clang all

library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_streamk.hpp

@@ -17,7 +17,7 @@ namespace tensor_operation {
 namespace device {
 namespace instance {
 #ifdef CK_ENABLE_FP16
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -28,7 +28,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -39,7 +39,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -50,7 +50,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -61,7 +61,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -72,7 +72,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -83,7 +83,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -94,7 +94,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -105,7 +105,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -116,7 +116,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Row,
                                                       Row,
@@ -127,7 +127,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -138,7 +138,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -149,7 +149,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -160,7 +160,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -171,7 +171,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -182,7 +182,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -193,7 +193,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -204,7 +204,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -215,7 +215,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -226,7 +226,7 @@ namespace instance {
                                                       PassThrough,
                                                       PassThrough>>>& instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
                                                       Col,
                                                       Row,
@@ -240,382 +240,381 @@ namespace instance {
 
 // Emin @Added
 #ifdef CK_ENABLE_BF16
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_mpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_mpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_mkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_mkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_mkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_mkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v2_mkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v2_mkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 #endif
 // Emin @Added
 
-
 #if(defined(CK_ENABLE_FP8))
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_kn_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f16_f8_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_default_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_default_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_default_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_kpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-    void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<
         DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
@@ -711,7 +710,7 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGemm_S
         }
 #endif
 
-//Emin @Added
+// Emin @Added
 #ifdef CK_ENABLE_BF16
         if constexpr(is_same_v<ADataType, bhalf_t> && is_same_v<BDataType, bhalf_t> &&
                      is_same_v<CDataType, bhalf_t>)
@@ -814,7 +813,7 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGemm_S
             }
         }
 #endif
-//EMin @Added
+        // EMin @Added
 
 #if(defined(CK_ENABLE_FP8))
         if constexpr(is_same_v<ADataType, half_t> && is_same_v<BDataType, f8_t> &&

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instance.cpp

@@ -17,10 +17,11 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_default_
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
-        instances, device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_instances<GemmDefault>{});
+        instances,
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_instances<GemmDefault>{});
 }
 
 } // 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_default_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_default_
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                            PassThrough>>>&instances)
+                                                      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

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_kpadding
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                             PassThrough>>>&instances)
+                                                      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_mnkpadding_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnkpaddi
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                             PassThrough>>>&instances)
+                                                      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_mnpadding_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnpaddin
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                             PassThrough>>>&instances)
+                                                      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_mem_v1_default_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_defaul
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Intrawave, GemmDefault>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Intrawave,
+                                                                                GemmDefault>{});
 }
 
 } // 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_mem_v1_kpadding_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_kpaddi
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Intrawave, GemmKPadding>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Intrawave,
+                                                                                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_mem_v1_mnkpadding_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v1_mnkpad
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Intrawave,GemmMNKPadding>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Intrawave,
+                                                                                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_mem_v2_default_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_defaul
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Interwave, GemmDefault>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Interwave,
+                                                                                GemmDefault>{});
 }
 
 } // 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_mem_v2_kpadding_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_kpaddi
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Interwave, GemmKPadding>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_instances<Interwave,
+                                                                                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_mem_v2_mnkpadding_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_mem_v2_mnkpad
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                            PassThrough>>>&instances)
+                                                      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_nk_mn_comp_default_instance.cpp

@@ -17,10 +17,11 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_default_
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                            PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
-        instances, device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_instances<GemmDefault>{});
+        instances,
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_instances<GemmDefault>{});
 }
 
 } // 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_nk_mn_comp_kpadding_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_kpadding
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                            PassThrough>>>&instances)
+                                                      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_nk_mn_comp_mkpadding_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_mkpaddin
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      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_nk_mn_comp_mpadding_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_comp_mpadding
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                            PassThrough>>>&instances)
+                                                      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_nk_mn_mem_v1_default_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_defaul
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                            PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_instances<Intrawave, GemmDefault>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_instances<Intrawave,
+                                                                                GemmDefault>{});
 }
 
 } // 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_nk_mn_mem_v1_kpadding_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_kpaddi
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_instances<Intrawave, GemmKPadding>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_instances<Intrawave,
+                                                                                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_nk_mn_mem_v1_mkpadding_instance.cpp

@@ -17,7 +17,7 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v1_mkpadd
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      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_nk_mn_mem_v2_default_instance.cpp

@@ -17,11 +17,12 @@ void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_v2_defaul
                                                       BF16,
                                                       PassThrough,
                                                       PassThrough,
-                                                    PassThrough>>>&instances)
+                                                      PassThrough>>>& instances)
 {
     add_device_operation_instances(
         instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_instances<Interwave, GemmDefault>{});
+        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_nk_mn_mem_instances<Interwave,
+                                                                                GemmDefault>{});
 }
 
 } // namespace instance