merge develop

6e3cf8b0 · Jing Zhang · 4ad62d7f · ba58a93f · 6e3cf8b0 · 6e3cf8b0
Commit 6e3cf8b0 authored May 24, 2022 by Jing Zhang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_atomic_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_atomic_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/conv3d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/conv3d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/convnd_bwd_data/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/convnd_bwd_data/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/device_conv2d.cpp
+++ b/library/src/tensor_operation_instance/gpu/device_conv2d.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bias2d/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias2d/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bias_relu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias_relu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bias_relu_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias_relu_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
--- 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/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