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
65 lines
1.8 KiB
C++
65 lines
1.8 KiB
C++
/*
|
|
* Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
*
|
|
* SPDX-License-Identifier: MIT
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <memory>
|
|
#include "rocprogram.hpp"
|
|
#include "top.hpp"
|
|
#include "rocprintf.hpp"
|
|
|
|
namespace amd::roc {
|
|
|
|
class Kernel : public device::Kernel {
|
|
public:
|
|
Kernel(const std::string& name, Program* prog) : device::Kernel(prog->device(), name, *prog) {}
|
|
|
|
virtual ~Kernel() {
|
|
if (program() != nullptr) {
|
|
// Add kernel to the map of all kernels on the device
|
|
program()->rocDevice().RemoveKernel(*this);
|
|
}
|
|
}
|
|
|
|
//! Initializes the metadata required for this kernel
|
|
virtual bool init() final;
|
|
|
|
//! Setup after code object loading
|
|
bool postLoad();
|
|
|
|
const Program* program() const { return static_cast<const Program*>(&prog_); }
|
|
|
|
//! Pull demangled name, used only for logging
|
|
const std::string& getDemangledName() {
|
|
std::call_once(demangle_once_, [this] {
|
|
amd::Os::CxaDemangle(name(), &demangled_name_);
|
|
});
|
|
return demangled_name_;
|
|
}
|
|
|
|
//! Returns the cached metadata kernel descriptor, or nullptr if lookup failed.
|
|
const hsa_amd_metadata_kernel_descriptor_t* MetadataKernelDescriptor() const {
|
|
return metadataKernelDescriptor_;
|
|
}
|
|
|
|
//! Kernarg preload length in DWORDs (from kernel descriptor)
|
|
uint16_t MetadataPreloadLength() const { return metadata_preload_length_; }
|
|
|
|
//! Kernarg preload offset in DWORDs (from kernel descriptor)
|
|
uint16_t MetadataPreloadOffset() const { return metadata_preload_offset_; }
|
|
|
|
std::string demangled_name_; //!< Cache demangled name
|
|
std::once_flag demangle_once_;
|
|
|
|
private:
|
|
const hsa_amd_metadata_kernel_descriptor_t* metadataKernelDescriptor_ = nullptr;
|
|
uint16_t metadata_preload_length_ = 0;
|
|
uint16_t metadata_preload_offset_ = 0;
|
|
};
|
|
|
|
} // namespace amd::roc
|
|
|