/*
 * Copyright (c) 2019-2023 Beijing Hanwei Innovation Technology Ltd. Co. and
 * its subsidiaries and affiliates (collectly called MKSEMI).
 *
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice,
 *    this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form, except as embedded into an MKSEMI
 *    integrated circuit in a product or a software update for such product,
 *    must reproduce the above copyright notice, this list of conditions and
 *    the following disclaimer in the documentation and/or other materials
 *    provided with the distribution.
 *
 * 3. Neither the name of MKSEMI nor the names of its contributors may be used
 *    to endorse or promote products derived from this software without
 *    specific prior written permission.
 *
 * 4. This software, with or without modification, must only be used with a
 *    MKSEMI integrated circuit.
 *
 * 5. Any software provided in binary form under this license must not be
 *    reverse engineered, decompiled, modified and/or disassembled.
 *
 * THIS SOFTWARE IS PROVIDED BY MKSEMI "AS IS" AND ANY EXPRESS OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 * MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED. IN NO EVENT SHALL MKSEMI OR CONTRIBUTORS BE LIABLE FOR ANY
 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#ifndef MK_LSP_H_
#define MK_LSP_H_
#include "mk_common.h"

#ifndef LSP_INT_MODE_EN
#define LSP_INT_MODE_EN (1)
#endif

/**
 * @addtogroup MK8000_LSP
 * @{
 */

/**
 * @brief Instance structure for the floating-point matrix structure.
 */
struct LSP_MATRIX_T
{
    uint16_t num_rows; /**< number of rows of the matrix.     */
    uint16_t num_cols; /**< number of columns of the matrix.  */
    float *data;       /**< points to the data of the matrix. */
};

#ifdef __cplusplus
extern "C" {
#endif

/**
 * @brief open LSP.
 *
 * @param int_en interrupt enable flag
 * @param callback register a callback
 */
int lsp_open(uint8_t int_en, drv_callback_t callback);

/**
 * @brief close LSP.
 */
int lsp_close(void);

/**
 * @brief Floating-point vector addition.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_add_f32(const float *pSrcA, const float *pSrcB, float *pDst, uint32_t blkCnt);

/**
 * @brief 8bit integer vector addition.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_add_int8(const int8_t *pSrcA, const int8_t *pSrcB, int16_t *pDst, uint32_t blkCnt);

/**
 * @brief 16bit integer vector addition.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_add_int16(const int16_t *pSrcA, const int16_t *pSrcB, int32_t *pDst, uint32_t blkCnt);

/**
 * @brief 32bit integer vector addition.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_add_int32(const int32_t *pSrcA, const int32_t *pSrcB, int32_t *pDst, uint32_t blkCnt);

/**
 * @brief Floating-point vector subtraction.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_sub_f32(const float *pSrcA, const float *pSrcB, float *pDst, uint32_t blkCnt);

/**
 * @brief 8bit integer vector subtraction.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_sub_int8(const int8_t *pSrcA, const int8_t *pSrcB, int16_t *pDst, uint32_t blkCnt);

/**
 * @brief 16bit integer vector subtraction.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_sub_int16(const int16_t *pSrcA, const int16_t *pSrcB, int32_t *pDst, uint32_t blkCnt);

/**
 * @brief 32bit integer vector subtraction.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_sub_int32(const int32_t *pSrcA, const int32_t *pSrcB, int32_t *pDst, uint32_t blkCnt);

/**
 * @brief Floating-point vector multiplication.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_mult_f32(const float *pSrcA, const float *pSrcB, float *pDst, uint32_t blkCnt);

/**
 * @brief 8bit integer vector multiplication.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_mult_int8(const int8_t *pSrcA, const int8_t *pSrcB, int16_t *pDst, uint32_t blkCnt);

/**
 * @brief 16bit integer vector multiplication.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_mult_int16(const int16_t *pSrcA, const int16_t *pSrcB, int32_t *pDst, uint32_t blkCnt);

/**
 * @brief 32bit integer vector multiplication.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_mult_int32(const int32_t *pSrcA, const int32_t *pSrcB, int32_t *pDst, uint32_t blkCnt);

