// SPDX-License-Identifier: MIT
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.

#include <hip/hip_runtime.h>

#include <cstring>
#include <iostream>
#include <sstream>
#include <string>
#include <tuple>

#include "ck_tile/ops/epilogue.hpp"
#include "ck_tile/ops/gemm.hpp"
#include "ck_tile/host.hpp"
#include "gemm_basic.hpp"

auto create_args(int argc, char* argv[])
{
    ck_tile::ArgParser arg_parser;
    arg_parser.insert("m", "3840", "m dimension")
        .insert("n", "4096", "n dimension")
        .insert("k", "2048", "k dimension")
        .insert("a_layout", "R", "A tensor data layout - Row by default")
        .insert("b_layout", "R", "B tensor data layout - Row by default")
        .insert("c_layout", "R", "C tensor data layout - Row by default")
        .insert("stride_a", "0", "Tensor A stride")
        .insert("stride_b", "0", "Tensor B stride")
        .insert("stride_c", "0", "Tensor C stride")
        .insert("v", "2", "0. No validation, 1. Validation on CPU, 2. Validation on GPU")
        .insert("prec", "fp16", "data type. fp16/bf16/fp8/bf8")
        .insert("warmup", "50", "number of iterations before benchmark the kernel")
        .insert("repeat", "100", "number of iterations to benchmark the kernel")
        .insert("timer", "gpu", "gpu:gpu timer, cpu:cpu timer")
        .insert("split_k", "1", "splitK value");

    bool result = arg_parser.parse(argc, argv);
    return std::make_tuple(result, arg_parser);
}

#include "run_gemm_example.inc"

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