removed conflicts in struct members between streamk and unievrsal streamk

example/01_gemm/common.hpp

@@ -43,6 +43,18 @@ struct ProblemSizeStreamK final
     ck::index_t StrideB = 4096;
     ck::index_t StrideC = 4096;
 
+    ck::index_t NumSKBlocks = -1;
+};
+struct ProblemSizeStreamK_universal final
+{
+    ck::index_t M = 3840;
+    ck::index_t N = 4096;
+    ck::index_t K = 4096;
+
+    ck::index_t StrideA = 4096;
+    ck::index_t StrideB = 4096;
+    ck::index_t StrideC = 4096;
+
     ck::index_t Grid_size   = -1; // defaults to max occupancy
     ck::index_t Streamk_sel = 1;  // defaults to 1-tile SK
 };

example/01_gemm/gemm_xdl_fp16_streamk_v3.cpp

@@ -45,4 +45,4 @@ using ReferenceGemmInstance = ck::tensor_operation::host::
 
 #include "run_gemm_example_streamk_v2.inc"
 
-int main(int argc, char* argv[]) { return !run_gemm_splitk_example(argc, argv); }
+int main(int argc, char* argv[]) { return !run_gemm_universal_streamk_example(argc, argv); }

example/01_gemm/run_gemm_example_streamk_v2.inc

@@ -290,9 +290,9 @@ bool run_gemm(const ProblemType& problem_size, const ExecutionConfig& config)
     return pass;
 }
 
-bool run_gemm_splitk_example(int argc, char* argv[])
+bool run_gemm_universal_streamk_example(int argc, char* argv[])
 {
-    ProblemSizeStreamK problem_size;
+    ProblemSizeStreamK_universal problem_size;
     ExecutionConfig config;
 
     return !parse_cmd_args(argc, argv, problem_size, config) || run_gemm(problem_size, config);