mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 14:11:29 +00:00
Compile for gfx908 and gfx90a (#130)
* adding compilation for multiple targets * fix build * clean * update Jekinsfile * update readme * update Jenkins * use ck::half_t instead of ushort for bf16 * rename enum classes * clean * rename * clean
This commit is contained in:
@@ -1,44 +1,11 @@
|
||||
# Instructions for ```gemm_xdl_alpha_beta``` Example
|
||||
# Instructions for ```example_gemm_xdl_alpha_beta```
|
||||
|
||||
## Docker script
|
||||
```bash
|
||||
docker run \
|
||||
-it \
|
||||
--rm \
|
||||
--privileged \
|
||||
--group-add sudo \
|
||||
-w /root/workspace \
|
||||
-v ${PATH_TO_LOCAL_WORKSPACE}:/root/workspace \
|
||||
rocm/tensorflow:rocm4.3.1-tf2.6-dev \
|
||||
/bin/bash
|
||||
```
|
||||
|
||||
## Build ```gemm_xdl_alpha_beta```
|
||||
```bash
|
||||
mkdir build && cd build
|
||||
```
|
||||
|
||||
```bash
|
||||
# Need to specify target ID, example below is gfx908
|
||||
cmake \
|
||||
-D BUILD_DEV=OFF \
|
||||
-D CMAKE_BUILD_TYPE=Release \
|
||||
-D CMAKE_CXX_FLAGS="-DCK_AMD_GPU_GFX908 --amdgpu-target=gfx908 -O3 " \
|
||||
-D CMAKE_CXX_COMPILER=/opt/rocm/bin/hipcc \
|
||||
-D CMAKE_PREFIX_PATH=/opt/rocm \
|
||||
..
|
||||
```
|
||||
|
||||
```bash
|
||||
make -j gemm_xdl_alpha_beta
|
||||
```
|
||||
|
||||
## Run ```gemm_xdl_alpha_beta```
|
||||
## Run ```example_gemm_xdl_alpha_beta```
|
||||
```bash
|
||||
#arg1: verification (0=no, 1=yes)
|
||||
#arg2: initialization (0=no init, 1=integer value, 2=decimal value)
|
||||
#arg3: run kernel # of times (>1)
|
||||
./example/gemm_xdl_alpha_beta 1 1 1 0.5 0.5
|
||||
./bin/example_gemm_xdl_alpha_beta 1 1 1 0.5 0.5
|
||||
```
|
||||
Result (MI100 @ 1502Mhz, 184.6TFlops peak FP16)
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user