ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 02:02:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add performance and large tensor tests for grouped conv (#1456)

Browse Source 
* Add performance and large tensor tests for grouped conv

* Resize tests

* Resize tests

* update the python script to parse the grouped_conv results

* Remove int8 tests

* change bwd wei layout

---------

Co-authored-by: illsilin <Illia.Silin@amd.com>

[ROCm/composable_kernel commit: 2581727d2a]
This commit is contained in:
Bartłomiej Kocot
2024-08-16 16:48:30 +02:00
committed by GitHub
parent e77e18da19
commit dffd5eacc0
11 changed files with 305 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
script/process_qa_data.sh
View File

@@ -15,8 +15,9 @@ python3 process_perf_data.py perf_resnet50_N256.log
python3 process_perf_data.py perf_resnet50_N4.log
python3 process_perf_data.py perf_batched_gemm.log
python3 process_perf_data.py perf_grouped_gemm.log
python3 process_perf_data.py perf_conv_fwd.log
python3 process_perf_data.py perf_conv_bwd_data.log
python3 process_perf_data.py perf_grouped_conv_fwd.log
python3 process_perf_data.py perf_grouped_conv_bwd_data.log
python3 process_perf_data.py perf_grouped_conv_bwd_weight.log
python3 process_perf_data.py perf_gemm_bilinear.log
python3 process_perf_data.py perf_reduction.log
python3 process_perf_data.py perf_splitK_gemm.log