Merge branch 'develop' of...

Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into navi3x_mD_batchedGEMM_GroupConvFwd

Merge branch 'develop' of...
Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into navi3x_mD_batchedGEMM_GroupConvFwd
f1b53d78 · aska-0096 · 0c9cdbce · 7494c1c6 · f1b53d78 · f1b53d78
Commit f1b53d78 authored Jan 30, 2023 by aska-0096
20 changed files
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_amax.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_avg.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_max.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64_min.cpp
--- 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_add.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8_add.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_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/profiler/include/profiler/profile_batchnorm_infer_impl.hpp
+++ b/profiler/include/profiler/profile_batchnorm_infer_impl.hpp
--- a/profiler/include/profiler/profile_gemm_add_multiply_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_add_multiply_impl.hpp
--- a/profiler/include/profiler/profile_reduce_impl.hpp
+++ b/profiler/include/profiler/profile_reduce_impl.hpp
--- a/profiler/include/profiler/profile_softmax_impl.hpp
+++ b/profiler/include/profiler/profile_softmax_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- a/profiler/src/profile_batchnorm_infer.cpp
+++ b/profiler/src/profile_batchnorm_infer.cpp
--- a/profiler/src/profile_gemm_add_multiply.cpp
+++ b/profiler/src/profile_gemm_add_multiply.cpp
--- a/profiler/src/profile_softmax.cpp
+++ b/profiler/src/profile_softmax.cpp
--- a/test/batchnorm/CMakeLists.txt
+++ b/test/batchnorm/CMakeLists.txt
--- a/test/batchnorm/batchnorm_infer_rank_4.cpp
+++ b/test/batchnorm/batchnorm_infer_rank_4.cpp