ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Codegen hipRTC compilation (#1579)

Browse Source 
* 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>
This commit is contained in:
arai713
2025-01-31 09:48:39 -08:00
committed by GitHub
parent 2ab8bf4c12
commit 2e3183af4f
65 changed files with 1119 additions and 385 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
include/ck/utility/tuple.hpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -32,7 +32,7 @@ struct TupleElementKeyData
template <typename T,
typename enable_if<!is_same<remove_cvref_t<T>, TupleElementKeyData>::value,
bool>::type = false>
__host__ __device__ constexpr TupleElementKeyData(T&& v) : mData(std::forward<T>(v))
__host__ __device__ constexpr TupleElementKeyData(T&& v) : mData(ck::forward<T>(v))
{
}
@@ -67,7 +67,7 @@ get_tuple_element_data_reference(TupleElementKeyData<Key, Data>&& x)
template <typename Key, typename Data>
__host__ __device__ constexpr Data get_tuple_element_data(const TupleElementKeyData<Key, Data>& x)
{
return std::forward(x.mData);
return ck::forward(x.mData);
}
template <typename Indices, typename... Xs>
@@ -83,13 +83,13 @@ struct TupleImpl<Sequence<Is...>, Xs...> : TupleElementKeyData<TupleElementKey<I
!is_same<remove_cvref_t<Y>, TupleImpl>::value,
bool>::type = false>
__host__ __device__ constexpr TupleImpl(Y&& y)
: TupleElementKeyData<TupleElementKey<Is>, Xs>(std::forward<Y>(y))...
: TupleElementKeyData<TupleElementKey<Is>, Xs>(ck::forward<Y>(y))...
{
}
template <typename... Ys, typename enable_if<sizeof...(Ys) >= 2, bool>::type = false>
__host__ __device__ constexpr TupleImpl(Ys&&... ys)
: TupleElementKeyData<TupleElementKey<Is>, Xs>(std::forward<Ys>(ys))...
: TupleElementKeyData<TupleElementKey<Is>, Xs>(ck::forward<Ys>(ys))...
{
static_assert(sizeof...(Is) == sizeof...(Xs) && sizeof...(Is) == sizeof...(Ys),
"wrong! inconsistent size");
@@ -123,14 +123,14 @@ struct Tuple : detail::TupleImpl<typename arithmetic_sequence_gen<0, sizeof...(X
template <typename Y,
typename enable_if<sizeof...(Xs) == 1 && !is_same<remove_cvref_t<Y>, Tuple>::value,
bool>::type = false>
__host__ __device__ constexpr Tuple(Y&& y) : base(std::forward<Y>(y))
__host__ __device__ constexpr Tuple(Y&& y) : base(ck::forward<Y>(y))
{
}
template <typename... Ys,
typename enable_if<sizeof...(Ys) == sizeof...(Xs) && sizeof...(Ys) >= 2, bool>::type =
false>
__host__ __device__ constexpr Tuple(Ys&&... ys) : base(std::forward<Ys>(ys)...)
__host__ __device__ constexpr Tuple(Ys&&... ys) : base(ck::forward<Ys>(ys)...)
{
}
@@ -210,7 +210,7 @@ using tuple_element_t = typename tuple_element<I, TTuple>::type;
template <typename... Xs>
__host__ __device__ constexpr auto make_tuple(Xs&&... xs)
{
return Tuple<remove_cvref_t<Xs>...>(std::forward<Xs>(xs)...);
return Tuple<remove_cvref_t<Xs>...>(ck::forward<Xs>(xs)...);
}
// https://en.cppreference.com/w/cpp/utility/tuple/tie