Modularize ckProfiler operations (#514)

* Re-structure ckProfiler source files

* Rename profiler.cpp to main.cpp

* Modularize ckProfiler operations

* Add description for profiler operations

* Use longer name to avoid name collision

* Use macro to delay expansion

* Use std::move() to avoid object copying

* Prohibit users from calling dtor

* Use macro to eliminate redundant code

* Make friend function hidden

* Add missing include directive <iostream>

* Fix wrong include directives

* Remove int8 from batchnorm-forward instances since it is not needed for forward training and could fail test

Co-authored-by: Qianfeng Zhang <Qianfeng.Zhang@amd.com>

[ROCm/composable_kernel commit: 8784a72e23]

profiler/src/profile_conv_bwd_data.cpp

@@ -6,7 +6,8 @@
 #include <initializer_list>
 #include <cstdlib>
 
-#include "profiler/include/profile_conv_bwd_data_impl.hpp"
+#include "profiler/profile_conv_bwd_data_impl.hpp"
+#include "profiler_operation_registry.hpp"
 
 namespace {
 
@@ -24,10 +25,13 @@ enum struct ConvDataType
     INT8_INT8_INT8, // 3
 };
 
+#define OP_NAME "conv_bwd_data"
+#define OP_DESC "Convolution Backward Data"
+
 static void print_helper_msg()
 {
     std::cout
-        << "arg1: tensor operation (conv_bwd_data: Convolution Backward Data)\n"
+        << "arg1: tensor operation (" OP_NAME ": " OP_DESC ")\n"
         << "arg2: data type (0: Input fp32, Weight fp32, Output fp32\n"
         << "                 1: Input fp16, Weight fp16, Output fp16\n"
         << "                 2: Input bf16, Weight bf16, Output bf16\n"
@@ -182,3 +186,5 @@ int profile_conv_bwd_data(int argc, char* argv[])
 
     return 1;
 }
+
+REGISTER_PROFILER_OPERATION(OP_NAME, OP_DESC, profile_conv_bwd_data);