[GEMM] F8 GEMM, performance optimized. (#1384)

* add ab_scale init support

* enabled interwave

* add scale type; update isSupport

* adjust example

* clean

* enable f8 pure gemm rcr ckprofiler

* Add gemm_multiply_multiply instances

* clang format

* Optimize for ScaleBlockMNK=128

* enable abscale f8 gemm ck profiler

* Add pure f8 gemm test suite

* Reverting to the state of project at f60fd77

* update copyright

* clang format

* update copyright

---------
Co-authored-by: root <jizhan@amd.com>

profiler/src/CMakeLists.txt

@@ -46,6 +46,8 @@ if(GPU_TARGETS MATCHES "gfx9")
     list(APPEND PROFILER_SOURCES profile_grouped_gemm_multiply_tile_loop.cpp)
   endif()
   list(APPEND PROFILER_SOURCES profile_gemm_multiply_add.cpp)
+  list(APPEND PROFILER_SOURCES profile_gemm_multiply_multiply.cpp)
+  list(APPEND PROFILER_SOURCES profile_gemm_ab_scale.cpp)
   list(APPEND PROFILER_SOURCES profile_batched_gemm.cpp)
   list(APPEND PROFILER_SOURCES profile_batched_gemm_reduce.cpp)
   list(APPEND PROFILER_SOURCES profile_gemm_add_multiply.cpp)
@@ -121,6 +123,8 @@ if(GPU_TARGETS MATCHES "gfx9")
   target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_batched_gemm_instance)
   target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_batched_gemm_reduce_instance)
   target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_gemm_multiply_add_instance)
+  target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_gemm_multiply_multiply_instance)
+  target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_gemm_ab_scale_instance)
   target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_gemm_splitk_instance)
   target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_gemm_universal_instance)
   target_link_libraries(${PROFILER_EXECUTABLE} PRIVATE device_gemm_universal_reduce_instance)