/**
 * @brief Floating-point vector inverse.
 * @param[in]  pSrc       points to the instance of the input vector.
 * @param[out] pDst       points to the instance of the output vector.
 * @param[in]  blkCnt     number of samples in intput vector
 */
void lsp_vinverse_f32(const float *pSrc, float *pDst, uint32_t blkCnt);

/**
 * @brief 8bit integer vector inverse.
 * @param[in]  pSrc       points to the instance of the input vector.
 * @param[out] pDst       points to the instance of the output vector.
 * @param[in]  blkCnt     number of samples in intput vector
 */
void lsp_vinverse_int8(const int8_t *pSrc, float *pDst, uint32_t blkCnt);

/**
 * @brief 16bit integer vector inverse.
 * @param[in]  pSrc       points to the instance of the input vector.
 * @param[out] pDst       points to the instance of the output vector.
 * @param[in]  blkCnt     number of samples in intput vector
 */
void lsp_vinverse_int16(const int16_t *pSrc, float *pDst, uint32_t blkCnt);

/**
 * @brief 32bit integer vector inverse.
 * @param[in]  pSrc       points to the instance of the input vector.
 * @param[out] pDst       points to the instance of the output vector.
 * @param[in]  blkCnt     number of samples in intput vector
 */
void lsp_vinverse_int32(const int32_t *pSrc, float *pDst, uint32_t blkCnt);

/**
 * @brief Floating-point vector inner product.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_inner_product_f32(const float *pSrcA, const float *pSrcB, float *pDst, uint32_t blkCnt);

/**
 * @brief 8bit integer vector inner product.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_inner_product_int8(const int8_t *pSrcA, const int8_t *pSrcB, int32_t *pDst, uint32_t blkCnt);

/**
 * @brief 16bit integer vector inner product.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_inner_product_int16(const int16_t *pSrcA, const int16_t *pSrcB, float *pDst, uint32_t blkCnt);

/**
 * @brief 32bit integer vector inner product.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  pSrcB      points to the second input vector
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in each vector
 */
void lsp_inner_product_int32(const int32_t *pSrcA, const int32_t *pSrcB, float *pDst, uint32_t blkCnt);

/**
 * @brief Floating-point vector inner product searching to find out the maximum or minimum result.
 * @param[in]  pSrcA      points to the first input vector
 * @param[in]  srcALen    the length of input vector SrcA, srcALen <= 16
 * @param[in]  pSrcB      points to the second input vector
 * @param[in]  iterations iteration times
 * @param[out] pDst       points to the output vector
 * @param[in]  isMax      maximum or minimum
 * @return the maximum or minimum inner product iteration count
 */
uint32_t lsp_correlate_f32(const float *pSrcA, uint32_t srcALen, const int8_t *pSrcB, uint32_t iterations, float *pDst, uint8_t isMax);

/**
 * @brief Multiplies a floating-point vector by a scalar.
 * @param[in]  pSrc       points to the input vector
 * @param[in]  scale      scale factor to be applied
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of samples in the vector
 */
void lsp_scale_f32(const float *pSrc, float scale, float *pDst, uint32_t blkCnt);

/**
 * @brief  integer 8 complex-by-complex multiplication
 * @param[in]  pSrcA       points to the first input vector
 * @param[in]  pSrcB       points to the second input vector
 * @param[out] pDst        points to the output vector
 * @param[in]  numSamples  number of complex samples in each vector
 * @param[in]  isConj      conjugate enbale or disable
 */
void lsp_cmplx_mult_cmplx_int8(const int8_t *pSrcA, const int8_t *pSrcB, int16_t *pDst, uint32_t numSamples, uint8_t isConj);

/**
 * @brief  integer 16 complex-by-complex multiplication
 * @param[in]  pSrcA       points to the first input vector
 * @param[in]  pSrcB       points to the second input vector
 * @param[out] pDst        points to the output vector
 * @param[in]  numSamples  number of complex samples in each vector
 * @param[in]  isConj      conjugate enbale or disable
 */
void lsp_cmplx_mult_cmplx_int16(const int16_t *pSrcA, const int16_t *pSrcB, int32_t *pDst, uint32_t numSamples, uint8_t isConj);

/**
 * @brief  Floating-point complex-by-complex multiplication
 * @param[in]  pSrcA       points to the first input vector
 * @param[in]  pSrcB       points to the second input vector
 * @param[out] pDst        points to the output vector
 * @param[in]  numSamples  number of complex samples in each vector
 * @param[in]  isConj      conjugate enbale or disable
 */
void lsp_cmplx_mult_cmplx_f32(const float *pSrcA, const float *pSrcB, float *pDst, uint32_t numSamples, uint8_t isConj);

