Merge pull request #1377 from undingen/new_bst4

BST: convert all nodes to directly operate at vregs instead of names

src/analysis/function_analysis.cpp

@@ -55,7 +55,7 @@ private:
     VRegMap<Status> statuses;
     LivenessAnalysis* analysis;
 
-    void _doLoad(int vreg, BST_Name* node) {
+    void _doLoad(int vreg) {
         Status& status = statuses[vreg];
         status.addUsage(Status::USED);
     }
@@ -70,50 +70,28 @@ private:
 
 public:
     LivenessBBVisitor(LivenessAnalysis* analysis)
-        : statuses(analysis->cfg->getVRegInfo().getTotalNumOfVRegs()), analysis(analysis) {}
+        : NoopBSTVisitor(true /* skip child CFG nodes */),
+          statuses(analysis->cfg->getVRegInfo().getTotalNumOfVRegs()),
+          analysis(analysis) {}
 
     bool firstIsUse(int vreg) const { return getStatusFirst(vreg) == Status::USED; }
-
     bool firstIsDef(int vreg) const { return getStatusFirst(vreg) == Status::DEFINED; }
 
-    bool isKilledAt(BST_Name* node, bool is_live_at_end) { return node->is_kill; }
-
-    bool visit_classdef(BST_ClassDef* node) {
-        for (auto e : node->bases)
-            e->accept(this);
-        for (auto e : node->decorator_list)
-            e->accept(this);
-
-        return true;
+    bool visit_vreg(int* vreg, bool is_dst) override {
+        if (*vreg >= 0) {
+            if (is_dst)
+                _doStore(*vreg);
+            else
+                _doLoad(*vreg);
         }
-
-    bool visit_functiondef(BST_FunctionDef* node) {
-        for (auto* d : node->decorator_list)
-            d->accept(this);
-        for (auto* d : node->args->defaults)
-            d->accept(this);
-
         return true;
     }
 
-    bool visit_name(BST_Name* node) {
-        if (node->vreg == -1)
-            return true;
-
-        if (node->ctx_type == AST_TYPE::Load)
-            _doLoad(node->vreg, node);
-        else if (node->ctx_type == AST_TYPE::Del) {
-            // Hack: we don't have a bytecode for temporary-kills:
-            if (node->vreg >= analysis->cfg->getVRegInfo().getNumOfUserVisibleVRegs())
+    bool visit_deletename(BST_DeleteName* node) override {
+        if (node->vreg < 0 || node->vreg >= analysis->cfg->getVRegInfo().getNumOfUserVisibleVRegs())
             return true;
-            _doLoad(node->vreg, node);
+        _doLoad(node->vreg);
         _doStore(node->vreg);
-        } else if (node->ctx_type == AST_TYPE::Store || node->ctx_type == AST_TYPE::Param)
-            _doStore(node->vreg);
-        else {
-            ASSERT(0, "%d", node->ctx_type);
-            abort();
-        }
         return true;
     }
 };
@@ -136,13 +114,6 @@ LivenessAnalysis::LivenessAnalysis(CFG* cfg) : cfg(cfg), result_cache(cfg->getVR
 LivenessAnalysis::~LivenessAnalysis() {
 }
 
-bool LivenessAnalysis::isKill(BST_Name* node, CFGBlock* parent_block) {
-    if (node->id.s()[0] != '#')
-        return false;
-
-    return liveness_cache[parent_block]->isKilledAt(node, isLiveAtEnd(node->vreg, parent_block));
-}
-
 bool LivenessAnalysis::isLiveAtEnd(int vreg, CFGBlock* block) {
     // Is a user-visible name, always live:
     if (vreg < block->cfg->getVRegInfo().getNumOfUserVisibleVRegs())
@@ -228,102 +199,55 @@ public:
     virtual void processBB(Map& starting, CFGBlock* block) const;
 };
 
-class DefinednessVisitor : public BSTVisitor {
+class DefinednessVisitor : public NoopBSTVisitor {
 private:
     typedef DefinednessBBAnalyzer::Map Map;
     Map& state;
 
     void _doSet(int vreg) {
+        if (vreg == VREG_UNDEFINED)
+            return;
         assert(vreg >= 0 && vreg < state.numVregs());
         state[vreg] = DefinednessAnalysis::Defined;
     }
 
