Merge branch 'develop' into amd-develop

705d5a08 · Jun Liu · d4ad52d6 · 8f84a012 · d4ad52d6 · d4ad52d6
Commit 705d5a08 authored Sep 08, 2023 by Jun Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_dpp8_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_dpp8_f16_f16_f16_km_nk_mn_instance.cpp
-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-#include <cstdlib>
-#include "ck/ck.hpp"
-#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_gemm_dl_dpp8.hpp"
-#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-using F16 = ck::half_t;
-using F32 = float;
-using Row = ck::tensor_layout::gemm::RowMajor;
-using Col = ck::tensor_layout::gemm::ColumnMajor;
-template <ck::index_t... Is>
-using S = ck::Sequence<Is...>;
-using PassThrough = ck::tensor_operation::element_wise::PassThrough;
-static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
-// Compilation parameters for a[k, m] * b[k, n] = c[m, n]
-using device_gemm_dl_dpp8_f16_f16_f16_km_nk_mn_instances = std::tuple<
-    // clang-format off
-        // ##########| AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer| K0Per| K1|      M1Per|      N1Per|   KPer|  M11N11Thread|  M11N11Thread|     ABlockTransfer|       ABlockTransfer| ABlockTransfer| ABlockTransfer|      ABlockTransfer|     ABlockTransfer|       ABlockTransfer|     BBlockTransfer|       BBlockTransfer| BBlockTransfer| BBlockTransfer|      BBlockTransfer|     BBlockTransfer|       BBlockTransfer|      CThreadTransfer|  CThreadTransfer|    CThreadTransfer|
-        // ##########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|   | ThreadM111| ThreadN111| Thread| ClusterM110Xs| ClusterN110Xs| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|     SrcVectorTensor|    SrcVectorTensor|      DstVectorTensor| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|     SrcVectorTensor|    SrcVectorTensor|      DstVectorTensor|         SrcDstAccess|  SrcDstVectorDim| DstScalarPerVector|
-        // ##########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |   |           |           |       |              |              |        K0_M0_M1_K1|          K0_M0_M1_K1|   ArrangeOrder|          Order| Lengths_K0_M0_M1_K1| ContiguousDimOrder|  Lengths_K0_M0_M1_K1|        K0_M0_M1_K1|          K0_M0_M1_K1|   ArrangeOrder|          Order| Lengths_K0_M0_M1_K1| ContiguousDimOrder|  Lengths_K0_M0_M1_K1|                Order|                 |                   |
-        // ##########|      |      |      |        |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |              |              |                   |                     |               |               |                    |                   |                     |                   |                     |               |               |                    |                   |                     |                     |                 |                   |
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,     8,     8,     8,     4,  2,          1,          8,      1,       S<1, 8>,       S<1, 1>,      S<1, 1, 4, 2>,       S<4, 1,  2, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 4, 2>,       S<4, 1, 1, 2>,      S<1, 1,   8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<4, 1>,      S<1, 1, 4, 2>,      S<16, 1,  2, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 2, 2>,      S<16, 1, 2, 2>,      S<1, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<4, 1>,      S<1, 1, 4, 2>,      S<16, 1,  2, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 2, 2>,       S<4, 1, 8, 2>,      S<4, 1,   8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<8, 1>,      S<1, 1, 2, 2>,      S<16, 1,  4, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 2, 1>,      S<0, 3, 1, 2>,       S<1, 1, 2, 2>,       S<4, 1, 4, 2>,      S<4, 1,  16, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,    64,    64,     8,  2,          4,          8,      1,       S<2, 8>,       S<4, 1>,      S<2, 1, 4, 2>,      S<4, 1,  16, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 4, 2>,       S<4, 1, 2, 2>,      S<2, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,     8,    64,    16,  2,          8,          1,      1,       S<1, 1>,       S<8, 8>,      S<1, 1, 2, 2>,      S<16, 1,  4, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 2, 1>,      S<0, 3, 1, 2>,       S<1, 1, 2, 2>,       S<4, 1, 4, 2>,      S<4, 1,  16, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  1>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    64,    64,    16,  2,          4,          8,      1,       S<2, 8>,       S<8, 1>,      S<2, 1, 4, 2>,      S<8, 1,  16, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 4, 2>,       S<4, 1, 2, 2>,      S<4, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,   128,    64,    16,  2,          1,          8,      8,       S<4, 8>,       S<4, 1>,      S<4, 1, 4, 2>,      S<4, 1,  32, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 4, 2>,       S<4, 1, 2, 2>,      S<4, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,     8,  2,          1,          8,      8,       S<8, 8>,       S<4, 1>,      S<1, 1, 4, 2>,      S<8, 1,  32, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 4, 2>,       S<4, 1, 1, 2>,      S<2, 1, 128, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    16,  2,          4,          8,      8,       S<2, 8>,      S<16, 1>,      S<2, 1, 4, 2>,      S<8, 1,  32, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,       S<1, 1, 4, 2>,       S<4, 1, 2, 2>,      S<4, 1,  64, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>
-    // clang-format on
-    >;
-void add_device_gemm_dl_dpp8_f16_f16_f16_km_nk_mn_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(instances, device_gemm_dl_dpp8_f16_f16_f16_km_nk_mn_instances{});
-}
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_dpp8_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_dpp8_f16_f16_f16_mk_kn_mn_instance.cpp
-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-#include <cstdlib>
-#include "ck/ck.hpp"
-#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_gemm_dl_dpp8.hpp"
-#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-using F16 = ck::half_t;
-using F32 = float;
-using Row = ck::tensor_layout::gemm::RowMajor;
-template <ck::index_t... Is>
-using S = ck::Sequence<Is...>;
-using PassThrough = ck::tensor_operation::element_wise::PassThrough;
-static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
-// Compilation parameters for a[k, m] * b[k, n] = c[m, n]
-using device_gemm_dl_dpp8_f16_f16_f16_mk_kn_mn_instances = std::tuple<
-    // clang-format off
-        // ##########| AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer| K0Per| K1|      M1Per|      N1Per|   KPer|  M11N11Thread|  M11N11Thread|     ABlockTransfer|       ABlockTransfer| ABlockTransfer| ABlockTransfer|      ABlockTransfer|     ABlockTransfer|       ABlockTransfer|     BBlockTransfer|       BBlockTransfer| BBlockTransfer| BBlockTransfer|      BBlockTransfer|     BBlockTransfer|       BBlockTransfer|      CThreadTransfer|  CThreadTransfer|    CThreadTransfer|
-        // ##########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|   | ThreadM111| ThreadN111| Thread| ClusterM110Xs| ClusterN110Xs| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|     SrcVectorTensor|    SrcVectorTensor|      DstVectorTensor| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|     SrcVectorTensor|    SrcVectorTensor|      DstVectorTensor|         SrcDstAccess|  SrcDstVectorDim| DstScalarPerVector|
-        // ##########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |   |           |           |       |              |              |        K0_M0_M1_K1|          K0_M0_M1_K1|   ArrangeOrder|          Order| Lengths_K0_M0_M1_K1| ContiguousDimOrder|  Lengths_K0_M0_M1_K1|        K0_M0_M1_K1|          K0_M0_M1_K1|   ArrangeOrder|          Order| Lengths_K0_M0_M1_K1| ContiguousDimOrder|  Lengths_K0_M0_M1_K1|                Order|                 |                   |
-        // ##########|      |      |      |        |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |              |              |                   |                     |               |               |                    |                   |                     |                   |                     |               |               |                    |                   |                     |                     |                 |                   |
