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

107 lines
3.7 KiB
C++

// Copyright Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#include <rocRoller/GPUArchitecture/GPUInstructionInfo.hpp>
#include <rocRoller/Scheduling/Observers/WaitState/MFMA/XDLWrite908.hpp>
namespace rocRoller
{
namespace Scheduling
{
int XDLWrite908::getMaxNops(Instruction const& inst) const
{
return getNopFromLatency(inst.getOpCode(), m_maxLatencyAndNops);
}
bool XDLWrite908::trigger(Instruction const& inst) const
{
return GPUInstructionInfo::isMFMA(inst.getOpCode());
};
int XDLWrite908::getNops(Instruction const& inst) const
{
if(GPUInstructionInfo::isMFMA(inst.getOpCode()))
{
std::optional<int> value;
auto const& srcs = inst.getSrcs();
// SrcC RAW
{
bool mismatched = false;
bool overlap = false;
int requiredNops = 0;
AssertFatal(srcs.at(2) != nullptr, "Empty SrcC");
for(auto const& srcId : srcs.at(2)->getRegisterIds())
{
if(m_hazardMap->contains(srcId))
{
for(auto const& hazard : m_hazardMap->at(srcId))
{
if(hazard.regWasWritten())
{
overlap = true;
requiredNops
= hazard.getRequiredNops() - hazard.getMaxNops() + 2;
}
}
}
else
{
mismatched = true;
}
}
if(overlap)
{
return mismatched ? requiredNops : 0;
}
}
// SrcA RAW
AssertFatal(srcs.at(0) != nullptr, "Empty SrcA");
for(auto const& srcId : srcs.at(0)->getRegisterIds())
{
if(m_hazardMap->contains(srcId))
{
for(auto const& hazard : m_hazardMap->at(srcId))
{
if(hazard.regWasWritten())
{
return hazard.getRequiredNops() - (hazard.getMaxNops() - 4);
}
}
}
}
// SrcB RAW
AssertFatal(srcs.at(1) != nullptr, "Empty SrcB");
for(auto const& srcId : srcs.at(1)->getRegisterIds())
{
if(m_hazardMap->contains(srcId))
{
for(auto const& hazard : m_hazardMap->at(srcId))
{
if(hazard.regWasWritten())
{
return hazard.getRequiredNops() - (hazard.getMaxNops() - 4);
}
}
}
}
}
else if(GPUInstructionInfo::isACCVGPRRead(inst.getOpCode()))
{
// ACCVGPR RAW
return checkSrcs(inst).value_or(0);
}
else if(GPUInstructionInfo::isACCVGPRWrite(inst.getOpCode()))
{
// ACCVGPR WAW
return checkDsts(inst).value_or(0) - 3;
}
return 0;
}
}
}