ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 02:54:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed GroupedGemmFixedNK with hipGraph (#1065)

Browse Source 
* fixed examples; add async_mem_set

* add stream to all deviceOp using SetWorkspace

---------

Co-authored-by: Jing Zhang <jizha@amd.com>

[ROCm/composable_kernel commit: 49df1dc595]
This commit is contained in:
zjing14
2023-11-30 15:09:27 -06:00
committed by GitHub
parent 53f676e54f
commit 7d995ced07
10 changed files with 30 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
View File

@@ -299,8 +299,8 @@ int main(int argc, char* argv[])
for(int i = 0; i < problem_size.group_count; i++)
{
problem_size.Ms.push_back(256 + 256 * i);
problem_size.Ns.push_back(128 + 128 * i);
problem_size.Ks.push_back(128 + 64 * i);
problem_size.Ns.push_back(256);
problem_size.Ks.push_back(128);
problem_size.stride_As.push_back(problem_size.Ks[i]);
problem_size.stride_Bs.push_back(problem_size.Ks[i]);

4
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
View File

@@ -300,8 +300,8 @@ int main(int argc, char* argv[])
for(int i = 0; i < problem_size.group_count; i++)
{
problem_size.Ms.push_back(256 + 256 * i);
problem_size.Ns.push_back(128 + 128 * i);
problem_size.Ks.push_back(128 + 64 * i);
problem_size.Ns.push_back(256);
problem_size.Ks.push_back(128);
problem_size.stride_As.push_back(problem_size.Ks[i]);
problem_size.stride_Bs.push_back(problem_size.Ks[i]);