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
67 lines
2.2 KiB
C++
67 lines
2.2 KiB
C++
//===--- AMDGPUMacroFusion.cpp - AMDGPU Macro Fusion ----------------------===//
|
|
//
|
|
// 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 file contains the AMDGPU implementation of the DAG scheduling
|
|
/// mutation to pair instructions back to back.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "AMDGPUMacroFusion.h"
|
|
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
|
|
#include "SIInstrInfo.h"
|
|
#include "llvm/CodeGen/MacroFusion.h"
|
|
|
|
using namespace llvm;
|
|
|
|
namespace {
|
|
|
|
/// Check if the instr pair, FirstMI and SecondMI, should be fused
|
|
/// together. Given SecondMI, when FirstMI is unspecified, then check if
|
|
/// SecondMI may be part of a fused pair at all.
|
|
static bool shouldScheduleAdjacent(const TargetInstrInfo &TII_,
|
|
const TargetSubtargetInfo &TSI,
|
|
const MachineInstr *FirstMI,
|
|
const MachineInstr &SecondMI) {
|
|
const SIInstrInfo &TII = static_cast<const SIInstrInfo&>(TII_);
|
|
|
|
switch (SecondMI.getOpcode()) {
|
|
case AMDGPU::V_ADDC_U32_e64:
|
|
case AMDGPU::V_SUBB_U32_e64:
|
|
case AMDGPU::V_SUBBREV_U32_e64:
|
|
case AMDGPU::V_CNDMASK_B32_e64: {
|
|
// Try to cluster defs of condition registers to their uses. This improves
|
|
// the chance VCC will be available which will allow shrinking to VOP2
|
|
// encodings.
|
|
if (!FirstMI)
|
|
return true;
|
|
|
|
const MachineBasicBlock &MBB = *FirstMI->getParent();
|
|
const MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
|
|
const TargetRegisterInfo *TRI = MRI.getTargetRegisterInfo();
|
|
const MachineOperand *Src2 = TII.getNamedOperand(SecondMI,
|
|
AMDGPU::OpName::src2);
|
|
return FirstMI->definesRegister(Src2->getReg(), TRI);
|
|
}
|
|
default:
|
|
return false;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
} // end namespace
|
|
|
|
|
|
namespace llvm {
|
|
|
|
std::unique_ptr<ScheduleDAGMutation> createAMDGPUMacroFusionDAGMutation() {
|
|
return createMacroFusionDAGMutation(shouldScheduleAdjacent);
|
|
}
|
|
|
|
} // end namespace llvm
|