ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-05 06:01:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add basic documentation structure (#1715)

Browse Source 
* Add basic documentation structure

* Add terminology placeholder

* Add codegen placeholder

* Create template for each page
This commit is contained in:
Bartłomiej Kocot
2024-12-04 00:46:47 +01:00
committed by GitHub
parent 08d5c02c37
commit 5affda819d
10 changed files with 62 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
profiler/README.md
View File

@@ -1,3 +1,5 @@
[Back to the main page](../README.md)
# Composable Kernel profiler
## Profile GEMM kernels
```bash
#arg1: tensor operation (gemm=GEMM)
@@ -180,3 +182,13 @@ Note: Column to image kernel adds to the output memory, this will cause output b
################ op datatype verify init log time dim0 dim1 dim2 in_stride0 in_stride1 in_stride2 out_stride0 out_stride1 out_stride2
./bin/ckProfiler permute_scale 0 1 1 0 1 64 64 64 4096 64 1 1 64 4096
```
## Convert MIOpen driver command to CKProfiler
```bash
python3 ../script/convert_miopen_driver_to_profiler.py
/opt/rocm/bin/MIOpenDriver conv -n 32 -c 64 -H 28 -W 28 -k 64 -y 3 -x 3
-p 1 -q 1 -u 2 -v 2 -l 1 -j 1 -m conv -g 32 -F 1 -t 1
```
Only convolution driver is supported.