-    void _doSet(BST* t) {
-        switch (t->type) {
-            case BST_TYPE::Attribute:
-                // doesn't affect definedness (yet?)
-                break;
-            case BST_TYPE::Name: {
-                auto name = bst_cast<BST_Name>(t);
-                if (name->lookup_type == ScopeInfo::VarScopeType::FAST
-                    || name->lookup_type == ScopeInfo::VarScopeType::CLOSURE) {
-                    assert(name->vreg != -1);
-                    _doSet(name->vreg);
-                } else if (name->lookup_type == ScopeInfo::VarScopeType::GLOBAL
-                           || name->lookup_type == ScopeInfo::VarScopeType::NAME) {
-                    assert(name->vreg == -1);
-                    // skip
-                } else {
-                    RELEASE_ASSERT(0, "%d", static_cast<int>(name->lookup_type));
-                }
-                break;
-            }
-            case BST_TYPE::Subscript:
-                break;
-            case BST_TYPE::Tuple: {
-                BST_Tuple* tt = bst_cast<BST_Tuple>(t);
-                for (int i = 0; i < tt->elts.size(); i++) {
-                    _doSet(tt->elts[i]);
-                }
-                break;
-            }
-            default:
-                ASSERT(0, "Unknown type for DefinednessVisitor: %d", t->type);
-        }
-    }
-
 public:
-    DefinednessVisitor(Map& state) : state(state) {}
-
-    virtual bool visit_assert(BST_Assert* node) { return true; }
-    virtual bool visit_branch(BST_Branch* node) { return true; }
-    virtual bool visit_expr(BST_Expr* node) { return true; }
-    virtual bool visit_invoke(BST_Invoke* node) { return false; }
-    virtual bool visit_jump(BST_Jump* node) { return true; }
-    virtual bool visit_print(BST_Print* node) { return true; }
-    virtual bool visit_raise(BST_Raise* node) { return true; }
-    virtual bool visit_return(BST_Return* node) { return true; }
-
-    virtual bool visit_delete(BST_Delete* node) {
-        auto t = node->target;
-        if (t->type == BST_TYPE::Name) {
-            BST_Name* name = bst_cast<BST_Name>(t);
-            if (name->lookup_type != ScopeInfo::VarScopeType::GLOBAL
-                && name->lookup_type != ScopeInfo::VarScopeType::NAME) {
-                assert(name->vreg != -1);
-                state[name->vreg] = DefinednessAnalysis::Undefined;
-            } else
-                assert(name->vreg == -1);
-        } else {
-            // The CFG pass should reduce all deletes to the "basic" deletes on names/attributes/subscripts.
-            // If not, probably the best way to do this would be to just do a full BST traversal
-            // and look for BST_Name's with a ctx of Del
-            assert(t->type == BST_TYPE::Attribute || t->type == BST_TYPE::Subscript);
-        }
-        return true;
+    DefinednessVisitor(Map& state) : NoopBSTVisitor(true /* skip child CFG nodes */), state(state) {}
+    bool visit_vreg(int* vreg, bool is_dest) override {
+        if (*vreg < 0)
+            return false;
+
+        if (is_dest)
+            state[*vreg] = DefinednessAnalysis::Defined;
+        else
+            state[*vreg] = DefinednessAnalysis::Undefined;
+        return false;
     }
 
-    virtual bool visit_classdef(BST_ClassDef* node) {
-        assert(0 && "I think this isn't needed");
-        //_doSet(node->name);
+    bool visit_deletename(BST_DeleteName* node) override {
+        if (node->lookup_type != ScopeInfo::VarScopeType::GLOBAL
+            && node->lookup_type != ScopeInfo::VarScopeType::NAME) {
+            assert(node->vreg >= 0);
+            state[node->vreg] = DefinednessAnalysis::Undefined;
+        } else
+            assert(node->vreg == VREG_UNDEFINED);
         return true;
     }
 
-    virtual bool visit_functiondef(BST_FunctionDef* node) {
-        assert(0 && "I think this isn't needed");
-        //_doSet(node->name);
+    bool visit_copyvreg(BST_CopyVReg* node) override {
+        // don't visit the vreg it will never get killed
+        // visit_vreg(&node->vreg_src, false);
+        _doSet(node->vreg_dst);
         return true;
     }
 
-    virtual bool visit_assign(BST_Assign* node) {
-        _doSet(node->target);
+    bool visit_loadname(BST_LoadName* node) override {
+        // don't visit the vreg it will never get killed
+        // visit_vreg(&node->vreg, false);
+        _doSet(node->vreg_dst);
         return true;
     }
 
-    virtual bool visit_arguments(BST_arguments* node) { RELEASE_ASSERT(0, "this shouldn't get hit"); }
-
-    virtual bool visit_exec(BST_Exec* node) { return true; }
-
     friend class DefinednessBBAnalyzer;
 };
 
@@ -460,11 +384,13 @@ const VRegSet& PhiAnalysis::getAllRequiredFor(CFGBlock* block) {
 }
 
 bool PhiAnalysis::isRequired(int vreg, CFGBlock* block) {
+    assert(vreg >= 0);
     assert(required_phis.count(block));
     return required_phis.find(block)->second[vreg];
 }
 
 bool PhiAnalysis::isRequiredAfter(int vreg, CFGBlock* block) {
+    assert(vreg >= 0);
     // If there are multiple successors, then none of them are allowed
     // to require any phi nodes
     if (block->successors.size() != 1)
@@ -475,6 +401,7 @@ bool PhiAnalysis::isRequiredAfter(int vreg, CFGBlock* block) {
 }
 
 bool PhiAnalysis::isPotentiallyUndefinedAfter(int vreg, CFGBlock* block) {
+    assert(vreg >= 0);
     for (auto b : block->successors) {
         if (isPotentiallyUndefinedAt(vreg, b))
             return true;
@@ -483,6 +410,7 @@ bool PhiAnalysis::isPotentiallyUndefinedAfter(int vreg, CFGBlock* block) {
 }
 
 bool PhiAnalysis::isPotentiallyUndefinedAt(int vreg, CFGBlock* block) {
+    assert(vreg >= 0);
     assert(definedness.defined_at_beginning.count(block));
     return definedness.defined_at_beginning.find(block)->second[vreg] != DefinednessAnalysis::Defined;
 }

src/analysis/function_analysis.h

@@ -26,9 +26,7 @@
 
 namespace pyston {
 
-class BST_arguments;
 class BST_Jump;
-class BST_Name;
 class CFG;
 class CFGBlock;
 class LivenessBBVisitor;
@@ -47,9 +45,6 @@ public:
     LivenessAnalysis(CFG* cfg);
     ~LivenessAnalysis();
 
