ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-24 14:54:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Improve external interface for GEMM and GEMM+add+add+fastgelu (#311)

Browse Source 
* interface for GEMM and GEMM+add+add+fastgelu

* rename namespace

* instance factory

* fix build

* fix build; add GEMM client example

* clean

[ROCm/composable_kernel commit: 0dcb3496cf]
This commit is contained in:
Chao Liu
2022-06-30 22:11:00 -05:00
committed by GitHub
parent 7094d7c910
commit 74b6e85eaf
259 changed files with 2915 additions and 2969 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
library/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp
View File

@@ -7,11 +7,12 @@
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/device_5ary_elementwise.hpp"
#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
using F16 = ck::half_t;
using F32 = float;
@@ -44,6 +45,7 @@ void add_device_normalize_from_mean_squaremean_f16_f32_f32_f16_f16_instances(
instances, device_normalize_from_mean_squaremean_f16_f32_f32_f16_f16_instances{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck