Merge branch 'develop' into grouped_gemm_dev_args_splitk

5387d422 · zjing14 · GitHub · d84022d4 · 7761e523 · 5387d422
Unverified Commit 5387d422 authored Jul 27, 2023 by zjing14 Committed by GitHub Jul 27, 2023
16 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_weight/device_grouped_conv3d_bwd_weight_xdl_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
--- a/library/src/utility/device_memory.cpp
+++ b/library/src/utility/device_memory.cpp
--- a/profiler/README.md
+++ b/profiler/README.md
--- a/profiler/include/profiler/profile_gemm_streamk_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_streamk_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- a/profiler/src/profile_gemm_streamk.cpp
+++ b/profiler/src/profile_gemm_streamk.cpp
--- a/profiler/src/profile_grouped_conv_bwd_weight.cpp
+++ b/profiler/src/profile_grouped_conv_bwd_weight.cpp
--- a/script/profile_batched_gemm.sh
+++ b/script/profile_batched_gemm.sh
--- a/test/batched_gemm_multi_d/CMakeLists.txt
+++ b/test/batched_gemm_multi_d/CMakeLists.txt
--- a/test/block_swizzle_test/block_swizzle_test.cpp
+++ b/test/block_swizzle_test/block_swizzle_test.cpp
--- a/test/block_swizzle_test/rebuild.sh
+++ b/test/block_swizzle_test/rebuild.sh
--- a/test/block_swizzle_test/simple_args.h
+++ b/test/block_swizzle_test/simple_args.h
--- a/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp
+++ b/test/grouped_convnd_bwd_weight/test_grouped_convnd_bwd_weight.cpp