Merge pull request #48 from ROCm/merge_from_public

Merge from public

library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -25,25 +25,35 @@ template <ck::index_t NDimSpatial,
           typename InElementwiseOperation,
           typename WeiElementwiseOperation,
           typename OutElementwiseOperation,
+          ck::index_t NumAElementwiseTensor                                         = 0,
+          ck::index_t NumBElementwiseTensor                                         = 0,
+          ck::index_t NumDElementwiseTensor                                         = 0,
           typename std::enable_if<NDimSpatial >= 1 && NDimSpatial <= 3, bool>::type = false>
 struct ReferenceConvBwdData : public device::BaseOperator
 {
     // Argument
     struct Argument : public device::BaseArgument
     {
-        Argument(Tensor<InDataType>& input,
-                 const Tensor<WeiDataType>& weight,
-                 const Tensor<OutDataType>& output,
-                 std::vector<ck::index_t> conv_filter_strides,
-                 std::vector<ck::index_t> conv_filter_dilations,
-                 std::vector<ck::index_t> input_left_pads,
-                 std::vector<ck::index_t> input_right_pads,
-                 InElementwiseOperation in_element_op,
-                 WeiElementwiseOperation wei_element_op,
-                 OutElementwiseOperation out_element_op)
+        Argument(
+            Tensor<InDataType>& input,
+            const Tensor<WeiDataType>& weight,
+            const Tensor<OutDataType>& output,
+            std::vector<ck::index_t> conv_filter_strides,
+            std::vector<ck::index_t> conv_filter_dilations,
+            std::vector<ck::index_t> input_left_pads,
+            std::vector<ck::index_t> input_right_pads,
+            InElementwiseOperation in_element_op,
+            WeiElementwiseOperation wei_element_op,
+            OutElementwiseOperation out_element_op,
+            const std::array<Tensor<InDataType>, NumAElementwiseTensor>& elementwise_a_tensors,
+            const std::array<Tensor<WeiDataType>, NumBElementwiseTensor>& elementwise_b_tensors,
+            const std::array<Tensor<OutDataType>, NumDElementwiseTensor>& elementwise_d_tensors)
             : input_{input},
               weight_{weight},
               output_{output},
+              elementwise_a_tensors_{elementwise_a_tensors},
+              elementwise_b_tensors_{elementwise_b_tensors},
+              elementwise_d_tensors_{elementwise_d_tensors},
               conv_strides_{conv_filter_strides},
               conv_dilations_{conv_filter_dilations},
               in_left_pads_{input_left_pads},
@@ -58,6 +68,10 @@ struct ReferenceConvBwdData : public device::BaseOperator
         const Tensor<WeiDataType>& weight_;
         const Tensor<OutDataType>& output_;
 
+        const std::array<Tensor<InDataType>, NumAElementwiseTensor>& elementwise_a_tensors_;
+        const std::array<Tensor<WeiDataType>, NumBElementwiseTensor>& elementwise_b_tensors_;
+        const std::array<Tensor<OutDataType>, NumDElementwiseTensor>& elementwise_d_tensors_;
+
         std::vector<index_t> conv_strides_;
         std::vector<index_t> conv_dilations_;
         std::vector<index_t> in_left_pads_;
@@ -106,26 +120,46 @@ struct ReferenceConvBwdData : public device::BaseOperator
                             {
                                 for(std::size_t k = 0; k < K; ++k)
                                 {
-                                    float v_out = 0;
-                                    float v_wei = 0;
-
-                                    arg.out_element_op_(
-                                        v_out, ck::type_convert<float>(arg.output_(g, n, k, wo)));
-
-                                    arg.wei_element_op_(
-                                        v_wei, ck::type_convert<float>(arg.weight_(g, k, c, x)));
-
-                                    v_acc += v_out * v_wei;
+                                    OutDataType v_out;
+                                    WeiDataType v_wei;
+
+                                    ExecuteElementwiseOp(arg.out_element_op_,
+                                                         arg.elementwise_a_tensors_,
+                                                         Number<NumAElementwiseTensor>{},
+                                                         v_out,
+                                                         arg.output_(g, n, k, wo),
+                                                         g,
+                                                         n,
+                                                         k,
+                                                         wo);
+                                    ExecuteElementwiseOp(arg.wei_element_op_,
+                                                         arg.elementwise_b_tensors_,
+                                                         Number<NumBElementwiseTensor>{},
+                                                         v_wei,
+                                                         arg.weight_(g, k, c, x),
+                                                         g,
+                                                         k,
+                                                         c,
+                                                         x);
+
+                                    v_acc += ck::type_convert<float>(v_out) *
+                                             ck::type_convert<float>(v_wei);
                                 }
                             }
                         }
                     }
 
-                    float v_in;
-
-                    arg.in_element_op_(v_in, v_acc);
-
-                    arg.input_(g, n, c, wi) = ck::type_convert<InDataType>(v_in);
+                    InDataType v_acc_converted = ck::type_convert<InDataType>(v_acc);
+                    InDataType& v_in           = arg.input_(g, n, c, wi);
+                    ExecuteElementwiseOp(arg.in_element_op_,
+                                         arg.elementwise_d_tensors_,
+                                         Number<NumDElementwiseTensor>{},
+                                         v_in,
+                                         v_acc_converted,
+                                         g,
+                                         n,
+                                         c,
+                                         wi);
                 };
 
                 make_ParallelTensorFunctor(f_ncw,
@@ -175,20 +209,34 @@ struct ReferenceConvBwdData : public device::BaseOperator
                                         {
                                             for(std::size_t k = 0; k < K; ++k)
                                             {
-                                                float v_out = 0;
-                                                float v_wei = 0;
+                                                OutDataType v_out;
+                                                WeiDataType v_wei;
 
-                                                arg.out_element_op_(
+                                                ExecuteElementwiseOp(
+                                                    arg.out_element_op_,
+                                                    arg.elementwise_a_tensors_,
+                                                    Number<NumAElementwiseTensor>{},
                                                     v_out,
-                                                    ck::type_convert<float>(
-                                                        arg.output_(g, n, k, ho, wo)));
-
-                                                arg.wei_element_op_(
+                                                    arg.output_(g, n, k, ho, wo),
+                                                    g,
+                                                    n,
+                                                    k,
+                                                    ho,
+                                                    wo);
+                                                ExecuteElementwiseOp(
+                                                    arg.wei_element_op_,
+                                                    arg.elementwise_b_tensors_,
+                                                    Number<NumBElementwiseTensor>{},
                                                     v_wei,
-                                                    ck::type_convert<float>(
-                                                        arg.weight_(g, k, c, y, x)));
-
-                                                v_acc += v_out * v_wei;
+                                                    arg.weight_(g, k, c, y, x),
+                                                    g,
+                                                    k,
+                                                    c,
+                                                    y,
+                                                    x);
+
+                                                v_acc += ck::type_convert<float>(v_out) *
+                                                         ck::type_convert<float>(v_wei);
                                             }
                                         }
                                     }
@@ -197,11 +245,18 @@ struct ReferenceConvBwdData : public device::BaseOperator
                         }
                     }
 
-                    float v_in;
-
-                    arg.in_element_op_(v_in, v_acc);
-
-                    arg.input_(g, n, c, hi, wi) = ck::type_convert<InDataType>(v_in);
+                    InDataType v_acc_converted = ck::type_convert<InDataType>(v_acc);
+                    InDataType& v_in           = arg.input_(g, n, c, hi, wi);
+                    ExecuteElementwiseOp(arg.in_element_op_,
+                                         arg.elementwise_d_tensors_,
+                                         Number<NumDElementwiseTensor>{},
+                                         v_in,
+                                         v_acc_converted,
+                                         g,
+                                         n,
+                                         c,
+                                         hi,
+                                         wi);
                 };
 
                 make_ParallelTensorFunctor(f_nchw,
@@ -270,20 +325,37 @@ struct ReferenceConvBwdData : public device::BaseOperator
                                                     {
                                                         for(std::size_t k = 0; k < K; ++k)
                                                         {
-                                                            float v_out = 0;
-                                                            float v_wei = 0;
+                                                            OutDataType v_out;
+                                                            WeiDataType v_wei;
 
-                                                            arg.out_element_op_(
+                                                            ExecuteElementwiseOp(
+                                                                arg.out_element_op_,
+                                                                arg.elementwise_a_tensors_,
+                                                                Number<NumAElementwiseTensor>{},
                                                                 v_out,
-                                                                ck::type_convert<float>(arg.output_(
-                                                                    g, n, k, do_, ho, wo)));
-
-                                                            arg.wei_element_op_(
+                                                                arg.output_(g, n, k, do_, ho, wo),
+                                                                g,
+                                                                n,
+                                                                k,
+                                                                do_,
+                                                                ho,
+                                                                wo);
+                                                            ExecuteElementwiseOp(
+                                                                arg.wei_element_op_,
+                                                                arg.elementwise_b_tensors_,
+                                                                Number<NumBElementwiseTensor>{},
                                                                 v_wei,
-                                                                ck::type_convert<float>(
-                                                                    arg.weight_(g, k, c, z, y, x)));
-
-                                                            v_acc += v_out * v_wei;
+                                                                arg.weight_(g, k, c, z, y, x),
+                                                                g,
+                                                                k,
+                                                                c,
+                                                                z,
+                                                                y,
+                                                                x);
+
+                                                            v_acc +=
+                                                                ck::type_convert<float>(v_out) *
+                                                                ck::type_convert<float>(v_wei);
                                                         }
                                                     }
                                                 }
@@ -295,11 +367,19 @@ struct ReferenceConvBwdData : public device::BaseOperator
                         }
                     }
 
-                    float v_in;
-
-                    arg.in_element_op_(v_in, v_acc);
-
-                    arg.input_(g, n, c, di, hi, wi) = ck::type_convert<InDataType>(v_in);
+                    InDataType v_acc_converted = ck::type_convert<InDataType>(v_acc);
+                    InDataType& v_in           = arg.input_(g, n, c, di, hi, wi);
+                    ExecuteElementwiseOp(arg.in_element_op_,
+                                         arg.elementwise_d_tensors_,
+                                         Number<NumDElementwiseTensor>{},
+                                         v_in,
+                                         v_acc_converted,
+                                         g,
+                                         n,
+                                         c,
+                                         di,
+                                         hi,
+                                         wi);
                 };
 
                 make_ParallelTensorFunctor(f_ncdhw,
@@ -325,6 +405,36 @@ struct ReferenceConvBwdData : public device::BaseOperator
         }
     };
 
+    template <typename... Args,
+              typename ElementwiseOp,
+              typename ElementwiseTensor,
+              typename NumTensor,
+              typename T>
+    static void ExecuteElementwiseOp(ElementwiseOp& elementwise_op,
+                                     ElementwiseTensor& elementwise_tensors,
+                                     NumTensor,
+                                     T& y,
+                                     const T& x,
+                                     Args... dims)
+    {
+        if constexpr(NumTensor::value == 0)
+        {
+            elementwise_op(y, x);
+        }
+        else if constexpr(NumTensor::value == 1)
+        {
+            elementwise_op(y, x, elementwise_tensors[0](dims...));
+        }
+        else if constexpr(NumTensor::value == 2)
+        {
+            elementwise_op(y, x, elementwise_tensors[0](dims...), elementwise_tensors[1](dims...));
+        }
+        else
+        {
+            throw std::runtime_error("ElementOp not supported in reference.");
+        }
+    }
+
     static constexpr bool IsValidCompilationParameter()
     {
         // TODO: properly implement this check
@@ -333,16 +443,20 @@ struct ReferenceConvBwdData : public device::BaseOperator
 
     bool IsSupportedArgument(const device::BaseArgument*) override { return true; }
 
-    static auto MakeArgument(Tensor<InDataType>& input,
-                             const Tensor<WeiDataType>& weight,
-                             const Tensor<OutDataType>& output,
-                             std::vector<ck::index_t> conv_filter_strides,
-                             std::vector<ck::index_t> conv_filter_dilations,
-                             std::vector<ck::index_t> input_left_pads,
-                             std::vector<ck::index_t> input_right_pads,
-                             InElementwiseOperation in_element_op,
-                             WeiElementwiseOperation wei_element_op,
-                             OutElementwiseOperation out_element_op)
+    static auto MakeArgument(
+        Tensor<InDataType>& input,
+        const Tensor<WeiDataType>& weight,
+        const Tensor<OutDataType>& output,
+        std::vector<ck::index_t> conv_filter_strides,
+        std::vector<ck::index_t> conv_filter_dilations,
+        std::vector<ck::index_t> input_left_pads,
+        std::vector<ck::index_t> input_right_pads,
+        InElementwiseOperation in_element_op,
+        WeiElementwiseOperation wei_element_op,
+        OutElementwiseOperation out_element_op,
+        const std::array<Tensor<InDataType>, NumAElementwiseTensor>& elementwise_a_tensors  = {},
+        const std::array<Tensor<WeiDataType>, NumBElementwiseTensor>& elementwise_b_tensors = {},
+        const std::array<Tensor<OutDataType>, NumDElementwiseTensor>& elementwise_d_tensors = {})
     {
         return Argument{input,
                         weight,
@@ -353,7 +467,10 @@ struct ReferenceConvBwdData : public device::BaseOperator
                         input_right_pads,
                         in_element_op,
                         wei_element_op,
-                        out_element_op};
+                        out_element_op,
+                        elementwise_a_tensors,
+                        elementwise_b_tensors,
+                        elementwise_d_tensors};
     }
 
     static auto MakeInvoker() { return Invoker{}; }

library/include/ck/library/reference_tensor_operation/cpu/reference_fpAintB_gemm.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <iostream>
+#include <sstream>
+
+#include "ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp"
+#include "ck/tensor_operation/gpu/device/device_base.hpp"
+#include "ck/library/utility/host_tensor.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace host {
+
+template <typename ADataType,
+          typename BDataType,
+          typename ScaleDataType,
+          typename CDataType,
+          typename AccDataType,
+          typename AElementwiseOperation,
+          typename BElementwiseOperation,
+          typename CElementwiseOperation>
+struct ReferencefpAintBGemm : public device::BaseOperator
+{
+    // Argument
+    struct Argument : public device::BaseArgument
+    {
+        Argument(const Tensor<ADataType>& a_m_k,
+                 const Tensor<BDataType>& b_k_n,
+                 const Tensor<ScaleDataType>& scale_k_n,
+                 Tensor<CDataType>& c_m_n,
+                 AElementwiseOperation a_element_op,
+                 BElementwiseOperation b_element_op,
+                 CElementwiseOperation c_element_op)
+            : a_m_k_{a_m_k},
+              b_k_n_{b_k_n},
+              scale_k_n_{scale_k_n},
+              c_m_n_{c_m_n},
+              a_element_op_{a_element_op},
+              b_element_op_{b_element_op},
+              c_element_op_{c_element_op}
+        {
+        }
+
+        const Tensor<ADataType>& a_m_k_;
+        const Tensor<BDataType>& b_k_n_;
+        const Tensor<ScaleDataType>& scale_k_n_;
+        Tensor<CDataType>& c_m_n_;
+
+        AElementwiseOperation a_element_op_;
+        BElementwiseOperation b_element_op_;
+        CElementwiseOperation c_element_op_;
+    };
+
+    // Invoker
+    struct Invoker : public device::BaseInvoker
+    {
+        using Argument = ReferencefpAintBGemm::Argument;
+
+        float Run(const Argument& arg)
+        {
+            auto f_mk_kn_mn = [&](auto m, auto n) {
+                const int K = arg.a_m_k_.mDesc.GetLengths()[1];
+
+                AccDataType v_acc = 0;
+
+                for(int k = 0; k < K; ++k)
+                {
+                    ADataType v_a;
+                    BDataType v_b;
+                    ScaleDataType v_scale;
+                    ADataType v_converted_b;
+
+                    // use PassThrough instead of ConvertBF16RTN for reference calculation
+                    if constexpr(is_same_v<AElementwiseOperation,
+                                           ck::tensor_operation::element_wise::ConvertBF16RTN>)
+                    {
+                        ck::tensor_operation::element_wise::PassThrough{}(v_a, arg.a_m_k_(m, k));
+                    }
+                    else
+                    {
+                        arg.a_element_op_(v_a, arg.a_m_k_(m, k));
+                    }
+
+                    // same for B matrix
+                    if constexpr(is_same_v<BElementwiseOperation,
+                                           ck::tensor_operation::element_wise::ConvertBF16RTN>)
+                    {
+                        ck::tensor_operation::element_wise::PassThrough{}(v_b, arg.b_k_n_(k, n));
+                    }
+                    else
+                    {
+                        arg.b_element_op_(v_b, arg.b_k_n_(k, n));
+                    }
+
+                    // same for scale matrix
+                    if constexpr(is_same_v<BElementwiseOperation,
+                                           ck::tensor_operation::element_wise::ConvertBF16RTN>)
+                    {
+                        ck::tensor_operation::element_wise::PassThrough{}(v_scale,
+                                                                          arg.scale_k_n_(k, n));
+                    }
+                    else
+                    {
+                        arg.b_element_op_(v_scale, arg.scale_k_n_(k, n));
+                    }
+
+                    v_converted_b = type_convert<ADataType>(v_b) * v_scale;
+                    v_acc += ck::type_convert<AccDataType>(v_a) *
+                             ck::type_convert<AccDataType>(v_converted_b);
+                }
+
+                AccDataType v_c;
+
+                arg.c_element_op_(v_c, v_acc);
+
+                arg.c_m_n_(m, n) = ck::type_convert<CDataType>(v_c);
+            };
+
+            make_ParallelTensorFunctor(
+                f_mk_kn_mn, arg.c_m_n_.mDesc.GetLengths()[0], arg.c_m_n_.mDesc.GetLengths()[1])(
+                std::thread::hardware_concurrency());
+
+            return 0;
+        }
+
+        float Run(const device::BaseArgument* p_arg,
+                  const StreamConfig& /* stream_config */ = StreamConfig{}) override
+        {
+            return Run(*dynamic_cast<const Argument*>(p_arg));
+        }
+    };
+
+    static constexpr bool IsValidCompilationParameter()
+    {
+        // TODO: properly implement this check
+        return true;
+    }
+
+    bool IsSupportedArgument(const device::BaseArgument*) override { return true; }
+
+    static auto MakeArgument(const Tensor<ADataType>& a_m_k,
+                             const Tensor<BDataType>& b_k_n,
+                             const Tensor<ScaleDataType>& scale_k_n,
+                             Tensor<CDataType>& c_m_n,
+                             AElementwiseOperation a_element_op,
+                             BElementwiseOperation b_element_op,
+                             CElementwiseOperation c_element_op)
+    {
+        return Argument{a_m_k, b_k_n, scale_k_n, c_m_n, a_element_op, b_element_op, c_element_op};
+    }
+
+    static auto MakeInvoker() { return Invoker{}; }
+
+    virtual std::unique_ptr<device::BaseInvoker> MakeInvokerPointer()
+    {
+        return std::make_unique<Invoker>(Invoker{});
+    }
+
+    std::string GetTypeString() const override
+    {
+        auto str = std::stringstream();
+
+        // clang-format off
+        str << "ReferenceGemm"
+            << std::endl;
+        // clang-format on
+
+        return str.str();
+    }
+};
+
+} // namespace host
+} // namespace tensor_operation
+} // namespace ck

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

@@ -384,6 +384,26 @@ void add_device_gemm_xdl_c_shuffle_f16_f8_f16_mk_nk_mn_instances(
         instances);
 #endif
 
+void add_device_gemm_wmma_f16_f16_f16_km_kn_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
+void add_device_gemm_wmma_f16_f16_f16_km_nk_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
+void add_device_gemm_wmma_f16_f16_f16_mk_kn_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
+void add_device_gemm_wmma_f16_f16_f16_mk_nk_mn_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
 template <typename ALayout,
           typename BLayout,
           typename CLayout,
@@ -478,6 +498,7 @@ struct DeviceOperationInstanceFactory<
                 add_device_gemm_dpp_f16_f16_f16_mk_kn_mn_irregular_instances(op_ptrs);
 #endif
                 add_device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instances(op_ptrs);
+                add_device_gemm_wmma_f16_f16_f16_mk_kn_mn_instances(op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
                               is_same_v<CLayout, Row>)
@@ -493,6 +514,7 @@ struct DeviceOperationInstanceFactory<
                 add_device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instances(op_ptrs);
                 add_device_gemm_xdl_c_shuffle_lds_direct_load_f16_f16_f16_mk_nk_mn_instances(
                     op_ptrs);
+                add_device_gemm_wmma_f16_f16_f16_mk_nk_mn_instances(op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Row> &&
                               is_same_v<CLayout, Row>)
@@ -505,6 +527,7 @@ struct DeviceOperationInstanceFactory<
                 add_device_gemm_dpp_f16_f16_f16_km_kn_mn_irregular_instances(op_ptrs);
 #endif
                 add_device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instances(op_ptrs);
+                add_device_gemm_wmma_f16_f16_f16_km_kn_mn_instances(op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Col> &&
                               is_same_v<CLayout, Row>)
@@ -517,6 +540,7 @@ struct DeviceOperationInstanceFactory<
                 add_device_gemm_dpp_f16_f16_f16_km_nk_mn_irregular_instances(op_ptrs);
 #endif
                 add_device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instances(op_ptrs);
+                add_device_gemm_wmma_f16_f16_f16_km_nk_mn_instances(op_ptrs);
             }
         }
 #endif

