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

profiler/CMakeLists.txt

@@ -27,6 +27,7 @@ set(PROFILER_SOURCE
     src/profile_layernorm.cpp
     src/profile_softmax.cpp
     src/profile_batchnorm_fwd.cpp
+    src/profile_batchnorm_bwd.cpp
 )
 
 add_executable(ckProfiler ${PROFILER_SOURCE})

profiler/src/profiler.cpp

@@ -25,6 +25,7 @@ int profile_layernorm(int, char*[]);
 int profile_groupnorm(int, char*[]);
 int profile_reduce(int, char*[]);
 int profile_batchnorm_forward(int, char*[]);
+int profile_batchnorm_backward(int, char*[]);
 
 static void print_helper_message()
 {
@@ -148,6 +149,10 @@ int main(int argc, char* argv[])
     {
         return profile_batchnorm_forward(argc, argv);
     }
+    else if(strcmp(argv[1], "bnorm_bwd") == 0)
+    {
+        return profile_batchnorm_backward(argc, argv);
+    }
     else
     {
         print_helper_message();