-    // we don't keep track of node->parent_block relationships, so you have to pass both:
-    bool isKill(BST_Name* node, CFGBlock* parent_block);
-
     bool isLiveAtEnd(int vreg, CFGBlock* block);
 };
 

src/analysis/scoping_analysis.cpp

@@ -36,16 +36,11 @@ ScopingResults::ScopingResults(ScopeInfo* scope_info, bool globals_from_module)
     deref_info = scope_info->getAllDerefVarsAndInfo();
 }
 
-DerefInfo ScopingResults::getDerefInfo(BST_Name* node) const {
+DerefInfo ScopingResults::getDerefInfo(BST_LoadName* node) const {
     assert(node->lookup_type == ScopeInfo::VarScopeType::DEREF);
     assert(node->deref_info.offset != INT_MAX);
     return node->deref_info;
 }
-size_t ScopingResults::getClosureOffset(BST_Name* node) const {
-    assert(node->lookup_type == ScopeInfo::VarScopeType::CLOSURE);
-    assert(node->closure_offset != -1);
-    return node->closure_offset;
-}
 
 class YieldVisitor : public NoopASTVisitor {
 public:

src/analysis/type_analysis.h

@@ -24,9 +24,9 @@
 namespace pyston {
 
 class CFGBlock;
+class ConstantVRegInfo;
 class BoxedClass;
-class BST_expr;
-class BST_slice;
+class BST_stmt_with_dest;
 class OSREntryDescriptor;
 
 class TypeAnalysis {
@@ -40,15 +40,14 @@ public:
 
     virtual ConcreteCompilerType* getTypeAtBlockStart(int vreg, CFGBlock* block) = 0;
     virtual ConcreteCompilerType* getTypeAtBlockEnd(int vreg, CFGBlock* block) = 0;
-    virtual BoxedClass* speculatedExprClass(BST_expr*) = 0;
-    virtual BoxedClass* speculatedExprClass(BST_slice*) = 0;
+    virtual BoxedClass* speculatedExprClass(BST_stmt_with_dest*) = 0;
 };
 
 TypeAnalysis* doTypeAnalysis(CFG* cfg, const ParamNames& param_names,
                              const std::vector<ConcreteCompilerType*>& arg_types, EffortLevel effort,
-                             TypeAnalysis::SpeculationLevel speculation);
+                             TypeAnalysis::SpeculationLevel speculation, const ConstantVRegInfo& constant_vregs);
 TypeAnalysis* doTypeAnalysis(const OSREntryDescriptor* entry_descriptor, EffortLevel effort,
-                             TypeAnalysis::SpeculationLevel speculation);
+                             TypeAnalysis::SpeculationLevel speculation, const ConstantVRegInfo& constant_vregs);
 }
 
 #endif

src/asm_writing/icinfo.cpp

@@ -341,7 +341,7 @@ ICSlotInfo* ICInfo::pickEntryForRewrite(const char* debug_name) {
 }
 
 static llvm::DenseMap<void*, ICInfo*> ics_by_return_addr;
-static llvm::DenseMap<BST*, ICInfo*> ics_by_ast_node;
+static llvm::DenseMap<BST_stmt*, ICInfo*> ics_by_ast_node;
 
 ICInfo::ICInfo(void* start_addr, void* slowpath_rtn_addr, void* continue_addr, StackInfo stack_info, int size,
                llvm::CallingConv::ID calling_conv, LiveOutSet _live_outs, assembler::GenericRegister return_register,
@@ -485,13 +485,13 @@ bool ICInfo::isMegamorphic() {
     return times_rewritten >= IC_MEGAMORPHIC_THRESHOLD;
 }
 
-ICInfo* ICInfo::getICInfoForNode(BST* node) {
+ICInfo* ICInfo::getICInfoForNode(BST_stmt* node) {
     auto&& it = ics_by_ast_node.find(node);
     if (it != ics_by_ast_node.end())
         return it->second;
     return NULL;
 }
-void ICInfo::associateNodeWithICInfo(BST* node, std::unique_ptr<TypeRecorder> type_recorder) {
+void ICInfo::associateNodeWithICInfo(BST_stmt* node, std::unique_ptr<TypeRecorder> type_recorder) {
     assert(!this->node);
     this->node = node;
     this->type_recorder = std::move(type_recorder);

src/asm_writing/icinfo.h

@@ -105,7 +105,7 @@ private:
     std::vector<Location> ic_global_decref_locations;
 
     // associated BST node for this IC
-    BST* node;
+    BST_stmt* node;
 
     // for ICSlotRewrite:
     ICSlotInfo* pickEntryForRewrite(const char* debug_name);
@@ -145,8 +145,8 @@ public:
 
     friend class ICSlotRewrite;
 
-    static ICInfo* getICInfoForNode(BST* node);
-    void associateNodeWithICInfo(BST* node, std::unique_ptr<TypeRecorder> type_recorder);
+    static ICInfo* getICInfoForNode(BST_stmt* node);
+    void associateNodeWithICInfo(BST_stmt* node, std::unique_ptr<TypeRecorder> type_recorder);
 
     void appendDecrefInfosTo(std::vector<DecrefInfo>& dest_decref_infos);
 };

src/codegen/ast_interpreter.h

@@ -23,7 +23,6 @@ namespace gc {
 class GCVisitor;
 }
 
-class BST_expr;
 class BST_stmt;
 class BST_Jump;
 class Box;
@@ -46,11 +45,11 @@ struct ASTInterpreterJitInterface {
     static int getGlobalsOffset();
 
     static void delNameHelper(void* _interpreter, InternedString name);
-    static Box* derefHelper(void* interp, BST_Name* node);
+    static Box* derefHelper(void* interp, BST_LoadName* node);
     static Box* landingpadHelper(void* interp);
     static void pendingCallsCheckHelper();
     static void setExcInfoHelper(void* interp, STOLEN(Box*) type, STOLEN(Box*) value, STOLEN(Box*) traceback);
-    static void setLocalClosureHelper(void* interp, BST_Name* name, Box* v);
+    static void setLocalClosureHelper(void* interp, int vreg, int closure_offset, Box* v);
     static void uncacheExcInfoHelper(void* interp);
     static void raise0Helper(void* interp) __attribute__((noreturn));
     static Box* yieldHelper(void* interp, STOLEN(Box*) value);
@@ -79,7 +78,7 @@ Box* astInterpretFunction(BoxedCode* f, Box* closure, Box* generator, Box* globa
                           Box** args);
 Box* astInterpretFunctionEval(BoxedCode* cf, Box* globals, Box* boxedLocals);
 // this function is implemented in the src/codegen/ast_interpreter_exec.S assembler file
-extern "C" Box* astInterpretDeopt(BoxedCode* cf, BST_expr* after_expr, BST_stmt* enclosing_stmt, Box* expr_val,
+extern "C" Box* astInterpretDeopt(BoxedCode* cf, BST_stmt* enclosing_stmt, Box* expr_val,
                                   STOLEN(FrameStackState) frame_state);
 
 struct FrameInfo;

src/codegen/ast_interpreter_exec.S

@@ -43,7 +43,7 @@ executeInnerAndSetupFrame:
 // Our unwinder must be able to detect deopt frames and by writting this wrapper in assembler we can be sure to correctly
 // detect the frame independent of compiler optimizations because this function will always appear in the call stack.
 //
-// Box* astInterpretDeopt(FunctionMetadata* cf, AST_expr* after_expr, AST_stmt* enclosing_stmt, Box* expr_val,
+// Box* astInterpretDeopt(FunctionMetadata* cf, AST_stmt* enclosing_stmt, Box* expr_val,
 //                        FrameStackState frame_state);
 .text
 .globl astInterpretDeopt

src/codegen/baseline_jit.h

@@ -231,7 +231,7 @@ private:
     JitCodeBlock& code_block;
     RewriterVar* interp;
     RewriterVar* vregs_array;
-    llvm::DenseMap<InternedString, RewriterVar*> local_syms;
+    llvm::DenseMap<int /*vreg*/, RewriterVar*> local_syms;
     // keeps track which non block local vregs are known to have a non NULL value
     llvm::DenseSet<int> known_non_null_vregs;
 
@@ -249,7 +249,7 @@ private:
         uint8_t* end_addr;
         std::unique_ptr<ICSetupInfo> ic;
         StackInfo stack_info;
-        BST* node;
+        BST_stmt* node;
         std::vector<Location> decref_infos;
         std::unique_ptr<TypeRecorder> type_recorder;
     };
@@ -266,39 +266,41 @@ public:
     RewriterVar* imm(uint64_t val);
     RewriterVar* imm(void* val);
 