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

@@ -189,6 +189,11 @@ void add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_v2_instances(
         DeviceGemmSplitK<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
+void add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_kpb128_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmSplitK<Row, Col, Row, F16, F8, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
 void add_device_gemm_xdl_splitk_f16_f16_f16_comp_f8_km_kn_mn_instances(
     std::vector<std::unique_ptr<
         DeviceGemmSplitK<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough, F8>>>&
@@ -352,6 +357,7 @@ struct DeviceOperationInstanceFactory<
                 add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_v1_instances(op_ptrs);
                 add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_v1_interwave_instances(op_ptrs);
                 add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_v2_instances(op_ptrs);
+                add_device_gemm_xdl_splitk_f16_f8_f16_mk_nk_mn_kpb128_instances(op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Row> &&
                               is_same_v<CLayout, Row>)

library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_bilinear_instance.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.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 BF16 = ck::bhalf_t;
+using F16  = ck::half_t;
+using F32  = float;
+using BF8  = ck::bf8_t;
+using F8   = ck::f8_t;
+
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+
+using namespace ck::tensor_layout::convolution;
+
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using Bilinear    = ck::tensor_operation::element_wise::Bilinear;
+
+static constexpr auto ConvBwdDataDefault = ConvolutionBackwardDataSpecialization::Default;
+
+static constexpr auto ConvBwdDataFilter1x1Stride1Pad0 =
+    ConvolutionBackwardDataSpecialization::Filter1x1Stride1Pad0;
+
+// f16_f16_f32_f16
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionBackwardDataSpecialization ConvSpec>
+using device_grouped_conv_bwd_data_xdl_bilinear_f16_instances = std::tuple<
+    // clang-format off
+        // ##############################################|       NDim| ALayout| BLayout|           DsLayout| ELayout| AData| BData| AccData| CShuffle|      DsData| EData| AElementwise| BElementwise| CDEElementwise| ConvolutionBackward| DoPad| DoPad|      NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MXdl|    NXdl|    ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|    BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffleMXdl| CShuffleNXdl|   CDEBlockTransfer| CDEBlockTransfer|
+        // ##############################################|    Spatial|        |        |                   |        |  Type|  Type|    Type| DataType|        Type|  Type|    Operation|    Operation|      Operation|  DataSpecialization| GemmM| GemmN| PrefetchStage|  Size| Block| Block| Block|    |    |  XDL|  XDL| PerWave| PerWave|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraM|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraN|      PerWave|      PerWave|  _MBlock_MPerBlock|  ScalarPerVector|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        | Lengths_AK0_M_AK1|   ArrangeOrder|               |               |      PerVector|  PerVector_AK1|          | Lengths_BK0_N_BK1|   ArrangeOrder|               |               |      PerVector|  PerVector_BK1|          |   PerShuffle|   PerShuffle|  _NBlock_NPerBlock|       _NPerBlock|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        |                  |               |               |               |               |               |          |                  |               |               |               |               |               |          |             |             |                   |                 |
+        // generic instance
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F16,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,    64,    64,    64,    32,   8,   8,   32,   32,       2,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,        S<4, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,         1,            1,            1,     S<1, 16, 1, 4>,                1>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F16,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              8,              8,         1,            1,            1,     S<1, 32, 1, 8>,                8>,
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F16,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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, 4, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,         1,            1,            1,     S<1, 32, 1, 4>,                1>,
+
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F16,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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>
+    // clang-format on
+    >;
+
+// bf16_bf16_f32_bf16
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionBackwardDataSpecialization ConvSpec>
+using device_grouped_conv_bwd_data_xdl_bilinear_bf16_instances = std::tuple<
+    // clang-format off
+        // ##############################################|       NDim| ALayout| BLayout|           DsLayout| ELayout| AData| BData| AccData| CShuffle|      DsData| EData| AElementwise| BElementwise| CDEElementwise| ConvolutionBackward| DoPad| DoPad|      NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MXdl|    NXdl|    ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|    BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffleMXdl| CShuffleNXdl|   CDEBlockTransfer| CDEBlockTransfer|
+        // ##############################################|    Spatial|        |        |                   |        |  Type|  Type|    Type| DataType|        Type|  Type|    Operation|    Operation|      Operation|  DataSpecialization| GemmM| GemmN| PrefetchStage|  Size| Block| Block| Block|    |    |  XDL|  XDL| PerWave| PerWave|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraM|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraN|      PerWave|      PerWave|  _MBlock_MPerBlock|  ScalarPerVector|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        | Lengths_AK0_M_AK1|   ArrangeOrder|               |               |      PerVector|  PerVector_AK1|          | Lengths_BK0_N_BK1|   ArrangeOrder|               |               |      PerVector|  PerVector_BK1|          |   PerShuffle|   PerShuffle|  _NBlock_NPerBlock|       _NPerBlock|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        |                  |               |               |               |               |               |          |                  |               |               |               |               |               |          |             |             |                   |                 |
+        // generic instance
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,  BF16,  BF16,     F32,     BF16,  Tuple<BF16>,  BF16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,    64,    64,    64,    32,   8,   8,   32,   32,       2,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,    S<4, 8, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,         1,            1,            1,     S<1, 16, 1, 4>,                1>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,  BF16,  BF16,     F32,     BF16,  Tuple<BF16>,  BF16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              8,              8,         1,            1,            1,     S<1, 32, 1, 8>,                8>,
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,  BF16,  BF16,     F32,     BF16,  Tuple<BF16>,  BF16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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, 4, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,         1,            1,            1,     S<1, 32, 1, 4>,                1>,
+
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,  BF16,  BF16,     F32,     BF16,  Tuple<BF16>,  BF16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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>
+    // clang-format on
+    >;
+
+// f32_f32_f32_f32
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionBackwardDataSpecialization ConvSpec>
+using device_grouped_conv_bwd_data_xdl_bilinear_f32_instances = std::tuple<
+    // clang-format off
+        // ##############################################|       NDim| ALayout| BLayout|           DsLayout| ELayout| AData| BData| AccData| CShuffle|      DsData| EData| AElementwise| BElementwise| CDEElementwise| ConvolutionBackward| DoPad| DoPad|      NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MXdl|    NXdl|    ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|    BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffleMXdl| CShuffleNXdl|   CDEBlockTransfer| CDEBlockTransfer|
+        // ##############################################|    Spatial|        |        |                   |        |  Type|  Type|    Type| DataType|        Type|  Type|    Operation|    Operation|      Operation|  DataSpecialization| GemmM| GemmN| PrefetchStage|  Size| Block| Block| Block|    |    |  XDL|  XDL| PerWave| PerWave|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraM|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraN|      PerWave|      PerWave|  _MBlock_MPerBlock|  ScalarPerVector|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        | Lengths_AK0_M_AK1|   ArrangeOrder|               |               |      PerVector|  PerVector_AK1|          | Lengths_BK0_N_BK1|   ArrangeOrder|               |               |      PerVector|  PerVector_BK1|          |   PerShuffle|   PerShuffle|  _NBlock_NPerBlock|       _NPerBlock|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        |                  |               |               |               |               |               |          |                  |               |               |               |               |               |          |             |             |                   |                 |
+        // generic instance
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F32,   F32,     F32,      F32,  Tuple<F32>,   F32,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,    64,    64,    64,    32,   8,   8,   32,   32,       2,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              4,         1,       S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              4,         1,            1,            1,     S<1, 16, 1, 4>,                1>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F32,   F32,     F32,      F32,  Tuple<F32>,   F32,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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,              4,         1,       S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,         1,            1,            1,     S<1, 32, 1, 8>,                4>,
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F32,   F32,     F32,      F32,  Tuple<F32>,   F32,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,   128,   128,    32,    32,   8,   8,   32,   32,       2,       1,       S<4, 32, 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,              1,              4,         1,            1,            1,     S<1, 32, 1, 4>,                1>,
+
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F32,   F32,     F32,      F32,  Tuple<F32>,   F32,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,   256,   128,   256,    32,   8,   2,   32,   32,       2,       4,       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,              4,              2,         0,            1,            1,     S<1, 32, 1, 8>,                4>
+    // clang-format on
+    >;
+
+// f16_f16_f16_comp_f8
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionBackwardDataSpecialization ConvSpec>
+using device_grouped_conv_bwd_data_xdl_bilinear_input_fp16_comp_bf8f8_instances = std::tuple<
+    // clang-format off
+        // ##############################################|       NDim| ALayout| BLayout|           DsLayout| ELayout| AData| BData| AccData| CShuffle|      DsData| EData| AElementwise| BElementwise| CDEElementwise| ConvolutionBackward| DoPad| DoPad|      NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer|    MXdl|    NXdl|    ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|    BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffleMXdl| CShuffleNXdl|   CDEBlockTransfer| CDEBlockTransfer|
+        // ##############################################|    Spatial|        |        |                   |        |  Type|  Type|    Type| DataType|        Type|  Type|    Operation|    Operation|      Operation|  DataSpecialization| GemmM| GemmN| PrefetchStage|  Size| Block| Block| Block|    |    |  XDL|  XDL| PerWave| PerWave|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraM|     ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar|    ExtraN|      PerWave|      PerWave|  _MBlock_MPerBlock|  ScalarPerVector|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        | Lengths_AK0_M_AK1|   ArrangeOrder|               |               |      PerVector|  PerVector_AK1|          | Lengths_BK0_N_BK1|   ArrangeOrder|               |               |      PerVector|  PerVector_BK1|          |   PerShuffle|   PerShuffle|  _NBlock_NPerBlock|       _NPerBlock|
+        // ##############################################|           |        |        |                   |        |      |      |        |         |            |      |             |             |               |                    |      |      |              |      |      |      |      |    |    |     |     |        |        |                  |               |               |               |               |               |          |                  |               |               |               |               |               |          |             |             |                   |                 |
+        // generic instance
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F32,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,    64,    64,    64,    32,   8,   8,   32,   32,       2,       2,       S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              4,         1,       S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              4,         1,            1,            1,     S<1, 16, 1, 4>,                1,  LoopScheduler::Default, BF8, F8>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F32,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             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,              4,         1,       S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,         1,            1,            1,     S<1, 32, 1, 8>,                4,  LoopScheduler::Default, BF8, F8>,
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F32,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,   128,   128,    32,    32,   8,   8,   32,   32,       2,       1,       S<4, 32, 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,              1,              4,         1,            1,            1,     S<1, 32, 1, 4>,                1,  LoopScheduler::Default, BF8, F8>,
+
+        DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1< NDimSpatial, ALayout, BLayout, ck::Tuple<ELayout>, ELayout,   F16,   F16,     F32,      F32,  Tuple<F16>,   F16,  PassThrough,  PassThrough,       Bilinear,            ConvSpec,  true,  true,             1,   256,   128,   256,    32,   8,   2,   32,   32,       2,       4,       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,              4,              2,         0,            1,            1,     S<1, 32, 1, 8>,                4,  LoopScheduler::Default, BF8, F8>
+    // clang-format on
+    >;
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_instance.hpp

