llvm/llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp

//===-- AMDGPUCodeGenPrepare.cpp ------------------------------------------===//
//
// 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 does misc. AMDGPU optimizations on IR *just* before instruction
/// selection.
//
//===----------------------------------------------------------------------===//

#include "AMDGPU.h"
#include "AMDGPUTargetMachine.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/UniformityAnalysis.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/InitializePasses.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/KnownBits.h"
#include "llvm/Transforms/Utils/Local.h"

#define DEBUG_TYPE …

usingnamespacellvm;

// Scalar load widening needs running after load-store-vectorizer as that pass
// doesn't handle overlapping cases. In addition, this pass enhances the
// widening to handle cases where scalar sub-dword loads are naturally aligned
// only but not dword aligned.
static cl::opt<bool>
    WidenLoads("amdgpu-late-codegenprepare-widen-constant-loads",
               cl::desc("Widen sub-dword constant address space loads in "
                        "AMDGPULateCodeGenPrepare"),
               cl::ReallyHidden, cl::init(true));

namespace {

class AMDGPULateCodeGenPrepare
    : public InstVisitor<AMDGPULateCodeGenPrepare, bool> { … };

ValueToValueMap;

class LiveRegOptimizer { … };

} // end anonymous namespace

bool AMDGPULateCodeGenPrepare::run(Function &F) { … }

Type *LiveRegOptimizer::calculateConvertType(Type *OriginalType) { … }

Value *LiveRegOptimizer::convertToOptType(Instruction *V,
                                          BasicBlock::iterator &InsertPt) { … }

Value *LiveRegOptimizer::convertFromOptType(Type *ConvertType, Instruction *V,
                                            BasicBlock::iterator &InsertPt,
                                            BasicBlock *InsertBB) { … }

bool LiveRegOptimizer::optimizeLiveType(
    Instruction *I, SmallVectorImpl<WeakTrackingVH> &DeadInsts) { … }

bool AMDGPULateCodeGenPrepare::canWidenScalarExtLoad(LoadInst &LI) const { … }

bool AMDGPULateCodeGenPrepare::visitLoadInst(LoadInst &LI) { … }

PreservedAnalyses
AMDGPULateCodeGenPreparePass::run(Function &F, FunctionAnalysisManager &FAM) { … }

class AMDGPULateCodeGenPrepareLegacy : public FunctionPass { … };

bool AMDGPULateCodeGenPrepareLegacy::runOnFunction(Function &F) { … }

INITIALIZE_PASS_BEGIN(AMDGPULateCodeGenPrepareLegacy, DEBUG_TYPE,
                      "AMDGPU IR late optimizations", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetPassConfig)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(UniformityInfoWrapperPass)
INITIALIZE_PASS_END(AMDGPULateCodeGenPrepareLegacy, DEBUG_TYPE,
                    "AMDGPU IR late optimizations", false, false)

char AMDGPULateCodeGenPrepareLegacy::ID = …;

FunctionPass *llvm::createAMDGPULateCodeGenPrepareLegacyPass() { … }