diff --git a/include/ck/tensor_operation/gpu/device/device_base.hpp b/include/ck/tensor_operation/gpu/device/device_base.hpp
index cf8a203562..5946daf21e 100644
--- a/include/ck/tensor_operation/gpu/device/device_base.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_base.hpp
@@ -37,42 +37,6 @@ struct BaseInvoker
     virtual ~BaseInvoker() {}
 };
 
-struct BaseParameters
-{
-    BaseParameters()                   = default;
-    BaseParameters(const BaseParameters&) = default;
-    BaseParameters& operator=(const BaseParameters&) = default;
-
-    virtual void SetAElementOp(const std::string&) {}
-
-    virtual void SetBElementOp(const std::string&) {}
-
-    virtual void SetCDEElementOp(const std::string&) {}
-
-    virtual void SetDsLayout(const std::string&) {}
-
-    virtual void SetDsDataType(const std::string&) {}
-
-    virtual void SetGemmSpec(const index_t, const index_t, const index_t) {}
-
-    virtual index_t GetGridSize(const index_t, const index_t) 
-    {
-        return 0;
-    }
-
-    virtual index_t GetBlockSize()
-    {
-        return 0;
-    }
-
-    virtual std::string GetParametersString()
-    {
-        return "";
-    }
-
-    virtual ~BaseParameters() {}
-};
-
 struct BaseOperator
 {
     BaseOperator()                    = default;
diff --git a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
index f9db70c83a..9113bb7b74 100644
--- a/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
@@ -51,26 +51,6 @@ struct DeviceGemmMultipleD : public BaseOperator
                         CDEElementwiseOperation cde_element_op) = 0;
 
     virtual std::unique_ptr<BaseInvoker> MakeInvokerPointer() = 0;
-
-    virtual std::unique_ptr<BaseParameters> MakeParametersPointer() 
-    {
-        return std::make_unique<BaseParameters>(BaseParameters{});
-    }
-
-    virtual index_t GetBlockSize() const
-    {
-        return 0;
-    }
-
-    virtual index_t GetMPerBlock() const
-    {
-        return 0;
-    }
-
-    virtual index_t GetNPerBlock() const
-    {
-        return 0;
-    }
 };
 
 } // namespace device
diff --git a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
index 779e865d32..74da68f88a 100644
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
@@ -699,195 +699,6 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout,
         return str.str();
     }
 
