// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.

#include "common.hpp"

#include "ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp"

using ADataType        = ck::half_t;
using BDataType        = ck::half_t;
using AccDataType      = float;
using CShuffleDataType = float;
using CDataType        = ck::half_t;

using ALayout = Row;
using BLayout = Col;
using CLayout = Row;

using AElementOp = PassThrough;
using BElementOp = PassThrough;
using CElementOp = PassThrough;

static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;

// clang-format off
using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmWmma_CShuffle
// ######| ALayout| BLayout| CLayout|     AData|     BData|     CData|     AccData|         CShuffle|           A|           B|           C|              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|
// ######|        |        |        |      Type|      Type|      Type|        Type|         DataType| Elementwise| Elementwise| Elementwise|    Spacialization|  Size| Block| Block| Block|    | WMMA| WMMA|       |       |   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN|MWmmaPerWave|NWmmaPerWave|        _MBlock_MWaveMPerWmma| ScalarPerVector|
// ######|        |        |        |          |          |          |            |                 |   Operation|   Operation|   Operation|                  |      |      |      |      |    |     |     |       |       | Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|
// ######|        |        |        |          |          |          |            |                 |            |            |            |                  |      |      |      |      |    |     |     |       |       |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
         < ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType,  AElementOp,  BElementOp,  CElementOp,    GemmMNKPadding,   256,   128,   256,     8,   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, 1>;
// clang-format on

using ReferenceGemmInstance = ck::tensor_operation::host::
    ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;

#include "run_gemm_example.inc"

int main(int argc, char* argv[]) { return !run_gemm_example(argc, argv); }