mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-06-08 15:30:23 +00:00
acbd7bd7c5
* fix relu * clean up * clean up * adding 1x1 conv * adding 1x1 conv * added 1x1 conv * refactor * refactor * refactor * added profiler for conv+bias+relu+add * clean up * adding conv+bias+relu * adding conv+bias+relu * added conv+bias+relu * Update README.md * update cpu verification * adding c shuffle * update static_tensor for dealing with invalid element * adding c shuffle * debugging * fix bug * convert to fp16 before shuffle * shuffle more than one M/NRepeat * clean up * remove coordinate step hack from GridwiseGemm_k0mk1_k0nk1_mn_xdlops_v3r1 * clean up * remove coordinate step hack from all gridwise gemm xdl * clean up coordinate step hack * clean up coordinate step hack * ThreadwiseTensorSliceTransfer_v3r2 support pointwise op on both src and dst * adding output shuffle in conv+bias+relu+add * update * added conv+bias+relu+add with c shuffle * added conv+bias+relu+add with c shuffle * fix forward_sweep bugs in threadwise copy * clean up * refactor * clean up * clean up * added conv_c_shuffle+bias_relu * clean up * added conv+bias+relu+atomic_add * clean up * clean up * clean up * clean up * clean up * clean up * misc fixes; add 1x1 specialization * clean up * delete unused device op * clean up * add support for odd C value
19 lines
402 B
C++
19 lines
402 B
C++
#ifndef CK_UTILITY_HPP
|
|
#define CK_UTILITY_HPP
|
|
|
|
#include "config.hpp"
|
|
|
|
namespace ck {
|
|
|
|
__device__ constexpr index_t get_wave_size() { return CK_GPU_WAVE_SIZE; }
|
|
|
|
__device__ index_t get_thread_local_1d_id() { return threadIdx.x; }
|
|
|
|
__device__ index_t get_wave_local_1d_id() { return threadIdx.x / get_wave_size(); }
|
|
|
|
__device__ index_t get_block_1d_id() { return blockIdx.x; }
|
|
|
|
} // namespace ck
|
|
|
|
#endif
|