-    struct Parameters : BaseParameters
-    {
-        template <class S>
-        static std::string GetSequenceString(S s)
-        {
-            auto str = std::stringstream();
-            str << "ck::Sequence<";
-            auto size = s.Size();
-            for(int i = 0; i < size; ++i)
-            {
-                str << s.At(i);
-                if(i < size - 1)
-                    str << ",";
-            }
-            str << ">";
-            return str.str();
-        }
-
-        template <class T>
-        static std::string GetTypeString(T)
-        {
-            return "";
-        }
-
-        template <>
-        static std::string GetTypeString<float>(float)
-        {
-            return "float";
-        }
-
-        template <>
-        static std::string GetTypeString<ck::half_t>(ck::half_t)
-        {
-            return "ck::half_t";
-        }
-
-        template <>
-        static std::string
-            GetTypeString<tensor_layout::gemm::RowMajor>(tensor_layout::gemm::RowMajor)
-        {
-            return "ck::tensor_layout::gemm::RowMajor";
-        }
-
-        template <>
-        static std::string
-            GetTypeString<tensor_layout::gemm::ColumnMajor>(tensor_layout::gemm::ColumnMajor)
-        {
-            return "ck::tensor_layout::gemm::ColumnMajor";
-        }
-
-        template <class T>
-        static std::string GetTupleString(T t)
-        {
-            auto str = std::stringstream();
-            str << "ck::Tuple<";
-            static_for<0, t.Size(), 1>{}([&](auto i) {
-                str << GetTypeString(t.At(i));
-                if(i < t.Size() - 1)
-                    str << ",";
-            });
-            str << ">";
-            return str.str();
-        }
-
-        template <>
-        static std::string GetTupleString<Tuple<>>(Tuple<>)
-        {
-            return "ck::Tuple<>";
-        }
-
-        void SetAElementOp(const std::string& s) override { a_elementwise_op = s; }
-
-        void SetBElementOp(const std::string& s) override { b_elementwise_op = s; }
-
-        void SetCDEElementOp(const std::string& s) override { cde_elementwise_op = s; }
-
-        void SetDsLayout(const std::string& s) override { ds_layout = s; }
-
-        void SetDsDataType(const std::string& s) override { ds_data_type = s; }
-
-        void SetGemmSpec(const index_t m, const index_t n, const index_t k) override
-        {
-            std::string spec = "";
-            if(math::integer_divide_ceil(m, MPerBlock) * MPerBlock - m != 0)
-                spec += "M";
-            if(math::integer_divide_ceil(n, NPerBlock) * NPerBlock - n != 0)
-                spec += "N";
-            if(math::integer_divide_ceil(k, KPerBlock) * KPerBlock - k != 0)
-                spec += "K";
-            if(spec == "")
-                gemm_spec = "ck::tensor_operation::device::GemmSpecialization::Default";
-            else
-                gemm_spec = "ck::tensor_operation::device::GemmSpecialization::" + spec + "Padding";
-        }
-
-        index_t GetGridSize(const index_t m, const index_t n) override
-        {
-            return math::integer_divide_ceil(m, MPerBlock) *
-                   math::integer_divide_ceil(n, NPerBlock);
-        }
-
-        index_t GetBlockSize() override { return BlockSize; }
-
-        std::string GetParametersString() override
-        {
-            auto str = std::stringstream();
-
-            std::map<LoopScheduler, std::string> LoopSchedToString{
-                {LoopScheduler::Default, "ck::LoopScheduler::Default"},
-                {LoopScheduler::Interwave, "ck::LoopScheduler::Interwave"}};
-
-            std::map<PipelineVersion, std::string> PipelineVersionToString{
-                {PipelineVersion::v1, "ck::PipelineVersion::v1"},
-                {PipelineVersion::v2, "ck::PipelineVersion::v2"}};
-
-            // clang-format off
