Merge branch 'navi3x_change_bwgemm' of...

Merge branch 'navi3x_change_bwgemm' of https://github.com/ROCmSoftwarePlatform/composable_kernel into HEAD

Jenkinsfile

@@ -172,7 +172,7 @@ def cmake_build(Map conf=[:]){
     if(conf.get("build_install","") == "true")
     {
         config_targets = 'install ' + config_targets
-        setup_args = ' -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install' + setup_args
+        setup_args = ' -DBUILD_DEV=On -DCMAKE_INSTALL_PREFIX=../install' + setup_args
     } else{
         setup_args = ' -DBUILD_DEV=On' + setup_args
     }
@@ -657,7 +657,7 @@ pipeline {
                 {
                     agent{ label rocmnode("gfx908 || gfx90a") }
                     environment{
-                        setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a;gfx1030" -DCMAKE_CXX_FLAGS="-O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" """ : """ -DBUILD_DEV=Off -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a;gfx1030" -DCMAKE_CXX_FLAGS="-O3 " """ }"
+                        setup_args = "${params.COMPILER_VERSION == "ck-9110" ? """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a;gfx1030" -DCMAKE_CXX_FLAGS="-O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" """ : """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a;gfx1030" -DCMAKE_CXX_FLAGS="-O3 " """ }"
                         execute_args = "${params.COMPILER_VERSION == "ck-9110" ? """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -DGPU_TARGETS="gfx908;gfx90a;gfx1030" -DCMAKE_CXX_FLAGS="-O3 -Xclang -mlink-builtin-bitcode -Xclang /opt/rocm/amdgcn/bitcode/oclc_abi_version_400.bc" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ : """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -DGPU_TARGETS="gfx908,gfx90a;gfx1030" -DCMAKE_CXX_FLAGS="-O3" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ }"
                     }
                     steps{

cmake/EnableCompilerWarnings.cmake

@@ -65,7 +65,8 @@ else()
             -Wuninitialized
             -Wunreachable-code
             -Wunused
-
+            -Wno-reserved-identifier
+            -Werror
             -Wsign-compare
             -Wno-extra-semi-stmt
         )

include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp

@@ -673,7 +673,7 @@ struct GridwiseGemmMultipleD_k0mk1_k0nk1_mn_wmma_cshuffle
         constexpr auto KPack = math::integer_least_multiple(K1, WmmaK);
 
         auto blockwise_gemm =
-            BlockwiseGemmWMMA_k0mk1_k0nk1_m0m1m2n0n1n2m3_CShuffle_FIFO<BlockSize,
+            BlockwiseGemmWMMA_k0mk1_k0nk1_m0m1m2n0n1n2m3_CShuffle<BlockSize,
                                                          ADataType,
                                                          BDataType,
                                                          AccDataType,