Files
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

91 lines
2.5 KiB
C++

//===-- SIFixVGPRCopies.cpp - Fix VGPR Copies after regalloc --------------===//
//
// 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
/// Add implicit use of exec to vector register copies.
///
//===----------------------------------------------------------------------===//
#include "SIFixVGPRCopies.h"
#include "AMDGPU.h"
#include "GCNSubtarget.h"
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
using namespace llvm;
#define DEBUG_TYPE "si-fix-vgpr-copies"
namespace {
class SIFixVGPRCopiesLegacy : public MachineFunctionPass {
public:
static char ID;
SIFixVGPRCopiesLegacy() : MachineFunctionPass(ID) {}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesAll();
MachineFunctionPass::getAnalysisUsage(AU);
}
bool runOnMachineFunction(MachineFunction &MF) override;
StringRef getPassName() const override { return "SI Fix VGPR copies"; }
};
class SIFixVGPRCopies {
public:
bool run(MachineFunction &MF);
};
} // End anonymous namespace.
INITIALIZE_PASS(SIFixVGPRCopiesLegacy, DEBUG_TYPE, "SI Fix VGPR copies", false,
false)
char SIFixVGPRCopiesLegacy::ID = 0;
char &llvm::SIFixVGPRCopiesID = SIFixVGPRCopiesLegacy::ID;
PreservedAnalyses SIFixVGPRCopiesPass::run(MachineFunction &MF,
MachineFunctionAnalysisManager &) {
SIFixVGPRCopies().run(MF);
return PreservedAnalyses::all();
}
bool SIFixVGPRCopiesLegacy::runOnMachineFunction(MachineFunction &MF) {
return SIFixVGPRCopies().run(MF);
}
bool SIFixVGPRCopies::run(MachineFunction &MF) {
const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
const SIRegisterInfo *TRI = ST.getRegisterInfo();
const SIInstrInfo *TII = ST.getInstrInfo();
bool Changed = false;
for (MachineBasicBlock &MBB : MF) {
for (MachineInstr &MI : MBB) {
switch (MI.getOpcode()) {
case AMDGPU::COPY:
if (TII->isVGPRCopy(MI) && !MI.readsRegister(AMDGPU::EXEC, TRI)) {
MI.addOperand(MF,
MachineOperand::CreateReg(AMDGPU::EXEC, false, true));
LLVM_DEBUG(dbgs() << "Add exec use to " << MI);
Changed = true;
}
break;
default:
break;
}
}
}
return Changed;
}