Implement LLVM bits

Author: yuxuanchen1997

llvm/include/llvm/Transforms/Coroutines/CoroAnnotationElide.h

@@ -0,0 +1,34 @@
+//===- CoroAnnotationElide.h - Optimizing a coro_must_elide call ----------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// \file
+// This pass transforms all Call or Invoke instructions that are annotated
+// "coro_must_elide" to call the `.noalloc` variant of coroutine instead.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TRANSFORMS_COROUTINES_COROANNOTATIONELIDE_H
+#define LLVM_TRANSFORMS_COROUTINES_COROANNOTATIONELIDE_H
+
+#include "llvm/Analysis/CGSCCPassManager.h"
+#include "llvm/Analysis/LazyCallGraph.h"
+#include "llvm/IR/PassManager.h"
+
+namespace llvm {
+
+struct CoroAnnotationElidePass : PassInfoMixin<CoroAnnotationElidePass> {
+  CoroAnnotationElidePass() {}
+
+  PreservedAnalyses run(LazyCallGraph::SCC &C, CGSCCAnalysisManager &AM,
+                        LazyCallGraph &CG, CGSCCUpdateResult &UR);
+
+  static bool isRequired() { return false; }
+};
+} // end namespace llvm
+
+#endif // LLVM_TRANSFORMS_COROUTINES_COROANNOTATIONELIDE_H

llvm/lib/Passes/PassBuilder.cpp

@@ -134,6 +134,7 @@
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/AggressiveInstCombine/AggressiveInstCombine.h"
 #include "llvm/Transforms/CFGuard.h"
+#include "llvm/Transforms/Coroutines/CoroAnnotationElide.h"
 #include "llvm/Transforms/Coroutines/CoroCleanup.h"
 #include "llvm/Transforms/Coroutines/CoroConditionalWrapper.h"
 #include "llvm/Transforms/Coroutines/CoroEarly.h"

llvm/lib/Passes/PassBuilderPipelines.cpp

@@ -32,6 +32,7 @@
 #include "llvm/Support/VirtualFileSystem.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/AggressiveInstCombine/AggressiveInstCombine.h"
+#include "llvm/Transforms/Coroutines/CoroAnnotationElide.h"
 #include "llvm/Transforms/Coroutines/CoroCleanup.h"
 #include "llvm/Transforms/Coroutines/CoroConditionalWrapper.h"
 #include "llvm/Transforms/Coroutines/CoroEarly.h"
@@ -968,8 +969,8 @@ PassBuilder::buildInlinerPipeline(OptimizationLevel Level,
   // it's been modified since.
   MainCGPipeline.addPass(createCGSCCToFunctionPassAdaptor(
       RequireAnalysisPass<ShouldNotRunFunctionPassesAnalysis, Function>()));
-
   MainCGPipeline.addPass(CoroSplitPass(Level != OptimizationLevel::O0));
+  MainCGPipeline.addPass(CoroAnnotationElidePass());
 
   // Make sure we don't affect potential future NoRerun CGSCC adaptors.
   MIWP.addLateModulePass(createModuleToFunctionPassAdaptor(

llvm/lib/Passes/PassRegistry.def

@@ -234,6 +234,7 @@ CGSCC_PASS("attributor-light-cgscc", AttributorLightCGSCCPass())
 CGSCC_PASS("invalidate<all>", InvalidateAllAnalysesPass())
 CGSCC_PASS("no-op-cgscc", NoOpCGSCCPass())
 CGSCC_PASS("openmp-opt-cgscc", OpenMPOptCGSCCPass())
+CGSCC_PASS("coro-annotation-elide", CoroAnnotationElidePass())
 #undef CGSCC_PASS
 
 #ifndef CGSCC_PASS_WITH_PARAMS

llvm/lib/Transforms/Coroutines/CMakeLists.txt

@@ -1,5 +1,6 @@
 add_llvm_component_library(LLVMCoroutines
   Coroutines.cpp
+  CoroAnnotationElide.cpp
   CoroCleanup.cpp
   CoroConditionalWrapper.cpp
   CoroEarly.cpp