-            str << "ck::tensor_operation::device::DeviceGemmMultipleD_Xdl_CShuffle"
-                << "<"
-                << GetTypeString(ALayout{}) << ", "
-                << GetTypeString(BLayout{}) << ", "
-                << ds_layout << ", "
-                << GetTypeString(ELayout{}) << ", "
-                << GetTypeString(ADataType{}) << ", "
-                << GetTypeString(BDataType{}) << ", "
-                << GetTypeString(AccDataType{}) << ", "
-                << GetTypeString(CShuffleDataType{}) << ", "
-                << ds_data_type << ", "
-                << GetTypeString(EDataType{}) << ", "
-                << a_elementwise_op << ", "
-                << b_elementwise_op << ", "
-                << cde_elementwise_op << ", "
-                << gemm_spec << ", "
-                << NumGemmKPrefetchStage << ", "
-                << BlockSize << ", "
-                << MPerBlock << ", "
-                << NPerBlock << ", "
-                << KPerBlock << ", "
-                << AK1 << ", "
-                << BK1 << ", "
-                << MPerXDL << ", "
-                << NPerXDL << ", "
-                << MXdlPerWave << ", "
-                << NXdlPerWave << ", "
-                << GetSequenceString(ABlockTransferThreadClusterLengths_AK0_M_AK1{}) << ", "
-                << GetSequenceString(ABlockTransferThreadClusterArrangeOrder{}) << ", "
-                << GetSequenceString(ABlockTransferSrcAccessOrder{}) << ", "
-                << ABlockTransferSrcVectorDim << ", "
-                << ABlockTransferSrcScalarPerVector << ", "
-                << ABlockTransferDstScalarPerVector_AK1 << ", "
-                << ABlockLdsExtraM << ", "
-                << GetSequenceString(BBlockTransferThreadClusterLengths_BK0_N_BK1{}) << ", "
-                << GetSequenceString(BBlockTransferThreadClusterArrangeOrder{}) << ", "
-                << GetSequenceString(BBlockTransferSrcAccessOrder{}) << ", "
-                << BBlockTransferSrcVectorDim << ", "
-                << BBlockTransferSrcScalarPerVector << ", "
-                << BBlockTransferDstScalarPerVector_BK1 << ", "
-                << BBlockLdsExtraN << ", "
-                << CShuffleMXdlPerWavePerShuffle << ", "
-                << CShuffleNXdlPerWavePerShuffle << ", "
-                << GetSequenceString(CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock{}) << ", "
-                << CDEBlockTransferScalarPerVector_NPerBlock << ", "
-                << LoopSchedToString[LoopSched] << ", "
-                << PipelineVersionToString[PipelineVer]
-                << ">";
-            // clang-format on
-
-            return str.str();
-        }
-
-        std::string a_elementwise_op   = "ck::tensor_operation::element_wise::PassThrough";
-        std::string b_elementwise_op   = "ck::tensor_operation::element_wise::PassThrough";
-        std::string cde_elementwise_op = "ck::tensor_operation::element_wise::PassThrough";
-        std::string ds_layout          = "ck::Tuple<>";
-        std::string ds_data_type       = "ck::Tuple<>";
-        std::string gemm_spec          = "ck::tensor_operation::device::GemmSpecialization::" +
-                                getGemmSpecializationString(GemmSpec);
-    };
-
-    std::unique_ptr<BaseParameters> MakeParametersPointer() override
-    {
-        return std::make_unique<Parameters>(Parameters{});
-    }
-
-    index_t GetBlockSize() const override { return BlockSize; }
-
-    index_t GetMPerBlock() const override { return MPerBlock; }
-
-    index_t GetNPerBlock() const override { return NPerBlock; }
-
     template <class ADesc, class BDesc, class DsDesc, class EDesc>
     struct Descriptor
     {
diff --git a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
index cd4842dfa9..ceb2b665b9 100644
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
@@ -4,7 +4,7 @@
 #pragma once
 
