mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-26 08:00:13 +00:00
* ad gelu and fast_gelu
* added GeLU and fast GeLU
* clean up
* add gemm+fastgelu example
* add gemm+gelu instances
* update profiler
* clean up
* clean up
* adding gemm+bias+activation
* clean
* adding bias
* clean
* adding gemm multiple d
* debugging
* add gemm bias add fastgelu
* rename, clean
* refactoring; add readme
* refactor
* refactor
* refactor
* refactor
* refactor
* refactor
* fix
* fix
* update example
* update example
* rename
* update example
* add ckProfiler
* clean
* clean
* clean
* clean
* add client app example
* update readme
* delete obselete files
* remove old client app
* delete old file
* cleaning
* clean
* remove half
* fix header path
* fix header path
* fix header path
* fix header path
* fix header path
* fix header path for all examples
* fix header path
* fix header path
* fix header path
* fix header path
* fix header path
* fix header path
* fix header path
* fix header path
* fix header path
* revert client app example
* clean build
* fix build
* temporary disable client test on Jenkins
* clean
* clean
* clean
[ROCm/composable_kernel commit: d1db6a0c3e]
26 lines
613 B
C++
26 lines
613 B
C++
#pragma once
|
|
|
|
#include "ck/ck.hpp"
|
|
|
|
namespace ck {
|
|
|
|
__host__ __device__ constexpr index_t get_warp_size()
|
|
{
|
|
// warpSize is defined by HIP
|
|
return warpSize;
|
|
}
|
|
|
|
__device__ index_t get_thread_local_1d_id() { return threadIdx.x; }
|
|
|
|
__device__ index_t get_thread_global_1d_id() { return blockIdx.x * blockDim.x + threadIdx.x; }
|
|
|
|
__device__ index_t get_warp_local_1d_id() { return threadIdx.x / get_warp_size(); }
|
|
|
|
__device__ index_t get_block_1d_id() { return blockIdx.x; }
|
|
|
|
__device__ index_t get_grid_size() { return gridDim.x; }
|
|
|
|
__device__ index_t get_block_size() { return blockDim.x; }
|
|
|
|
} // namespace ck
|