/**
 * Copyright (c) 2026 Huawei Technologies Co., Ltd.
 * This program is free software, you can redistribute it and/or modify it under the terms and conditions of
 * CANN Open Software License Agreement Version 2.0 (the "License").
 * Please refer to the License for details. You may not use this file except in compliance with the License.
 * THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
 * INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
 * See LICENSE in the root of the software repository for the full text of the License.
 */

/* Generated By CANNBot */

/*!
 * \file sparse_bincount.cpp
 * \brief Kernel entry for sparse_bincount operator.
 *        Scene mode dispatched via TilingKey (isPrecise x isDeterministic x is1D x binaryOutput x hasWeights = 32
 * variants). dtype dispatched via DTYPE_VALUES / DTYPE_SIZE macros.
 *
 * TilingKey encoding: schMode = isPrecise * 16 + isDeterministic * 8 + is1D * 4 + binaryOutput * 2 + hasWeights
 *    0-7:  non-precise, non-deterministic modes (atomic-add scatter)
 *   8-15:  non-precise, deterministic modes (fixed-order gather accumulation, bitwise reproducible)
 *  16-23:  precise, non-deterministic modes
 *  24-31:  precise, deterministic modes (fixed-order + precise accumulation)
 */

#include "arch35/sparse_bincount_simt.h"

template <uint32_t schMode>
__global__ __aicore__ void sparse_bincount(GM_ADDR indices, GM_ADDR values, GM_ADDR dense_shape, GM_ADDR size,
                                           GM_ADDR weights, GM_ADDR output, GM_ADDR workspace, GM_ADDR tiling)
{
    REGISTER_TILING_DEFAULT(SparseBincountTilingData);
    GET_TILING_DATA_WITH_STRUCT(SparseBincountTilingData, tilingData, tiling);

    // Decode scene mode from tiling key
    constexpr bool IS_PRECISE = ((schMode & 0x10) != 0);
    constexpr bool IS_DETERMINISTIC = ((schMode & 0x8) != 0);
    constexpr bool IS_1D = ((schMode & 0x4) != 0);
    constexpr bool BINARY_OUTPUT = ((schMode & 0x2) != 0);
    constexpr bool HAS_WEIGHTS = ((schMode & 0x1) != 0);

    NsSparseBincount::Process<DTYPE_VALUES, DTYPE_SIZE, IS_PRECISE, IS_1D, BINARY_OUTPUT, HAS_WEIGHTS,
                              IS_DETERMINISTIC>(indices, values, dense_shape, size, weights, output, &tilingData);
}