llvm/lib/Transforms/Coroutines/CoroAnnotationElide.cpp

@@ -0,0 +1,135 @@
+//===- CoroSplit.cpp - Converts a coroutine into a state machine ----------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Transforms/Coroutines/CoroAnnotationElide.h"
+
+#include "llvm/Analysis/LazyCallGraph.h"
+#include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/IR/Analysis.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InstIterator.h"
+#include "llvm/IR/Instruction.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/PassManager.h"
+#include "llvm/Transforms/Utils/CallGraphUpdater.h"
+
+#include <cassert>
+
+using namespace llvm;
+
+#define DEBUG_TYPE "coro-annotation-elide"
+
+#define CORO_MUST_ELIDE_ANNOTATION "coro_must_elide"
+
+static Instruction *getFirstNonAllocaInTheEntryBlock(Function *F) {
+  for (Instruction &I : F->getEntryBlock())
+    if (!isa<AllocaInst>(&I))
+      return &I;
+  llvm_unreachable("no terminator in the entry block");
+}
+
+static Value *allocateFrameInCaller(Function *Caller, uint64_t FrameSize,
+                                    Align FrameAlign) {
+  LLVMContext &C = Caller->getContext();
+  BasicBlock::iterator InsertPt =
+      getFirstNonAllocaInTheEntryBlock(Caller)->getIterator();
+  const DataLayout &DL = Caller->getDataLayout();
+  auto FrameTy = ArrayType::get(Type::getInt8Ty(C), FrameSize);
+  auto *Frame = new AllocaInst(FrameTy, DL.getAllocaAddrSpace(), "", InsertPt);
+  Frame->setAlignment(FrameAlign);
+  return new BitCastInst(Frame, PointerType::getUnqual(C), "vFrame", InsertPt);
+}
+
+static void processCall(CallBase *CB, Function *Caller, Function *NewCallee,
+                        uint64_t FrameSize, Align FrameAlign) {
+  auto *FramePtr = allocateFrameInCaller(Caller, FrameSize, FrameAlign);
+  auto NewCBInsertPt = CB->getIterator();
+  llvm::CallBase *NewCB = nullptr;
+  SmallVector<Value *, 4> NewArgs;
+  NewArgs.append(CB->arg_begin(), CB->arg_end());
+  NewArgs.push_back(FramePtr);
+
+  if (auto *CI = dyn_cast<CallInst>(CB)) {
+    auto *NewCI = CallInst::Create(NewCallee->getFunctionType(), NewCallee,
+                                   NewArgs, "", NewCBInsertPt);
+    NewCI->setTailCallKind(CI->getTailCallKind());
+    NewCB = NewCI;
+  } else if (auto *II = dyn_cast<InvokeInst>(CB)) {
+    NewCB = InvokeInst::Create(NewCallee->getFunctionType(), NewCallee,
+                               II->getNormalDest(), II->getUnwindDest(),
+                               NewArgs, std::nullopt, "", NewCBInsertPt);
+  } else {
+    llvm_unreachable("CallBase should either be Call or Invoke!");
+  }
+
+  NewCB->setCalledFunction(NewCallee->getFunctionType(), NewCallee);
+  NewCB->setCallingConv(CB->getCallingConv());
+  NewCB->setAttributes(CB->getAttributes());
+  NewCB->setDebugLoc(CB->getDebugLoc());
+  std::copy(CB->bundle_op_info_begin(), CB->bundle_op_info_end(),
+            NewCB->bundle_op_info_begin());
+
+  NewCB->removeFnAttr(llvm::Attribute::CoroMustElide);
+  CB->replaceAllUsesWith(NewCB);
+  CB->eraseFromParent();
+}
+
+PreservedAnalyses CoroAnnotationElidePass::run(LazyCallGraph::SCC &C,
+                                               CGSCCAnalysisManager &AM,
+                                               LazyCallGraph &CG,
+                                               CGSCCUpdateResult &UR) {
+  bool Changed = false;
+  CallGraphUpdater CGUpdater;
+  CGUpdater.initialize(CG, C, AM, UR);
+
+  auto &FAM =
+      AM.getResult<FunctionAnalysisManagerCGSCCProxy>(C, CG).getManager();
+
+  for (LazyCallGraph::Node &N : C) {
+    Function *Callee = &N.getFunction();
+    Function *NewCallee = Callee->getParent()->getFunction(
+        (Callee->getName() + ".noalloc").str());
+    if (!NewCallee) {
+      continue;
+    }
+
+    auto FramePtrArgPosition = NewCallee->arg_size() - 1;
+    auto FrameSize =
+        NewCallee->getParamDereferenceableBytes(FramePtrArgPosition);
+    auto FrameAlign =
+        NewCallee->getParamAlign(FramePtrArgPosition).valueOrOne();
+
+    SmallVector<CallBase *, 4> Users;
+    for (auto *U : Callee->users()) {
+      if (auto *CB = dyn_cast<CallBase>(U)) {
+        Users.push_back(CB);
+      }
+    }
+
+    auto &ORE = FAM.getResult<OptimizationRemarkEmitterAnalysis>(*Callee);
+
+    for (auto *CB : Users) {
+      auto *Caller = CB->getFunction();
+      if (Caller && Caller->isPresplitCoroutine() &&
+          CB->hasFnAttr(llvm::Attribute::CoroMustElide)) {
+        processCall(CB, Caller, NewCallee, FrameSize, FrameAlign);
+        CGUpdater.reanalyzeFunction(*Caller);
+
+        ORE.emit([&]() {
+          return OptimizationRemark(DEBUG_TYPE, "CoroAnnotationElide", Caller)
+                 << "'" << ore::NV("callee", Callee->getName())
+                 << "' elided in '" << ore::NV("caller", Caller->getName());
+        });
+        Changed = true;
+      }
+    }
+  }
+  return Changed ? PreservedAnalyses::none() : PreservedAnalyses::all();
+}

llvm/lib/Transforms/Coroutines/CoroInternal.h

@@ -26,6 +26,10 @@ bool declaresIntrinsics(const Module &M,
                         const std::initializer_list<StringRef>);
 void replaceCoroFree(CoroIdInst *CoroId, bool Elide);
 
+void suppressCoroAllocs(CoroIdInst *CoroId);
+void suppressCoroAllocs(LLVMContext &Context,
+                        ArrayRef<CoroAllocInst *> CoroAllocs);
+
 /// Attempts to rewrite the location operand of debug intrinsics in terms of
 /// the coroutine frame pointer, folding pointer offsets into the DIExpression
 /// of the intrinsic.