clang

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_default_instance.cpp

@@ -9,9 +9,15 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_default_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm_Streamk_V2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>& 
-        instances)
+    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Col,
+                                                      Row,
+                                                      Row,
+                                                      BF16,
+                                                      BF16,
+                                                      BF16,
+                                                      PassThrough,
+                                                      PassThrough,
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instance.cpp

@@ -9,12 +9,19 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm_Streamk_V2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough,PassThrough>>>& 
-        instances)
+    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Col,
+                                                      Row,
+                                                      Row,
+                                                      BF16,
+                                                      BF16,
+                                                      BF16,
+                                                      PassThrough,
+                                                      PassThrough,
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
-        instances, device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_instances<GemmKPadding>{});
+        instances,
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_instances<GemmKPadding>{});
 }
 
 } // namespace instance

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instance.cpp

@@ -9,12 +9,19 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm_Streamk_V2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>& 
-        instances)
+    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Col,
+                                                      Row,
+                                                      Row,
+                                                      BF16,
+                                                      BF16,
+                                                      BF16,
+                                                      PassThrough,
+                                                      PassThrough,
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
-        instances, device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_instances<GemmMNKPadding>{});
+        instances,
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_instances<GemmMNKPadding>{});
 }
 
 } // namespace instance

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instance.cpp

@@ -9,9 +9,15 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-    DeviceGemm_Streamk_V2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough,PassThrough>>>& 
-    instances)
+    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Col,
+                                                      Row,
+                                                      Row,
+                                                      BF16,
+                                                      BF16,
+                                                      BF16,
+                                                      PassThrough,
+                                                      PassThrough,
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_kpadding_instance.cpp

@@ -9,9 +9,15 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_kpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm_Streamk_V2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
+    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
+                                                      Row,
+                                                      Row,
+                                                      BF16,
+                                                      BF16,
+                                                      BF16,
+                                                      PassThrough,
+                                                      PassThrough,
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp

@@ -9,9 +9,15 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm_Streamk_V2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
+    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
+                                                      Row,
+                                                      Row,
+                                                      BF16,
+                                                      BF16,
+                                                      BF16,
+                                                      PassThrough,
+                                                      PassThrough,
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,

profiler/src/profile_gemm_universal_streamk.cpp

@@ -91,8 +91,6 @@ int profile_gemm_universal_streamk(int argc, char* argv[])
     using F8 = ck::f8_t;
 #endif
 
-
-
     using Row = ck::tensor_layout::gemm::RowMajor;
     using Col = ck::tensor_layout::gemm::ColumnMajor;