remove redundant RCR gemm_universal instance

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

@@ -77,16 +77,6 @@ void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(
         DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
@@ -97,11 +87,6 @@ void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_kpadding_instance
         DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
@@ -111,11 +96,6 @@ void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_kpadding_instance
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
 #endif
 #if(defined(CK_ENABLE_FP16) && defined(CK_ENABLE_FP8))
 void add_device_gemm_xdl_universal_f16_f8_f16_mk_kn_mn_comp_default_instances(
@@ -177,16 +157,6 @@ void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_kpadding_instances(
         DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
@@ -196,12 +166,6 @@ void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_kpadding_instances
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
@@ -212,10 +176,6 @@ void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_kpadding_instances
         DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
 void add_device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
@@ -275,16 +235,6 @@ void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(
         DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
-void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
@@ -295,11 +245,6 @@ void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_kpadding_instances
         DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
@@ -309,11 +254,6 @@ void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_kpadding_instances
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-
-void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
 #endif
 #ifdef CK_ENABLE_BF16
 void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instances(
@@ -376,16 +316,6 @@ void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instanc
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_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>>>&
@@ -396,11 +326,6 @@ void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_kpadding_insta
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_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>>>&
@@ -410,11 +335,6 @@ void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_kpadding_insta
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
 #endif
 #if(defined(CK_ENABLE_BF16) && defined(CK_ENABLE_FP8))
 void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_default_instances(
@@ -427,16 +347,6 @@ void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instances(
         DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
-void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
@@ -447,11 +357,6 @@ void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_kpadding_instances
         DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
-void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
-
 void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
@@ -461,11 +366,6 @@ void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_kpadding_instances
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
-
-void add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances);
 #endif
 
 template <typename ADataType,
@@ -532,24 +432,16 @@ struct DeviceOperationInstanceFactory<
             {
                 add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(op_ptrs);
-                add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
-                    op_ptrs);
-                add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_default_instances(
                     op_ptrs);
                 add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_default_instances(
                     op_ptrs);
                 add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-                    op_ptrs);
             }
         }
 #endif
@@ -562,21 +454,14 @@ struct DeviceOperationInstanceFactory<
             {
                 add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_kpadding_instances(op_ptrs);
-                add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instances(op_ptrs);
-                add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Row> &&
                               is_same_v<CLayout, Row>)
@@ -608,21 +493,14 @@ struct DeviceOperationInstanceFactory<
             {
                 add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(op_ptrs);
-                add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(op_ptrs);
-                add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Row> &&
                               is_same_v<CLayout, Row>)
@@ -684,24 +562,16 @@ struct DeviceOperationInstanceFactory<
                     op_ptrs);
                 add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instances(
-                    op_ptrs);
-                add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_default_instances(
                     op_ptrs);
                 add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_default_instances(
                     op_ptrs);
                 add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_mnkpadding_instances(
-                    op_ptrs);
             }
         }
 #endif
@@ -714,21 +584,14 @@ struct DeviceOperationInstanceFactory<
             {
                 add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instances(op_ptrs);
-                add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instances(op_ptrs);
-                add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_mnkpadding_instances(
-                    op_ptrs);
 
                 add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_default_instances(op_ptrs);
                 add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_kpadding_instances(
                     op_ptrs);
-                add_device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_mnkpadding_instances(
-                    op_ptrs);
             }
         }
 #endif