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,     8,     8,     8,     4,  2,          1,          8,      1,       S<1, 8>,       S<1, 1>,      S<4, 1, 1, 2>,       S<1, 1,  8, 1>,  S<1, 2, 0 ,3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<1, 1, 4, 2>,        S<4, 1, 2, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<4, 1>,      S<4, 1, 1, 2>,        S<4, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,      S<16, 1, 2, 2>,       S<1, 1, 32, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 2, 1>,      S<0, 3, 1, 2>,        S<1, 1, 2, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<4, 1>,      S<4, 1, 1, 2>,        S<4, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 8, 2>,        S<4, 1, 8, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<8, 1>,      S<2, 1, 1, 2>,        S<8, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<2, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 4, 2>,       S<4, 1, 16, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,    64,    64,     8,  2,          4,          8,      1,       S<2, 8>,       S<4, 1>,      S<4, 1, 2, 2>,       S<2, 1, 32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<2, 1, 4, 2>,       S<4, 1, 16, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,     8,    64,    16,  2,          8,          1,      1,       S<1, 1>,       S<8, 8>,      S<2, 1, 1, 2>,        S<8, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<2, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 4, 2>,       S<4, 1, 16, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  1>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    64,    64,    16,  2,          4,          8,      1,       S<2, 8>,       S<8, 1>,      S<4, 1, 2, 2>,       S<4, 1, 32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<2, 1, 4, 2>,       S<8, 1, 16, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,   128,    64,    16,  2,          1,          8,      8,       S<4, 8>,       S<4, 1>,      S<4, 1, 4, 2>,       S<4, 1, 32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<2, 1, 4, 2>,       S<8, 1, 16, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,     8,  2,          1,          8,      8,       S<8, 8>,       S<4, 1>,      S<4, 1, 1, 2>,      S<2, 1, 128, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<1, 1, 4, 2>,       S<8, 1, 32, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    16,  2,          4,          8,      8,       S<2, 8>,      S<16, 1>,      S<4, 1, 2, 2>,       S<4, 1, 64, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<2, 1, 4, 2>,       S<8, 1, 32, 1>,  S<0, 3, 1, 2>,  S<0, 3, 1, 2>,       S<1, 1, 4, 1>,      S<0, 3, 1, 2>,        S<1, 1, 4, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>
-    // clang-format on
-    >;
-void add_device_gemm_dl_dpp8_f16_f16_f16_mk_kn_mn_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(instances, device_gemm_dl_dpp8_f16_f16_f16_mk_kn_mn_instances{});
-}
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_dpp8_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_dpp8_f16_f16_f16_mk_nk_mn_instance.cpp
-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-#include <cstdlib>
-#include "ck/ck.hpp"
-#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
-#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_gemm_dl_dpp8.hpp"
-#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-using F16 = ck::half_t;
-using F32 = float;
-using Row = ck::tensor_layout::gemm::RowMajor;
-using Col = ck::tensor_layout::gemm::ColumnMajor;
-template <ck::index_t... Is>
-using S = ck::Sequence<Is...>;
-using PassThrough = ck::tensor_operation::element_wise::PassThrough;
-static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
-// Compilation parameters for a[k, m] * b[k, n] = c[m, n]
-using device_gemm_dl_dpp8_f16_f16_f16_mk_nk_mn_instances = std::tuple<
-    // clang-format off
-        // ##########| AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer| K0Per| K1|      M1Per|      N1Per|   KPer|  M11N11Thread|  M11N11Thread|     ABlockTransfer|       ABlockTransfer| ABlockTransfer| ABlockTransfer|      ABlockTransfer|     ABlockTransfer|       ABlockTransfer|     BBlockTransfer|       BBlockTransfer| BBlockTransfer| BBlockTransfer|      BBlockTransfer|     BBlockTransfer|       BBlockTransfer|      CThreadTransfer|  CThreadTransfer|    CThreadTransfer|
-        // ##########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|   | ThreadM111| ThreadN111| Thread| ClusterM110Xs| ClusterN110Xs| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|     SrcVectorTensor|    SrcVectorTensor|      DstVectorTensor| ThreadSliceLengths| ThreadClusterLengths|  ThreadCluster|      SrcAccess|     SrcVectorTensor|    SrcVectorTensor|      DstVectorTensor|         SrcDstAccess|  SrcDstVectorDim| DstScalarPerVector|
-        // ##########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |   |           |           |       |              |              |        K0_M0_M1_K1|          K0_M0_M1_K1|   ArrangeOrder|          Order| Lengths_K0_M0_M1_K1| ContiguousDimOrder|  Lengths_K0_M0_M1_K1|        K0_M0_M1_K1|          K0_M0_M1_K1|   ArrangeOrder|          Order| Lengths_K0_M0_M1_K1| ContiguousDimOrder|  Lengths_K0_M0_M1_K1|                Order|                 |                   |
-        // ##########|      |      |      |        |        |        |        |            |            |            |               |      |      |      |      |   |           |           |       |              |              |                   |                     |               |               |                    |                   |                     |                   |                     |               |               |                    |                   |                     |                     |                 |                   |
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,     8,     8,     8,     4,  2,          1,          8,      1,       S<1, 8>,       S<1, 1>,      S<4, 1, 1, 2>,       S<1, 1,  8, 1>,  S<1, 2, 0 ,3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 1, 2>,      S<1, 1,   8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<4, 1>,      S<4, 1, 1, 2>,        S<4, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,      S<16, 1, 2, 2>,      S<1, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<4, 1>,      S<4, 1, 1, 2>,        S<4, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 8, 2>,      S<4, 1,   8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,     8,    64,    16,  2,          1,          8,      1,       S<1, 8>,       S<8, 1>,      S<2, 1, 1, 2>,        S<8, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<2, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 4, 2>,      S<4, 1,  16, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,    64,    64,     8,  2,          4,          8,      1,       S<2, 8>,       S<4, 1>,      S<4, 1, 2, 2>,       S<2, 1, 32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 2, 2>,      S<2, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,     8,    64,    16,  2,          8,          1,      1,       S<1, 1>,       S<8, 8>,      S<2, 1, 1, 2>,        S<8, 1, 8, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<2, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 4, 2>,      S<4, 1,  16, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  1>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    64,    64,    16,  2,          4,          8,      1,       S<2, 8>,       S<8, 1>,      S<4, 1, 2, 2>,       S<4, 1, 32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 2, 2>,      S<4, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,   128,    64,    16,  2,          1,          8,      8,       S<4, 8>,       S<4, 1>,      S<4, 1, 4, 2>,       S<4, 1, 32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 2, 2>,      S<4, 1,  32, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,     8,  2,          1,          8,      8,       S<8, 8>,       S<4, 1>,      S<4, 1, 1, 2>,      S<2, 1, 128, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 1, 2>,      S<2, 1, 128, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>,
-        DeviceGemmDlDpp8< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    16,  2,          4,          8,      8,       S<2, 8>,      S<16, 1>,      S<4, 1, 2, 2>,       S<4, 1, 64, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,       S<1, 1, 1, 2>,       S<4, 1, 2, 2>,      S<4, 1,  64, 1>,  S<1, 2, 0, 3>,  S<1, 2, 0, 3>,       S<4, 1, 1, 2>,      S<1, 2, 0, 3>,        S<1, 1, 1, 2>,  S<0, 1, 2, 3, 4, 5>,                5,                  4>
-    // clang-format on
-    >;
-void add_device_gemm_dl_dpp8_f16_f16_f16_mk_nk_mn_instances(
-    std::vector<std::unique_ptr<
-        DeviceGemm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
-        instances)
-{
-    add_device_operation_instances(instances, device_gemm_dl_dpp8_f16_f16_f16_mk_nk_mn_instances{});
-}
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_kn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F16 = ck::half_t;
