mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 02:27:57 +00:00
1ca4ad2739
* updating codegen build for MIOpen access: adding .cmake for codegen component
* updating CMake
* adding in header guards for some headers due to issues with hiprtc compilation in MIOpen
* some more header guards
* putting env file in header guard
* cleaning up some includes
* updated types file for hiprtc purposes
* fixed types file: bit-wise/memcpy issue
* updating multiple utility files to deal with standard header inclusion for hiprtc
* added some more header guards in the utility files, replacing some standard header functionality
* added some more header guards
* fixing some conflicts in utility files, another round of header guards
* fixing errors in data type file
* resolved conflict errors in a few utility files
* added header guards/replicated functionality in device files
* resolved issues with standard headers in device files: device_base and device_grouped_conv_fwd_multiple_abd
* resolved issues with standard headers in device files: device_base.hpp, device_grouped_conv_fwd_multiple_abd.hpp, device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
* added header guards for gridwise gemm files: gridwise_gemm_multiple_abd_xdl_cshuffle.hpp and gridwise_gemm_multiple_d_xdl_cshuffle.hpp
* fixed issue with numerics header, removed from transform_conv_fwd_to_gemm and added to device_column_to_image_impl, device_grouped_conv_fwd_multiple_abd_xdl_cshuffle, device_grouped_conv_fwd_multiple_abd_xdl_cshuffle_v3, device_image_to_column_impl
* replaced standard header usage and added header guards in block to ctile map and gridwise_gemm_pipeline_selector
* resolved errors in device_gemm_xdl_splitk_c_shuffle files in regards to replacement of standard headers in previous commit
* added replicated functionality for standard header methods in utility files
* replaced standard header functionality in threadwise tensor slice transfer files and added header guards in element_wise_operation.hpp
* temp fix for namespace error in MIOpen
* remove standard header usage in codegen device op
* removed standard header usage in elementwise files, resolved namespace errors
* formatting fix
* changed codegen argument to ON for testing
* temporarily removing codegen compiler flag for testing purposes
* added codegen flag again, set default to ON
* set codegen flag default back to OFF
* replaced enable_if_t standard header usage in data_type.hpp
* added some debug prints to pinpoint issues in MIOpen
* added print outs to debug in MIOpen
* removed debug print outs from device op
* resolved stdexcept include error
* formatting fix
* adding includes to new fp8 file to resolve ck::enable_if_t errors
* made changes to amd_wave_read_first_lane
* updated functionality in type utility file
* fixed end of file issue
* resovled errors in type utility file, added functionality to array utility file
* fixed standard header usage replication in data_type file, resolves error with failing examples on navi3x
* formatting fix
* replaced standard header usage in amd_ck_fp8 file
* added include to random_gen file
* removed and replicated standard header usage from data_type and type_convert files for fp8 changes
* replicated standard unsigned integer types in random_gen
* resolved comments from review: put calls to reinterpret_cast for size_t in header guards
* updated/added copyright headers
* removed duplicate header
* fixed typo in header guard
* updated copyright headers
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
[ROCm/composable_kernel commit: 2e3183af4f]
66 lines
1.7 KiB
C++
66 lines
1.7 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#ifndef GUARD_HOST_TEST_RTC_INCLUDE_RTC_KERNEL
|
|
#define GUARD_HOST_TEST_RTC_INCLUDE_RTC_KERNEL
|
|
|
|
#include <hip/hip_runtime_api.h>
|
|
#include <memory>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
namespace rtc {
|
|
|
|
struct kernel_argument
|
|
{
|
|
template <class T,
|
|
class U = std::remove_reference_t<T>,
|
|
class = std::enable_if_t<not std::is_base_of<kernel_argument, T>{}>>
|
|
kernel_argument(T&& x) : size(sizeof(U)), align(alignof(U)), data(&x) // NOLINT
|
|
{
|
|
}
|
|
std::size_t size;
|
|
std::size_t align;
|
|
void* data;
|
|
};
|
|
|
|
std::vector<char> pack_args(const std::vector<kernel_argument>& args);
|
|
|
|
struct kernel_impl;
|
|
|
|
struct kernel
|
|
{
|
|
kernel() = default;
|
|
kernel(const char* image, const std::string& name);
|
|
template <class T>
|
|
kernel(const std::vector<T>& image, const std::string& name)
|
|
: kernel(reinterpret_cast<const char*>(image.data()), name)
|
|
{
|
|
static_assert(sizeof(T) == 1, "Only byte types");
|
|
}
|
|
|
|
void launch(hipStream_t stream,
|
|
std::size_t global,
|
|
std::size_t local,
|
|
const std::vector<kernel_argument>& args) const;
|
|
|
|
void launch(hipStream_t stream,
|
|
std::size_t global,
|
|
std::size_t local,
|
|
std::vector<void*> args) const;
|
|
|
|
template <class... Ts>
|
|
auto launch(hipStream_t stream, std::size_t global, std::size_t local, Ts... zs) const
|
|
{
|
|
return [=](auto&&... xs) {
|
|
launch(stream, global, local, std::vector<kernel_argument>{xs...}, zs...);
|
|
};
|
|
}
|
|
|
|
private:
|
|
std::shared_ptr<kernel_impl> impl;
|
|
};
|
|
} // namespace rtc
|
|
|
|
#endif
|