Skip to content

/github/workspace/src/MatrixFunctions/mat_trans/plp_mat_trans_i16_parallel.c

Functions

Name
void plp_mat_trans_i16_parallel(const int16_t restrict pSrc, uint32_t M, uint32_t N, uint32_t nPE, int16_t restrict pDst)
Glue code for parallel matrix transpose of 16-bit integer matrices.

Functions Documentation

function plp_mat_trans_i16_parallel

void plp_mat_trans_i16_parallel(
    const int16_t *__restrict__ pSrc,
    uint32_t M,
    uint32_t N,
    uint32_t nPE,
    int16_t *__restrict__ pDst
)

Glue code for parallel matrix transpose of 16-bit integer matrices.

Parameters:

  • pSrc Points to the input matrix of shape MxN
  • M Height of the input matrix and width of the output matrix
  • N Width of the input matrix and height of the output matrix
  • nPE Number of cores to use for computation
  • pDst Points to the output matrix of shape NxM

Return: none

Glue code for parallel matrix transpose of a 16-bit integer matrices.

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_mat_trans_i16_parallel.c
 * Description:  parallel 16-bit integer matrix transpose 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_trans_i16_parallel(const int16_t *__restrict__ pSrc,
                                uint32_t M,
                                uint32_t N,
                                uint32_t nPE,
                                int16_t *__restrict__ pDst) {

    if (hal_cluster_id() == ARCHI_FC_CID) {
        printf("parallel processing supported only for cluster side\n");
        return;
    } else {
        plp_mat_trans_instance_i16 args = {
            .pSrc = pSrc, .M = M, .N = N, .nPE = nPE, .pDst = pDst
        };

        hal_cl_team_fork(nPE, plp_mat_trans_i16p_xpulpv2, (void *)&args);
    }
}

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