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

Ammending changes for adding support for padding instances for f16xf16xf16

Browse Source
This commit is contained in:
Anca Hamuraru
2025-05-14 09:41:19 +00:00
parent dd47f39a0a
commit 647024db6f
3 changed files with 114 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
View File

@@ -64,21 +64,45 @@ struct DeviceOperationInstanceFactory<
is_same_v<CLayout, Row>)
{
add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instances(op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
op_ptrs);
}
else if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
is_same_v<CLayout, Row>)
{
add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
op_ptrs);
}
else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Row> &&
is_same_v<CLayout, Row>)
{
add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instances(op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_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_f16_f16_km_nk_mn_comp_default_instances(op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instances(
op_ptrs);
add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instances(
op_ptrs);
}
}
#endif

57
library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc
View File

@@ -13,21 +13,78 @@ void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
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);
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);
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);
void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instances(
std::vector<std::unique_ptr<
DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
#endif
#ifdef CK_ENABLE_BF16
void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instances(

36
library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt
View File

@@ -3,10 +3,25 @@ set(GEMM_UNIVERSAL_INSTANCES)
list(APPEND GEMM_UNIVERSAL_INSTANCES
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instance.cpp
device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instance.cpp
device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_default_instance.cpp
@@ -68,9 +83,24 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES
)
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
set_source_files_properties(device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")