@@ -54,36 +54,36 @@ template <index_t NDSpatial,
           ConvolutionForwardSpecialization ConvSpec>
 using device_grouped_conv_fwd_wmma_f16_instances = std::tuple<
     // clang-format off
-        //########################################|    NumDim|       A|       B|       Ds|       E| AData| BData|         Ds|  EData| AccData| CShuffle|            A|           B|          CDE|    ConvForward|           GEMM| Block|  MPer|  NPer|  KPer| K1|  MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
-        //########################################|   Spatial|  Layout|  Layout|   Layout|  Layout|  Type|  Type|   DataType|   Type|    Type| DataType|  Elementwise| Elementwise|  Elementwise| Specialization| 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|
-        //########################################|          |        |        |         |        |      |      |           |       |        |         |             |            |             |               |               |      |      |      |      |   |      |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        //########################################|    NumDim|       A|       B|       Ds|       E| AData| BData| AccData| CShuffle|         Ds|  EData|            A|           B|          CDE|    ConvForward|           GEMM| Prefetch| Block|  MPer|  NPer|  KPer| K1|  MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //########################################|   Spatial|  Layout|  Layout|   Layout|  Layout|  Type|  Type|    Type| DataType|   DataType|   Type|  Elementwise| Elementwise|  Elementwise| Specialization| Specialization|    Stage|  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|
+        //########################################|          |        |        |         |        |      |      |        |         |           |       |             |            |             |               |               |         |      |      |      |      |   |      |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
         // generic instance
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,    64,     4,  8,    16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 32, 1, 4>,               1>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,    64,    64,    32,  8,    16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 32, 1, 4>,               1>,
         // blocksize=256
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,     4,  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,           1,               S<1, 32, 1, 8>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   256,    64,   256,     4,  8,    16,   16,       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, 32, 1, 8>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   256,   256,    64,     4,  8,    16,   16,       8,       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, 32, 1, 8>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, 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,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    256,   128,   128,    32,  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,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    256,    64,   256,    32,  8,    16,   16,       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, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    256,   256,    64,    32,  8,    16,   16,       8,       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, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    256,   128,   128,    64,  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,           1,               S<1, 32, 1, 8>,               8>,
         // blocksize=128
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,    64,     4,  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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, 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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,   128,     4,  8,    16,   16,       2,       4,     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, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,   128,     8,  8,    16,   16,       2,       4,     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, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,   128,    64,     4,  8,    16,   16,       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, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,   128,    64,     8,  8,    16,   16,       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, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   256,     4,  8,    16,   16,       1,       8,     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, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,   256,    32,     4,  8,    16,   16,       8,       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, 32, 1, 4>,               8>,      
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,    64,    64,    32,  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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,    64,    64,    64,  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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,    64,   128,    32,  8,    16,   16,       2,       4,     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, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,    64,   128,    64,  8,    16,   16,       2,       4,     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, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,   128,    64,    32,  8,    16,   16,       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, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,   128,    64,    64,  8,    16,   16,       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, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,    32,   256,    32,  8,    16,   16,       1,       8,     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, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,    128,   256,    32,    32,  8,    16,   16,       8,       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, 32, 1, 4>,               8>,      
         // blocksize=64
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,     4,  8,    16,   16,       1,       4,     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, 32, 1, 2>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,     4,  8,    16,   16,       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, 32, 1, 2>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, 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,           1,               S<1, 32, 1, 2>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    64,    32,   128,     4,  8,    16,   16,       1,       8,     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, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     64,    32,    64,    32,  8,    16,   16,       1,       4,     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, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     64,    64,    32,    32,  8,    16,   16,       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, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     64,    32,    32,    64,  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,           1,               S<1, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     64,    32,   128,    32,  8,    16,   16,       1,       8,     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, 32, 1, 2>,               8>,
         // blocksize=32
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    32,    16,    64,     4,  8,    16,   16,       1,       4,     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>,  
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    32,    64,    16,     4,  8,    16,   16,       4,       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>,  
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    32,    32,    32,     4,  8,    16,   16,       2,       2,     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>,  
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16, DsDatatype,    F16,     F32,      F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    32,    16,    16,     4,  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>
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     32,    16,    64,    32,  8,    16,   16,       1,       4,     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>,  
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     32,    64,    16,    32,  8,    16,   16,       4,       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>,  
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     32,    32,    32,    32,  8,    16,   16,       2,       2,     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>,  
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  F16,   F16,     F32,      F16, DsDatatype,    F16,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,         1,     32,    16,    16,    32,  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>
     // clang-format on
     >;
 
@@ -97,36 +97,36 @@ template <index_t NDSpatial,
           ConvolutionForwardSpecialization ConvSpec>
 using device_grouped_conv_fwd_wmma_i8_instances = std::tuple<
     // clang-format off
-        //########################################|    NumDim|       A|       B|       Ds|       E| AData| BData|         Ds|  EData| AccData| CShuffle|            A|           B|          CDE|    ConvForward|           GEMM| Block|  MPer|  NPer|  KPer| K1|  MPer| NPer| MRepeat| NRepeat|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
-        //########################################|   Spatial|  Layout|  Layout|   Layout|  Layout|  Type|  Type|   DataType|   Type|    Type| DataType|  Elementwise| Elementwise|  Elementwise| Specialization| 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|
-        //########################################|          |        |        |         |        |      |      |           |       |        |         |             |            |             |               |               |      |      |      |      |   |      |     |        |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        //########################################|    NumDim|       A|       B|       Ds|       E| AData| BData| AccData| CShuffle|         Ds|  EData|            A|           B|          CDE|    ConvForward|           GEMM| Prefetch| Block|  MPer|  NPer|  KPer| K1|  MPer| NPer| MRepeat| NRepeat|   ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer|  ABlockTransfer|  ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer|  BBlockTransfer|  BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
+        //########################################|   Spatial|  Layout|  Layout|   Layout|  Layout|  Type|  Type|    Type| DataType|   DataType|   Type|  Elementwise| Elementwise|  Elementwise| Specialization| Specialization|    Stage|  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|
+        //########################################|          |        |        |         |        |      |      |        |         |           |       |             |            |             |               |               |         |      |      |      |      |   |      |     |        |        |                 |               |               |               |                |                |          |                |               |               |              |                |                |          |            |            |                             |                |
         //generic instance
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,    64,     4,  16,    16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,               1,              16,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,               1,              16,         1,           1,           1,               S<1, 32, 1, 4>,               1>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,   128,    64,    64,    64,  16,    16,   16,       2,       2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,               1,              16,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,               1,              16,         1,           1,           1,               S<1, 32, 1, 4>,               1>,
         // blocksize=256
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, 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,           1,               S<1, 32, 1, 8>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   256,    64,   256,     4,  16,    16,   16,       2,       4,     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,           1,               S<1, 32, 1, 8>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   256,   256,    64,     4,  16,    16,   16,       8,       1,     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,           1,               S<1, 32, 1, 8>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   256,   128,   128,     8,  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,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,   256,   128,   128,    64,  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,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,   256,    64,   256,    64,  16,    16,   16,       2,       4,     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,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,   256,   256,    64,    64,  16,    16,   16,       8,       1,     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,           1,               S<1, 32, 1, 8>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,   256,   128,   128,   128,  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,           1,               S<1, 32, 1, 8>,               8>,
         // blocksize=128
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, 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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,    64,     8,  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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,   128,     4,  16,    16,   16,       2,       4,     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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    64,   128,     8,  16,    16,   16,       2,       4,     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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,   128,    64,     4,  16,    16,   16,       4,       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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,   128,    64,     8,  16,    16,   16,       4,       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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   256,     4,  16,    16,   16,       1,       8,     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,           1,               S<1, 32, 1, 4>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,   128,   256,    32,     4,  16,    16,   16,       8,       1,     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,           1,               S<1, 32, 1, 4>,               8>,      
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,    64,    64,   64,  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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,    64,    64,  128,  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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,    64,   128,   64,  16,    16,   16,       2,       4,     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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,    64,   128,  128,  16,    16,   16,       2,       4,     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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,   128,    64,   64,  16,    16,   16,       4,       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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,   128,    64,  128,  16,    16,   16,       4,       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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,    32,   256,   64,  16,    16,   16,       1,       8,     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,           1,               S<1, 32, 1, 4>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,    128,   256,    32,   64,  16,    16,   16,       8,       1,     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,           1,               S<1, 32, 1, 4>,               8>,      
         // blocksize=64
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,     4,  16,    16,   16,       1,       4,     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,           1,               S<1, 32, 1, 2>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,     4,  16,    16,   16,       2,       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,           1,               S<1, 32, 1, 2>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    32,     8,  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,           1,               S<1, 32, 1, 2>,               8>,
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    64,    32,   128,     4,  16,    16,   16,       1,       8,     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,           1,               S<1, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     64,    32,    64,   64,  16,    16,   16,       1,       4,     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,           1,               S<1, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     64,    64,    32,   64,  16,    16,   16,       2,       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,           1,               S<1, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     64,    32,    32,  128,  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,           1,               S<1, 32, 1, 2>,               8>,
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     64,    32,   128,   64,  16,    16,   16,       1,       8,     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,           1,               S<1, 32, 1, 2>,               8>,
         // blocksize=32
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    32,    16,    64,     4,  16,    16,   16,       1,       4,     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>,  
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    32,    64,    16,     4,  16,    16,   16,       4,       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>,  
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,    32,    32,    32,     4,  16,    16,   16,       2,       2,     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>,  
-        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,  I8,   I8, DsDatatype,    I8,     I32,      I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, 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>
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     32,    16,    64,   64,  16,    16,   16,       1,       4,     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>,  
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     32,    64,    16,   64,  16,    16,   16,       4,       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>,  
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     32,    32,    32,   64,  16,    16,   16,       2,       2,     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>,  
+        DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout,    I8,    I8,     I32,       I8, DsDatatype,     I8,  PassThrough, PassThrough, CDEElementOp,       ConvSpec, GemmMNKPadding,        1,     32,    16,    16,   64,  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>
     // clang-format on
     >;
 

