From 0482b83fe682ba64f3b02d238b56ec0f8a2e6eba Mon Sep 17 00:00:00 2001 From: Anca Hamuraru Date: Wed, 14 May 2025 14:36:10 +0000 Subject: [PATCH] Added padding instances for bf16xbf16, f8xf8 --- .../gpu/gemm_universal.hpp | 34 +++++++++ .../gpu/gemm_universal_wmma.inc | 72 +++++++++++++++++++ .../gpu/gemm_universal/CMakeLists.txt | 45 ++++++++++++ ...6_bf16_km_kn_mn_comp_kpadding_instance.cpp | 25 +++++++ ...bf16_km_kn_mn_comp_mnkpadding_instance.cpp | 25 +++++++ ..._bf16_km_kn_mn_comp_mnpadding_instance.cpp | 25 +++++++ ...6_bf16_km_nk_mn_comp_kpadding_instance.cpp | 25 +++++++ ...bf16_km_nk_mn_comp_mnkpadding_instance.cpp | 25 +++++++ ..._bf16_km_nk_mn_comp_mnpadding_instance.cpp | 25 +++++++ ...6_bf16_mk_kn_mn_comp_kpadding_instance.cpp | 25 +++++++ ...bf16_mk_kn_mn_comp_mnkpadding_instance.cpp | 25 +++++++ ..._bf16_mk_kn_mn_comp_mnpadding_instance.cpp | 25 +++++++ ...6_bf16_mk_nk_mn_comp_kpadding_instance.cpp | 25 +++++++ ...bf16_mk_nk_mn_comp_mnkpadding_instance.cpp | 25 +++++++ ..._bf16_mk_nk_mn_comp_mnpadding_instance.cpp | 25 +++++++ ...8_bf16_mk_kn_mn_comp_kpadding_instance.cpp | 27 +++++++ ...bf16_mk_kn_mn_comp_mnkpadding_instance.cpp | 27 +++++++ ..._bf16_mk_kn_mn_comp_mnpadding_instance.cpp | 27 +++++++ ...8_bf16_mk_nk_mn_comp_kpadding_instance.cpp | 27 +++++++ ...bf16_mk_nk_mn_comp_mnkpadding_instance.cpp | 27 +++++++ ..._bf16_mk_nk_mn_comp_mnpadding_instance.cpp | 27 +++++++ 21 files changed, 613 insertions(+) create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_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 94f442d63f..947a39397c 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 @@ -115,24 +115,48 @@ struct DeviceOperationInstanceFactory< { add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instances( op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_mk_nk_mn_comp_default_instances( op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_kn_mn_comp_default_instances( op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_nk_mn_comp_default_instances( op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_kpadding_default_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_mnpadding_default_instances( + op_ptrs); + add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_mnkpadding_default_instances( + op_ptrs); } } #endif @@ -144,11 +168,21 @@ struct DeviceOperationInstanceFactory< is_same_v) { add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_default_instances(op_ptrs); + add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instances(op_ptrs); + add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16_mk_nk_mn_comp_default_instances(op_ptrs); + add_device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instances(op_ptrs); + add_device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instances( + op_ptrs); + add_device_gemm_wmma_universal_f8_f8_bf16_mk_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 c4f52073ac..ae2ac7e795 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 @@ -91,32 +91,104 @@ void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instanc std::vector>>& instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances); #endif #if(defined(CK_ENABLE_BF16) && defined(CK_ENABLE_FP8)) void add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances); void add_device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_default_instances( std::vector>>& instances); +void add_device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances); +void add_device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances); #endif } // namespace instance 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 4338cfb4f4..7ffc5e0334 100644 --- a/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt @@ -23,9 +23,24 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES 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_kn_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_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_mk_nk_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_default_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_default_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_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 @@ -103,9 +118,25 @@ set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_w 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_kn_mn_comp_kpadding_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_mnpadding_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_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_nk_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_kpadding_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_mnpadding_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_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_km_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_km_kn_mn_comp_kpadding_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_km_kn_mn_comp_mnpadding_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_km_kn_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_km_nk_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_km_nk_mn_comp_kpadding_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_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_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_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") @@ -131,7 +162,14 @@ set_source_files_properties(device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm list(APPEND GEMM_UNIVERSAL_INSTANCES device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp + device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_default_instance.cpp + device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp + device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instance.cpp + device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_kn_mn_comp_default_instance.cpp device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_kn_mn_comp_kpadding_instance.cpp @@ -188,7 +226,14 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES ) set_source_files_properties(device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") +set_source_files_properties(device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") +set_source_files_properties(device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") + set_source_files_properties(device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") +set_source_files_properties(device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") +set_source_files_properties(device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1") set_source_files_properties(device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_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_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..2d7be90ae6 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..c1ade989e1 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..76f0d7e122 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..e38a89a549 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..fa77376cb0 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..b4e5e3a2dd --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_km_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..eff6823843 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_mk_kn_mn_comp_KPadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..f0ec566878 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..6fe412e778 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..327c28c7e7 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..6141cbbbff --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..5b68474f24 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_bf16_bf16_bf16_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_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + add_device_operation_instances( + instances, + device_gemm_wmma_universal_bf16_bf16_bf16_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..6439f27f35 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_kpadding_instance.cpp @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16_mk_kn_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + if(ck::is_gfx11_supported()) + return; + + add_device_operation_instances( + instances, device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..513acdd975 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16_mk_kn_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + if(ck::is_gfx11_supported()) + return; + + add_device_operation_instances( + instances, device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..877ccac0a6 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16_mk_kn_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + if(ck::is_gfx11_supported()) + return; + + add_device_operation_instances( + instances, device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp new file mode 100644 index 0000000000..c625cda347 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16_mk_nk_mn_comp_kpadding_instances( + std::vector>>& + instances) +{ + if(ck::is_gfx11_supported()) + return; + + add_device_operation_instances( + instances, device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp new file mode 100644 index 0000000000..42d26a31d9 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instances( + std::vector>>& + instances) +{ + if(ck::is_gfx11_supported()) + return; + + add_device_operation_instances( + instances, device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instance.cpp new file mode 100644 index 0000000000..6b83ba4e64 --- /dev/null +++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f8_bf16/device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instance.cpp @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: MIT +// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved. + +#include "device_gemm_wmma_universal_f8_f8_bf16_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_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instances( + std::vector>>& + instances) +{ + if(ck::is_gfx11_supported()) + return; + + add_device_operation_instances( + instances, device_gemm_wmma_universal_f8_f8_bf16_mk_nk_mn_comp_instances{}); +} + +} // namespace instance +} // namespace device +} // namespace tensor_operation +} // namespace ck