llvm/llvm/lib/CodeGen/HardwareLoops.cpp

//===-- HardwareLoops.cpp - Target Independent Hardware Loops --*- C++ -*-===//
//
// 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
/// Insert hardware loop intrinsics into loops which are deemed profitable by
/// the target, by querying TargetTransformInfo. A hardware loop comprises of
/// two intrinsics: one, outside the loop, to set the loop iteration count and
/// another, in the exit block, to decrement the counter. The decremented value
/// can either be carried through the loop via a phi or handled in some opaque
/// way by the target.
///
//===----------------------------------------------------------------------===//

#include "llvm/CodeGen/HardwareLoops.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/BranchProbabilityInfo.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/OptimizationRemarkEmitter.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Value.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/PassRegistry.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Transforms/Utils.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"

#define DEBUG_TYPE …

#define HW_LOOPS_NAME …

usingnamespacellvm;

static cl::opt<bool>
ForceHardwareLoops("force-hardware-loops", cl::Hidden, cl::init(false),
                   cl::desc("Force hardware loops intrinsics to be inserted"));

static cl::opt<bool>
ForceHardwareLoopPHI(
  "force-hardware-loop-phi", cl::Hidden, cl::init(false),
  cl::desc("Force hardware loop counter to be updated through a phi"));

static cl::opt<bool>
ForceNestedLoop("force-nested-hardware-loop", cl::Hidden, cl::init(false),
                cl::desc("Force allowance of nested hardware loops"));

static cl::opt<unsigned>
LoopDecrement("hardware-loop-decrement", cl::Hidden, cl::init(1),
            cl::desc("Set the loop decrement value"));

static cl::opt<unsigned>
CounterBitWidth("hardware-loop-counter-bitwidth", cl::Hidden, cl::init(32),
                cl::desc("Set the loop counter bitwidth"));

static cl::opt<bool>
ForceGuardLoopEntry(
  "force-hardware-loop-guard", cl::Hidden, cl::init(false),
  cl::desc("Force generation of loop guard intrinsic"));

STATISTIC(NumHWLoops, "Number of loops converted to hardware loops");

#ifndef NDEBUG
static void debugHWLoopFailure(const StringRef DebugMsg,
    Instruction *I) {
  dbgs() << "HWLoops: " << DebugMsg;
  if (I)
    dbgs() << ' ' << *I;
  else
    dbgs() << '.';
  dbgs() << '\n';
}
#endif

static OptimizationRemarkAnalysis
createHWLoopAnalysis(StringRef RemarkName, Loop *L, Instruction *I) { … }

namespace {

  void reportHWLoopFailure(const StringRef Msg, const StringRef ORETag,
      OptimizationRemarkEmitter *ORE, Loop *TheLoop, Instruction *I = nullptr) { … }

  TTI;

  class HardwareLoopsLegacy : public FunctionPass { … };

  class HardwareLoopsImpl { … };

  class HardwareLoop { … };
}

char HardwareLoopsLegacy::ID = …;

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

PreservedAnalyses HardwareLoopsPass::run(Function &F,
                                         FunctionAnalysisManager &AM) { … }

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

// Return true if the search should stop, which will be when an inner loop is
// converted and the parent loop doesn't support containing a hardware loop.
bool HardwareLoopsImpl::TryConvertLoop(Loop *L, LLVMContext &Ctx) { … }

bool HardwareLoopsImpl::TryConvertLoop(HardwareLoopInfo &HWLoopInfo) { … }

void HardwareLoop::Create() { … }

static bool CanGenerateTest(Loop *L, Value *Count) { … }

Value *HardwareLoop::InitLoopCount() { … }

Value* HardwareLoop::InsertIterationSetup(Value *LoopCountInit) { … }

void HardwareLoop::InsertLoopDec() { … }

Instruction* HardwareLoop::InsertLoopRegDec(Value *EltsRem) { … }

PHINode* HardwareLoop::InsertPHICounter(Value *NumElts, Value *EltsRem) { … }

void HardwareLoop::UpdateBranch(Value *EltsRem) { … }

INITIALIZE_PASS_BEGIN(HardwareLoopsLegacy, DEBUG_TYPE, HW_LOOPS_NAME, false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
INITIALIZE_PASS_DEPENDENCY(OptimizationRemarkEmitterWrapperPass)
INITIALIZE_PASS_END(HardwareLoopsLegacy, DEBUG_TYPE, HW_LOOPS_NAME, false, false)

FunctionPass *llvm::createHardwareLoopsLegacyPass() { … }