Merge branch 'develop' into bnorm_bwd_pr

d0b49a14 · Qianfeng Zhang · 29026b0e · 87fd1152 · d0b49a14 · d0b49a14
Commit d0b49a14 authored Oct 28, 2022 by Qianfeng Zhang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_norm2.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_avg.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_amax.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_max.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8_min.cpp
--- a/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/softmax/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f16_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f16_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f32_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f32_f32_instance.cpp
--- a/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt
--- 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_masking_scale_softmax_gemm_permute_impl.hpp
+++ b/profiler/include/profile_batched_gemm_masking_scale_softmax_gemm_permute_impl.hpp
--- a/profiler/include/profile_groupnorm_impl.hpp
+++ b/profiler/include/profile_groupnorm_impl.hpp
--- a/profiler/include/profile_layernorm_impl.hpp
+++ b/profiler/include/profile_layernorm_impl.hpp
--- a/profiler/include/profile_reduce_impl.hpp
+++ b/profiler/include/profile_reduce_impl.hpp
--- a/profiler/include/profile_normalization_impl.hpp
+++ b/profiler/include/profile_normalization_impl.hpp
--- a/profiler/src/profile_layernorm.cpp
+++ b/profiler/src/profile_layernorm.cpp
--- a/profiler/src/profile_normalization.cpp
+++ b/profiler/src/profile_normalization.cpp
--- a/script/cmake-ck-dev.sh
+++ b/script/cmake-ck-dev.sh