Merge remote-tracking branch 'origin/develop' into cpu_avx2

07a673c6 · carlushuang · c0f698d5 · ac0d8066 · 07a673c6 · 07a673c6
Commit 07a673c6 authored Apr 14, 2022 by carlushuang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt
--- a/profiler/src/README.md
+++ b/profiler/src/README.md
--- a/profiler/include/profile_batched_gemm_impl.hpp
+++ b/profiler/include/profile_batched_gemm_impl.hpp
--- a/profiler/include/profile_conv_bwd_data_impl.hpp
+++ b/profiler/include/profile_conv_bwd_data_impl.hpp
--- a/profiler/include/profile_conv_bwd_weight_impl.hpp
+++ b/profiler/include/profile_conv_bwd_weight_impl.hpp
--- a/profiler/include/profile_conv_fwd_bias_relu_add_impl.hpp
+++ b/profiler/include/profile_conv_fwd_bias_relu_add_impl.hpp
--- a/profiler/include/profile_conv_fwd_bias_relu_atomic_add_impl.hpp
+++ b/profiler/include/profile_conv_fwd_bias_relu_atomic_add_impl.hpp
--- a/profiler/include/profile_conv_fwd_bias_relu_impl.hpp
+++ b/profiler/include/profile_conv_fwd_bias_relu_impl.hpp
--- a/profiler/include/profile_conv_fwd_impl.hpp
+++ b/profiler/include/profile_conv_fwd_impl.hpp
--- a/profiler/include/profile_convnd_bwd_data_impl.hpp
+++ b/profiler/include/profile_convnd_bwd_data_impl.hpp
--- a/profiler/include/profile_gemm_bias_2d_impl.hpp
+++ b/profiler/include/profile_gemm_bias_2d_impl.hpp
--- a/profiler/include/profile_gemm_bias_relu_add_impl.hpp
+++ b/profiler/include/profile_gemm_bias_relu_add_impl.hpp
--- a/profiler/include/profile_gemm_bias_relu_impl.hpp
+++ b/profiler/include/profile_gemm_bias_relu_impl.hpp
--- a/profiler/include/profile_gemm_impl.hpp
+++ b/profiler/include/profile_gemm_impl.hpp
--- a/profiler/include/profile_grouped_gemm_impl.hpp
+++ b/profiler/include/profile_grouped_gemm_impl.hpp
--- a/profiler/include/profile_reduce_impl.hpp
+++ b/profiler/include/profile_reduce_impl.hpp
--- a/profiler/src/profile_batched_gemm.cpp
+++ b/profiler/src/profile_batched_gemm.cpp
--- a/profiler/src/profile_batched_gemm_reduce.cpp
+++ b/profiler/src/profile_batched_gemm_reduce.cpp