library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_bilinear_instance.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp"
+#include "ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+using BF16 = ck::bhalf_t;
+using F16  = ck::half_t;
+using F32  = float;
+
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+
+using namespace ck::tensor_layout::convolution;
+
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using Bilinear    = ck::tensor_operation::element_wise::Bilinear;
+
+static constexpr auto ConvFwdDefault =
+    ck::tensor_operation::device::ConvolutionForwardSpecialization::Default;
+
+static constexpr auto ConvFwd1x1P0 = ConvolutionForwardSpecialization::Filter1x1Pad0;
+
+static constexpr auto ConvFwd1x1S1P0 = ConvolutionForwardSpecialization::Filter1x1Stride1Pad0;
+
+static constexpr auto ConvFwdOddC =
+    ck::tensor_operation::device::ConvolutionForwardSpecialization::OddC;
+
+static constexpr auto GemmMNKPadding = GemmSpecialization::MNKPadding;
+
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionForwardSpecialization ConvSpec>
+using device_grouped_conv_fwd_xdl_bilinear_bf16_instances = std::tuple<
+    // clang-format off
+        //########################################|     NumDim|      A|      B|          Ds|      E| AData| BData| AccData| CShuffle|          Ds| EData|           A|           B|             CDE|    ConvForward|           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|
+        //########################################|    Spatial| Layout| Layout|      Layout| Layout|  Type|  Type|    Type| DataType|    DataType|  Type| Elementwise| Elementwise|     Elementwise| Specialization| 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|
+        //########################################|           |       |       |            |       |      |      |        |         |            |      |            |            |                |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        // generic instance
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32, BF16, ck::Tuple<BF16>, BF16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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,              1,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 16, 1, 4>,               1>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32, BF16, ck::Tuple<BF16>, BF16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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, 16, 1, 4>,               1>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32, BF16, ck::Tuple<BF16>, BF16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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,              1,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,  BF16,  BF16,     F32, BF16, ck::Tuple<BF16>, BF16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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, 32, 1, 8>,               8>
+    // clang-format on
+    >;
+
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionForwardSpecialization ConvSpec>
+using device_grouped_conv_fwd_xdl_bilinear_f16_instances = std::tuple<
+    // clang-format off
+        //########################################|     NumDim|      A|      B|          Ds|      E| AData| BData| AccData| CShuffle|          Ds| EData|           A|           B|             CDE|    ConvForward|           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|
+        //########################################|    Spatial| Layout| Layout|      Layout| Layout|  Type|  Type|    Type| DataType|    DataType|  Type| Elementwise| Elementwise|     Elementwise| Specialization| 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|
+        //########################################|           |       |       |            |       |      |      |        |         |            |      |            |            |                |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        // generic instance
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32, F16, ck::Tuple<F16>, F16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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,              1,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 16, 1, 4>,               1>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32, F16, ck::Tuple<F16>, F16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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, 16, 1, 4>,               1>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32, F16, ck::Tuple<F16>, F16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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,              1,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32, F16, ck::Tuple<F16>, F16, PassThrough, PassThrough, Bilinear,  ConvSpec, 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, 32, 1, 8>,               8>
+    // clang-format on
+    >;
+
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionForwardSpecialization ConvSpec>
+using device_grouped_conv_fwd_xdl_bilinear_f32_instances = std::tuple<
+    // clang-format off
+        //########################################|     NumDim|      A|      B|          Ds|      E| AData| BData| AccData| CShuffle|          Ds| EData|           A|           B|             CDE|    ConvForward|           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|
+        //########################################|    Spatial| Layout| Layout|      Layout| Layout|  Type|  Type|    Type| DataType|    DataType|  Type| Elementwise| Elementwise|     Elementwise| Specialization| 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|
+        //########################################|           |       |       |            |       |      |      |        |         |            |      |            |            |                |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        // generic instance
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F32,   F32,     F32, F32, ck::Tuple<F32>, F32, PassThrough, PassThrough, Bilinear,  ConvSpec, GemmMNKPadding,        1,    64,    64,    64,    16,   4,   4,   32,   32,    2,    2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              4,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              4,         1,           1,           1,              S<1,  8, 1,  8>,              1>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F32,   F32,     F32, F32, ck::Tuple<F32>, F32, PassThrough, PassThrough, Bilinear,  ConvSpec, GemmMNKPadding,        1,    64,    64,    32,    16,   4,   4,   32,   32,    2,    1,     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,           1,              S<1,  8, 1,  8>,              1>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F32,   F32,     F32, F32, ck::Tuple<F32>, F32, PassThrough, PassThrough, Bilinear,  ConvSpec, GemmMNKPadding,        1,   256,   128,   128,    16,   4,   4,   32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              4,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              4,         1,           1,           1,              S<1, 16, 1, 16>,              4>,
+
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F32,   F32,     F32, F32, ck::Tuple<F32>, F32, PassThrough, PassThrough, Bilinear,  ConvSpec, GemmMNKPadding,        1,   256,   256,   128,    16,   4,   4,   32,   32,    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,           1,              S<1, 16, 1, 16>,              4>
+    // clang-format on
+    >;
+
+template <index_t NDimSpatial,
+          typename ALayout,
+          typename BLayout,
+          typename DsLayout,
+          typename ELayout,
+          ConvolutionForwardSpecialization ConvSpec>
+using device_grouped_conv_fwd_xdl_bilinear_int8_instances = std::tuple<
+    // clang-format off
+        //########################################|     NumDim|      A|      B|          Ds|      E| AData| BData| AccData| CShuffle|                 Ds| EData|           A|           B|             CDE|    ConvForward|           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|
+        //########################################|    Spatial| Layout| Layout|      Layout| Layout|  Type|  Type|    Type| DataType|           DataType|  Type| Elementwise| Elementwise|     Elementwise| Specialization| 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|
+        //########################################|           |       |       |            |       |      |      |        |         |                   |      |            |            |                |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
+        // generic instance
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout, int8_t, int8_t, int32_t, int8_t, ck::Tuple<int8_t>, int8_t, PassThrough, PassThrough, Bilinear,  ConvSpec, 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,              1,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 16, 1, 4>,               1>,
+        // instances for small conv.K and conv.C
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout, int8_t, int8_t, int32_t, int8_t, ck::Tuple<int8_t>, int8_t, PassThrough, PassThrough, Bilinear,  ConvSpec, 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, 16, 1, 4>,               1>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout, int8_t, int8_t, int32_t, int8_t, ck::Tuple<int8_t>, int8_t, PassThrough, PassThrough, Bilinear,  ConvSpec, 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,              1,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 32, 1, 8>,               8>,
+
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout, int8_t, int8_t, int32_t, int8_t, ck::Tuple<int8_t>, int8_t, PassThrough, PassThrough, Bilinear,  ConvSpec, 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, 32, 1, 8>,               8>
+    // clang-format on
+    >;
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/tensor_operation_instance/device_operation_instance_factory.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+#ifdef CK_ENABLE_FP16
+void add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f16_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvBwdDataMultipleD<3,
+                                                                  NDHWGK,
+                                                                  GKZYXC,
+                                                                  Tuple<NDHWGC>,
+                                                                  NDHWGC,
+                                                                  F16,
+                                                                  F16,
+                                                                  Tuple<F16>,
+                                                                  F16,
+                                                                  PassThrough,
+                                                                  PassThrough,
+                                                                  Bilinear>>>& instances);
+#endif
+#ifdef CK_ENABLE_FP32
+void add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f32_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvBwdDataMultipleD<3,
+                                                                  NDHWGK,
+                                                                  GKZYXC,
+                                                                  Tuple<NDHWGC>,
+                                                                  NDHWGC,
+                                                                  F32,
+                                                                  F32,
+                                                                  Tuple<F32>,
+                                                                  F32,
+                                                                  PassThrough,
+                                                                  PassThrough,
+                                                                  Bilinear>>>& instances);
+#endif
+#ifdef CK_ENABLE_BF16
+void add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_bf16_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvBwdDataMultipleD<3,
+                                                                  NDHWGK,
+                                                                  GKZYXC,
+                                                                  Tuple<NDHWGC>,
+                                                                  NDHWGC,
+                                                                  BF16,
+                                                                  BF16,
+                                                                  Tuple<BF16>,
+                                                                  BF16,
+                                                                  PassThrough,
+                                                                  PassThrough,
+                                                                  Bilinear>>>& instances);
+#endif
+template <ck::index_t NumDimSpatial,
+          typename OutLayout,
+          typename WeiLayout,
+          typename InLayout,
+          typename OutDataType,
+          typename WeiDataType,
+          typename InDataType,
+          typename ComputeTypeA,
+          typename ComputeTypeB>
+struct DeviceOperationInstanceFactory<
+    ck::tensor_operation::device::DeviceGroupedConvBwdDataMultipleD<
+        NumDimSpatial,
+        OutLayout,
+        WeiLayout,
+        Tuple<InLayout>,
+        InLayout,
+        OutDataType,
+        WeiDataType,
+        Tuple<InDataType>,
+        InDataType,
+        ck::tensor_operation::element_wise::PassThrough,
+        ck::tensor_operation::element_wise::PassThrough,
+        ck::tensor_operation::element_wise::Bilinear,
+        ComputeTypeA,
+        ComputeTypeB>>
+{
+    using DeviceOp =
+        DeviceGroupedConvBwdDataMultipleD<NumDimSpatial,
+                                          OutLayout,
+                                          WeiLayout,
+                                          Tuple<InLayout>,
+                                          InLayout,
+                                          OutDataType,
+                                          WeiDataType,
+                                          Tuple<InDataType>,
+                                          InDataType,
+                                          ck::tensor_operation::element_wise::PassThrough,
+                                          ck::tensor_operation::element_wise::PassThrough,
+                                          ck::tensor_operation::element_wise::Bilinear,
+                                          ComputeTypeA,
+                                          ComputeTypeB>;
+
+    static auto GetInstances()
+    {
+        std::vector<std::unique_ptr<DeviceOp>> op_ptrs;
+        if constexpr(NumDimSpatial == 3)
+        {
+            if constexpr(is_same_v<InLayout, NDHWGC> && is_same_v<WeiLayout, GKZYXC> &&
+                         is_same_v<OutLayout, NDHWGK>)
+            {
+#ifdef CK_ENABLE_FP16
+                if constexpr(is_same_v<InDataType, F16> && is_same_v<WeiDataType, F16> &&
+                             is_same_v<OutDataType, F16> && is_same_v<ComputeTypeA, F16> &&
+                             is_same_v<ComputeTypeB, F16>)
+                {
+                    add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f16_instances(
+                        op_ptrs);
+                }
+#endif
+#ifdef CK_ENABLE_FP32
+                else if constexpr(is_same_v<InDataType, F32> && is_same_v<WeiDataType, F32> &&
+                                  is_same_v<OutDataType, F32> && is_same_v<ComputeTypeA, F32> &&
+                                  is_same_v<ComputeTypeB, F32>)
+                {
+                    add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_f32_instances(
+                        op_ptrs);
+                }
+#endif
+#ifdef CK_ENABLE_BF16
+                else if constexpr(is_same_v<InDataType, BF16> && is_same_v<WeiDataType, BF16> &&
+                                  is_same_v<OutDataType, BF16> && is_same_v<ComputeTypeA, BF16> &&
+                                  is_same_v<ComputeTypeB, BF16>)
+                {
+                    add_device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgk_gkzyxc_ndhwgc_bf16_instances(
+                        op_ptrs);
+                }
+#endif
+            }
+        }
+
+        return op_ptrs;
+    }
+};
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