-    RewriterVar* emitAugbinop(BST_expr* node, RewriterVar* lhs, RewriterVar* rhs, int op_type);
+    RewriterVar* emitAugbinop(BST_stmt* node, RewriterVar* lhs, RewriterVar* rhs, int op_type);
     RewriterVar* emitApplySlice(RewriterVar* target, RewriterVar* lower, RewriterVar* upper);
-    RewriterVar* emitBinop(BST_expr* node, RewriterVar* lhs, RewriterVar* rhs, int op_type);
-    RewriterVar* emitCallattr(BST_expr* node, RewriterVar* obj, BoxedString* attr, CallattrFlags flags,
+    RewriterVar* emitBinop(BST_stmt* node, RewriterVar* lhs, RewriterVar* rhs, int op_type);
+    RewriterVar* emitCallattr(BST_stmt* node, RewriterVar* obj, BoxedString* attr, CallattrFlags flags,
                               const llvm::ArrayRef<RewriterVar*> args, std::vector<BoxedString*>* keyword_names);
-    RewriterVar* emitCompare(BST_expr* node, RewriterVar* lhs, RewriterVar* rhs, int op_type);
+    RewriterVar* emitCompare(BST_stmt* node, RewriterVar* lhs, RewriterVar* rhs, int op_type);
     RewriterVar* emitCreateDict();
     void emitDictSet(RewriterVar* dict, RewriterVar* k, RewriterVar* v);
     RewriterVar* emitCreateList(const llvm::ArrayRef<STOLEN(RewriterVar*)> values);
     RewriterVar* emitCreateSet(const llvm::ArrayRef<RewriterVar*> values);
     RewriterVar* emitCreateSlice(RewriterVar* start, RewriterVar* stop, RewriterVar* step);
     RewriterVar* emitCreateTuple(const llvm::ArrayRef<RewriterVar*> values);
-    RewriterVar* emitDeref(BST_Name* name);
+    RewriterVar* emitDeref(BST_LoadName* name);
     RewriterVar* emitExceptionMatches(RewriterVar* v, RewriterVar* cls);
-    RewriterVar* emitGetAttr(RewriterVar* obj, BoxedString* s, BST_expr* node);
-    RewriterVar* emitGetBlockLocal(BST_Name* name);
-    void emitKillTemporary(BST_Name* name);
+    RewriterVar* emitGetAttr(BST_stmt* node, RewriterVar* obj, BoxedString* s);
+    RewriterVar* emitGetBlockLocal(InternedString name, int vreg);
+    RewriterVar* emitGetBlockLocalMustExist(int vreg);
+    void emitKillTemporary(int vreg);
     RewriterVar* emitGetBoxedLocal(BoxedString* s);
     RewriterVar* emitGetBoxedLocals();
     RewriterVar* emitGetClsAttr(RewriterVar* obj, BoxedString* s);
     RewriterVar* emitGetGlobal(BoxedString* s);
-    RewriterVar* emitGetItem(BST_expr* node, RewriterVar* value, RewriterVar* slice);
-    RewriterVar* emitGetLocal(BST_Name* name);
+    RewriterVar* emitGetItem(BST_stmt* node, RewriterVar* value, RewriterVar* slice);
+    RewriterVar* emitGetLocal(InternedString name, int vreg);
+    RewriterVar* emitGetLocalMustExist(int vreg);
     RewriterVar* emitGetPystonIter(RewriterVar* v);
     RewriterVar* emitHasnext(RewriterVar* v);
-    RewriterVar* emitImportFrom(RewriterVar* module, BoxedString* name);
-    RewriterVar* emitImportName(int level, RewriterVar* from_imports, llvm::StringRef module_name);
+    RewriterVar* emitImportFrom(RewriterVar* module, RewriterVar* name);
+    RewriterVar* emitImportName(int level, RewriterVar* from_imports, RewriterVar* module_name);
     RewriterVar* emitImportStar(RewriterVar* module);
     RewriterVar* emitLandingpad();
     RewriterVar* emitNonzero(RewriterVar* v);
     RewriterVar* emitNotNonzero(RewriterVar* v);
     RewriterVar* emitRepr(RewriterVar* v);
-    RewriterVar* emitRuntimeCall(BST_expr* node, RewriterVar* obj, ArgPassSpec argspec,
+    RewriterVar* emitRuntimeCall(BST_stmt* node, RewriterVar* obj, ArgPassSpec argspec,
                                  const llvm::ArrayRef<RewriterVar*> args, std::vector<BoxedString*>* keyword_names);
     RewriterVar* emitUnaryop(RewriterVar* v, int op_type);
     std::vector<RewriterVar*> emitUnpackIntoArray(RewriterVar* v, uint64_t num);
@@ -317,14 +319,15 @@ public:
     void emitRaise0();
     void emitRaise3(RewriterVar* arg0, RewriterVar* arg1, RewriterVar* arg2);
     void emitReturn(RewriterVar* v);
-    void emitSetAttr(BST_expr* node, RewriterVar* obj, BoxedString* s, STOLEN(RewriterVar*) attr);
-    void emitSetBlockLocal(BST_Name* name, STOLEN(RewriterVar*) v);
+    void emitSetAttr(BST_stmt* node, RewriterVar* obj, BoxedString* s, STOLEN(RewriterVar*) attr);
+    void emitSetBlockLocal(int vreg, STOLEN(RewriterVar*) v);
     void emitSetCurrentInst(BST_stmt* node);
     void emitSetExcInfo(RewriterVar* type, RewriterVar* value, RewriterVar* traceback);
     void emitSetGlobal(BoxedString* s, STOLEN(RewriterVar*) v, bool are_globals_from_module);
     void emitSetItemName(BoxedString* s, RewriterVar* v);
     void emitSetItem(RewriterVar* target, RewriterVar* slice, RewriterVar* value);
-    void emitSetLocal(BST_Name* name, bool set_closure, STOLEN(RewriterVar*) v);
+    void emitSetLocal(int vreg, STOLEN(RewriterVar*) v);
+    void emitSetLocalClosure(BST_StoreName* name, STOLEN(RewriterVar*) v);
     // emitSideExit steals a full ref from v, not just a vref
     void emitSideExit(STOLEN(RewriterVar*) v, Box* cmp_value, CFGBlock* next_block);
     void emitUncacheExcInfo();
@@ -351,7 +354,7 @@ private:
                                            const llvm::ArrayRef<RewriterVar*> additional_uses);
     std::pair<RewriterVar*, RewriterAction*> emitPPCall(void* func_addr, llvm::ArrayRef<RewriterVar*> args,
                                                         unsigned short pp_size, bool should_record_type = false,
-                                                        BST* bst_node = NULL,
+                                                        BST_stmt* bst_node = NULL,
                                                         llvm::ArrayRef<RewriterVar*> additional_uses = {});
 
     static void assertNameDefinedHelper(const char* id);
@@ -371,7 +374,7 @@ private:
     void _emitJump(CFGBlock* b, RewriterVar* block_next, ExitInfo& exit_info);
     void _emitOSRPoint();
     void _emitPPCall(RewriterVar* result, void* func_addr, llvm::ArrayRef<RewriterVar*> args, unsigned short pp_size,
-                     BST* bst_node, llvm::ArrayRef<RewriterVar*> vars_to_bump);
+                     BST_stmt* bst_node, llvm::ArrayRef<RewriterVar*> vars_to_bump);
     void _emitRecordType(RewriterVar* obj_cls_var);
     void _emitReturn(RewriterVar* v);
     void _emitSideExit(STOLEN(RewriterVar*) var, RewriterVar* val_constant, CFGBlock* next_block,

src/codegen/codegen.h

@@ -73,7 +73,7 @@ struct GlobalState {
     llvm::Type* llvm_value_type, *llvm_value_type_ptr, *llvm_value_type_ptr_ptr;
     llvm::Type* llvm_class_type, *llvm_class_type_ptr;
     llvm::Type* llvm_opaque_type;
-    llvm::Type* llvm_boxedstring_type_ptr, *llvm_dict_type_ptr, *llvm_bststmt_type_ptr, *llvm_bstexpr_type_ptr;
+    llvm::Type* llvm_boxedstring_type_ptr, *llvm_dict_type_ptr, *llvm_bststmt_type_ptr;
     llvm::Type* llvm_frame_info_type;
     llvm::Type* llvm_code_type_ptr, *llvm_closure_type_ptr, *llvm_generator_type_ptr;
     llvm::Type* llvm_module_type_ptr, *llvm_bool_type_ptr;

