ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 10:59:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'f05e45ba59b76cb6ea83c471860ded65d5fc623f' into develop

Browse Source
This commit is contained in:
github-actions[bot]
2025-05-12 21:01:10 +00:00
parent daf55de9dd
commit 0bfff09142
14 changed files with 448 additions and 934 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
example/65_gemm_multiply_multiply/gemm_multiply_multiply_xdl_fp8_bpreshuffle.cpp
View File

@@ -9,7 +9,6 @@
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3_b_preshuffle.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_v3.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp"
@@ -142,12 +141,12 @@ using DeviceOpInstance = ck::tensor_operation::device::DeviceGemmMultiD_Xdl_CShu
AElementOp, BElementOp, CDEElementOp, GemmSpec, 256,
128, 128, 128,
16, 16,
32, 32,
2, 2,
16, 16,
8, 2,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, 0,
1, 1, S<1, 32, 1, 8>, S<8, 8, 1>,
ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v1, FP8>;
2, 1, S<1, 32, 1, 8>, S<8, 8, 1>,
ck::BlockGemmPipelineScheduler::Intrawave, ck::BlockGemmPipelineVersion::v3, FP8>;
// clang-format on
int main(int argc, char* argv[])