+using F32 = float;
+using Row = ck::tensor_layout::gemm::RowMajor;
+using Col = ck::tensor_layout::gemm::ColumnMajor;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
+// Compilation parameters for a[k, m] * b[k, n] = c[m, n]
+// clang-format off
+using device_gemm_dpp_f16_f16_f16_km_kn_mn_instances = std::tuple<
+    // ########| AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MDpp|    NDpp|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CThreadTransfer| CThreadTransfer|
+    // ########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    |    |  Dpp|  Dpp| PerWave| PerWave|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| SrcDstVectorDim|       DstScalar|
+    // ########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |    |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |                |       PerVector|
+    // ########|      |      |      |        |        |        |        |            |            |            |               |      |      |      |      |    |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |                |                |
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   4,   4,   16,   16,       2,       4,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,      true,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   4,   4,   32,    8,       2,       4,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,      true,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    64,    64,    64,   4,   4,   32,    8,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    32,    32,    32,   4,   4,   32,    8,       1,       1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              4,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,    64,    64,    64,   4,   4,   32,    8,       2,       4,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,      true,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    32,    32,    32,   4,   4,   32,    8,       1,       4,      S<4, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,      true,      S<4, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    16,    16,    16,   4,   4,   16,   16,       1,       1,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              4,      true,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              4,      true,               5,               1>
+    >;
+// clang-format on
+void add_device_gemm_dpp_f16_f16_f16_km_kn_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(instances, device_gemm_dpp_f16_f16_f16_km_kn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_km_nk_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F16 = ck::half_t;
+using F32 = float;
+using Row = ck::tensor_layout::gemm::RowMajor;
+using Col = ck::tensor_layout::gemm::ColumnMajor;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
+// Compilation parameters for a[k, m] * b[n, k] = c[m, n]
+// clang-format off
+using device_gemm_dpp_f16_f16_f16_km_nk_mn_instances = std::tuple<
+    // ########| AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MDpp|    NDpp|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CThreadTransfer| CThreadTransfer|
+    // ########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    |    |  Dpp|  Dpp| PerWave| PerWave|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| SrcDstVectorDim|       DstScalar|
+    // ########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |    |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |                |       PerVector|
+    // ########|      |      |      |        |        |        |        |            |            |            |               |      |      |      |      |    |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |                |                |
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   4,   8,   16,   16,       2,       4,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   4,   8,   32,    8,       2,       4,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    64,    64,    64,   4,   8,   32,    8,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    32,    32,    32,   4,   8,   32,    8,       1,       1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              4,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,    64,    64,    64,   4,   8,   32,    8,       2,       4,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    32,    32,    32,   4,   8,   32,    8,       1,       4,      S<4, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,      true,      S<4, 8, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Col,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    16,    16,    16,   4,   8,   16,   16,       1,       1,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              4,      true,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>
+    >;
+// clang-format on
+void add_device_gemm_dpp_f16_f16_f16_km_nk_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(instances, device_gemm_dpp_f16_f16_f16_km_nk_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_kn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F16 = ck::half_t;
+using F32 = float;
+using Row = ck::tensor_layout::gemm::RowMajor;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
+// Compilation parameters for a[m, k] * b[k, n] = c[m, n]
+// clang-format off
+using device_gemm_dpp_f16_f16_f16_mk_kn_mn_instances = std::tuple<
+    // ########| AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MDpp|    NDpp|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CThreadTransfer| CThreadTransfer|
+    // ########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    |    |  Dpp|  Dpp| PerWave| PerWave|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| SrcDstVectorDim|       DstScalar|
+    // ########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |    |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |                |       PerVector|
+    // ########|      |      |      |        |        |        |        |            |            |            |               |      |      |      |      |    |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |                |                |
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   8,   4,   16,   16,       2,       4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   8,   4,   32,    8,       2,       4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    64,    64,    64,   8,   4,   32,    8,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    32,    32,    32,   8,   4,   32,    8,       1,       1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,    64,    64,    64,   8,   4,   32,    8,       2,       4,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    32,    32,    32,   8,   4,   32,    8,       1,       4,      S<4, 8, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,      S<4, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              4,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Row,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    16,    16,    16,   8,   4,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              4,      true,               5,               1>
+    >;
+// clang-format on
+void add_device_gemm_dpp_f16_f16_f16_mk_kn_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(instances, device_gemm_dpp_f16_f16_f16_mk_kn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dpp_f16_f16_f16_mk_nk_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_dpp.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F16 = ck::half_t;
+using F32 = float;
+using Row = ck::tensor_layout::gemm::RowMajor;
+using Col = ck::tensor_layout::gemm::ColumnMajor;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
+// Compilation parameters for a[m, k] * b[n, k] = c[m, n]
+// clang-format off
+using device_gemm_dpp_f16_f16_f16_mk_nk_mn_instances = std::tuple<
+    // ########| AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|           GEMM| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MDpp|    NDpp|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CThreadTransfer| CThreadTransfer|
+    // ########|  Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    |    |  Dpp|  Dpp| PerWave| PerWave|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| SrcDstVectorDim|       DstScalar|
+    // ########|      |      |      |        |        |        |        |   Operation|   Operation|   Operation|               |      |      |      |      |    |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |                |       PerVector|
+    // ########|      |      |      |        |        |        |        |            |            |            |               |      |      |      |      |    |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |                |                |
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   8,   8,   16,   16,       2,       4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   256,   128,   128,    64,   8,   8,   32,    8,       2,       4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    64,    64,    64,   8,   8,   32,    8,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,   128,    32,    32,    32,   8,   8,   32,    8,       1,       1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    64,    64,    64,    64,   8,   8,   32,    8,       2,       4,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    32,    32,    32,   8,   8,   32,    8,       1,       4,      S<4, 8, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,      S<4, 8, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>,
+    DeviceGemmDpp< F16,   F16,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    GemmDefault,    32,    16,    16,    16,   8,   8,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,               5,               1>
+    >;
+// clang-format on
+void add_device_gemm_dpp_f16_f16_f16_mk_nk_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(instances, device_gemm_dpp_f16_f16_f16_mk_nk_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/CMakeLists.txt
@@ -4,5 +4,9 @@ add_instance_library(device_gemm_bilinear_instance
   device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_km_nk_mn_mn_instance.cpp
   device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_kn_mn_mn_instance.cpp
   device_gemm_bilinear_xdl_c_shuffle_f16_f16_f16_f16_mk_nk_mn_mn_instance.cpp
+   device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
+   device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
+   device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
+   device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
 )
 endif()
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using I8       = std::int8_t;
+using I32      = std::int32_t;
+using I8_Tuple = ck::Tuple<std::int8_t>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using Bilinear    = ck::tensor_operation::element_wise::Bilinear;
+static constexpr auto GemmDefault    = ck::tensor_operation::device::GemmSpecialization::Default;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+// e[m, n] = bilinear(a[m, k] * b[k, n], d[m, n])
+using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instances = std::tuple<
+    // clang-format off
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        // M/N/K padding
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,             16,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   8,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           2,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   8,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           2,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   8,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              8,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           2,               S<1, 32, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   8,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              8,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   4,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           2,               S<1, 32, 1, 8>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   4,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           2,               S<1, 32, 1, 4>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   4,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           2,               S<1, 32, 1, 2>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   4,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              2,              4,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           1,               S<1, 16, 1, 2>,               4>
+    // clang-format on
+    >;
+void add_device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Col,
+                                                    Row,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    I8,
+                                                    I8,
+                                                    I8_Tuple,
+                                                    I8,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    Bilinear>>>& instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using I8       = std::int8_t;
+using I32      = std::int32_t;
+using I8_Tuple = ck::Tuple<std::int8_t>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using Bilinear    = ck::tensor_operation::element_wise::Bilinear;
+static constexpr auto GemmDefault    = ck::tensor_operation::device::GemmSpecialization::Default;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+// e[m, n] = bilinear(a[m, k] * b[k, n], d[m, n])
+using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instances = std::tuple<
+    // clang-format off
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        // M/N/K padding
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   8,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,           1,           2,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   8,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,           1,           2,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   8,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,           1,           2,               S<1, 32, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   8,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   4,   16,   16,       4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,           1,           2,               S<1, 32, 1, 8>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   4,   16,   16,       2,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,           1,           2,               S<1, 32, 1, 4>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   4,   16,   16,       1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,           1,           2,               S<1, 32, 1, 2>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Col,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   4,   16,   16,       1,       1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,           1,           1,               S<1, 16, 1, 2>,               4>
+    // clang-format on
+    >;
+void add_device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Col,
+                                                    Col,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    I8,
+                                                    I8,
+                                                    I8_Tuple,
+                                                    I8,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    Bilinear>>>& instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using I8       = std::int8_t;
+using I32      = std::int32_t;
+using I8_Tuple = ck::Tuple<std::int8_t>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using Bilinear    = ck::tensor_operation::element_wise::Bilinear;
+static constexpr auto GemmDefault    = ck::tensor_operation::device::GemmSpecialization::Default;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+// e[m, n] = bilinear(a[m, k] * b[k, n], d[m, n])
+using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instances = std::tuple<
+    // clang-format off
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        // M/N/K padding
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   8,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           2,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   8,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           2,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   8,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           2,               S<1, 32, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   8,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   4,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           2,               S<1, 32, 1, 8>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   4,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           2,               S<1, 32, 1, 4>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   4,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           2,               S<1, 32, 1, 2>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Row, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   4,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<4,  8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              4,         1,           1,           1,               S<1, 16, 1, 2>,               4>
