ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-11 00:40:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add s_nops after v_dot to avoid hazard (#808)

Browse Source 
* Add s_nops after v_dot to avoid hazard

* Fix builtin for inner_produxt fp16

* Skip inline version to builtin

* Add comments regarding isa

* Fix comment regarding s_nop
This commit is contained in:
Bartłomiej Kocot
2023-07-27 20:29:44 +02:00
committed by GitHub
parent e7dca79d27
commit 7761e5232c
5 changed files with 28 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
test/batched_gemm_multi_d/CMakeLists.txt
View File

@@ -1,7 +1,5 @@
# TODO: Enable for gfx90a after complier fix
if(DL_KERNELS)
if(NOT GPU_TARGETS MATCHES "gfx90a")
add_gtest_executable(test_batched_gemm_multi_d test_batched_gemm_multi_d.cpp)
target_link_libraries(test_batched_gemm_multi_d PRIVATE utility device_batched_gemm_multi_d_instance)
endif()
add_gtest_executable(test_batched_gemm_multi_d test_batched_gemm_multi_d.cpp)
target_link_libraries(test_batched_gemm_multi_d PRIVATE utility device_batched_gemm_multi_d_instance)
endif()