/**
 * @brief 8bit integer complex vector inner product, output integer format.
 * @param[in]  pSrcA        points to the first input vector
 * @param[in]  pSrcB        points to the second input vector
 * @param[out] pDst         points to the output vector
 * @param[in]  numSamples   number of complex samples in each vector
 * @param[in]  isConj       conjugate enbale or disable
 */
void lsp_cmplx_inner_product_int8(const int8_t *pSrcA, const int8_t *pSrcB, int32_t *pDst, uint32_t numSamples, uint8_t isConj);

/**
 * @brief 16bit integer complex vector inner product.
 * @param[in]  pSrcA        points to the first input vector
 * @param[in]  pSrcB        points to the second input vector
 * @param[out] pDst         points to the output vector
 * @param[in]  numSamples   number of complex samples in each vector
 * @param[in]  isConj       conjugate enbale or disable
 */
void lsp_cmplx_inner_product_int16(const int16_t *pSrcA, const int16_t *pSrcB, float *pDst, uint32_t numSamples, uint8_t isConj);

/**
 * @brief Floating-point complex vector inner product.
 * @param[in]  pSrcA        points to the first input vector
 * @param[in]  pSrcB        points to the second input vector
 * @param[out] pDst         points to the output vector
 * @param[in]  numSamples   number of complex samples in each vector
 * @param[in]  isConj       conjugate enbale or disable
 */
void lsp_cmplx_inner_product_f32(const float *pSrcA, const float *pSrcB, float *pDst, uint32_t numSamples, uint8_t isConj);

/**
 * @brief Multiplies a floating-point complex vector by a scalar.
 * @param[in]  pSrc       points to the input vector
 * @param[in]  re_scale   scale factor to be applied on real part
 * @param[in]  im_scale   scale factor to be applied on imaginary part
 * @param[out] pDst       points to the output vector
 * @param[in]  blkCnt     number of complex samples in the vector
 * @param[in]  isConj     conjugate enbale or disable
 */
void lsp_cmplx_scale_f32(const float *pSrc, float re_scale, float im_scale, float *pDst, uint32_t blkCnt, uint8_t isConj);

/**
 * @brief Floating-point matrix inverse.
 * @param[in]  pSrc     points to the instance of the input floating-point matrix structure.
 * @param[out] pDst     points to the instance of the output floating-point matrix structure.
 * @param[in]  rv       matrix regularization
 */
void lsp_cmplx_mat_inverse_f32(const struct LSP_MATRIX_T *pSrc, struct LSP_MATRIX_T *pDst, float rv);

/**
 * @brief Floating-point matrix LDL factorization.
 * @param[in]  pSrc     points to the instance of the input floating-point matrix structure.
 * @param[out] pDst     points to the instance of the output floating-point matrix structure.
 * @param[in]  rv       matrix regularization
 */
void lsp_cmplx_mat_ldl_f32(const struct LSP_MATRIX_T *pSrc, struct LSP_MATRIX_T *pDst, float rv);

/**
 * @brief Floating-point matrix multiplication
 * @param[in]  pSrcA     points to the first input matrix structure
 * @param[in]  pSrcB     points to the second input matrix structure
 * @param[out] pDst      points to output matrix structure
 */
void lsp_mat_mult_f32(const struct LSP_MATRIX_T *pSrcA, const struct LSP_MATRIX_T *pSrcB, struct LSP_MATRIX_T *pDst);

/**
 * @brief Floating-point complex matrix multiplication
 * @param[in]  pSrcA     points to the first input matrix structure
 * @param[in]  pSrcB     points to the second input matrix structure
 * @param[out] pDst      points to output matrix structure
 * @param[out] isConj    conjugate enbale or disable
 */
void lsp_cmplx_mat_mult_f32(const struct LSP_MATRIX_T *pSrcA, const struct LSP_MATRIX_T *pSrcB, struct LSP_MATRIX_T *pDst, uint8_t isConj);

#ifdef __cplusplus
}
#endif

/**
 * @}
 */

#endif /* MK_LSP_H_ */