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

#pragma once

#include "ck_tile/core.hpp"

// GEMM config with 16x16 warp tile
struct MXfp4_FlatmmConfig16
{
    static constexpr ck_tile::index_t M_Tile = 128;
    static constexpr ck_tile::index_t N_Tile = 512;
    static constexpr ck_tile::index_t K_Tile = 256;

    static constexpr ck_tile::index_t M_Warp = 1;
    static constexpr ck_tile::index_t N_Warp = 4;
    static constexpr ck_tile::index_t K_Warp = 1;

    static constexpr ck_tile::index_t M_Warp_Tile = 16;
    static constexpr ck_tile::index_t N_Warp_Tile = 16;
    static constexpr ck_tile::index_t K_Warp_Tile = 128;

    static constexpr bool kPadM = false;
    static constexpr bool kPadN = false;
    static constexpr bool kPadK = false;

    static constexpr bool TransposeC            = false;
    static constexpr bool UseStructuredSparsity = false;

    static constexpr int kBlockPerCu                = 1;
    static constexpr int TileParitionerGroupNum     = 8;
    static constexpr int TileParitionerM01          = 4;
    static constexpr auto Scheduler                 = ck_tile::GemmPipelineScheduler::Default;
    static constexpr ck_tile::index_t NumWaveGroups = 1;
    static constexpr bool DoubleSmemBuffer          = false;

    static constexpr int N_Repeat          = N_Tile / N_Warp_Tile / N_Warp;
    static constexpr bool TiledMMAPermuteN = false;
};