src/codegen/compvars.cpp

@@ -2762,6 +2762,15 @@ public:
 
         return new ConcreteCompilerVariable(SLICE, rtn);
     }
+
+    CompilerVariable* dup(VAR* v, DupCache& cache) override {
+        // TODO copied from UnknownType
+        auto& rtn = cache[v];
+        if (rtn == NULL) {
+            rtn = new VAR(this, v->getValue());
+        }
+        return rtn;
+    }
 } _UNBOXED_SLICE;
 CompilerType* UNBOXED_SLICE = &_UNBOXED_SLICE;
 

src/codegen/irgen.cpp

@@ -337,6 +337,38 @@ llvm::Value* handlePotentiallyUndefined(ConcreteCompilerVariable* is_defined_var
     return phi;
 }
 
+// This is used to filter out any names set by an invoke statement at the end of the previous block, if we're in the
+// unwind path.
+class SymTableDstVRegDeleter : NoopBSTVisitor {
+private:
+    SymbolTable* sym_table;
+    bool created_new_sym_table;
+
+    SymTableDstVRegDeleter(SymbolTable* sym_table)
+        : NoopBSTVisitor(true /* skip child CFG nodes */), sym_table(sym_table), created_new_sym_table(false) {}
+
+protected:
+    bool visit_vreg(int* vreg, bool is_dst = false) override {
+        if (!is_dst || *vreg == VREG_UNDEFINED || !(*sym_table)[*vreg])
+            return false;
+
+        if (!created_new_sym_table) {
+            sym_table = new SymbolTable(*sym_table);
+            created_new_sym_table = true;
+        }
+        (*sym_table)[*vreg] = NULL;
+        return false;
+    }
+
+public:
+    static std::pair<SymbolTable*, bool /* created_new_sym_table */> removeDestVRegsFromSymTable(SymbolTable* sym_table,
+                                                                                                 BST_Invoke* stmt) {
+        SymTableDstVRegDeleter visitor(sym_table);
+        stmt->accept(&visitor);
+        return std::make_pair(visitor.sym_table, visitor.created_new_sym_table);
+    }
+};
+
 static void emitBBs(IRGenState* irstate, TypeAnalysis* types, const OSREntryDescriptor* entry_descriptor,
                     const BlockSet& blocks) {
     SourceInfo* source = irstate->getSourceInfo();
@@ -551,7 +583,7 @@ static void emitBBs(IRGenState* irstate, TypeAnalysis* types, const OSREntryDesc
         if (block == cfg->getStartingBlock()) {
             assert(entry_descriptor == NULL);
 
-            if (ENABLE_REOPT && effort < EffortLevel::MAXIMAL && source->ast_type != BST_TYPE::Module) {
+            if (ENABLE_REOPT && effort < EffortLevel::MAXIMAL && source->ast_type != AST_TYPE::Module) {
                 llvm::BasicBlock* preentry_bb = llvm::BasicBlock::Create(
                     g.context, "pre_entry", irstate->getLLVMFunction(), llvm_entry_blocks[cfg->getStartingBlock()]);
                 llvm::BasicBlock* reopt_bb = llvm::BasicBlock::Create(g.context, "reopt", irstate->getLLVMFunction());
@@ -695,16 +727,6 @@ static void emitBBs(IRGenState* irstate, TypeAnalysis* types, const OSREntryDesc
                 // analysis frameworks can't (yet) support the idea of a block flowing differently to its different
                 // successors.
                 //
-                // There are four kinds of BST statements which can set a name:
-                // - Assign
-                // - ClassDef
-                // - FunctionDef
-                // - Import, ImportFrom
-                //
-                // However, all of these get translated away into Assigns, so we only need to worry about those. Also,
-                // as an invariant, all assigns that can fail assign to a temporary rather than a python name. This
-                // ensures that we interoperate properly with definedness analysis.
-                //
                 // We only need to do this in the case that we have exactly one predecessor, because:
                 // - a block ending in an invoke will have multiple successors
                 // - critical edges (block with multiple successors -> block with multiple predecessors)
@@ -715,38 +737,9 @@ static void emitBBs(IRGenState* irstate, TypeAnalysis* types, const OSREntryDesc
 
                 SymbolTable* sym_table = ending_symbol_tables[pred];
                 bool created_new_sym_table = false;
-                if (last_inst->type == BST_TYPE::Invoke && bst_cast<BST_Invoke>(last_inst)->exc_dest == block) {
-                    BST_stmt* stmt = bst_cast<BST_Invoke>(last_inst)->stmt;
-
-                    // The CFG pass translates away these statements, so we should never encounter them.
-                    // If we did, we'd need to remove a name here.
-                    assert(stmt->type != BST_TYPE::ClassDef);
-                    assert(stmt->type != BST_TYPE::FunctionDef);
-                    assert(stmt->type != BST_TYPE::Import);
-                    assert(stmt->type != BST_TYPE::ImportFrom);
-
-                    if (stmt->type == BST_TYPE::Assign) {
-                        auto asgn = bst_cast<BST_Assign>(stmt);
-                        if (asgn->target->type == BST_TYPE::Name) {
-                            auto asname = bst_cast<BST_Name>(asgn->target);
-                            assert(asname->lookup_type != ScopeInfo::VarScopeType::UNKNOWN);
-
-                            InternedString name = asname->id;
-                            int vreg = bst_cast<BST_Name>(asgn->target)->vreg;
-                            assert(name.c_str()[0] == '#'); // it must be a temporary
-                            // You might think I need to check whether `name' is being assigned globally or locally,
-                            // since a global assign doesn't affect the symbol table. However, the CFG pass only
-                            // generates invoke-assigns to temporary variables. Just to be sure, we assert:
-                            assert(asname->lookup_type != ScopeInfo::VarScopeType::GLOBAL);
-
-                            // TODO: inefficient
-                            sym_table = new SymbolTable(*sym_table);
-                            ASSERT((*sym_table)[vreg] != NULL, "%d %s\n", block->idx, name.c_str());
-                            (*sym_table)[vreg] = NULL;
-                            created_new_sym_table = true;
-                        }
-                    }
-                }
+                if (last_inst->type == BST_TYPE::Invoke && bst_cast<BST_Invoke>(last_inst)->exc_dest == block)
+                    std::tie(sym_table, created_new_sym_table) = SymTableDstVRegDeleter::removeDestVRegsFromSymTable(
+                        sym_table, bst_cast<BST_Invoke>(last_inst));
 
