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

b134b7d6 · carlushuang · 090ba885 · 9f71ff48 · b134b7d6 · b134b7d6
Commit b134b7d6 authored May 16, 2022 by carlushuang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
--- a/library/src/utility/CMakeLists.txt
+++ b/library/src/utility/CMakeLists.txt
--- a/library/src/utility/conv_fwd_util.cpp
+++ b/library/src/utility/conv_fwd_util.cpp
--- a/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt
--- a/profiler/include/profile_batched_gemm_impl.hpp
+++ b/profiler/include/profile_batched_gemm_impl.hpp
--- a/profiler/include/profile_batched_gemm_reduce_impl.hpp
+++ b/profiler/include/profile_batched_gemm_reduce_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_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