ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 19:09:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow building CK for specific data types and split off last remaining DL instances. (#830)

Browse Source 
* properly split conv_nd_bwd_data instances

* split conv2d_fwd instance data types

* split the gemm, conv2d_fwd and batched_gemm_softamx_gemm

* split the tests by data types where possible

* filter examples by DTYPES

* split few remaining examples by DTYPES

* filter most instances by DTYPES

* add new lines at end of headers, fix grouped_gemm profiler

* fix syntax

* split the ckprofiler instances by DTYPES

* split the conv2d and quantization DL and XDL instances

* fix the splitting of conv2d DL instances

* split softmax and pool_fwd tests for fp16 and fp32 types

* fix syntax

* fix the dl_int8 quantization instances isolation

[ROCm/composable_kernel commit: 08eb176929]
This commit is contained in:
Illia Silin
2023-08-07 14:56:10 -07:00
committed by GitHub
parent 33496a08cc
commit 25efecc13e
117 changed files with 976 additions and 590 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
example/14_gemm_quantization/CMakeLists.txt
View File

@@ -1,6 +1,8 @@
if(DTYPES MATCHES "int8" OR NOT DEFINED DTYPES)
# dlops
add_example_executable(example_gemm_dl_quantization_int8 gemm_dl_quantization_int8.cpp)
if(DL_KERNELS)
add_example_executable(example_gemm_dl_quantization_int8 gemm_dl_quantization_int8.cpp)
endif()
# xdlops
list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942)