mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 02:27:57 +00:00
3f732cceab
* adding compilation for multiple targets
* fix build
* clean
* update Jekinsfile
* update readme
* update Jenkins
* use ck::half_t instead of ushort for bf16
* rename enum classes
* clean
* rename
* clean
[ROCm/composable_kernel commit: cd167e492a]
22 lines
337 B
C++
22 lines
337 B
C++
#ifndef CK_SYNCHRONIZATION_AMD_HPP
|
|
#define CK_SYNCHRONIZATION_AMD_HPP
|
|
|
|
#include "config.hpp"
|
|
|
|
namespace ck {
|
|
|
|
__device__ void block_sync_lds()
|
|
{
|
|
#if CK_EXPERIMENTAL_BLOCK_SYNC_LDS_WITHOUT_SYNC_VMEM
|
|
asm volatile("\
|
|
s_waitcnt lgkmcnt(0) \n \
|
|
s_barrier \
|
|
" ::);
|
|
#else
|
|
__syncthreads();
|
|
#endif
|
|
}
|
|
|
|
} // namespace ck
|
|
#endif
|