+    // clang-format on
+    >;
+void add_device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Row,
+                                                    Row,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    I8,
+                                                    I8,
+                                                    I8_Tuple,
+                                                    I8,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    Bilinear>>>& instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using I8       = std::int8_t;
+using I32      = std::int32_t;
+using I8_Tuple = ck::Tuple<std::int8_t>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using Bilinear    = ck::tensor_operation::element_wise::Bilinear;
+static constexpr auto GemmDefault    = ck::tensor_operation::device::GemmSpecialization::Default;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+// e[m, n] = bilinear(a[m, k] * b[n, k], d[m, n])
+using device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instances = std::tuple<
+    // clang-format off
+        // no padding
+        // N % 16 == 0 && K % 16 == 0
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear,    GemmDefault,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        // M/N/K padding
+        // N % 16 == 0 && K % 16 == 0
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     4,  16,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           2,               S<1, 32, 1, 8>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     4,  16,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           2,               S<1, 32, 1, 4>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     4,  16,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           2,               S<1, 32, 1, 2>,              16>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     4,  16,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,             16,             16,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,             16,             16,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        // M/N/K padding
+        // N % 8 == 0 && K % 8 == 0
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   8,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           2,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   8,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           2,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   8,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           2,               S<1, 32, 1, 2>,               8>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   8,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,               S<1, 16, 1, 2>,               8>,
+        // M/N/K padding
+        // N % 8 == 0 && K % 8 == 0
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   4,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              4,              4,         1,           1,           2,               S<1, 32, 1, 8>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   4,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              4,              4,         1,           1,           2,               S<1, 32, 1, 4>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   4,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              4,              4,         1,           1,           2,               S<1, 32, 1, 2>,               4>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   4,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              4,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              4,              4,         1,           1,           1,               S<1, 16, 1, 2>,               4>,
+        // M/N/K padding
+        // N % 1 == 0 && K % 8 == 0
+        //################################|      A|      B|        Ds|      E| AData| BData|    DsData| EData| AccData| CShuffle|           A|           B|         CDE|           GEMM| Block|  MPer|  NPer| K0Per|  K1| MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //################################| Layout| Layout|    Layout| Layout|  Type|  Type|      Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|  Size| Block| Block| Block|    | WMMA| WMMA|        |        |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //################################|       |       |          |       |      |      |          |      |        |         |   Operation|   Operation|   Operation|               |      |      |      |      |    |     |     |        |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //################################|       |       |          |       |      |      |          |      |        |         |            |            |            |               |      |      |      |      |    |     |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   256,   128,   128,     8,   8,   16,   16,       4,       2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           2,               S<1, 32, 1, 8>,               1>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,   128,    64,    64,     8,   8,   16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           2,               S<1, 32, 1, 4>,               1>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    64,    32,    32,     8,   8,   16,   16,       1,       2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           2,               S<1, 32, 1, 2>,               1>,
+        DeviceGemmMultipleD_Wmma_CShuffle<     Row,    Col, Row_Tuple,    Row,    I8,    I8,  I8_Tuple,    I8,     I32,      I32, PassThrough, PassThrough,    Bilinear, GemmMNKPadding,    32,    16,    16,     8,   8,   16,   16,       1,       1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,               S<1, 16, 1, 2>,               1>
+    // clang-format on
+    >;
+void add_device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Row,
+                                                    Col,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    I8,
+                                                    I8,
+                                                    I8_Tuple,
+                                                    I8,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    Bilinear>>>& instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/CMakeLists.txt
+add_instance_library(device_gemm_multiply_add_instance
+   device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
+   device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
+   device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
+   device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
+)
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F16       = ck::half_t;
+using F32       = float;
+using F16_Tuple = ck::Tuple<F16, F16>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row, Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using MultiplyAdd = ck::tensor_operation::element_wise::MultiplyAdd;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+using device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instances =
+    std::tuple<
+        // clang-format off
+        // M/N/K padding
+        //##############################|      A|      B|        Ds|      E| AData| BData| AccData| CShuffle|    DsData| EData|           A|           B|            CDE|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //##############################| Layout| Layout|    Layout| Layout|  Type|  Type|    Type| DataType|      Type|  Type| Elementwise| Elementwise|    Elementwise| Specialization| Prefetch|  Size| Block| Block| Block|    |    |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //##############################|       |       |          |       |      |      |        |         |          |      |   Operation|   Operation|      Operation|               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //##############################|       |       |          |       |      |      |        |         |          |      |            |            |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   256,   128,    32,   8,   2,   32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   256,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   256,    32,   8,   2,   32,   32,    2,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   256,    32,   8,   8,   32,   32,    2,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,   128,    32,   8,   2,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,         1,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   128,    32,   8,   2,   32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    64,    32,   8,   2,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    64,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   2,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,         1,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,    64,    32,   8,   2,   32,   32,    2,    1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<16,16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,    64,    32,   8,   8,   32,   32,    2,    1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,    64,   128,    32,   8,   2,   32,   32,    1,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,    64,   128,    32,   8,   8,   32,   32,    1,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>
