup a name. It is recursive to support lazy Phis on loops (coming in chapter 8). + public Node lookup(String name) { return update(name,null,_scopes.size()-1); } + // If the name is present in any scope, then redefine else null + public Node update(String name, Node n) { return update(name,n,_scopes.size()-1); } + // Both recursive lookup and update. + private Node update( String name, Node n, int i ) { + if( i<0 ) return null; // Missed in all scopes, not found + var syms = _scopes.get(i); + var idx = syms.get(name); + if( idx == null ) return update(name,n,i-1); // Missed in this scope, recursively look + Node old = in(idx); + // If n is null we are looking up rather than updating + return n==null ? old : set_def(idx,n); + } + + public Node ctrl() { return in(0); } + + /** + * The ctrl of a ScopeNode is always bound to the currently active + * control node in the graph, via a special name '$ctrl' that is not + * a valid identifier in the language grammar and hence cannot be + * referenced in Simple code. + * + * @param n The node to be bound to '$ctrl' + * + * @return Node that was bound + */ + public Node ctrl(Node n) { return set_def(0,n); } + + /** + * Duplicate a ScopeNode; including all levels, up to Nodes. So this is + * neither shallow (would dup the Scope but not the internal HashMap + * tables), nor deep (would dup the Scope, the HashMap tables, but then + * also the program Nodes). + * <p> + * The new Scope is a full-fledged Node with proper use<->def edges. + */ + public ScopeNode dup() { return dup(false); } + public ScopeNode dup(boolean loop) { + ScopeNode dup = new ScopeNode(); + // Our goals are: + // 1) duplicate the name bindings of the ScopeNode across all stack levels + // 2) Make the new ScopeNode a user of all the nodes bound + // 3) Ensure that the order of defs is the same to allow easy merging + for( HashMap<String,Integer> syms : _scopes ) + dup._scopes.push(new HashMap<>(syms)); + String[] reverse = reverse_names(); + dup.add_def(ctrl()); // Control input is just copied + for( int i=1; i<nIns(); i++ ) { + if ( !loop ) { dup.add_def(in(i)); } + else { + // Create a phi node with second input as null - to be filled in + // by endLoop() below + dup.add_def(new PhiNode(reverse[i], ctrl(), in(i), null).peephole()); + // Ensure our node has the same phi in case we created one + set_def(i, dup.in(i)); + } + } + return dup; + } + + /** + * Merges the names whose node bindings differ, by creating Phi node for such names + * The names could occur at all stack levels, but a given name can only differ in the + * innermost stack level where the name is bound. + * + * @param that The ScopeNode to be merged into this + * @return A new node representing the merge point + */ + public Node mergeScopes(ScopeNode that) { + RegionNode r = (RegionNode) ctrl(new RegionNode(null,ctrl(), that.ctrl()).keep()); + String[] ns = reverse_names(); + // Note that we skip i==0, which is bound to '$ctrl' + for (int i = 1; i < nIns(); i++) + if( in(i) != that.in(i) ) // No need for redundant Phis + set_def(i, new PhiNode(ns[i], r, in(i), that.in(i)).peephole()); + that.kill(); // Kill merged scope + return r.unkeep().peephole(); + } + + // Merge the backedge scope into this loop head scope + // We set the second input to the phi from the back edge (i.e. loop body) + public void endLoop(ScopeNode back, ScopeNode exit ) { + Node ctrl = ctrl(); + assert ctrl instanceof LoopNode loop && loop.inProgress(); + ctrl.set_def(2,back.ctrl()); + for( int i=1; i<nIns(); i++ ) { + PhiNode phi = (PhiNode)in(i); + assert phi.region()==ctrl && phi.in(2)==null; + phi.set_def(2,back.in(i)); + // Do an eager useless-phi removal + Node in = phi.peephole(); + if( in != phi ) + phi.subsume(in); + } + back.kill(); // Loop backedge is dead + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/StartNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/StartNode.java new file mode 100644 index 00000000..19d03e0f --- /dev/null +++ b/chapter07/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.TypeTuple; + +import