ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-08 08:07:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixes for padding instances for f16xf16xf16

Browse Source
This commit is contained in:
Anca Hamuraru
2025-05-14 10:50:34 +00:00
parent ab28ac0b81
commit e2855633ee
3 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
View File

@@ -9,13 +9,13 @@ namespace tensor_operation {
namespace device {
namespace instance {
void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(
void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(
instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmDefault>{});
instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmKPadding>{});
}
} // namespace instance

5
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
View File

@@ -9,13 +9,14 @@ namespace tensor_operation {
namespace device {
namespace instance {
void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(
void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(
instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmDefault>{});
instances,
device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
}
} // namespace instance

4
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
View File

@@ -9,13 +9,13 @@ namespace tensor_operation {
namespace device {
namespace instance {
void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(
void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances)
{
add_device_operation_instances(
instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmDefault>{});
instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmMNPadding>{});
}
} // namespace instance