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

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+
+#include <vector>
+#include <memory>
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
+
+#include "ck/library/tensor_operation_instance/device_operation_instance_factory.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+using Bilinear    = ck::tensor_operation::element_wise::Bilinear;
+
+#ifdef CK_ENABLE_BF16
+// grouped conv3d forward, NDHWGC/GKZYXC/NDHWGK
+void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
+                                                                NDHWGC,
+                                                                GKZYXC,
+                                                                ck::Tuple<NDHWGK>,
+                                                                NDHWGK,
+                                                                BF16,
+                                                                BF16,
+                                                                ck::Tuple<BF16>,
+                                                                BF16,
+                                                                PassThrough,
+                                                                PassThrough,
+                                                                Bilinear>>>& instances);
+#endif
+
+#ifdef CK_ENABLE_FP16
+void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
+                                                                NDHWGC,
+                                                                GKZYXC,
+                                                                ck::Tuple<NDHWGK>,
+                                                                NDHWGK,
+                                                                F16,
+                                                                F16,
+                                                                ck::Tuple<F16>,
+                                                                F16,
+                                                                PassThrough,
+                                                                PassThrough,
+                                                                Bilinear>>>& instances);
+#endif
+
+#ifdef CK_ENABLE_FP32
+void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
+                                                                NDHWGC,
+                                                                GKZYXC,
+                                                                ck::Tuple<NDHWGK>,
+                                                                NDHWGK,
+                                                                F32,
+                                                                F32,
+                                                                ck::Tuple<F32>,
+                                                                F32,
+                                                                PassThrough,
+                                                                PassThrough,
+                                                                Bilinear>>>& instances);
+#endif
+
+#ifdef CK_ENABLE_INT8
+void add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_int8_instances(
+    std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
+                                                                NDHWGC,
+                                                                GKZYXC,
+                                                                ck::Tuple<NDHWGK>,
+                                                                NDHWGK,
+                                                                int8_t,
+                                                                int8_t,
+                                                                ck::Tuple<int8_t>,
+                                                                int8_t,
+                                                                PassThrough,
+                                                                PassThrough,
+                                                                Bilinear>>>& instances);
+#endif
+
+template <ck::index_t NumDimSpatial,
+          typename InLayout,
+          typename WeiLayout,
+          typename DLayouts,
+          typename OutLayout,
+          typename InDataType,
+          typename WeiDataType,
+          typename DDataTypes,
+          typename OutDataType,
+          typename ComputeType>
+struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD<
+    NumDimSpatial,
+    InLayout,
+    WeiLayout,
+    DLayouts,
+    OutLayout,
+    InDataType,
+    WeiDataType,
+    DDataTypes,
+    OutDataType,
+    ck::tensor_operation::element_wise::PassThrough,
+    ck::tensor_operation::element_wise::PassThrough,
+    ck::tensor_operation::element_wise::Bilinear,
+    ComputeType>>
+{
+    using DeviceOp =
+        DeviceGroupedConvFwdMultipleABD<NumDimSpatial,
+                                        InLayout,
+                                        WeiLayout,
+                                        DLayouts,
+                                        OutLayout,
+                                        InDataType,
+                                        WeiDataType,
+                                        DDataTypes,
+                                        OutDataType,
+                                        ck::tensor_operation::element_wise::PassThrough,
+                                        ck::tensor_operation::element_wise::PassThrough,
+                                        ck::tensor_operation::element_wise::Bilinear,
+                                        ComputeType>;
+
+    static auto GetInstances()
+    {
+        std::vector<std::unique_ptr<DeviceOp>> op_ptrs;
+        if constexpr(NumDimSpatial == 3 && is_same_v<InLayout, NDHWGC> &&
+                     is_same_v<WeiLayout, GKZYXC> && is_same_v<OutLayout, NDHWGK> &&
+                     DLayouts::Size() == 1 && is_same_v<tuple_element_t<0, DLayouts>, NDHWGK>)
+        {
+#ifdef CK_ENABLE_FP32
+            if constexpr(is_same_v<InDataType, float> && is_same_v<WeiDataType, float> &&
+                         is_same_v<OutDataType, float>)
+            {
+                add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instances(
+                    op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_FP16
+            if constexpr(is_same_v<InDataType, half_t> && is_same_v<WeiDataType, half_t> &&
+                         is_same_v<OutDataType, half_t> && is_same_v<ComputeType, half_t>)
+            {
+                add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instances(
+                    op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_BF16
+            if constexpr(is_same_v<InDataType, ck::bhalf_t> &&
+                         is_same_v<WeiDataType, ck::bhalf_t> && is_same_v<OutDataType, ck::bhalf_t>)
+            {
+                add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
+                    op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_INT8
+            if constexpr(is_same_v<InDataType, int8_t> && is_same_v<WeiDataType, int8_t> &&
+                         is_same_v<OutDataType, int8_t>)
+            {
+                add_device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_int8_instances(
+                    op_ptrs);
+            }
+#endif
+        }
+
+        return op_ptrs;
+    }
+};
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

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

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -97,6 +97,35 @@ void add_device_grouped_gemm_xdl_fixed_nk_f16_i8_f16_mk_nk_mn_instances(
                                                          PassThrough,
                                                          PassThrough>>>& instances);
 
+// bf16_inputA i8_inputB
+#if defined(CK_ENABLE_BF16) && defined(CK_ENABLE_INT8)
+void add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_instances(
+    std::vector<std::unique_ptr<DeviceGroupedGemmFixedNK<Row,
+                                                         Row,
+                                                         Empty_Tuple,
+                                                         Row,
+                                                         BF16,
+                                                         I8,
+                                                         Empty_Tuple,
+                                                         BF16,
+                                                         PassThrough,
+                                                         PassThrough,
+                                                         PassThrough>>>& instances);
+
+void add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_instances(
+    std::vector<std::unique_ptr<DeviceGroupedGemmFixedNK<Row,
+                                                         Col,
+                                                         Empty_Tuple,
+                                                         Row,
+                                                         BF16,
+                                                         I8,
+                                                         Empty_Tuple,
+                                                         BF16,
+                                                         PassThrough,
+                                                         PassThrough,
+                                                         PassThrough>>>& instances);
+#endif
+
 template <typename ALayout,
           typename BLayout,
           typename ELayout,
@@ -180,6 +209,24 @@ struct DeviceOperationInstanceFactory<
             }
         }
 
+// bf16_i8_input
+#if defined(CK_ENABLE_BF16) && defined(CK_ENABLE_INT8)
+        if constexpr(is_same_v<ADataType, bhalf_t> && is_same_v<BDataType, int8_t> &&
+                     is_same_v<EDataType, bhalf_t>)
+        {
+            if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Row> &&
+                         is_same_v<ELayout, Row>)
+            {
+                add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_instances(op_ptrs);
+            }
+            if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
+                         is_same_v<ELayout, Row>)
+            {
+                add_device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_instances(op_ptrs);
+            }
+        }
+#endif
+
         return op_ptrs;
     }
 };

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

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 
@@ -17,7 +17,32 @@ namespace tensor_operation {
 namespace device {
 namespace instance {
 
-void add_device_permute_scale_f16_instances(
+#ifdef CK_ENABLE_FP16
+void add_device_permute_scale_1d_f16_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
+                                                  ck::Tuple<F16>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  1>>>&);
+
+void add_device_permute_scale_2d_f16_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
+                                                  ck::Tuple<F16>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  2>>>&);
+
+void add_device_permute_scale_3d_f16_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
+                                                  ck::Tuple<F16>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  3>>>&);
+
+void add_device_permute_scale_4d_f16_instances(
     std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
                                                   ck::Tuple<F16>,
                                                   PassThrough,
@@ -25,7 +50,50 @@ void add_device_permute_scale_f16_instances(
                                                   Scale,
                                                   4>>>&);
 
-void add_device_permute_scale_f32_instances(
+void add_device_permute_scale_5d_f16_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
+                                                  ck::Tuple<F16>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  5>>>&);
+
+void add_device_permute_scale_6d_f16_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F16>,
+                                                  ck::Tuple<F16>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  6>>>&);
+
+#endif
+
+#ifdef CK_ENABLE_FP32
+void add_device_permute_scale_1d_f32_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
+                                                  ck::Tuple<F32>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  1>>>&);
+
+void add_device_permute_scale_2d_f32_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
+                                                  ck::Tuple<F32>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  2>>>&);
+
+void add_device_permute_scale_3d_f32_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
+                                                  ck::Tuple<F32>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  3>>>&);
+
+void add_device_permute_scale_4d_f32_instances(
     std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
                                                   ck::Tuple<F32>,
                                                   PassThrough,
@@ -33,6 +101,23 @@ void add_device_permute_scale_f32_instances(
                                                   Scale,
                                                   4>>>&);
 
+void add_device_permute_scale_5d_f32_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
+                                                  ck::Tuple<F32>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  5>>>&);
+
+void add_device_permute_scale_6d_f32_instances(
+    std::vector<std::unique_ptr<DeviceElementwise<ck::Tuple<F32>,
+                                                  ck::Tuple<F32>,
+                                                  PassThrough,
+                                                  element_wise::UnarySquare,
+                                                  Scale,
+                                                  6>>>&);
+#endif
+
 template <typename InDataTypeTuple,
           typename OutDataTypeTuple,
           typename ElementwiseOperation,
@@ -57,15 +142,107 @@ struct DeviceOperationInstanceFactory<
     static auto GetInstances()
     {
         std::vector<std::unique_ptr<DeviceOp>> op_ptrs;
-        if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
-                     is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
+        if constexpr(NumDim == 1)
+        {
+#ifdef CK_ENABLE_FP32
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
+            {
+                add_device_permute_scale_1d_f32_instances(op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_FP16
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
+            {
+                add_device_permute_scale_1d_f16_instances(op_ptrs);
+            }
+#endif
+        }
+        else if constexpr(NumDim == 2)
+        {
+#ifdef CK_ENABLE_FP32
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
+            {
+                add_device_permute_scale_2d_f32_instances(op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_FP16
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
+            {
+                add_device_permute_scale_2d_f16_instances(op_ptrs);
+            }
+#endif
+        }
+        else if constexpr(NumDim == 3)
+        {
+#ifdef CK_ENABLE_FP32
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
+            {
+                add_device_permute_scale_3d_f32_instances(op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_FP16
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
+            {
+                add_device_permute_scale_3d_f16_instances(op_ptrs);
+            }
+#endif
+        }
+        else if constexpr(NumDim == 4)
+        {
+#ifdef CK_ENABLE_FP32
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
+            {
+                add_device_permute_scale_4d_f32_instances(op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_FP16
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
+            {
+                add_device_permute_scale_4d_f16_instances(op_ptrs);
+            }
+#endif
+        }
+        else if constexpr(NumDim == 5)
         {
-            add_device_permute_scale_f32_instances(op_ptrs);
+#ifdef CK_ENABLE_FP32
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
+            {
+                add_device_permute_scale_5d_f32_instances(op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_FP16
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
+            {
+                add_device_permute_scale_5d_f16_instances(op_ptrs);
+            }
+#endif
         }
-        else if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
-                          is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
+        else if constexpr(NumDim == 6)
         {
-            add_device_permute_scale_f16_instances(op_ptrs);
+#ifdef CK_ENABLE_FP32
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F32>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F32>>)
+            {
+                add_device_permute_scale_6d_f32_instances(op_ptrs);
+            }
+#endif
+#ifdef CK_ENABLE_FP16
+            if constexpr(is_same_v<InDataTypeTuple, ck::Tuple<F16>> &&
+                         is_same_v<OutDataTypeTuple, ck::Tuple<F16>>)
+            {
+                add_device_permute_scale_6d_f16_instances(op_ptrs);
+            }
+#endif
         }
         return op_ptrs;
     }