java.util.BitSet; + +/** + * 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 { + + final TypeTuple _args; + + public StartNode(Type[] args) { + super(); + _args = new TypeTuple(args); + _type = _args; + } + + @Override + public String label() { return "Start"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + return sb.append(label()); + } + + @Override public boolean isCFG() { return true; } + @Override public boolean isMultiHead() { return true; } + + @Override + public TypeTuple compute() { return _args; } + + @Override + public Node idealize() { return null; } + + // No immediate dominator, and idepth==0 + @Override + Node idom() { return null; } + +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/StopNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/StopNode.java new file mode 100644 index 00000000..c4375771 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/StopNode.java @@ -0,0 +1,53 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; + +import java.util.BitSet; + +public class StopNode extends Node { + public StopNode(Node... inputs) { + super(inputs); + } + + @Override + public String label() { + return "Stop"; + } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + if( ret()!=null ) return ret()._print0(sb, visited); + sb.append("Stop[ "); + for( Node ret : _inputs ) + ret._print0(sb, visited).append(" "); + return sb.append("]"); + } + + @Override public boolean isCFG() { return true; } + + // If a single Return, return it. + // Otherwise, null because ambiguous. + public ReturnNode ret() { + return nIns()==1 ? (ReturnNode)in(0) : null; + } + + @Override + public Type compute() { + return Type.BOTTOM; + } + + @Override + public Node idealize() { + int len = nIns(); + for( int i=0; i<nIns(); i++ ) + if( in(i)._type==Type.XCONTROL ) + delDef(i--); + if( len != nIns() ) return this; + return null; + } + + public Node addReturn(Node node) { + return add_def(node); + } + +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/node/SubNode.java b/chapter07/src/main/java/com/seaofnodes/simple/node/SubNode.java new file mode 100644 index 00000000..1484ab8a --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/node/SubNode.java @@ -0,0 +1,43 @@ +package com.seaofnodes.simple.node; + +import com.seaofnodes.simple.type.Type; +import com.seaofnodes.simple.type.TypeInteger; + +import java.util.BitSet; + +public class SubNode extends Node { + public SubNode(Node lhs, Node rhs) { super(null, lhs, rhs); } + + @Override public String label() { return "Sub"; } + + @Override public String glabel() { return "-"; } + + @Override + StringBuilder _print1(StringBuilder sb, BitSet visited) { + in(1)._print0(sb.append("("), visited); + in(2)._print0(sb.append("-"), visited); + return sb.append(")"); + } + + @Override + public Type compute() { + 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 Type.BOTTOM; + } + + @Override + public Node idealize() { + // Sub of same is 0 + if( in(1)==in(2) ) + return new ConstantNode(TypeInteger.constant(0)); + + return null; + } + + @Override Node copy(Node lhs, Node rhs) { return new SubNode(lhs,rhs); } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/type/Type.java b/chapter07/src/main/java/com/seaofnodes/simple/type/Type.java new file mode 100644 index 00000000..f88403a5 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/type/Type.java @@ -0,0 +1,77 @@ +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 class Type { + + // ---------------------------------------------------------- + // Simple types are implemented fully here. "Simple" means: the code and + // type hierarchy are simple, not that the Type is conceptually simple. + static final byte TBOT = 0; // Bottom (ALL) + static final byte TTOP = 1; // Top (ANY) + static final byte TCTRL = 2; // Ctrl flow bottom + static final byte TXCTRL = 3; // Ctrl flow top (mini-lattice: any-xctrl-ctrl-all) + static final byte TSIMPLE = 4; // End of the Simple Types + static final byte TINT = 5; // All Integers; see TypeInteger + static final byte TTUPLE = 6; // Tuples; finite collections of unrelated Types, kept in parallel + + public final byte _type; + + public boolean is_simple() { return _type < TSIMPLE; } + private static final String[] STRS = new String[]{"Bot","Top","Ctrl","~Ctrl"}; + protected Type(byte type) { _type = type; } + + public static final Type BOTTOM = new Type( TBOT ); // ALL + public static final Type TOP = new Type( TTOP ); // ANY + public static final Type CONTROL = new Type( TCTRL ); // Ctrl + public static final Type XCONTROL = new Type( TXCTRL ); // ~Ctrl + + public boolean isConstant() { return _type == TTOP || _type == TXCTRL; } + + public StringBuilder _print(StringBuilder sb) {return is_simple() ? sb.append(STRS[_type]) : sb;} + + public final Type meet(Type t) { + // Shortcut for the self case + if( t == this ) return this; + // Same-type is always safe in the subclasses + if( _type==t._type ) return xmeet(t); + // Reverse; xmeet 2nd arg is never "is_simple" and never equal to "this". + if( is_simple() ) return this.xmeet(t ); + if( t.is_simple() ) return t .xmeet(this); + return 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) { + assert is_simple(); // Should be overridden in subclass + // ANY meet anything is thing; thing meet ALL is ALL + if( _type==TBOT || t._type==TTOP ) return this; + if( _type==TTOP || t._type==TBOT ) return t; + // 'this' is {TCTRL,TXCTRL} + if( !t.is_simple() ) return BOTTOM; + // 't' is {TCTRL,TXCTRL} + return _type==TCTRL || t._type==TCTRL ? CONTROL : XCONTROL; + } + + @Override + public final String toString() { + return _print(new StringBuilder()).toString(); + } +} diff --git a/chapter07/src/main/java/com/seaofnodes/simple/type/TypeInteger.java b/chapter07/src/main/java/com/seaofnodes/simple/type/TypeInteger.java new file mode 100644 index 00000000..93f5eae3 --- /dev/null +++ b/chapter07/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); + public final static TypeInteger ZERO= new TypeInteger(true, 0); + + 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) { + super(TINT); + _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 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 xmeet(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/chapter07/src/main/java/com/seaofnodes/simple/type/TypeTuple.java b/chapter07/src/main/java/com/seaofnodes/simple/type/TypeTuple.java new file mode 100644 index 00000000..f8c3b3c8 --- /dev/null +++ b/chapter07/src/main/java/com/seaofnodes/simple/type/TypeTuple.java @@ -0,0 +1,32 @@ +package com.seaofnodes.simple.type; + +public class TypeTuple extends Type { + + public final Type[] _types; + + public TypeTuple(Type... _types) { + super(TTUPLE); + this._types = _types; + } + + @Override + public Type xmeet(Type other) { + throw new UnsupportedOperationException("Meet on Tuple Type not yet implemented"); + } + + @Override + public StringBuilder _print(StringBuilder sb) { + sb.append("["); + for( Type t : _types ) + t._print(sb).append(","); + sb.setLength(sb.length()-1); + sb.append("]"); + return sb; + } + + public static final TypeTuple IF_BOTH = new TypeTuple(new Type[]{Type.CONTROL, Type.CONTROL}); + public static final TypeTuple IF_NEITHER = new TypeTuple(new Type[]{Type.XCONTROL,Type.XCONTROL}); + public static final TypeTuple IF_TRUE = new TypeTuple(new Type[]{Type.CONTROL, Type.XCONTROL}); + public static final TypeTuple IF_FALSE = new TypeTuple(new Type[]{Type.XCONTROL,Type.CONTROL}); + +} diff --git a/chapter07/src/test/java/com/seaofnodes/simple/Chapter07Test.java b/chapter07/src/test/java/com/seaofnodes/simple/Chapter07Test.java new file mode 100644 index 00000000..efcf90f5 --- /dev/null +++ b/chapter07/src/test/java/com/seaofnodes/simple/Chapter07Test.java @@ -0,0 +1,1026 @@ +package com.seaofnodes.simple; + +import com.seaofnodes.simple.node.*; +import com.seaofnodes.simple.type.TypeInteger; +import org.junit.Test; + +import static org.junit.Assert.