+        // clang-format on
+        >;
+void add_device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Row,
+                                                    Row,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    F16,
+                                                    F16,
+                                                    F16_Tuple,
+                                                    F16,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    MultiplyAdd>>>& instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F16       = ck::half_t;
+using F32       = float;
+using F16_Tuple = ck::Tuple<F16, F16>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row, Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using MultiplyAdd = ck::tensor_operation::element_wise::MultiplyAdd;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+using device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instances =
+    std::tuple<
+        // clang-format off
+        // M/N/K padding
+        // N % 8 == 0 && K % 1 == 0
+        //##############################|      A|      B|        Ds|      E| AData| BData| AccData| CShuffle|    DsData| EData|           A|           B|            CDE|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //##############################| Layout| Layout|    Layout| Layout|  Type|  Type|    Type| DataType|      Type|  Type| Elementwise| Elementwise|    Elementwise| Specialization| Prefetch|  Size| Block| Block| Block|    |    |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //##############################|       |       |          |       |      |      |        |         |          |      |   Operation|   Operation|      Operation|               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //##############################|       |       |          |       |      |      |        |         |          |      |            |            |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   256,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   256,    32,   8,   8,   32,   32,    2,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    64,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,    64,    64,    64,    32,   8,   8,   32,   32,    2,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,    64,    32,   8,   8,   32,   32,    2,    1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,    64,   128,    32,   8,   8,   32,   32,    1,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    32,    32,   8,   8,   32,   32,    2,    1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    32,   128,    32,   8,   8,   32,   32,    1,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,    64,    64,    32,    32,   8,   8,   32,   32,    2,    1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,   F16,     F32,      F16, F16_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,    64,    32,    64,    32,   8,   8,   32,   32,    1,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 32>,               1>
+        // clang-format on
+        >;
+void add_device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Row,
+                                                    Col,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    F16,
+                                                    F16,
+                                                    F16_Tuple,
+                                                    F16,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    MultiplyAdd>>>& instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_add_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F8        = ck::f8_t;
+using F16       = ck::half_t;
+using F32       = float;
+using F32_Tuple = ck::Tuple<F32, F32>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row, Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using MultiplyAdd = ck::tensor_operation::element_wise::MultiplyAdd;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+using device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_generic_instances =
+    std::tuple<
+        // clang-format off
+        // M/N/K padding
+        //##############################|      A|      B|        Ds|      E| AData| BData| AccData| CShuffle|    DsData| EData|           A|           B|            CDE|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //##############################| Layout| Layout|    Layout| Layout|  Type|  Type|    Type| DataType|      Type|  Type| Elementwise| Elementwise|    Elementwise| Specialization| Prefetch|  Size| Block| Block| Block|    |    |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //##############################|       |       |          |       |      |      |        |         |          |      |   Operation|   Operation|      Operation|               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //##############################|       |       |          |       |      |      |        |         |          |      |            |            |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,    64,   128,    32,   8,   8,   32,   32,    1,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,         1,           1,           1,               S<1, 32, 1, 8>,               1>
+        // clang-format on
+        >;
+using device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instances =
+    std::tuple<
+        // clang-format off
+        // M/N/K padding
+        //##############################|      A|      B|        Ds|      E| AData| BData| AccData| CShuffle|    DsData| EData|           A|           B|            CDE|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //##############################| Layout| Layout|    Layout| Layout|  Type|  Type|    Type| DataType|      Type|  Type| Elementwise| Elementwise|    Elementwise| Specialization| Prefetch|  Size| Block| Block| Block|    |    |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //##############################|       |       |          |       |      |      |        |         |          |      |   Operation|   Operation|      Operation|               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //##############################|       |       |          |       |      |      |        |         |          |      |            |            |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   256,   128,    32,   8,   2,   32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   256,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   256,    32,   8,   2,   32,   32,    2,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   256,    32,   8,   8,   32,   32,    2,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,   128,    32,   8,   2,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,         1,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   128,    32,   8,   2,   32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    64,    32,   8,   2,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    64,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   2,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,         1,           1,           1,               S<1, 16, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,    64,    32,   8,   2,   32,   32,    2,    1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<16,16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,    64,    32,   8,   8,   32,   32,    2,    1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,    64,   128,    32,   8,   2,   32,   32,    1,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              2,         0,           1,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Row, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,    64,   128,    32,   8,   8,   32,   32,    1,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>
+        // clang-format on
+        >;
+void add_device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Row,
+                                                    Row,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    F16,
