// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT

#pragma once

#include <algorithm>
#include <cstddef>
#include <iostream>
#include <stdexcept>
#include <string>

#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"

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

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

#include "ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle_v3.hpp"

#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/utility/data_type.hpp"

#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
#include "ck/library/utility/check_err.hpp"
#include "ck/library/utility/device_memory.hpp"
#include "ck/library/utility/host_tensor.hpp"
#include "ck/library/utility/host_tensor_generator.hpp"
#include "ck/library/utility/literals.hpp"

using ::ck::DeviceMem;
using ::ck::HostTensorDescriptor;
using ::ck::Tensor;

template <ck::index_t... Is>
using S = ck::Sequence<Is...>;

using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;

using PassThrough = ck::tensor_operation::element_wise::PassThrough;
using Add         = ck::tensor_operation::element_wise::Add;

using BF16 = ck::bhalf_t;
using F16  = ck::half_t;
using F32  = float;

using Row_Tuple  = ck::Tuple<Row>;
using F16_Tuple  = ck::Tuple<F16>;
using BF16_Tuple = ck::Tuple<BF16>;

struct ProblemSize final
{
    ck::index_t M = 3840;
    ck::index_t N = 4096;
    ck::index_t K = 4096;

    ck::index_t StrideA = 4096;
    ck::index_t StrideB = 4096;
    ck::index_t StrideD = 4096;
    ck::index_t StrideE = 4096;
};
struct ExecutionConfig final
{
    bool do_verification = true;
    int init_method      = 1;
    bool time_kernel     = false;
};

inline bool
parse_cmd_args(int argc, char* argv[], ProblemSize& problem_size, ExecutionConfig& config)
{
    if(argc == 1)
    {
        // use default case
    }
    else if(argc == 4)
    {
        config.do_verification = std::stoi(argv[1]);
        config.init_method     = std::stoi(argv[2]);
        config.time_kernel     = std::stoi(argv[3]);
    }
    else if(argc == 6)
    {
        config.do_verification = std::stoi(argv[1]);
        config.init_method     = std::stoi(argv[2]);
        config.time_kernel     = std::stoi(argv[3]);
    }
    else if(argc == 11)
    {
        config.do_verification = std::stoi(argv[1]);
        config.init_method     = std::stoi(argv[2]);
        config.time_kernel     = std::stoi(argv[3]);

        problem_size.M = std::stoi(argv[4]);
        problem_size.N = std::stoi(argv[5]);
        problem_size.K = std::stoi(argv[6]);

        problem_size.StrideA = std::stoi(argv[7]);
        problem_size.StrideB = std::stoi(argv[8]);
        problem_size.StrideD = std::stoi(argv[9]);
        problem_size.StrideE = std::stoi(argv[10]);
    }
    else
    {
        std::cerr << "arg1: verification (0=no, 1=yes)" << std::endl
                  << "arg2: initialization (0=no init, 1=integer value, 2=decimal value)"
                  << std::endl
                  << "arg3: time kernel (0=no, 1=yes)" << std::endl
                  << "arg4 to 10: M (256x), N(128x), K(32x), StrideA, StrideB, StrideD,"
                     "StrideE"
                  << std::endl;
        return false;
    }

    return true;
}