                 generator->copySymbolsFrom(sym_table);
                 for (auto&& p : *definedness_tables[pred]) {
@@ -1034,7 +1027,7 @@ std::pair<CompiledFunction*, llvm::Function*> doCompile(BoxedCode* code, SourceI
     assert((entry_descriptor != NULL) + (spec != NULL) == 1);
 
     if (VERBOSITY("irgen") >= 2)
-        source->cfg->print();
+        source->cfg->print(code->constant_vregs);
 
     assert(g.cur_module == NULL);
 
@@ -1108,9 +1101,10 @@ std::pair<CompiledFunction*, llvm::Function*> doCompile(BoxedCode* code, SourceI
         speculation_level = TypeAnalysis::SOME;
     TypeAnalysis* types;
     if (entry_descriptor)
-        types = doTypeAnalysis(entry_descriptor, effort, speculation_level);
+        types = doTypeAnalysis(entry_descriptor, effort, speculation_level, code->constant_vregs);
     else
-        types = doTypeAnalysis(source->cfg, *param_names, spec->arg_types, effort, speculation_level);
+        types = doTypeAnalysis(source->cfg, *param_names, spec->arg_types, effort, speculation_level,
+                               code->constant_vregs);
 
 
     _t2.split();

src/codegen/irgen.h

@@ -29,7 +29,6 @@
 
 namespace pyston {
 
-class BST_expr;
 class BST_stmt;
 class CFGBlock;
 class GCBuilder;
@@ -37,6 +36,7 @@ class IREmitter;
 
 struct UnwindInfo {
 public:
+    BoxedCode* code;
     BST_stmt* current_stmt;
 
     llvm::BasicBlock* exc_dest;
@@ -46,15 +46,15 @@ public:
 
     bool hasHandler() const { return exc_dest != NULL; }
 
-    UnwindInfo(BST_stmt* current_stmt, llvm::BasicBlock* exc_dest, bool is_after_deopt = false)
-        : current_stmt(current_stmt), exc_dest(exc_dest), is_after_deopt(is_after_deopt) {}
+    UnwindInfo(BoxedCode* code, BST_stmt* current_stmt, llvm::BasicBlock* exc_dest, bool is_after_deopt = false)
+        : code(code), current_stmt(current_stmt), exc_dest(exc_dest), is_after_deopt(is_after_deopt) {}
 
     ExceptionStyle preferredExceptionStyle() const;
 
     // Risky!  This means that we can't unwind from this location, and should be used in the
     // rare case that there are language-specific reasons that the statement should not unwind
     // (ex: loading function arguments into the appropriate scopes).
-    static UnwindInfo cantUnwind() { return UnwindInfo(NULL, NULL); }
+    static UnwindInfo cantUnwind() { return UnwindInfo(NULL, NULL, NULL); }
 };
 
 // TODO get rid of this
@@ -119,7 +119,7 @@ public:
     // virtual void checkAndPropagateCapiException(const UnwindInfo& unw_info, llvm::Value* returned_val,
     // llvm::Value* exc_val, bool double_check = false) = 0;
 
-    virtual llvm::Value* createDeopt(BST_stmt* current_stmt, BST_expr* node, llvm::Value* node_value) = 0;
+    virtual llvm::Value* createDeopt(BST_stmt* current_stmt, llvm::Value* node_value) = 0;
 
     virtual BORROWED(Box*) getIntConstant(int64_t n) = 0;
     virtual BORROWED(Box*) getFloatConstant(double d) = 0;

src/codegen/irgen/irgenerator.h

@@ -203,8 +203,6 @@ class BST_Call;
 IREmitter* createIREmitter(IRGenState* irstate, llvm::BasicBlock*& curblock, IRGenerator* irgenerator = NULL);
 IRGenerator* createIRGenerator(IRGenState* irstate, std::unordered_map<CFGBlock*, llvm::BasicBlock*>& entry_blocks,
                                CFGBlock* myblock, TypeAnalysis* types);
-
-std::vector<BoxedString*>* getKeywordNameStorage(BST_Call* node);
 }
 
 #endif

src/codegen/runtime_hooks.cpp

@@ -151,10 +151,6 @@ void initGlobalFuncs(GlobalState& g) {
     assert(g.llvm_bststmt_type_ptr);
     g.llvm_bststmt_type_ptr = g.llvm_bststmt_type_ptr->getPointerTo();
 