+                                                    F8,
+                                                    F32_Tuple,
+                                                    F16,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    MultiplyAdd>>>& instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_generic_instances{});
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_kn_mn_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_add/device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instance.cpp
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+#include <cstdlib>
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+using F8        = ck::f8_t;
+using F16       = ck::half_t;
+using F32       = float;
+using F32_Tuple = ck::Tuple<F32, F32>;
+using Row       = ck::tensor_layout::gemm::RowMajor;
+using Col       = ck::tensor_layout::gemm::ColumnMajor;
+using Row_Tuple = ck::Tuple<Row, Row>;
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using MultiplyAdd = ck::tensor_operation::element_wise::MultiplyAdd;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+using device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_generic_instances =
+    std::tuple<
+        // clang-format off
+        // M/N/K padding
+        // N % 8 == 0 && K % 1 == 0
+        //##############################|      A|      B|        Ds|      E| AData| BData| AccData| CShuffle|    DsData| EData|           A|           B|            CDE|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //##############################| Layout| Layout|    Layout| Layout|  Type|  Type|    Type| DataType|      Type|  Type| Elementwise| Elementwise|    Elementwise| Specialization| Prefetch|  Size| Block| Block| Block|    |    |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //##############################|       |       |          |       |      |      |        |         |          |      |   Operation|   Operation|      Operation|               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //##############################|       |       |          |       |      |      |        |         |          |      |            |            |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,    64,    32,    64,    32,   8,   8,   32,   32,    1,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,              S<1,  2, 1, 32>,               1>
+        // clang-format on
+        >;
+using device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instances =
+    std::tuple<
+        // clang-format off
+        // M/N/K padding
+        // N % 8 == 0 && K % 1 == 0
+        //##############################|      A|      B|        Ds|      E| AData| BData| AccData| CShuffle|    DsData| EData|           A|           B|            CDE|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //##############################| Layout| Layout|    Layout| Layout|  Type|  Type|    Type| DataType|      Type|  Type| Elementwise| Elementwise|    Elementwise| Specialization| Prefetch|  Size| Block| Block| Block|    |    |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|
+        //##############################|       |       |          |       |      |      |        |         |          |      |   Operation|   Operation|      Operation|               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
+        //##############################|       |       |          |       |      |      |        |         |          |      |            |            |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   256,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   256,    32,   8,   8,   32,   32,    2,    4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    64,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    64,   128,    32,   8,   8,   32,   32,    2,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,    64,    64,    64,    32,   8,   8,   32,   32,    2,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,   128,    64,    32,   8,   8,   32,   32,    2,    1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   256,    64,   128,    32,   8,   8,   32,   32,    1,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,   128,    32,    32,   8,   8,   32,   32,    2,    1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  4, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,   128,    32,   128,    32,   8,   8,   32,   32,    1,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 64>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,    64,    64,    32,    32,   8,   8,   32,   32,    2,    1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 32>,               1>,
+        DeviceGemmMultipleD_Xdl_CShuffle<    Row,    Col, Row_Tuple,    Row,   F16,    F8,     F32,      F32, F32_Tuple,   F16, PassThrough, PassThrough,    MultiplyAdd, GemmMNKPadding,        1,    64,    32,    64,    32,   8,   8,   32,   32,    1,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,           1,           1,              S<1,  2, 1, 32>,               1>
+        // clang-format on
+        >;
+void add_device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGemmMultipleD<Row,
+                                                    Col,
+                                                    Row_Tuple,
+                                                    Row,
+                                                    F16,
+                                                    F8,
+                                                    F32_Tuple,
+                                                    F16,
+                                                    PassThrough,
+                                                    PassThrough,
+                                                    MultiplyAdd>>>& instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_generic_instances{});
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_add_xdl_c_shuffle_f16_f8_f32_f32_f16_mk_nk_mn_mn_mn_instances{});
+}
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instance.cpp
@@ -30,6 +30,16 @@ using PassThrough = ck::tensor_operation::element_wise::PassThrough;
 // static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
 static constexpr auto GemmMNPadding = ck::tensor_operation::device::GemmSpecialization::MNPadding;
+using device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_generic_instances = std::tuple<
+    // clang-format off
+        //#########################|AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|          GEMM| Block|  MPer|  NPer| K0Per| K1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle|     CBlockTransferClusterLengths|  CBlockTransfer| Compute|
+        //#########################| Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise|Specialization|  Size| Block| Block| Block|   |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector|    Type|
+        //#########################|     |      |      |        |        |        |        |   Operation|   Operation|   Operation|              |      |      |      |      |   |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl|   _NWaveNPerXdl|        |
+        //#########################|     |      |      |        |        |        |        |            |            |            |              |      |      |      |      |   |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                                 |                |        |
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,      Row,    Row, PassThrough, PassThrough, PassThrough, GemmMNPadding,   128,    32,    64,     4,  8,   32,   32,    1,    1,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              1,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             2,              1,              8,      true,           1,           1,                   S<1, 16, 1, 8>,               2,    F16>
+    // clang-format on
+    >;
 // Compilation parameters for a[m, k] * b[k, n] = c[m, n]
 using device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instances = std::tuple<
    // clang-format off
@@ -61,6 +71,8 @@ void add_device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instances(
        DeviceGemmSplitK<Row, Row, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
        instances)
 {
+    add_device_operation_instances(instances,
+                                   device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_generic_instances{});
    add_device_operation_instances(instances,
                                   device_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_instances{});
 }

--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instance.cpp
@@ -27,7 +27,17 @@ using S = ck::Sequence<Is...>;
 using PassThrough = ck::tensor_operation::element_wise::PassThrough;