library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.cpp → library/include/ck/library/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.hpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "ck/ck.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_elementwise_scale_impl.hpp"
-#include "ck/utility/data_type.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 Pass    = ck::tensor_operation::element_wise::PassThrough;
-using UnaryOp = ck::tensor_operation::element_wise::UnarySquare;
-using Scale   = ck::tensor_operation::element_wise::Scale;
-
-// clang-format off
-using device_permute_scale_f16_instances =
-    std::tuple <
-        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 1, ck::Sequence<1>, ck::Sequence<1>>,
-        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 8, ck::Sequence<1>, ck::Sequence<1>>,
-        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 4, ck::Sequence<1>, ck::Sequence<1>>,
-        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4, 2, ck::Sequence<1>, ck::Sequence<1>>
-    >;
-
-using device_permute_scale_f32_instances = std::tuple<
-         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 1, ck::Sequence<1>, ck::Sequence<1>>,
-         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 8, ck::Sequence<1>, ck::Sequence<1>>,
-         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 4, ck::Sequence<1>, ck::Sequence<1>>,
-         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4, 2, ck::Sequence<1>, ck::Sequence<1>>
-    >;
-// clang-format on
-
-void add_device_permute_scale_f16_instances(
-    std::vector<std::unique_ptr<
-        DeviceElementwise<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, 4>>>& instances)
-{
-    add_device_operation_instances(instances, device_permute_scale_f16_instances{});
-}
-
-void add_device_permute_scale_f32_instances(
-    std::vector<std::unique_ptr<
-        DeviceElementwise<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, 4>>>& instances)
-{
-    add_device_operation_instances(instances, device_permute_scale_f32_instances{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_elementwise_scale_impl.hpp"
+#include "ck/utility/data_type.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+using F16 = ck::half_t;
+using F32 = float;
+
+using Pass    = ck::tensor_operation::element_wise::PassThrough;
+using UnaryOp = ck::tensor_operation::element_wise::UnarySquare;
+using Scale   = ck::tensor_operation::element_wise::Scale;
+
+// clang-format off
+template <index_t NDims>
+using device_permute_scale_f16_instances =
+    std::tuple <
+        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 1, ck::Sequence<1>, ck::Sequence<1>>,
+        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 8, ck::Sequence<8>, ck::Sequence<1>>,
+        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 4, ck::Sequence<4>, ck::Sequence<1>>,
+        DeviceElementwiseImpl<ck::Tuple<F16>, ck::Tuple<F16>, Pass, UnaryOp, Scale, NDims, 2, ck::Sequence<2>, ck::Sequence<1>>
+    >;
+
+template <index_t NDims>
+using device_permute_scale_f32_instances = std::tuple<
+         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 1, ck::Sequence<1>, ck::Sequence<1>>,
+         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 8, ck::Sequence<8>, ck::Sequence<1>>,
+         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 4, ck::Sequence<4>, ck::Sequence<1>>,
+         DeviceElementwiseImpl<ck::Tuple<F32>, ck::Tuple<F32>, Pass, UnaryOp, Scale, NDims, 2, ck::Sequence<2>, ck::Sequence<1>>
+    >;
+// clang-format on
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

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

@@ -111,6 +111,12 @@ list(APPEND GEMM_INSTANCES
     device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_kn_mn_instance.cpp
     device_gemm_xdl_c_shuffle_fp8_fp8_fp8_km_nk_mn_instance.cpp)
 
+list(APPEND GEMM_INSTANCES
+    device_gemm_wmma_f16_f16_f16_mk_kn_mn_instance.cpp
+    device_gemm_wmma_f16_f16_f16_mk_nk_mn_instance.cpp
+    device_gemm_wmma_f16_f16_f16_km_kn_mn_instance.cpp
+    device_gemm_wmma_f16_f16_f16_km_nk_mn_instance.cpp)
+
 add_instance_library(device_gemm_instance ${GEMM_INSTANCES})
 
 set(ENABLE_PIPELINE_V2_OPT)

library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_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_wmma.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;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+
+// Compilation parameters for a[k, m] * b[k, n] = c[m, n]
+using device_gemm_wmma_f16_f16_f16_km_kn_mn_instances = std::tuple<
+    // clang-format off
+        //######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle|           A|           B|           C|          GEMM| NumPrefetch| Block|  MPer|  NPer|  KPer| K1| MPer| NPer|      M|       N|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
+        //######################|        |        |        |  Type|  Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise|Specialization|            |  Size| Block| Block| Block|   | WMMA| WMMA| Repeat|  Repeat|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN|  MRepeat|  MRepeat|        ClusterLengths|       ScalarPerVector|
+        //######################|        |        |        |      |      |      |        |         |   Operation|   Operation|   Operation|              |            |      |      |      |      |   |     |     |       |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          | PerStore| PerStore|      MBlock_MPerBlock|                      |
+        //######################|        |        |        |      |      |      |        |         |            |            |            |              |            |      |      |      |      |   |     |     |       |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |         |         |      NBlock_NPerBlock|                      |
+        /* Prefetch 2, consume enormous vgpr resource*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   256,   128,   128,    32,  8,   16,   16,      4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   128,   128,    64,    64,  8,   16,   16,      4,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    64,    64,    32,    32,  8,   16,   16,      4,       1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    32,    16,    16,    32,  8,   16,   16,      1,       1,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   256,    64,  8,   16,   16,      4,       4,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   128,    64,  8,   16,   16,      4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   160,    64,  8,   16,   16,      2,       5,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 64, 1,  4>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   128,   128,    32,  8,   16,   16,      4,       4,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   256,    64,    64,  8,   16,   16,      8,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,   256,    64,  8,   16,   16,      2,       8,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,    80,    64,  8,   16,   16,      1,       5,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<8, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 64, 1,  2>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    16,    64,    64,  8,   16,   16,      1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    64,    32,    64,  8,   16,   16,      4,       1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    32,    64,    64,  8,   16,   16,      2,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    32,    64,  8,   16,   16,      1,       2,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    16,    64,  8,   16,   16,      1,       1,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>
+    // clang-format on
+    >;
+
+void add_device_gemm_wmma_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_wmma_f16_f16_f16_km_kn_mn_instances{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_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_wmma.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;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+
+// Compilation parameters for a[k, m] * b[n, k] = c[m, n]
+using device_gemm_wmma_f16_f16_f16_km_nk_mn_instances = std::tuple<
+    // clang-format off
+        //######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle|           A|           B|           C|          GEMM| NumPrefetch| Block|  MPer|  NPer|  KPer| K1| MPer| NPer|      M|       N|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
+        //######################|        |        |        |  Type|  Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise|Specialization|            |  Size| Block| Block| Block|   | WMMA| WMMA| Repeat|  Repeat|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN|  MRepeat|  MRepeat|        ClusterLengths|       ScalarPerVector|
+        //######################|        |        |        |      |      |      |        |         |   Operation|   Operation|   Operation|              |            |      |      |      |      |   |     |     |       |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          | PerStore| PerStore|      MBlock_MPerBlock|                      |
+        //######################|        |        |        |      |      |      |        |         |            |            |            |              |            |      |      |      |      |   |     |     |       |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |         |         |      NBlock_NPerBlock|                      |
+        /* Prefetch 2, consume enormous vgpr resource*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   256,   128,   128,    32,  8,   16,   16,      4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   128,   128,    64,    64,  8,   16,   16,      4,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    64,    64,    32,    32,  8,   16,   16,      4,       1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    32,    16,    16,    32,  8,   16,   16,      1,       1,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   256,    64,  8,   16,   16,      4,       4,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   128,    64,  8,   16,   16,      4,       2,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   160,    64,  8,   16,   16,      2,       5,     S<4, 64, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 64, 1,  4>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   128,   128,    32,  8,   16,   16,      4,       4,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   256,    64,    64,  8,   16,   16,      8,       2,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,   256,    64,  8,   16,   16,      2,       8,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,    80,    64,  8,   16,   16,      1,       5,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 64, 1,  2>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    16,    64,    64,  8,   16,   16,      1,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    64,    32,    64,  8,   16,   16,      4,       1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    32,    64,    64,  8,   16,   16,      2,       2,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    32,    64,  8,   16,   16,      1,       2,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        DeviceGemmWmma_CShuffle<      Col,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    16,    64,  8,   16,   16,      1,       1,     S<2, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              1,              8,      true,     S<2, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>
+    // clang-format on
+    >;
+
+void add_device_gemm_wmma_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_wmma_f16_f16_f16_km_nk_mn_instances{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_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_wmma.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;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+
+// Compilation parameters for a[m, k] * b[k, n] = c[m, n]
+using device_gemm_wmma_f16_f16_f16_mk_kn_mn_instances = std::tuple<
+    // clang-format off
+        //######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle|           A|           B|           C|          GEMM| NumPrefetch| Block|  MPer|  NPer|  KPer| K1| MPer| NPer|      M|       N|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
+        //######################|        |        |        |  Type|  Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise|Specialization|            |  Size| Block| Block| Block|   | WMMA| WMMA| Repeat|  Repeat|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN|  MRepeat|  MRepeat|        ClusterLengths|       ScalarPerVector|
+        //######################|        |        |        |      |      |      |        |         |   Operation|   Operation|   Operation|              |            |      |      |      |      |   |     |     |       |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          | PerStore| PerStore|      MBlock_MPerBlock|                      |
+        //######################|        |        |        |      |      |      |        |         |            |            |            |              |            |      |      |      |      |   |     |     |       |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |         |         |      NBlock_NPerBlock|                      |
+        /* Prefetch 2, consume enormous vgpr resource*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   256,   128,   128,    32,  8,   16,   16,      4,       2,     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,              1,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   128,   128,    64,    64,  8,   16,   16,      4,       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,              1,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    64,    64,    32,    32,  8,   16,   16,      4,       1,     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,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    32,    16,    16,    32,  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<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   256,    64,  8,   16,   16,      4,       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,              1,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   128,    64,  8,   16,   16,      4,       2,     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,              1,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   160,    64,  8,   16,   16,      2,       5,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,      true,        1,        1,       S<1, 64, 1,  4>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   128,   128,    32,  8,   16,   16,      4,       4,     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,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   256,    64,    64,  8,   16,   16,      8,       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,              1,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,   256,    64,  8,   16,   16,      2,       8,     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,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,    80,    64,  8,   16,   16,      1,       5,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,      true,        1,        1,       S<1, 64, 1,  2>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    16,    64,    64,  8,   16,   16,      1,       2,     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,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    64,    32,    64,  8,   16,   16,      4,       1,     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,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    32,    64,    64,  8,   16,   16,      2,       2,     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,              1,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    32,    64,  8,   16,   16,      1,       2,     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,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    16,    64,  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<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>
+#if 0
+        /* Prefetch 2, consume enormous vgpr resource*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   256,   128,   128,    32,  8,   16,   16,      4,       2,     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,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   128,   128,    64,    64,  8,   16,   16,      4,       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,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    64,    64,    32,    32,  8,   16,   16,      4,       1,     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,              2,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    32,    16,    16,    32,  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<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   256,    64,  8,   16,   16,      4,       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,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   128,    64,  8,   16,   16,      4,       2,     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,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   160,    64,  8,   16,   16,      2,       5,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,      true,        1,        1,       S<1, 64, 1,  4>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   128,   128,    32,  8,   16,   16,      4,       4,     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,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   256,    64,    64,  8,   16,   16,      8,       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,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,   256,    64,  8,   16,   16,      2,       8,     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,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,    80,    64,  8,   16,   16,      1,       5,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,      true,        1,        1,       S<1, 64, 1,  2>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    16,    64,    64,  8,   16,   16,      1,       2,     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,              2,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    64,    32,    64,  8,   16,   16,      4,       1,     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,              2,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    32,    64,    64,  8,   16,   16,      2,       2,     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,              2,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    32,    64,  8,   16,   16,      1,       2,     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,              2,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    16,    64,  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<0, 2, 1>,     S<0, 2, 1>,             1,              2,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 2, consume enormous vgpr resource*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   256,   128,   128,    32,  8,   16,   16,      4,       2,     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,              4,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   128,   128,    64,    64,  8,   16,   16,      4,       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,              4,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    64,    64,    32,    32,  8,   16,   16,      4,       1,     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,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    32,    16,    16,    32,  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<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   256,    64,  8,   16,   16,      4,       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,              4,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   128,    64,  8,   16,   16,      4,       2,     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,              4,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   160,    64,  8,   16,   16,      2,       5,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,      true,        1,        1,       S<1, 64, 1,  4>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   128,   128,    32,  8,   16,   16,      4,       4,     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,              4,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   256,    64,    64,  8,   16,   16,      8,       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,              4,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,   256,    64,  8,   16,   16,      2,       8,     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,              4,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,    80,    64,  8,   16,   16,      1,       5,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,      true,        1,        1,       S<1, 64, 1,  2>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    16,    64,    64,  8,   16,   16,      1,       2,     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,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    64,    32,    64,  8,   16,   16,      4,       1,     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,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    32,    64,    64,  8,   16,   16,      2,       2,     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,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    32,    64,  8,   16,   16,      1,       2,     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,              4,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    16,    64,  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<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 2, consume enormous vgpr resource*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   256,   128,   128,    32,  8,   16,   16,      4,       2,     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,              8,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   128,   128,    64,    64,  8,   16,   16,      4,       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,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    64,    64,    32,    32,  8,   16,   16,      4,       1,     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,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    32,    16,    16,    32,  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<0, 2, 1>,     S<0, 2, 1>,             1,              8,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   256,    64,  8,   16,   16,      4,       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,              8,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   128,    64,  8,   16,   16,      4,       2,     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,              8,              8,      true,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   160,    64,  8,   16,   16,      2,       5,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              8,              8,      true,        1,        1,       S<1, 64, 1,  4>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   128,   128,    32,  8,   16,   16,      4,       4,     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,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   256,    64,    64,  8,   16,   16,      8,       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,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,   256,    64,  8,   16,   16,      2,       8,     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,              8,              8,      true,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,    80,    64,  8,   16,   16,      1,       5,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              8,              8,      true,        1,        1,       S<1, 64, 1,  2>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    16,    64,    64,  8,   16,   16,      1,       2,     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,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    64,    32,    64,  8,   16,   16,      4,       1,     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,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    32,    64,    64,  8,   16,   16,      2,       2,     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,              8,              8,      true,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    32,    64,  8,   16,   16,      1,       2,     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,              8,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Row,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    16,    64,  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<0, 2, 1>,     S<0, 2, 1>,             1,              8,              8,      true,        1,        1,       S<1, 16, 1,  2>,                      8>
+#endif
+    // clang-format on
+    >;
+
+void add_device_gemm_wmma_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_wmma_f16_f16_f16_mk_kn_mn_instances{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_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_wmma.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;
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+
+// Compilation parameters for a[m, k] * b[n, k] = c[m, n]
+using device_gemm_wmma_f16_f16_f16_mk_nk_mn_instances = std::tuple<
+    // clang-format off
+        //######################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle|           A|           B|           C|           GEMM| NumPrefetch| Block|  MPer|  NPer|  KPer| K1| MPer| NPer|      M|       N|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CShuffleBlockTransfer| CShuffleBlockTransfer|
+        //######################|        |        |        |  Type|  Type|  Type|    Type| DataType| Elementwise| Elementwise| Elementwise| Specialization|            |  Size| Block| Block| Block|   | WMMA| WMMA| Repeat|  Repeat|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN|  MRepeat|  MRepeat|        ClusterLengths|       ScalarPerVector|
+        //######################|        |        |        |      |      |      |        |         |   Operation|   Operation|   Operation|               |            |      |      |      |      |   |     |     |       |        | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          | PerStore| PerStore|      MBlock_MPerBlock|                      |
+        //######################|        |        |        |      |      |      |        |         |            |            |            |               |            |      |      |      |      |   |     |     |       |        |                |               |               |               |               |               |          |                |               |               |              |               |               |          |         |         |      NBlock_NPerBlock|                      |
+        /* Prefetch 2, consume enormous vgpr resource*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   256,   128,   128,    32,  8,   16,   16,      4,       2,     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,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,   128,   128,    64,    64,  8,   16,   16,      4,       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,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    64,    64,    32,    32,  8,   16,   16,      4,       1,     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,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           2,    32,    16,    16,    32,  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,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        /* Prefetch 1, prefer larger KPerBlock value for better latency hiding*/
+        // 8 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   256,    64,  8,   16,   16,      4,       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,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   128,    64,  8,   16,   16,      4,       2,     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,        1,        1,       S<1, 32, 1,  8>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   256,   128,   160,    64,  8,   16,   16,      2,       5,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 64, 1,  4>,                      8>,
+        // 4 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   128,   128,    32,  8,   16,   16,      4,       4,     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,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,   256,    64,    64,  8,   16,   16,      8,       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,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,   256,    64,  8,   16,   16,      2,       8,     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,        1,        1,       S<1, 32, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,   128,    64,    80,    64,  8,   16,   16,      1,       5,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,      true,        1,        1,       S<1, 64, 1,  2>,                      8>,
+        // 2 Waves
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    16,    64,    64,  8,   16,   16,      1,       2,     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,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    64,    32,    64,  8,   16,   16,      4,       1,     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,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    64,    32,    64,    64,  8,   16,   16,      2,       2,     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,        1,        1,       S<1, 16, 1,  4>,                      8>,
+        // 1 Wave
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    32,    64,  8,   16,   16,      1,       2,     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,        1,        1,       S<1, 16, 1,  2>,                      8>,
+        DeviceGemmWmma_CShuffle<      Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough, GemmMNKPadding,           1,    32,    16,    16,    64,  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,        1,        1,       S<1, 16, 1,  2>,                      8>
+    // clang-format on
+    >;
+
+void add_device_gemm_wmma_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_wmma_f16_f16_f16_mk_nk_mn_instances{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp

@@ -34,6 +34,15 @@ static constexpr auto MNPadding = ck::tensor_operation::device::GemmSpecializati
 
 static constexpr auto MNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
 
+using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_generic_instances = std::tuple<
+    // clang-format off
+        //#####################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle|           A|           B|           C|           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|          LoopScheduler|                    Pipeline|
+        //#####################|        |        |        |  Type|  Type|  Type|    Type| DataType| 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|                       |                            |
+        DeviceGemm_Xdl_CShuffle<     Row,      Row,    Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough,     MNKPadding,        1,   128,   128,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              1,              8,         1,           1,           1,               S<1, 16, 1, 8>,              1,  LoopScheduler::Default,        PipelineVersion::v1>
+    // clang-format on
+    >;
+
 // Compilation parameters for a[m, k] * b[k, n] = c[m, n]
 template <ck::tensor_operation::device::GemmSpecialization GemmSpec>
 using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instances = std::tuple<
@@ -108,6 +117,9 @@ void add_device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instances(
         DeviceGemm<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances)
 {
+    add_device_operation_instances(
+        instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_generic_instances{});
+
     add_device_operation_instances(
         instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instances<GemmDefault>{});
 

library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp

@@ -32,6 +32,17 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa
 static constexpr auto MNPadding   = ck::tensor_operation::device::GemmSpecialization::MNPadding;
 static constexpr auto MNKPadding  = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
 
+// Compilation parameters for a[m, k] * b[n, k] = c[m, n]
+using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_generic_instances = std::tuple<
+    // clang-format off
+        //#####################| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle|           A|           B|           C|           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|          LoopScheduler|                    Pipeline|
+        //#####################|        |        |        |  Type|  Type|  Type|    Type| DataType| 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|                       |                            |
+        //#####################|        |        |        |      |      |      |        |         |            |            |            |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |                       |                            |
+        DeviceGemm_Xdl_CShuffle<     Row,     Col,     Row,   F16,   F16,   F16,     F32,      F16, PassThrough, PassThrough, PassThrough,     MNKPadding,        1,   128,   128,   128,    32,   8,   8,   32,   32,    4,    2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,           1,           1,               S<1, 16, 1, 8>,              1,  LoopScheduler::Default,        PipelineVersion::v1>
+    // clang-format on
+    >;
+
 template <ck::tensor_operation::device::GemmSpecialization GemmSpec>
 // Compilation parameters for a[m, k] * b[n, k] = c[m, n]
 using device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instances = std::tuple<
@@ -97,6 +108,9 @@ void add_device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instances(
         DeviceGemm<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances)
 {
+    add_device_operation_instances(
+        instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_generic_instances{});
+
     add_device_operation_instances(
         instances, device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instances<GemmDefault>{});
 

library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp

@@ -36,32 +36,32 @@ static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecial
 // 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>,
+        //################################|      A|      B|        Ds|      E| AData| BData|  AccData| CShuffle|   DsData| EData|            A|           B|         CDE|           GEMM| Prefetch| 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| DataType|     Type|  Type|  Elementwise| Elementwise| Elementwise| Specialization|    Stage|  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear,    GemmDefault,        1,   256,   128,   128,    64,  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear,    GemmDefault,        1,   128,    64,    64,    64,  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear,    GemmDefault,        1,    64,    32,    32,    64,  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear,    GemmDefault,        1,    32,    16,    16,    64,  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>
+        //################################|      A|      B|        Ds|      E| AData| BData|  AccData| CShuffle|   DsData| EData|            A|           B|         CDE|           GEMM| Prefetch| 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| DataType|     Type|  Type|  Elementwise| Elementwise| Elementwise| Specialization|    Stage|  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,   256,   128,   128,    64,  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,   128,    64,    64,    64,  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,    64,    32,    32,    64,  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,    32,    16,    16,    64,  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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,   256,   128,   128,    64,   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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,   128,    64,    64,    64,   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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,    64,    32,    32,    64,   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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,    32,    16,    16,    64,   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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,   256,   128,   128,    32,   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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,   128,    64,    64,    32,   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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,    64,    32,    32,    32,   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,      I32,      I32, I8_Tuple,    I8,  PassThrough, PassThrough,    Bilinear, GemmMNKPadding,        1,    32,    16,    16,    32,   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
     >;