 #include "ck/utility/data_type.hpp"
-#include "ck/utility/math.hpp"
+#include "ck/utility/math_v2.hpp"
 #include "ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp"
 #include "ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp"
 #include "ck/tensor_operation/gpu/element/quantization_operation.hpp"
diff --git a/library/src/tensor_operation_instance/gpu/CMakeLists.txt b/library/src/tensor_operation_instance/gpu/CMakeLists.txt
index e9a1dccbc7..c206c4dc04 100644
--- a/library/src/tensor_operation_instance/gpu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/CMakeLists.txt
@@ -21,6 +21,7 @@ ENDFOREACH()
 add_library(device_operations STATIC ${CK_DEVICE_INSTANCES})
 add_library(composablekernels::device_operations ALIAS device_operations)
 
+
 set(DEV_OPS_INC_DIRS
     ${PROJECT_SOURCE_DIR}/include/ck/
     ${PROJECT_SOURCE_DIR}/library/include/ck/
@@ -55,7 +56,7 @@ target_compile_options(device_operations PRIVATE
 )
 
 # install(TARGETS device_operations LIBRARY DESTINATION lib)
-rocm_install(TARGETS device_operations 
+rocm_install(TARGETS device_operations
         EXPORT device_operationsTargets)
 
 rocm_install(DIRECTORY ${DEV_OPS_INC_DIRS} DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/ck)
diff --git a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/gemm_add_add_fastgelu_instances.hpp b/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/gemm_add_add_fastgelu_instances.hpp
deleted file mode 100644
index b425abbb92..0000000000
--- a/library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/gemm_add_add_fastgelu_instances.hpp
+++ /dev/null
@@ -1,252 +0,0 @@
-// SPDX-License-Identifier: MIT 
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
-
-#pragma once
-
-#include <cstdlib>
-#include <vector>
-#include <memory>
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-struct gemm_add_add_fastgelu_instances
-{
-    static inline std::vector<std::string> device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance  = 
-    {
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 2, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 2, 32, 32, 2, 4, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, 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, 4, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 2, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 2, 32, 32, 2, 2, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 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, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 2, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 2, 32, 32, 2, 2, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 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, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 2, 32, 32, 2, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, 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, 1, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 2, 32, 32, 1, 2, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 2, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 2, 32, 32, 2, 4, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, 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, 4, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 2, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 2, 32, 32, 2, 2, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 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, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 2, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 2, 32, 32, 2, 2, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 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, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 2, 32, 32, 2, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, 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, 1, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 2, 32, 32, 1, 2, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 2, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 2, 32, 32, 2, 4, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, 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, 4, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 2, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 2, 32, 32, 2, 2, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 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, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 2, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 2, 32, 32, 2, 2, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 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, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 2, 32, 32, 2, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, 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, 1, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 2, 32, 32, 1, 2, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, 1, 1, S<1,16,1,4>, 1, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, 1, 1, S<1,16,1,4>, 1, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, 1, 1, S<1,16,1,4>, 1, LoopScheduler::Default, PipelineVersion::v2>"
-    };
-
-    static inline std::vector<std::string> device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance  = 
-    {
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 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, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 8, 32, 32, 2, 4, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 8, 32, 32, 2, 2, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 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, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 8, 32, 32, 2, 2, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 8, 32, 32, 2, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 8, 32, 32, 1, 2, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 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, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 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, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 8, 32, 32, 2, 4, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 8, 32, 32, 2, 2, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 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, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 8, 32, 32, 2, 2, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 8, 32, 32, 2, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 8, 32, 32, 1, 2, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 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, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 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, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 8, 32, 32, 2, 4, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 8, 32, 32, 2, 2, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 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, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 8, 32, 32, 2, 2, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 8, 32, 32, 2, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 8, 32, 32, 1, 2, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 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, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 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, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 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, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, S<0,2,1>, S<0,2,1>, 1, 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, LoopScheduler::Default, PipelineVersion::v2>"
-    };
-
-    static inline std::vector<std::string> device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance  = 
-    {
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 2, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 2, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 2, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 2, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 2, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 2, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 2, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 2, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 2, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 2, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 2, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 2, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 2, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 2, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 2, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 2, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 2, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<16,16,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 1, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 2, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<8,32,1>, S<0,2,1>, S<0,2,1>, 1, 4, 2, 0, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<0,2,1>, S<0,2,1>, 1, 2, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, 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, 1, 8, 1, 1, 1, S<1,16,1,4>, 1, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, 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, 1, 8, 1, 1, 1, S<1,16,1,4>, 1, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, S<4,16,1>, 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, 1, 8, 1, 1, 1, S<1,16,1,4>, 1, LoopScheduler::Default, PipelineVersion::v2>"
-    };
-
-    static inline std::vector<std::string> device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance  = 
-    {
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 64, 64, 32, 8, 8, 32, 32, 2, 2, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 32, 32, 8, 8, 32, 32, 2, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 32, 128, 32, 8, 8, 32, 32, 1, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 32, 64, 32, 8, 8, 32, 32, 1, 2, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,4>, 8, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 64, 64, 32, 8, 8, 32, 32, 2, 2, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 32, 32, 8, 8, 32, 32, 2, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 32, 128, 32, 8, 8, 32, 32, 1, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 32, 64, 32, 8, 8, 32, 32, 1, 2, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,4>, 8, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 64, 64, 32, 8, 8, 32, 32, 2, 2, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,64,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 32, 32, 8, 8, 32, 32, 2, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,32,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 32, 128, 32, 8, 8, 32, 32, 1, 2, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,32,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,8>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 32, 64, 32, 8, 8, 32, 32, 1, 2, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, S<4,16,1>, S<1,0,2>, S<1,0,2>, 2, 8, 8, 1, 1, 1, S<1,16,1,4>, 8, LoopScheduler::Default, PipelineVersion::v2>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, 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, LoopScheduler::Default, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, 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, LoopScheduler::Interwave, PipelineVersion::v1>",
-        "DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmMNKPadding, 1, 64, 16, 16, 32, 8, 8, 16, 16, 1, 1, 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, LoopScheduler::Default, PipelineVersion::v2>"
-    };
-
-    static auto get_col_row_instances()
-    {
-        return device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance;
-    }
-
-    static auto get_col_col_instances()
-    {
-        return device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance;
-    }
-
-    static auto get_row_row_instances()
-    {
-        return device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance;
-    }
-
-    static auto get_row_col_instances()
-    {
-        return device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance;
-    }
-};
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck