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

63 lines
1.8 KiB
C++

// Copyright Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#include <concepts>
#include <string>
#include <vector>
#include <rocRoller/CodeGen/Instruction.hpp>
#include <rocRoller/GPUArchitecture/GPUArchitecture.hpp>
#include <rocRoller/GPUArchitecture/GPUInstructionInfo.hpp>
#include <rocRoller/Scheduling/Observers/FunctionalUnit/WMMAObserver.hpp>
#include <rocRoller/Utilities/Settings.hpp>
namespace rocRoller
{
namespace Scheduling
{
WMMAObserver::WMMAObserver() {}
WMMAObserver::WMMAObserver(ContextPtr ctx)
: m_context(ctx)
{
}
bool WMMAObserver::isWMMAInstruction(const Instruction& inst) const
{
return GPUInstructionInfo::isWMMA(inst.getOpCode());
}
InstructionStatus WMMAObserver::peek(const Instruction& inst) const
{
InstructionStatus rv;
if(isWMMAInstruction(inst))
rv.stallCycles = m_remainingCycles;
return rv;
}
void WMMAObserver::modify(Instruction& inst) const
{
if(m_remainingCycles > 0 && !inst.isCommentOnly()
&& Settings::Get(Settings::LogLvl) >= LogLevel::Debug)
inst.addComment(concatenate("WMMA remaining: ", m_remainingCycles));
}
void WMMAObserver::observe(const Instruction& inst)
{
if(isWMMAInstruction(inst))
{
auto info
= m_context.lock()->targetArchitecture().GetInstructionInfo(inst.getOpCode());
m_remainingCycles = info.getLatency();
}
else
{
m_remainingCycles = std::max(0, m_remainingCycles - inst.numExecutedInstructions());
}
}
}
}