*; + +public class Chapter07Test { + + @Test + public void testChapter7Example() { + Parser parser = new Parser( + """ + while(arg < 10) { + arg = arg + 1; + #showGraph; + } + return arg; + """); + Node._disablePeephole = true; + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop6,arg,(Phi_arg+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + Node._disablePeephole = false; + } + + @Test + public void testChapter7Regression() { + Parser parser = new Parser( + +""" +int a = 1; +if(arg){}else{ + while(a < 10) { + a = a + 1; + } +} +return a; +"""); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Region23,1,Phi(Loop11,1,(Phi_a+1)));", stop.toString()); + } + + @Test + public void testChapter7WhileNested() { + Parser parser = new Parser( + +""" +int sum = 0; +int i = 0; +while(i < arg) { + i = i + 1; + int j = 0; + while( j < arg ) { + sum = sum + j; + j = j + 1; + } +} +return sum; +"""); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop8,0,Phi(Loop21,Phi_sum,(Phi(Loop,0,(Phi_j+1))+Phi_sum)));", stop.toString()); + System.out.println(IRPrinter.prettyPrint(stop,99)); + } + + @Test + public void testChapter7WhileScope() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + if (a == 2) a = 3; + else b = 4; +} +return b; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop8,2,Phi(Region27,Phi_b,4));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + Node._disablePeephole = false; + System.out.println(IRPrinter.prettyPrint(stop,99)); + } + + @Test + public void testChapter7WhileNestedIfAndInc() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + if (a == 2) a = 3; + else b = 4; + b = b + 1; + a = a + 1; +} +return b; +"""); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop8,2,(Phi(Region27,Phi_b,4)+1));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + System.out.println(IRPrinter.prettyPrint(stop,99)); + } + + + @Test + public void testChapter7While() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + a = a + 1; + a = a + 2; +} +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop7,1,((Phi_a+1)+2));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + Node._disablePeephole = false; + } + + @Test + public void testChapter7WhilePeep() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + a = a + 1; + a = a + 2; +} +return a; +"""); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop7,1,(Phi_a+3));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + @Test + public void testChapter7While2() { + Parser parser = new Parser( +""" +int a = 1; +while(arg) a = 2; +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop7,1,2);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + Node._disablePeephole = false; + System.out.println(IRPrinter.prettyPrint(stop,99)); + } + + @Test + public void testChapter7While2Peep() { + Parser parser = new Parser( +""" +int a = 1; +while(arg) a = 2; +return a; +"""); + StopNode stop = parser.parse(false); + assertEquals("return Phi(Loop7,1,2);", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + System.out.println(IRPrinter.prettyPrint(stop, 99)); + } + + @Test + public void testChapter7While3() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop7,1,((Phi_a+1)+2));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + Node._disablePeephole = false; + } + + @Test + public void testChapter7While3Peep() { + Parser parser = new Parser( +""" +int a = 1; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop7,1,(Phi_a+3));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + @Test + public void testChapter7While4() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + Node._disablePeephole = true; + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop8,1,((Phi_a+1)+2));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + Node._disablePeephole = false; + } + + @Test + public void testChapter7While4Peep() { + Parser parser = new Parser( +""" +int a = 1; +int b = 2; +while(a < 10) { + int b = a + 1; + a = b + 2; +} +return a; +"""); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Loop8,1,(Phi_a+3));", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + @Test + public void testChapter6PeepholeReturn() { + Parser parser = new Parser( +""" +if( true ) return 