Skip to content

/github/workspace/src/MatrixFunctionsStride/mat_mult_trans_stride/plp_mat_mult_trans_stride_q32.c

Functions

Name
void plp_mat_mult_trans_stride_q32(const int32_t restrict pSrcA, const int32_t restrict pSrcB, uint32_t M, uint32_t N, uint32_t O, uint32_t strideA, uint32_t strideB, uint32_t strideC, uint32_t shift, int32_t *restrict pDstC)
Glue code for strided matrix multiplication of 32-bit fix-point matrices.

Functions Documentation

function plp_mat_mult_trans_stride_q32

void plp_mat_mult_trans_stride_q32(
    const int32_t *__restrict__ pSrcA,
    const int32_t *__restrict__ pSrcB,
    uint32_t M,
    uint32_t N,
    uint32_t O,
    uint32_t strideA,
    uint32_t strideB,
    uint32_t strideC,
    uint32_t shift,
    int32_t *__restrict__ pDstC
)

Glue code for strided matrix multiplication of 32-bit fix-point matrices.

Parameters:

  • pSrcA points to the first input matrix
  • pSrcB points to the second input matrix
  • M height of the first input matrix
  • N width of the first input matrix and hight of the second
  • O width of the second input matrix
  • strideA Stride of matrix A (elements between each row)
  • strideB Stride of matrix B (elements between each row)
  • strideC Stride of output matrix (elements between each row)
  • shift Amount to shift the result of each multiplication.
  • pDstC points to the output matrix

Return: none

Par: Fix-Point and Shifting

The result will be shifted by the parameter shift to the right (multiplied by 2^-shift). Assume that matrix A is represented as pSrcA * 2^-x, and matrix B as pSrcB * 2^-y (in other words, A has it's x last digits after the binary point). Then, the output is represented as pDstC * 2^-(x + y - shift).

Glue code for strided matrix transposed matrix multiplication of a 32-bit fix-point matrices.

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_mat_mult_trans_stride_i32.c
 * Description:  32-bit integer strided matrix multiplication glue code
 *
 * $Date:        14. July 2020
 * $Revision:    V0
 *
 * Target Processor: PULP cores
 * ===================================================================== */
/*
 * Copyright (C) 2020 ETH Zurich and University of Bologna.
 *
 * Author: Tibor Schneider, ETH Zurich
 *
 * SPDX-License-Identifier: Apache-2.0
 *
 * Licensed under the Apache License, Version 2.0 (the License); you may
 * not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
 * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#include "plp_math.h"

void plp_mat_mult_trans_stride_q32(const int32_t *__restrict__ pSrcA,
                                   const int32_t *__restrict__ pSrcB,
                                   uint32_t M,
                                   uint32_t N,
                                   uint32_t O,
                                   uint32_t strideA,
                                   uint32_t strideB,
                                   uint32_t strideC,
                                   uint32_t shift,
                                   int32_t *__restrict__ pDstC) {

    if (hal_cluster_id() == ARCHI_FC_CID) {
        plp_mat_mult_trans_stride_q32s_rv32im(pSrcA, pSrcB, M, N, O, strideA, strideB, strideC,
                                              shift, pDstC);
    } else {
        plp_mat_mult_trans_stride_q32s_xpulpv2(pSrcA, pSrcB, M, N, O, strideA, strideB, strideC,
                                               shift, pDstC);
    }
}

Updated on 2023-03-01 at 16:16:33 +0000