Files
TheRock/rocm-libraries/shared/rocroller/lib/include/rocRoller/Scheduling/Scheduling_impl.hpp
T
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

119 lines
3.9 KiB
C++

// Copyright Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#pragma once
#include <rocRoller/Scheduling/Scheduling.hpp>
namespace rocRoller
{
namespace Scheduling
{
inline InstructionStatus::InstructionStatus()
{
waitLengths.fill(0);
allocatedRegisters.fill(0);
remainingRegisters.fill(-1);
highWaterMarkRegistersDelta.fill(0);
outOfRegisters.reset();
}
inline InstructionStatus InstructionStatus::StallCycles(unsigned int const value)
{
InstructionStatus rv;
rv.stallCycles = value;
return rv;
}
inline InstructionStatus InstructionStatus::Wait(WaitCount const& value)
{
InstructionStatus rv;
rv.waitCount = value;
return rv;
}
inline InstructionStatus InstructionStatus::Nops(unsigned int const value)
{
InstructionStatus rv;
rv.nops = value;
return rv;
}
inline InstructionStatus InstructionStatus::Error(std::string const& msg)
{
InstructionStatus rv;
rv.errors = {msg};
return rv;
}
inline std::string InstructionStatus::toString() const
{
return concatenate("Status: {",
"stall ",
stallCycles,
", additional ",
additionalCycles,
", wait ",
waitCount.toString(LogLevel::Terse),
", nop ",
nops,
", reused ",
reusedOperands,
", q {",
waitLengths,
"}, a {",
allocatedRegisters,
"}, h {",
highWaterMarkRegistersDelta,
"}, c {",
disallowedCoexec,
"}}");
}
inline void InstructionStatus::combine(InstructionStatus const& other)
{
stallCycles = std::max(stallCycles, other.stallCycles);
additionalCycles = std::max(additionalCycles, other.additionalCycles);
waitCount.combine(other.waitCount);
nops = std::max(nops, other.nops);
reusedOperands = std::max(reusedOperands, other.reusedOperands);
for(int i = 0; i < waitLengths.size(); i++)
{
waitLengths[i] = std::max(waitLengths[i], other.waitLengths[i]);
}
for(int i = 0; i < allocatedRegisters.size(); i++)
{
allocatedRegisters[i]
= std::max(allocatedRegisters[i], other.allocatedRegisters[i]);
}
for(int i = 0; i < remainingRegisters.size(); i++)
{
if(remainingRegisters[i] < 0)
remainingRegisters[i] = other.remainingRegisters[i];
else if(other.remainingRegisters[i] >= 0)
remainingRegisters[i]
= std::min(remainingRegisters[i], other.remainingRegisters[i]);
}
for(int i = 0; i < highWaterMarkRegistersDelta.size(); i++)
{
highWaterMarkRegistersDelta[i] = std::max(highWaterMarkRegistersDelta[i],
other.highWaterMarkRegistersDelta[i]);
}
outOfRegisters |= other.outOfRegisters;
errors.insert(errors.end(), other.errors.begin(), other.errors.end());
combineCoexec(disallowedCoexec, other.disallowedCoexec, 0);
}
inline IObserver::~IObserver() = default;
}
}