Skip to content

/github/workspace/src/MatrixFunctions/mat_mult_cmplx/kernels/plp_mat_mult_cmplx_q32s_xpulpv2.c

Functions

Name
void plp_mat_mult_cmplx_q32s_xpulpv2(const int32_t restrict pSrcA, const int32_t restrict pSrcB, uint32_t M, uint32_t N, uint32_t O, uint32_t shift, int32_t *restrict pDstC)
Matrix matrix multiplication for complex 32-bit fix-point on XpulpV2.

Defines

Name
BASIC_VERSION

Functions Documentation

function plp_mat_mult_cmplx_q32s_xpulpv2

void plp_mat_mult_cmplx_q32s_xpulpv2(
    const int32_t *__restrict__ pSrcA,
    const int32_t *__restrict__ pSrcB,
    uint32_t M,
    uint32_t N,
    uint32_t O,
    uint32_t shift,
    int32_t *__restrict__ pDstC
)

Matrix matrix multiplication for complex 32-bit fix-point on XpulpV2.

Parameters:

  • pSrcA Points to the first input matrix of shape MxN
  • pSrcB Points to the second input matrix of shape NxO
  • M Height of matrix SrcA and DstC
  • N Width of matrix SrcA and height of matrix SrcB
  • O Width of matrix SrcB and DstC
  • shift Amount to shift the result of each multiplication ot the right
  • pDstC Points to the output matrix of shape MxO

Return: none

Par: Fix-Point

Fix-Point and Shifting The result will be shifted by the parameter shift to the right (which corresponds to a multiplication by 2^-shift). Assume that matrix A is represente as pSrcA * 2^-x and matrix B as pSrcB * 2^-y (which means that A has x, and B has y bits after the binary point). Then, the output matrix C is represented as pDstC * 2^-(x + y - shift). The output matrix is also stored with the same number of bits as the inputs. Set the shift parameter such that no overflow occurrs.

Macros Documentation

define BASIC_VERSION

#define BASIC_VERSION

Source code

/* =====================================================================
 * Project:      PULP DSP Library
 * Title:        plp_mat_mult_cmplx_q32s_xpulpv2.c
 * Description:  32-bit fix-point complex matrix matrix multiplication for XPULPV2
 *
 * $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_mult_cmplx_q32s_xpulpv2(const int32_t *__restrict__ pSrcA,
                                     const int32_t *__restrict__ pSrcB,
                                     uint32_t M,
                                     uint32_t N,
                                     uint32_t O,
                                     uint32_t shift,
                                     int32_t *__restrict__ pDstC) {

#define BASIC_VERSION // if used don't forget to also use the undefine at end of file
#ifdef BASIC_VERSION

    for (int m = 0; m < M; m++) {
        for (int o = 0; o < O; o++) {
            int32_t sum_re = 0;
            int32_t sum_im = 0;
            for (int n = 0; n < N; n++) {
                int32_t a_re = (int32_t)pSrcA[(m * N + n) * 2 + 0];
                int32_t a_im = (int32_t)pSrcA[(m * N + n) * 2 + 1];
                int32_t b_re = (int32_t)pSrcB[(n * O + o) * 2 + 0];
                int32_t b_im = (int32_t)pSrcB[(n * O + o) * 2 + 1];
                sum_re += __ROUNDNORM_REG(a_re * b_re - a_im * b_im, shift);
                sum_im += __ROUNDNORM_REG(a_re * b_im + a_im * b_re, shift);
            }
            pDstC[(m * O + o) * 2 + 0] = (int32_t)sum_re;
            pDstC[(m * O + o) * 2 + 1] = (int32_t)sum_im;
        }
    }

#else

    // TODO: Hackathon

#endif
#undef BASIC_VERSION
}

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