mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-16 10:59:55 +00:00
0d278b8cc8
* Add online-compiling facility
* Synchronize from fwd-v4r5 and implement host interfaces to call conv-fwd v4r4/v4r5 using on-line compiling method
* Tiny adjustment to time reporting
* Use object assignment to replace explicit bytes copying in the first kernel of v4r4/v4r5
* Use single thread to assign descriptor object to device memory
* Adjust to the workload assignment of the two kernels of v4r4 (experimental)
* Revert "Adjust to the workload assignment of the two kernels of v4r4 (experimental)"
This reverts commit eb38461456bb0c82b6c0d32cdd616e181907e20c.
* Update to make constexpr for generating descriptor types in kernel 2 of dynamic conv-fwd v4r4
* Update to dynamic conv-fwd v4r4 online-compiling
* Update to dynamic conv-fwd v4r5 online-compiling (result not accurate)
* Tiny update to driver/CMakeLists.txt
* clang-format
* Tiny comments change
* Add env OLC_DUMP_SAVE_TMP_DIR to support saving of temperary dir
* Fwd v4r5 olc perf (#39)
* added hip-clang flags that fix perf issue of online compilation
* fix bug for olc fwd-v4r5-nchw
* Move constexpr and type reference statements out of the function body in conv-fwd v4r4/v4r5 kernel wrapper
* Remove printing in hip_build_utils.cpp
* Update to root CMakeLists.txt
* Revert "Move constexpr and type reference statements out of the function body in conv-fwd v4r4/v4r5 kernel wrapper"
This reverts commit 3d2c5d8ecdd8298b72d127110500ed5b38d9835c.
Co-authored-by: Chao Liu <chao.liu2@amd.com>
Co-authored-by: Chao Liu <lc.roy86@gmail.com>
Co-authored-by: root <root@dc-smc-18.amd.com>
[ROCm/composable_kernel commit: 1685048a67]
37 lines
831 B
C++
37 lines
831 B
C++
#ifndef CK_SEQUENCE_HELPER_HPP
|
|
#define CK_SEQUENCE_HELPER_HPP
|
|
|
|
#include "tuple.hpp"
|
|
|
|
namespace ck {
|
|
|
|
template <index_t... Is>
|
|
__host__ __device__ constexpr auto make_sequence(Number<Is>...)
|
|
{
|
|
return Sequence<Is...>{};
|
|
}
|
|
|
|
// F returns index_t
|
|
template <typename F, index_t N>
|
|
__host__ __device__ constexpr auto generate_sequence(F, Number<N>)
|
|
{
|
|
return typename sequence_gen<N, F>::type{};
|
|
}
|
|
|
|
// F returns Number<>
|
|
template <typename F, index_t N>
|
|
__host__ __device__ constexpr auto generate_sequence_v2(F&& f, Number<N>)
|
|
{
|
|
return unpack([&f](auto&&... xs) { return make_sequence(f(xs)...); },
|
|
typename arithmetic_sequence_gen<0, N, 1>::type{});
|
|
}
|
|
|
|
template <index_t... Is>
|
|
__host__ __device__ constexpr auto to_sequence(Tuple<Number<Is>...>)
|
|
{
|
|
return Sequence<Is...>{};
|
|
}
|
|
|
|
} // namespace ck
|
|
#endif
|