ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 13:41:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK] Integrate GPU reference into ckProfiler for convolutions (#3379)

Browse Source 
Refactor and integrate CK GPU references into ckProfiler.
- All convolution layouts and groupings supported for all three directions
- Unit tests verifying GPU and CPU reference is the same
- Support added to profiler (do_verification = 2 enables GPU reference)
- One profiler-based test per direction changed to GPU reference to demonstrate usag

Closes AICK-427
This commit is contained in:
Johannes Graner
2025-12-18 07:59:45 +01:00
committed by GitHub
parent 87dd073887
commit bb8445dca8
31 changed files with 3351 additions and 953 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
test/grouped_convnd_fwd/test_grouped_convnd_fwd.cpp
View File

@@ -46,7 +46,7 @@ class TestGroupedConvndFwd : public ::testing::Test
DataType,
DataType,
IndexType>(
true, // do_verification
2, // do_verification
1, // init_method: integer value
false, // do_log
false, // time_kernel