-    g.llvm_bstexpr_type_ptr = g.stdlib_module->getTypeByName("class.pyston::BST_expr");
-    assert(g.llvm_bstexpr_type_ptr);
-    g.llvm_bstexpr_type_ptr = g.llvm_bstexpr_type_ptr->getPointerTo();
-
     // The LLVM vector type for the arguments that we pass to runtimeCall and related functions.
     // It will be a pointer to a type named something like class.std::vector or
     // class.std::vector.##. We can figure out exactly what it is by looking at the last

src/codegen/type_recording.cpp

@@ -42,7 +42,7 @@ Box* recordType(TypeRecorder* self, Box* obj) {
     return obj;
 }
 
-BoxedClass* predictClassFor(BST* node) {
+BoxedClass* predictClassFor(BST_stmt* node) {
     ICInfo* ic = ICInfo::getICInfoForNode(node);
     if (!ic || !ic->getTypeRecorder())
         return NULL;

src/codegen/type_recording.h

@@ -19,7 +19,7 @@
 
 namespace pyston {
 
-class BST;
+class BST_stmt;
 class Box;
 class BoxedClass;
 
@@ -44,7 +44,7 @@ public:
     friend Box* recordType(TypeRecorder*, Box*);
 };
 
-BoxedClass* predictClassFor(BST* node);
+BoxedClass* predictClassFor(BST_stmt* node);
 }
 
 #endif

src/codegen/unwinding.cpp

@@ -636,7 +636,7 @@ public:
 
             if (!getIsReraiseFlag()) {
                 // TODO: shouldn't fetch this multiple times?
-                frame_iter.getCurrentStatement()->cxx_exception_count++;
+                ++frame_iter.getFrameInfo()->code->cxx_exception_count[frame_iter.getCurrentStatement()];
                 exceptionAtLine(&exc_info.traceback);
             } else
                 getIsReraiseFlag() = false;

src/core/cfg.h

@@ -88,8 +88,7 @@ public:
     void unconnectFrom(CFGBlock* successor);
 
     void push_back(BST_stmt* node) { body.push_back(node); }
-    void print(llvm::raw_ostream& stream = llvm::outs());
-    void _print() { print(); }
+    void print(const ConstantVRegInfo& constant_vregs, llvm::raw_ostream& stream = llvm::outs());
 };
 
 // the vregs are split into three parts.
@@ -110,8 +109,8 @@ class VRegInfo {
 private:
 #ifndef NDEBUG
     // this maps use too much memory, we only use them in the debug build for asserts
-    llvm::DenseMap<InternedString, DefaultedInt<-1>> sym_vreg_map_user_visible;
-    llvm::DenseMap<InternedString, DefaultedInt<-1>> sym_vreg_map;
+    llvm::DenseMap<InternedString, DefaultedInt<VREG_UNDEFINED>> sym_vreg_map_user_visible;
+    llvm::DenseMap<InternedString, DefaultedInt<VREG_UNDEFINED>> sym_vreg_map;
 #endif
 
     // Reverse map, from vreg->symbol name.
@@ -126,8 +125,8 @@ public:
 #ifndef NDEBUG
     // map of all assigned names. if the name is block local the vreg number is not unique because this vregs get reused
     // between blocks.
-    const llvm::DenseMap<InternedString, DefaultedInt<-1>>& getSymVRegMap() const { return sym_vreg_map; }
-    const llvm::DenseMap<InternedString, DefaultedInt<-1>>& getUserVisibleSymVRegMap() const {
+    const llvm::DenseMap<InternedString, DefaultedInt<VREG_UNDEFINED>>& getSymVRegMap() const { return sym_vreg_map; }
+    const llvm::DenseMap<InternedString, DefaultedInt<VREG_UNDEFINED>>& getUserVisibleSymVRegMap() const {
         return sym_vreg_map_user_visible;
     }
 
@@ -169,7 +168,7 @@ public:
     int getNumOfCrossBlockVRegs() const { return num_vregs_cross_block; }
 
     bool hasVRegsAssigned() const { return num_vregs != -1; }
-    void assignVRegs(CFG* cfg, const ParamNames& param_names);
+    void assignVRegs(CFG* cfg, const ParamNames& param_names, llvm::DenseMap<int*, InternedString>& id_vreg);
 };
 
 // Control Flow Graph
@@ -211,7 +210,7 @@ public:
         blocks.push_back(block);
     }
 
-    void print(llvm::raw_ostream& stream = llvm::outs());
+    void print(const ConstantVRegInfo& constant_vregs, llvm::raw_ostream& stream = llvm::outs());
 };
 
 class VRegSet {
@@ -332,7 +331,7 @@ public:
 
 BoxedCode* computeAllCFGs(AST* ast, bool globals_from_module, FutureFlags future_flags, BoxedString* fn,
                           BoxedModule* bm);
-void printCFG(CFG* cfg);
+void printCFG(CFG* cfg, const ConstantVRegInfo& constant_vregs);
 }
 
 #endif

src/runtime/code.cpp

@@ -113,9 +113,10 @@ void BoxedCode::dealloc(Box* b) noexcept {
 }
 
 BoxedCode::BoxedCode(int num_args, bool takes_varargs, bool takes_kwargs, int firstlineno,
-                     std::unique_ptr<SourceInfo> source, ParamNames param_names, BoxedString* filename,
-                     BoxedString* name, Box* doc)
+                     std::unique_ptr<SourceInfo> source, ConstantVRegInfo constant_vregs, ParamNames param_names,
+                     BoxedString* filename, BoxedString* name, Box* doc)
     : source(std::move(source)),
+      constant_vregs(std::move(constant_vregs)),
       filename(incref(filename)),
       name(incref(name)),
       firstlineno(firstlineno),