From bbda71f0964bfe13139d041762586ea74f254ffb Mon Sep 17 00:00:00 2001 From: Anca Hamuraru Date: Fri, 16 May 2025 08:31:32 +0000 Subject: [PATCH] Added padding instances for f16xf8xf16, f16xi4xf16 --- .../gpu/gemm_universal.hpp | 31 ++++++++ .../gpu/gemm_universal_wmma.inc | 72 +++++++++++++++++++ .../gpu/gemm_universal/CMakeLists.txt | 47 +++++++++++- ...f8_f16_km_kn_mn_comp_kpadding_instance.cpp | 24 +++++++ ..._f16_km_kn_mn_comp_mnkpadding_instance.cpp | 24 +++++++ ...8_f16_km_kn_mn_comp_mnpadding_instance.cpp | 24 +++++++ ...f8_f16_km_nk_mn_comp_kpadding_instance.cpp | 24 +++++++ ..._f16_km_nk_mn_comp_mnkpadding_instance.cpp | 24 +++++++ ...8_f16_km_nk_mn_comp_mnpadding_instance.cpp | 24 +++++++ ...f8_f16_mk_kn_mn_comp_kpadding_instance.cpp | 24 +++++++ ..._f16_mk_kn_mn_comp_mnkpadding_instance.cpp | 24 +++++++ ...8_f16_mk_kn_mn_comp_mnpadding_instance.cpp | 24 +++++++ ...f8_f16_mk_nk_mn_comp_kpadding_instance.cpp | 24 +++++++ ..._f16_mk_nk_mn_comp_mnkpadding_instance.cpp | 24 +++++++ ...8_f16_mk_nk_mn_comp_mnpadding_instance.cpp | 24 +++++++ ...i4_f16_km_nk_mn_comp_kpadding_instance.cpp | 24 +++++++ ..._f16_km_nk_mn_comp_mnkpadding_instance.cpp | 24 +++++++ ...4_f16_km_nk_mn_comp_mnpadding_instance.cpp | 24 +++++++ ...i4_f16_mk_nk_mn_comp_kpadding_instance.cpp | 24 +++++++ ..._f16_mk_nk_mn_comp_mnkpadding_instance.cpp | 24 +++++++ ...4_f16_mk_nk_mn_comp_mnpadding_instance.cpp | 24 +++++++ 21 files changed, 580 insertions(+), 2 deletions(-) create mode 100644 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_comp_kpadding_instance.cpp create mode 100644 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_comp_mnkpadding_instance.cpp create mode 100644 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_comp_mnpadding_instance.cpp create mode 100644 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_comp_kpadding_instance.cpp create mode 100644 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_comp_mnkpadding_instance.cpp create mode 100644 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_comp_mnpadding_instance.cpp create mode 100644 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_comp_kpadding_instance.cpp create mode 100644 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_comp_mnkpadding_instance.cpp create mode 100644 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_comp_mnpadding_instance.cpp create mode 100644 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_comp_kpadding_instance.cpp create mode 100644 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_comp_mnkpadding_instance.cpp create mode 100644 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_comp_mnpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instance.cpp diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp index ace8f00cb9..9d8c208483 100644 --- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp +++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp @@ -269,21 +269,42 @@ struct DeviceOperationInstanceFactory< is_same_v) { add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_default_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_kpaddingt_instances( + op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnkpadding_instances( + op_ptrs); } else if constexpr(is_same_v && is_same_v && is_same_v) { add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_default_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_kpadding_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instances( + op_ptrs); } else if constexpr(is_same_v && is_same_v && is_same_v) { add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_default_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_kpadding_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_mnkpadding_instances( + op_ptrs); } else if constexpr(is_same_v && is_same_v && is_same_v) { add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_default_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_kpadding_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnkpadding_instances( + op_ptrs); } } @@ -294,11 +315,21 @@ struct DeviceOperationInstanceFactory< is_same_v) { 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_kpadding_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instances( + op_ptrs); } else if constexpr(is_same_v && is_same_v && is_same_v) { 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_kpadding_instances(op_ptrs); + add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instances( + op_ptrs); } } #endif diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc index 18da3a21a2..699b5414fe 100644 --- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc +++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc @@ -297,31 +297,103 @@ void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_kpadding_default_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_mnpadding_default_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_mnkpadding_default_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_kpadding_default_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_mnpadding_default_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_mnkpadding_default_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances); #endif } // namespace instance } // namespace device diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt b/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt index f70b53d455..6a9cf9a2bc 100644 --- a/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt @@ -53,7 +53,14 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES device_gemm_wmma_universal_bf16_i4_bf16/device_gemm_wmma_universal_bf16_i4_bf16_km_nk_mn_comp_mnkpadding_instance.cpp device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instance.cpp + device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instance.cpp device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_default_instance.cpp device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp @@ -76,9 +83,24 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnkpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_mnkpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnkpadding_instance.cpp device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_kn_mn_comp_default_instance.cpp device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp @@ -186,9 +208,15 @@ set_source_files_properties(device_gemm_wmma_universal_bf16_i4_bf16/device_gemm_ set_source_files_properties(device_gemm_wmma_universal_bf16_i4_bf16/device_gemm_wmma_universal_bf16_i4_bf16_km_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") set_source_files_properties(device_gemm_wmma_universal_bf16_i4_bf16/device_gemm_wmma_universal_bf16_i4_bf16_km_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") +set_source_files_properties(device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_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_i4_f16/device_gemm_wmma_universal_f16_i4_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_i4_f16/device_gemm_wmma_universal_f16_i4_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_i4_f16/device_gemm_wmma_universal_f16_i4_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_i4_bf16/device_gemm_wmma_universal_f16_i4_bf16_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_i4_bf16/device_gemm_wmma_universal_f16_i4_bf16_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_i4_f16/device_gemm_wmma_universal_f16_i4_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_i4_f16/device_gemm_wmma_universal_f16_i4_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_i4_f16/device_gemm_wmma_universal_f16_i4_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_i4_f16/device_gemm_wmma_universal_f16_i4_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_f8_f16_f16/device_gemm_wmma_universal_f8_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_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") @@ -211,9 +239,24 @@ set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wm set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_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_f16_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_kmnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") + set_source_files_properties(device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_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_f8_f16/device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") set_source_files_properties(device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_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_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") diff --git a/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_comp_kpadding_instance.cpp b/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_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..669d66776c --- /dev/null +++ b/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_comp_kpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_km_kn_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnkpadding_instance.cpp b/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_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..6b51066995 --- /dev/null +++ b/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_comp_mnkpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_km_kn_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnpadding_instance.cpp b/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_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..0ef41d88d7 --- /dev/null +++ b/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_comp_mnpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_km_kn_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_km_kn_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_kpadding_instance.cpp b/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_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..db982d444a --- /dev/null +++ b/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_comp_kpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_km_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnkpadding_instance.cpp b/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_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..629348bd64 --- /dev/null +++ b/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_comp_mnkpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_km_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnpadding_instance.cpp b/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_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..46fadb42fc --- /dev/null +++ b/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_comp_mnpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_km_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_km_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_kpadding_instance.cpp b/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_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..a4b4ee34b1 --- /dev/null +++ b/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_comp_kpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnkpadding_instance.cpp b/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_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..85f8d1d4a6 --- /dev/null +++ b/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_comp_mnkpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnpadding_instance.cpp b/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_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..6a7fdcc07a --- /dev/null +++ b/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_comp_mnpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_kpadding_instance.cpp b/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_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..91ecd5cde8 --- /dev/null +++ b/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_comp_kpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnkpadding_instance.cpp b/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_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..8a763ba7a4 --- /dev/null +++ b/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_comp_mnkpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/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_comp_mnpadding_instance.cpp b/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_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..106b0acdd7 --- /dev/null +++ b/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_comp_mnpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..de7d3dc5bf --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_kpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_i4_f16_km_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..34ef320ad1 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_i4_f16_km_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..5e29496ef1 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_i4_f16_km_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..111e35e7fe --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_kpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..bdf4090c84 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..4b9d57cbd0 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn.hpp" +#include "ck/host_utility/device_prop.hpp" + +namespace ck { +namespace tensor_operation { +namespace device { +namespace instance { + +void add_device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, device_gemm_wmma_universal_f16_i4_f16_mk_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck