ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add grouped conv bwd wei merged grouped instance for larger filter (#1984)

Browse Source 
* Add grouped conv bwd wei merged grouped instance for larger filter

* Update readme
This commit is contained in:
Bartłomiej Kocot
2025-03-18 16:16:24 +01:00
committed by GitHub
parent 1342ecf7fb
commit fdaff5603e
2 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
client_example/11_grouped_conv_bwd_weight/README.md
View File

@@ -36,10 +36,10 @@ Table of supported cases by instance factory with XDL instruction:
| |NHWGC/GKYXC/NHWGK|NGCHW/GKYXC/NGKHW|GNHWC/GKYXC/GNHWK|
|-------|---|---|---|
|bf16|2D, 3D|✗|✗|
|bf16|2D, 3D|2D, 3D|✗|
|bf16(fp32 for weight)|2D, 3D|✗|1D, 2D, 3D|
|fp16 |2D, 3D|✗|1D, 2D, 3D|
|fp32 |2D, 3D|✗|1D, 2D, 3D|
|fp16 |2D, 3D|2D, 3D|1D, 2D, 3D|
|fp32 |2D, 3D|2D, 3D|1D, 2D, 3D|
Table of supported cases by instance factory with WMMA instruction: