Group norm (#417)

* Add groupnorm example by layernorm
1.  Reference is not ready
2. shape of gamma and beta need to be fix

* Let shape of gamma and beta can be same as x

* Modify test, instance and client example

* [What] Fix bug of layernorm for greater than 2 dimension.
[Why] We need to get upper length from merge transform instead of embed transform.

* Add reference for groupnorm

* Fuse sigmoid after groupnorm

* [What] Rename original layernorm into layernorm2d
[Why] Prepare to add groupnorm using layernorm5d

* clang-format

* Add groupnorm test

* Refine error message

* Add groupnorm ckProfiler

* Test groupnorm kernel from device_instance

* update example

* upadte profiler

* Fix test naming

* Fix argc number

* Move descriptor and sweeponce to argument for quick debugging

Co-authored-by: Chao Liu <chao.liu2@amd.com>

[ROCm/composable_kernel commit: 4eba345f6e]

profiler/src/profile_layernorm.cpp

@@ -5,6 +5,7 @@
 #include <vector>
 #include <unordered_map>
 
+#include "profiler/include/data_type_enum.hpp"
 #include "profiler/include/profile_layernorm_impl.hpp"
 
 using ck::index_t;
@@ -49,7 +50,7 @@ void print_help_layernorm()
               << "arg2: verification (0: no; 1: yes)\n"
               << "arg3: initialization (0: no init; 1: integer value; 2: decimal value)\n"
               << "arg4: print tensor value (0: no; 1: yes)\n"
-              << "arg5: time kernel (0=n0, 1=yes)\n"
+              << "arg5: time kernel (0=no, 1=yes)\n"
               << "--length: tensor extents (e.g, --length 1024 1024) \n"
               << "--strideXY: tensor strides (e.g, --strideXY 1024 1)\n"
               << "--strideGamma: tensor strides (e.g, --strideGamma 1)\n"
@@ -114,10 +115,3 @@ int profile_layernorm(int argc, char* argv[])
 
     return 0;
 }
-
-// hijack main() for quick debugging
-// int main(int argc, char* argv[])
-// {
-//     profile_layernorm(argc, argv);
-//     return 0;
-// }