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

87 lines
2.9 KiB
C++

// Copyright Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#include <rocRoller/Context.hpp>
#include <rocRoller/Scheduling/Costs/Cost.hpp>
namespace rocRoller
{
namespace Scheduling
{
const std::string Cost::Basename = "Cost";
std::string toString(CostFunction proc)
{
switch(proc)
{
case CostFunction::None:
return "None";
case CostFunction::Uniform:
return "Uniform";
case CostFunction::MinNops:
return "MinNops";
case CostFunction::WaitCntNop:
return "WaitCntNop";
case CostFunction::LinearWeighted:
return "LinearWeighted";
case CostFunction::LinearWeightedSimple:
return "LinearWeightedSimple";
case CostFunction::LinearWeightedSimpleStreamK:
return "LinearWeightedSimpleStreamK";
case CostFunction::Count:
return "Count";
}
Throw<FatalError>("Invalid Cost Function: ", ShowValue(static_cast<int>(proc)));
}
std::ostream& operator<<(std::ostream& stream, CostFunction proc)
{
return stream << toString(proc);
}
Cost::Result Cost::operator()(std::vector<Generator<Instruction>::iterator>& iters) const
{
Cost::Result retval;
auto context = m_ctx.lock();
size_t n = iters.size();
for(size_t i = 0; i < n; ++i)
{
if(iters[i] != std::default_sentinel_t{})
{
auto const& inst = *(iters[i]);
auto status = context->peek(inst);
float peek = cost(inst, status);
std::tuple<int, float> new_val{i, peek};
retval.insert(
std::upper_bound(
retval.begin(),
retval.end(),
new_val,
[](std::tuple<int, float> lhs, std::tuple<int, float> rhs) -> bool {
return (std::get<1>(lhs) < std::get<1>(rhs))
|| (std::get<1>(lhs) == std::get<1>(rhs)
&& std::get<0>(lhs) < std::get<0>(rhs));
}),
new_val);
}
}
return retval;
}
float Cost::operator()(Instruction const& inst) const
{
auto status = m_ctx.lock()->peek(inst);
return cost(inst, status);
}
float Cost::operator()(Generator<Instruction>::iterator& iter) const
{
auto const& inst = *iter;
return (*this)(inst);
}
}
}