ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-08 16:17:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Pre-commit hooks fixes

Browse Source
This commit is contained in:
Anca Hamuraru
2025-05-08 13:48:18 +00:00
parent 97e024918e
commit 744262dd88
10 changed files with 13 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
View File

@@ -133,7 +133,7 @@ struct DeviceOperationInstanceFactory<
is_same_v<CDataType, bhalf_t>)
{
if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
is_same_v<CLayout, Row>)
is_same_v<CLayout, Row>)
{
add_device_gemm_wmma_universal_bf16_i4_bf16_mk_nk_mn_comp_default_instances(
op_ptrs);
@@ -201,16 +201,14 @@ struct DeviceOperationInstanceFactory<
is_same_v<CDataType, half_t>)
{
if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
is_same_v<CLayout, Row>)
is_same_v<CLayout, Row>)
{
add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_default_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_default_instances(op_ptrs);
}
else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Col> &&
is_same_v<CLayout, Row>)
{
add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_default_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_default_instances(op_ptrs);
}
}
#endif

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_kn_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_nk_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn.hpp
View File

@@ -13,7 +13,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
using F8 = f8_t;
using F8 = f8_t;
using F16 = half_t;
using F32 = float;

2
test/gemm_universal/test_gemm_universal_wmma_bf16.cpp
View File

@@ -7,7 +7,7 @@
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "test_gemm_universal_util.hpp"
using I4 = pk_i4_t;
using I4 = pk_i4_t;
using BF16 = ck::bhalf_t;
using F32 = float;