2; +return 1; +"""); + StopNode stop = parser.parse(true); + assertEquals("return 2;", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + @Test + public void testChapter6PeepholeRotate() { + Parser parser = new Parser( +""" +int a = 1; +if (arg) + a = 2; +return (arg < a) < 3; +"""); + StopNode stop = parser.parse(false); + assertEquals("return ((arg<Phi(Region12,2,1))<3);", stop.toString()); + } + + @Test + public void testChapter6PeepholeCFG() { + Parser parser = new Parser( +""" +int a=1; +if( true ) + a=2; +else + a=3; +return a; +"""); + StopNode stop = parser.parse(true); + assertEquals("return 2;", stop.toString()); + assertTrue(stop.ret().ctrl() instanceof ProjNode); + } + + @Test + public void testChapter6IfIf() { + Parser parser = new Parser( +""" +int a=1; +if( arg!=1 ) + a=2; +else + a=3; +int b=4; +if( a==2 ) + b=42; +else + b=5; +return b;""", TypeInteger.BOT); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Region32,42,5);", stop.toString()); + } + + @Test + public void testChapter6IfArgIf() { + Parser parser = new Parser( +""" +int a=1; +if( 1==1 ) + a=2; +else + a=3; +int b=4; +if( arg==2 ) + b=a; +else + b=5; +return b;""", TypeInteger.BOT); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Region28,2,5);", stop.toString()); + } + + @Test + public void testChapter6Merge3With2() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( arg==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +#showGraph;""", TypeInteger.constant(2)); + StopNode stop = parser.parse(); + assertEquals("return 5;", stop.toString()); + } + + @Test + public void testChapter6Merge3With1() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( arg==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.constant(1)); + StopNode stop = parser.parse(true); + assertEquals("return 3;", stop.toString()); + } + + @Test + public void testChapter6Merge3Peephole() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( 1==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.BOT); + StopNode stop = parser.parse(true); + assertEquals("return Phi(Region36,3,Phi(Region34,4,5));", stop.toString()); + } + + @Test + public void testChapter6Merge3Peephole1() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( 1==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.constant(1)); + StopNode stop = parser.parse(true); + assertEquals("return 3;", stop.toString()); + } + + @Test + public void testChapter6Merge3Peephole3() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( 1==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +""", TypeInteger.constant(3)); + StopNode stop = parser.parse(true); + assertEquals("return 4;", stop.toString()); + } + + @Test + public void testChapter6Demo1NonConst() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +if( arg ) { + a = 2; + if( arg ) { b = 2; } + else b = 3; +} +return a+b; +"""); + StopNode ret = parser.parse(true); + assertEquals("return Phi(Region22,4,1);", ret.toString()); + } + + + @Test + public void testChapter6Demo1True() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +if( arg ) { + a = 2; + if( arg ) { b = 2; } + else b = 3; +} +return a+b; +""", TypeInteger.constant(1)); + StopNode ret = parser.parse(true); + assertEquals("return 4;", ret.toString()); + } + + @Test + public void testChapter6Demo1False() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +if( arg ) { + a = 2; + if( arg ) { b = 2; } + else b = 3; +} +return a+b; +""", TypeInteger.constant(0)); + StopNode ret = parser.parse(true); + assertEquals("return 1;", ret.toString()); + } + + @Test + public void testChapter6Demo2NonConst() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +int c = 0; +if( arg ) { + a = 1; + if( arg==2 ) { c=2; } else { c=3; } + if( arg ) { b = 2; } + else b = 3; +} +return a+b+c; +"""); + StopNode ret = parser.parse(true); + assertEquals("return (Phi(Region33,Phi(Region22,2,3),0)+Phi(Region,3,1));", ret.toString()); + } + + + @Test + public void testChapter6Demo2True() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +int c = 0; +if( arg ) { + a = 1; + if( arg==2 ) { c=2; } else { c=3; } + if( arg ) { b = 2; } + else b = 3; +} +return a+b+c; +""", TypeInteger.constant(1)); + StopNode ret = parser.parse(true); + assertEquals("return 6;", ret.toString()); + } + + @Test + public void testChapter6Demo2arg2() { + Parser parser = new Parser(""" +int a = 0; +int b = 1; +int c = 0; +if( arg ) { + a = 1; + if( arg==2 ) { c=2; } else { c=3; } + if( arg ) { b = 2; } + else b = 3; +} +return a+b+c; +""", TypeInteger.constant(2)); + StopNode ret = parser.parse(true); + assertEquals("return 5;", ret.toString()); + } + + + + @Test + public void testChapter5IfStmt() { + Parser parser = new Parser( +""" +int a = 1; +if (arg == 1) + a = arg+2; +else { + a = arg-3; + #showGraph; +} +#showGraph; +return a;"""); + StopNode ret = parser.parse(true); + assertEquals("return Phi(Region17,(arg+2),(arg-3));", ret.toString()); + } + + @Test + public void testChapter5Test() { + Parser parser = new Parser( +""" +int c = 3; +int b = 2; +if (arg == 1) { + b = 3; + c = 4; +} +return c;""", TypeInteger.BOT); + StopNode ret = parser.parse(true); + assertEquals("return Phi(Region16,4,3);", ret.toString()); + } + + @Test + public void testChapter5Return2() { + Parser parser = new Parser( +""" +if( arg==1 ) + return 3; +else + return 4; +#showGraph;""", TypeInteger.BOT); + StopNode stop = parser.parse(); + assertEquals("Stop[ return 3; return 4; ]", stop.toString()); + } + + @Test + public void testChapter5IfMergeB() { + Parser parser = new Parser( +""" +int a=arg+1; +int b=0; +if( arg==1 ) + b=a; +else + b=a+1; +return a+b;"""); + StopNode ret = parser.parse(true); + assertEquals("return ((arg*2)+Phi(Region20,2,3));", ret.toString()); + } + + @Test + public void testChapter5IfMerge2() { + Parser parser = new Parser( +""" +int a=arg+1; +int b=arg+2; +if( arg==1 ) + b=b+a; +else + a=b+1; +return a+b;"""); + StopNode ret = parser.parse(true); + assertEquals("return ((Phi(Region31,(arg*2),arg)+arg)+Phi(Region,4,5));", ret.toString()); + } + + @Test + public void testChapter5Merge3() { + Parser parser = new Parser( +""" +int a=1; +if( arg==1 ) + if( arg==2 ) + a=2; + else + a=3; +else if( arg==3 ) + a=4; +else + a=5; +return a; +#showGraph;""", TypeInteger.BOT); + StopNode stop = parser.parse(); + assertEquals("return Phi(Region33,Phi(Region21,2,3),Phi(Region31,4,5));", stop.toString()); + } + + @Test + public void testChapter5Merge4() { + Parser parser = new Parser( +""" +int a=0; +int b=0; +if( arg ) + a=1; +if( arg==0 ) + b=2; +return arg+a+b; +#showGraph;""", TypeInteger.BOT); + StopNode stop = parser.parse(); + assertEquals("return ((arg+Phi(Region13,1,0))+Phi(Region22,2,0));", stop.toString()); + } + + @Test + public void testChapter5Merge5() { + Parser parser = new Parser( +""" +int a=arg==2; +if( arg==1 ) +{ + a=arg==3; +} +return a;"""); + StopNode ret = parser.parse(true); + assertEquals("return (arg==Phi(Region16,3,2));", ret.toString()); + } + + @Test + public void testChapter5True() { + StopNode stop = new Parser("return true;").parse(); + assertEquals("return 1;",stop.toString()); + } + + @Test + public void testChapter5HalfDef() { + try { + new Parser("if( arg==1 ) int b=2; return b;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Cannot define a new name on one arm of an if",e.getMessage()); + } + } + + @Test + public void testChapter5HalfDef2() { + try { + new Parser("if( arg==1 ) { int b=2; } else { int b=3; } return b;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'b'",e.getMessage()); + } + } + + @Test + public void testChapter5BadNum() { + try { + new Parser("return 1-;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected an identifier or expression: ;",e.getMessage()); + } + } + + @Test + public void testChapter5Keyword1() { + try { + new Parser("int true=0; return true;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Expected an identifier, found 'true'",e.getMessage()); + } + } + + @Test + public void testChapter5Keyword2() { + try { + new Parser("int else=arg; if(else) else=2; else else=1; return else;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Expected an identifier, found 'else'",e.getMessage()); + } + } + + @Test + public void testChapter5Keyword3() { + try { + new Parser("int a=1; ififif(arg)inta=2;return a;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected =: (",e.getMessage()); + } + } + + @Test + public void testChapter4Peephole() { + Parser parser = new Parser("return 1+arg+2; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return (arg+3);", ret.print()); + } + + @Test + public void testChapter4Peephole2() { + Parser parser = new Parser("return (1+arg)+2;"); + StopNode ret = parser.parse(); + assertEquals("return (arg+3);", ret.print()); + } + + @Test + public void testChapter4Add0() { + Parser parser = new Parser("return 0+arg;"); + StopNode ret = parser.parse(); + assertEquals("return arg;", ret.print()); + } + + @Test + public void testChapter4AddAddMul() { + Parser parser = new Parser("return arg+0+arg;"); + StopNode ret = parser.parse(); + assertEquals("return (arg*2);", ret.print()); + } + + @Test + public void testChapter4Peephole3() { + Parser parser = new Parser("return 1+arg+2+arg+3; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return ((arg*2)+6);", ret.print()); + } + + @Test + public void testChapter4Mul1() { + Parser parser = new Parser("return 1*arg;"); + StopNode ret = parser.parse(); + assertEquals("return arg;", ret.print()); + } + + @Test + public void testChapter4VarArg() { + Parser parser = new Parser("return arg; #showGraph;"); + StopNode stop = parser.parse(); + ReturnNode ret = stop.ret(); + assertTrue(ret.in(0) instanceof ProjNode); + assertTrue(ret.in(1) instanceof ProjNode); + } + + @Test + public void testChapter4ConstantArg() { + Parser parser = new Parser("return arg; #showGraph;", TypeInteger.constant(2)); + StopNode ret = parser.parse(); + assertEquals("return 2;", ret.print()); + } + + @Test + public void testChapter4CompEq() { + Parser parser = new Parser("return 3==3; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return 1;", ret.print()); + } + + @Test + public void testChapter4CompEq2() { + Parser parser = new Parser("return 3==4; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return 0;", ret.print()); + } + + @Test + public void testChapter4CompNEq() { + Parser parser = new Parser("return 3!=3; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return 0;", ret.print()); + } + + @Test + public void testChapter4CompNEq2() { + Parser parser = new Parser("return 3!=4; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return 1;", ret.print()); + } + + @Test + public void testChapter4Bug1() { + Parser parser = new Parser("int a=arg+1; int b=a; b=1; return a+2; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return (arg+3);", ret.print()); + } + + @Test + public void testChapter4Bug2() { + Parser parser = new Parser("int a=arg+1; a=a; return a; #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return (arg+1);", ret.print()); + } + + @Test + public void testChapter4Bug3() { + try { + new Parser("inta=1; return a;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'inta'",e.getMessage()); + } + } + + @Test + public void testChapter4Bug4() { + Parser parser = new Parser("return -arg;"); + StopNode ret = parser.parse(); + assertEquals("return (-arg);", ret.print()); + } + + @Test + public void testVarDecl() { + Parser parser = new Parser("int a=1; return a;"); + StopNode ret = parser.parse(); + assertEquals("return 1;", ret.print()); + } + + @Test + public void testVarAdd() { + Parser parser = new Parser("int a=1; int b=2; return a+b;"); + StopNode ret = parser.parse(); + assertEquals("return 3;", ret.print()); + } + + @Test + public void testVarScope() { + Parser parser = new Parser("int a=1; int b=2; int c=0; { int b=3; c=a+b; } return c;"); + StopNode ret = parser.parse(); + assertEquals("return 4;", ret.print()); + } + + @Test + public void testVarScopeNoPeephole() { + Parser parser = new Parser("int a=1; int b=2; int c=0; { int b=3; c=a+b; #showGraph; } return c; #showGraph;"); + Node._disablePeephole = true; + StopNode ret = parser.parse(); + Node._disablePeephole = false; + assertEquals("return (1+3);", ret.print()); + } + + @Test + public void testVarDist() { + Parser parser = new Parser("int x0=1; int y0=2; int x1=3; int y1=4; return (x0-x1)*(x0-x1) + (y0-y1)*(y0-y1); #showGraph;"); + StopNode ret = parser.parse(); + assertEquals("return 8;", ret.print()); + } + + @Test + public void testSelfAssign() { + try { + new Parser("int a=a; return a;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Undefined name 'a'",e.getMessage()); + } + } + + @Test + public void testChapter2ParseGrammar() { + Parser parser = new Parser("return 1+2*3+-5;"); + Node._disablePeephole = true; // disable peephole so we can observe full graph + StopNode ret = parser.parse(); + assertEquals("return (1+((2*3)+(-5)));", ret.print()); + GraphVisualizer gv = new GraphVisualizer(); + System.out.println(gv.generateDotOutput(parser)); + Node._disablePeephole = false; + } + + @Test + public void testChapter2AddPeephole() { + Parser parser = new Parser("return 1+2;"); + StopNode ret = parser.parse(); + assertEquals("return 3;", ret.print()); + } + + @Test + public void testChapter2SubPeephole() { + Parser parser = new Parser("return 1-2;"); + StopNode ret = parser.parse(); + assertEquals("return -1;", ret.print()); + } + + @Test + public void testChapter2MulPeephole() { + Parser parser = new Parser("return 2*3;"); + StopNode ret = parser.parse(); + assertEquals("return 6;", ret.print()); + } + + @Test + public void testChapter2DivPeephole() { + Parser parser = new Parser("return 6/3;"); + StopNode ret = parser.parse(); + assertEquals("return 2;", ret.print()); + } + + @Test + public void testChapter2MinusPeephole() { + Parser parser = new Parser("return 6/-3;"); + StopNode ret = parser.parse(); + assertEquals("return -2;", ret.print()); + } + + @Test + public void testChapter2Example() { + Parser parser = new Parser("return 1+2*3+-5;"); + StopNode ret = parser.parse(); + assertEquals("return 2;", ret.print()); + GraphVisualizer gv = new GraphVisualizer(); + System.out.println(gv.generateDotOutput(parser)); + } + + @Test + public void testSimpleProgram() { + Parser parser = new Parser("return 1;"); + StopNode stop = parser.parse(); + StartNode start = Parser.START; + ReturnNode ret = (ReturnNode)stop.in(0); + + assertTrue(ret.ctrl() instanceof ProjNode); + Node expr = ret.expr(); + if( expr instanceof ConstantNode con ) { + assertEquals(start,con.in(0)); + assertEquals(TypeInteger.constant(1), con._type); + } else { + fail(); + } + } + + @Test + public void testZero() { + Parser parser = new Parser("return 0;"); + parser.parse(); + StartNode start = Parser.START; + for( Node use : start._outputs ) + if( use instanceof ConstantNode con ) + assertEquals(TypeInteger.constant(0),con._type); + } + + @Test + public void testBad1() { + try { + new Parser("ret").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected =: ",e.getMessage()); + } + } + + @Test + public void testBad2() { + try { + new Parser("return 0123;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error: integer values cannot start with '0'",e.getMessage()); + } + } + + @Test + public void testNotBad3() { + // this test used to fail in chapter 1 + assertEquals("return 12;", new Parser("return --12;").parse().print()); + } + + @Test + public void testBad4() { + try { + new Parser("return 100").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected ;: ",e.getMessage()); + } + } + + @Test + public void testNotBad5() { + // this test used to fail in chapter 1 + assertEquals("return -100;", new Parser("return -100;").parse().print()); + } + + @Test + public void testBad6() { + try { + new Parser("int a=1; int b=2; int c=0; { int b=3; c=a+b;").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, expected }: ",e.getMessage()); + } + } + + @Test + public void testBad7() { + try { + new Parser("return 1;}").parse(); + fail(); + } catch( RuntimeException e ) { + assertEquals("Syntax error, unexpected }",e.getMessage()); + } + } + +} |