Merge branch 'develop' into add_int8_wmma_example_instance

9697ad4e · zjing14 · GitHub · 1c97db8a · 582e31e8 · 9697ad4e
Unverified Commit 9697ad4e authored May 31, 2023 by zjing14 Committed by GitHub May 31, 2023
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_irregular_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool_fwd/pool_fwd_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/pool_fwd/pool_fwd_instance_common.hpp
--- a/profiler/include/profiler/data_type_enum_helper.hpp
+++ b/profiler/include/profiler/data_type_enum_helper.hpp
--- a/profiler/include/profiler/profile_convnd_bwd_data_impl.hpp
+++ b/profiler/include/profiler/profile_convnd_bwd_data_impl.hpp
--- a/profiler/include/profiler/profile_convnd_bwd_weight_impl.hpp
+++ b/profiler/include/profiler/profile_convnd_bwd_weight_impl.hpp
--- a/profiler/include/profiler/profile_gemm_splitk_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_splitk_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_impl.hpp
--- a/profiler/include/profiler/profile_pool2d_fwd_impl.hpp
+++ b/profiler/include/profiler/profile_pool2d_fwd_impl.hpp
--- a/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
+++ b/profiler/include/profiler/profile_pool3d_fwd_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- a/profiler/src/profile_avg_pool2d_fwd.cpp
+++ b/profiler/src/profile_avg_pool2d_fwd.cpp