Skip to content

/github/workspace/src/MatrixFunctionsStride/mat_mult_trans_stride/plp_mat_mult_trans_stride_i32_parallel.c

Functions

Name
void plp_mat_mult_trans_stride_i32_parallel(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 nPE, int32_t *restrict pDstC)
Glue code for parallel strided matrix multiplication of 32-bit integer matrices.

Functions Documentation

function plp_mat_mult_trans_stride_i32_parallel

void plp_mat_mult_trans_stride_i32_parallel(
    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 nPE,
    int32_t *__restrict__ pDstC
)

Glue code for parallel strided matrix multiplication of 32-bit integer 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)
  • nPE Number of cores to use
  • pDstC points to the output matrix

Return: none

Glue code for parallel strided matrix matrix multiplication of a 32-bit integer matrices.

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_mat_mult_trans_stride_i32_parallel.c
 * Description:  parallel 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_i32_parallel(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 nPE,
                                            int32_t *__restrict__ pDstC) {

    if (hal_cluster_id() == ARCHI_FC_CID) {
        printf("parallel processing supported only for cluster side\n");
        return;
    } else {
        plp_mat_mult_stride_instance_i32 args = { .pSrcA = pSrcA,
                                                  .pSrcB = pSrcB,
                                                  .M = M,
                                                  .N = N,
                                                  .O = O,
                                                  .strideA = strideA,
                                                  .strideB = strideB,
                                                  .strideC = strideC,
                                                  .nPE = nPE,
                                                  .pDstC = pDstC };
        hal_cl_team_fork(nPE, plp_mat_mult_trans_stride_i32p_xpulpv2, (void *)&args);
    }
}

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