Merge branch 'develop' into bnorm_bwd_pr

a781d078 · Qianfeng Zhang · fd76c787 · 4c4c7328 · a781d078 · a781d078
Commit a781d078 authored Nov 16, 2022 by Qianfeng Zhang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce2.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce3.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_f32_f32_instance_rank4_reduce4.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce1.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce1.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce2.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce2.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce3.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank3_reduce3.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce1.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce1.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce2.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce2.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce3.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce3.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce4.cpp
+++ b/library/src/tensor_operation_instance/gpu/softmax/device_softmax_i8_i8_instance_rank4_reduce4.cpp
--- a/library/src/utility/convolution_parameter.cpp
+++ b/library/src/utility/convolution_parameter.cpp
--- a/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt
--- a/profiler/include/profile_batched_gemm_add_relu_gemm_add_impl.hpp
+++ b/profiler/include/profile_batched_gemm_add_relu_gemm_add_impl.hpp
--- a/profiler/include/profile_batched_gemm_gemm_impl.hpp
+++ b/profiler/include/profile_batched_gemm_gemm_impl.hpp
--- 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_batched_gemm_softmax_gemm_impl.hpp
+++ b/profiler/include/profile_batched_gemm_softmax_gemm_impl.hpp
--- a/profiler/include/profile_batched_gemm_softmax_gemm_permute_impl.hpp
+++ b/profiler/include/profile_batched_gemm_softmax_gemm_permute_impl.hpp
--- a/profiler/include/profile_conv_bwd_data_impl.hpp
+++ b/profiler/include/profile_conv_bwd_data_impl.hpp