/github/workspace/src/MatrixFunctionsStride/mat_copy_stride/plp_mat_copy_stride_f32_parallel.c

Functions

	Name
void	plp_mat_copy_stride_f32_parallel(const float restrict pSrc, uint32_t M, uint32_t N, uint32_t strideSrc, uint32_t strideDst, uint32_t nPE, float restrict pDst) Glue code to copy an MxN strided 32-bit floats matrix in parallel.

Functions Documentation

function plp_mat_copy_stride_f32_parallel

void plp_mat_copy_stride_f32_parallel(
    const float *__restrict__ pSrc,
    uint32_t M,
    uint32_t N,
    uint32_t strideSrc,
    uint32_t strideDst,
    uint32_t nPE,
    float *__restrict__ pDst
)

Glue code to copy an MxN strided 32-bit floats matrix in parallel.

Parameters:

• pSrc Points to the input matrix of shape MxN
• M Height of both matrices
• N Width of both matrices
• strideSrc Stride of the input matrix (elements between each row)
• strideDst Stride of the output matrix (elements between each row)
• nPE Number of cores to use for processing
• pDst Points to the output matrix of shape MxN

Return: none

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_mat_copy_stride_f32_parallel.c
 * Description:  parallel 32-bit floating-point strided matrix copy glue code
 *
 * $Date:        17. July 2020
 * $Revision:    V0
 *
 * Target Processor: PULP cores
 * ===================================================================== */
/*
 * Copyright (C) 2020 ETH Zurich and Ubiversity of Bologna. All rights reserved.
 *
 * 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_copy_stride_f32_parallel(const float *__restrict__ pSrc,
                                      uint32_t M,
                                      uint32_t N,
                                      uint32_t strideSrc,
                                      uint32_t strideDst,
                                      uint32_t nPE,
                                      float *__restrict__ pDst) {

    if (hal_cluster_id() == ARCHI_FC_CID) {
        printf("parallel and floating-point processing supported only for cluster side\n");
        return;
    } else {
        plp_mat_copy_stride_instance_f32 args = { .pSrc = pSrc,
                                                  .M = M,
                                                  .N = N,
                                                  .strideSrc = strideSrc,
                                                  .strideDst = strideDst,
                                                  .nPE = nPE,
                                                  .pDst = pDst };

        hal_cl_team_fork(nPE, plp_mat_copy_stride_f32p_xpulpv2, (void *)&args);
    }
}

---

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