library/src/tensor_operation_instance/gpu/gemm_multiply_multiply/device_gemm_multiply_multiply_xdl_f8_f8_bf16/device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemmMultipleDSplitK<Row,
-                                                          Col,
-                                                          Tuple<Row, Col>,
-                                                          Row,
-                                                          F8,
-                                                          F8,
-                                                          Tuple<F32, F32>,
-                                                          BF16,
-                                                          PassThrough,
-                                                          PassThrough,
-                                                          MultiplyMultiply>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_multiply_multiply/device_gemm_multiply_multiply_xdl_f8_f8_bf16/device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemmMultipleDSplitK<Row,
-                                                          Col,
-                                                          Tuple<Row, Col>,
-                                                          Row,
-                                                          F8,
-                                                          F8,
-                                                          Tuple<F32, F32>,
-                                                          BF16,
-                                                          PassThrough,
-                                                          PassThrough,
-                                                          MultiplyMultiply>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_comp_instances<GemmMNPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_multiply_multiply/device_gemm_multiply_multiply_xdl_f8_f8_bf16/device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemmMultipleDSplitK<Row,
-                                                          Col,
-                                                          Tuple<Row, Col>,
-                                                          Row,
-                                                          F8,
-                                                          F8,
-                                                          Tuple<F32, F32>,
-                                                          BF16,
-                                                          PassThrough,
-                                                          PassThrough,
-                                                          MultiplyMultiply>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_mem_instances<Intrawave,
-                                                                            GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_multiply_multiply/device_gemm_multiply_multiply_xdl_f8_f8_bf16/device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemmMultipleDSplitK<Row,
-                                                          Col,
-                                                          Tuple<Row, Col>,
-                                                          Row,
-                                                          F8,
-                                                          F8,
-                                                          Tuple<F32, F32>,
-                                                          BF16,
-                                                          PassThrough,
-                                                          PassThrough,
-                                                          MultiplyMultiply>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_multiply_multiply_xdl_f8_f8_bf16_mk_nk_mn_mem_instances<Interwave,
-                                                                            GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt

@@ -14,14 +14,10 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES
         device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp
         device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp
         device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
-        device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
-        device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
         device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_default_instance.cpp
         device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_kpadding_instance.cpp
-        device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp
         device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_default_instance.cpp
         device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_kpadding_instance.cpp
-        device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp
         
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instance.cpp
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_kn_mn_comp_kpadding_instance.cpp
@@ -35,14 +31,10 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instance.cpp
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_kpadding_instance.cpp
-        device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instance.cpp
-        device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_default_instance.cpp
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_kpadding_instance.cpp
-        device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_default_instance.cpp
         device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_kpadding_instance.cpp
-        device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp
         )
         
 if(GPU_TARGETS MATCHES "gfx94")
@@ -59,14 +51,10 @@ if(GPU_TARGETS MATCHES "gfx94")
           device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_default_instance.cpp
           device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_kpadding_instance.cpp
-          device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instance.cpp
-          device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_default_instance.cpp
           device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_kpadding_instance.cpp
-          device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_default_instance.cpp
           device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_kpadding_instance.cpp
-          device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp
 
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn_comp_default_instance.cpp
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
@@ -80,25 +68,17 @@ if(GPU_TARGETS MATCHES "gfx94")
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_default_instance.cpp
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_default_instance.cpp
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_kpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_default_instance.cpp
           device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_kpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp
                 
           device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_default_instance.cpp
           device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_kpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_mnpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_default_instance.cpp
           device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_kpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp
           device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_default_instance.cpp
           device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_kpadding_instance.cpp
-          device_gemm_xdl_universal_f8_f8_bf16/device_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp
         )
 endif()
 

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_instances<GemmMNPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_instances<Intrawave,
-                                                                        GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_mem_instances<Interwave,
-                                                                        GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances, device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances, device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmMNPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_instances<Intrawave, GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f16_f16/device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_f16_f16_f16_mk_nk_mn_mem_instances<Interwave, GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances, device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-using F16 = ck::half_t;
-using F32 = float;
-
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances, device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_comp_instances<GemmMNPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_instances<Intrawave, GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f16_f8_f16/device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_f16_f8_f16_mk_nk_mn_mem_instances<Interwave, GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances, device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_xdl_universal_f8_f16_f16/device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-using F16 = ck::half_t;
-using F32 = float;
-
-void add_device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(
-        instances, device_gemm_xdl_universal_f8_f16_f16_mk_nk_mn_comp_instances<GemmMNPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck