llvm/llvm/lib/Target/NVPTX/NVPTXPeephole.cpp

//===-- NVPTXPeephole.cpp - NVPTX Peephole Optimiztions -------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// In NVPTX, NVPTXFrameLowering will emit following instruction at the beginning
// of a MachineFunction.
//
//   mov %SPL, %depot
//   cvta.local %SP, %SPL
//
// Because Frame Index is a generic address and alloca can only return generic
// pointer, without this pass the instructions producing alloca'ed address will
// be based on %SP. NVPTXLowerAlloca tends to help replace store and load on
// this address with their .local versions, but this may introduce a lot of
// cvta.to.local instructions. Performance can be improved if we avoid casting
// address back and forth and directly calculate local address based on %SPL.
// This peephole pass optimizes these cases, for example
//
// It will transform the following pattern
//    %0 = LEA_ADDRi64 %VRFrame64, 4
//    %1 = cvta_to_local_64 %0
//
// into
//    %1 = LEA_ADDRi64 %VRFrameLocal64, 4
//
// %VRFrameLocal64 is the virtual register name of %SPL
//
//===----------------------------------------------------------------------===//

#include "NVPTX.h"
#include "NVPTXRegisterInfo.h"
#include "NVPTXSubtarget.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"

usingnamespacellvm;

#define DEBUG_TYPE …

namespace llvm {
void initializeNVPTXPeepholePass(PassRegistry &);
}

namespace {
struct NVPTXPeephole : public MachineFunctionPass { … };
}

char NVPTXPeephole::ID = …;

INITIALIZE_PASS(…)

static bool isCVTAToLocalCombinationCandidate(MachineInstr &Root) { … }

static void CombineCVTAToLocal(MachineInstr &Root) { … }

bool NVPTXPeephole::runOnMachineFunction(MachineFunction &MF) { … }

MachineFunctionPass *llvm::createNVPTXPeephole() { … }