-static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
+static constexpr auto MNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+using device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_generic_instances = std::tuple<
+    // clang-format off
+        //#########################|AData| BData| CData| AccData| ALayout| BLayout| CLayout|           A|           B|           C|          GEMM| Block|  MPer|  NPer| K0Per| K1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle|     CBlockTransferClusterLengths|  CBlockTransfer| Compute|
+        //#########################| Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise|Specialization|  Size| Block| Block| Block|   |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector|    Type|
+        //#########################|     |      |      |        |        |        |        |   Operation|   Operation|   Operation|              |      |      |      |      |   |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl|   _NWaveNPerXdl|        |
+        //#########################|     |      |      |        |        |        |        |            |            |            |              |      |      |      |      |   |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                                 |                |        |
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,    64,    32,    64,     4,  8,   32,   32,    1,    2,  S<1, 4, 16, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              1,              8,      true,  S<1, 4, 16, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              1,              8,      true,           1,           1,                   S<1, 16, 1, 4>,               2,    F16>
+    // clang-format on
+    >;
 // Compilation parameters for a[m, k] * b[k, n] = c[m, n]
 using device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instances = std::tuple<
@@ -36,19 +46,19 @@ using device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instances = std::tuple<
        //#########################| Type|  Type|  Type|    Type|        |        |        | Elementwise| Elementwise| Elementwise|Specialization|  Size| Block| Block| Block|   |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector|    Type|
        //#########################|     |      |      |        |        |        |        |   Operation|   Operation|   Operation|              |      |      |      |      |   |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl|   _NWaveNPerXdl|        |
        //#########################|     |      |      |        |        |        |        |            |            |            |              |      |      |      |      |   |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                                 |                |        |
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   256,   256,   128,     4,  8,   32,   32,    4,    2,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   256,   256,   128,     4,  8,   32,   32,    4,    2,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   256,   128,   256,     4,  8,   32,   32,    2,    4,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   256,   128,   256,     4,  8,   32,   32,    2,    4,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   128,   128,   128,     4,  8,   32,   32,    4,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   128,   128,   128,     4,  8,   32,   32,    4,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   256,   128,   128,     4,  8,   32,   32,    2,    2,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   256,   128,   128,     4,  8,   32,   32,    2,    2,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   128,   128,    64,     4,  8,   32,   32,    2,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 4>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   128,   128,    64,     4,  8,   32,   32,    2,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 4>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   128,    64,   128,     4,  8,   32,   32,    2,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   128,    64,   128,     4,  8,   32,   32,    2,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,    64,    64,    64,     4,  8,   32,   32,    2,    2,  S<1, 4, 16, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 16, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 4>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,    64,    64,    64,     4,  8,   32,   32,    2,    2,  S<1, 4, 16, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 16, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 4>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   256,   128,    64,     4,  8,   32,   32,    2,    1,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   256,   128,    64,     4,  8,   32,   32,    2,    1,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   256,    64,   128,     4,  8,   32,   32,    1,    2,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   256,    64,   128,     4,  8,   32,   32,    1,    2,  S<1, 4, 64, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 64, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   128,   128,    32,     4,  8,   32,   32,    2,    1,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 4>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   128,   128,    32,     4,  8,   32,   32,    2,    1,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 32, 1, 4>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,   128,    32,   128,     4,  8,   32,   32,    1,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 8>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,   128,    32,   128,     4,  8,   32,   32,    1,    2,  S<1, 4, 32, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 32, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 8>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,    64,    64,    32,     4,  8,   32,   32,    2,    1,  S<1, 4, 16, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 16, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 4>,               8,    F16>,
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,    64,    64,    32,     4,  8,   32,   32,    2,    1,  S<1, 4, 16, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 16, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 4>,               8,    F16>,
-        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,   GemmDefault,    64,    32,    64,     4,  8,   32,   32,    1,    2,  S<1, 4, 16, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 16, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 4>,               8,    F16>
+        DeviceGemmXdlSplitKCShuffle<  F16,    F8,   F16,     F32,     Row,     Col,     Row, PassThrough, PassThrough, PassThrough,    MNKPadding,    64,    32,    64,     4,  8,   32,   32,    1,    2,  S<1, 4, 16, 1>,  S<0, 2, 1, 3>,  S<0, 2, 1, 3>,              3,              8,              8,      true,  S<1, 4, 16, 1>,  S<0, 1, 3, 2>,  S<0, 1, 3, 2>,             3,              8,              8,      true,           1,           1,                   S<1, 16, 1, 4>,               8,    F16>
    // clang-format on
    >;
@@ -57,6 +67,8 @@ void add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instances(
        DeviceGemmSplitK<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
        instances)
 {
+    add_device_operation_instances(instances,
+                                   device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_generic_instances{});
    add_device_operation_instances(instances,
                                   device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_instances{});
 }

--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
 add_instance_library(device_grouped_conv2d_fwd_instance
+   #xdl
   # GNHWC, GKYXC, GNHWK
   device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_bf16_instance.cpp
   device_grouped_conv2d_fwd_xdl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
@@ -8,6 +9,13 @@ add_instance_library(device_grouped_conv2d_fwd_instance
   device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
   device_grouped_conv2d_fwd_xdl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
   #dl
+   # GNHWC, GKYXC, GNHWK
   device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
   device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
+   # WMMA
+   device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp
+   device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp
+   # NHWGC, GKYXC, NHWGK
+   device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instance.cpp
+   device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instance.cpp
 )