pcpack.c

Go to the documentation of this file.

#include <stdlib.h>
#include <sys/types.h>
#include "common.h"

void plasma_pcpack(plasma_context_t *plasma)
{
    PLASMA_Complex32_t *A, *W, *Wl;
    PLASMA_sequence *sequence;
    PLASMA_request *request;
    int m, n, m0;
    int i, m1, size, rank, start, end, bs, mod;

    plasma_unpack_args_6(m, n, A, m0, sequence, request);
    if (sequence->status != PLASMA_SUCCESS)
        return;

    /* Quick return */
    if ( n <= 1 )
      return;

    m1 = m - m0;

    size = PLASMA_SIZE;
    rank = PLASMA_RANK;

    mod   = (n-1) % size;
    bs    = (n-1) / size;
    start = rank * bs;
    if ( rank < mod ) {
        bs++;
    }
    start += min( mod, rank );

    W  = (PLASMA_Complex32_t*)plasma_private_alloc(plasma, (m0*bs), PlasmaComplexFloat);
    Wl = (PLASMA_Complex32_t*)plasma_private_alloc(plasma, m1,      PlasmaComplexFloat);

    /* Save leftover pieces that are otherwise going to be overwritten */
    CORE_clacpy( PlasmaUpperLower, m0, bs, &(A[(int64_t)start*m+m1]), m, W, m0 );

    /* Pack A */
    end = ((n-1) / size) * size + 1;
    for(i=rank+1; i<end; i+=size) {
        memcpy( Wl, &(A[i*m]), m1*sizeof(PLASMA_Complex32_t));
        plasma_barrier(plasma);
        memcpy( &(A[i*m1]), Wl, m1*sizeof(PLASMA_Complex32_t));
    }

    if ( rank < (n - end)) {
        i = end + rank;
        memcpy( Wl, &(A[i*m]), m1*sizeof(PLASMA_Complex32_t));
        plasma_barrier(plasma);
        memcpy( &(A[i*m1]), Wl, m1*sizeof(PLASMA_Complex32_t));
    }
    else
        plasma_barrier(plasma);

    /* Restore leftover pieces */
    CORE_clacpy( PlasmaUpperLower, m0, bs, W, m0, &(A[(int64_t)m1*n+start*m0]), m0 );

    plasma_private_free(plasma, W);
    plasma_private_free(plasma, Wl);
}


void plasma_pcunpack(plasma_context_t *plasma)
{
    PLASMA_Complex32_t *A, *W, *Wl;
    PLASMA_sequence *sequence;
    PLASMA_request *request;
    int m, n, m0;
    int i, m1, size, rank, start, end, bs, mod;

    plasma_unpack_args_6(m, n, A, m0, sequence, request);
    if (sequence->status != PLASMA_SUCCESS)
        return;

    /* Quick return */
    if ( n <= 1 )
      return;

    m1 = m - m0;

    size = PLASMA_SIZE;
    rank = PLASMA_RANK;

    mod   = (n-1) % size;
    bs    = (n-1) / size;
    start = rank * bs;
    if ( rank < mod ) {
        bs++;
    }
    start += min( mod, rank );

    W  = (PLASMA_Complex32_t*)plasma_private_alloc(plasma, (m0*bs), PlasmaComplexFloat);
    Wl = (PLASMA_Complex32_t*)plasma_private_alloc(plasma, m1,      PlasmaComplexFloat);

    /* Save leftover pieces that are otherwise going to be overwritten */
    CORE_clacpy( PlasmaUpperLower, m0, bs, &(A[(int64_t)m1*n+start*m0]), m0, W, m0 );

    /* Unpack A */
    end = ((n-1) % size) ;
    for(i=n-1-rank; i>end; i-=size) {
        memcpy( Wl, &(A[i*m1]), m1*sizeof(PLASMA_Complex32_t));
        plasma_barrier(plasma);
        memcpy( &(A[i*m]), Wl, m1*sizeof(PLASMA_Complex32_t));
    }

    if ( rank < end ) {
        i = rank+1;
        memcpy( Wl, &(A[i*m1]), m1*sizeof(PLASMA_Complex32_t));
        plasma_barrier(plasma);
        memcpy( &(A[i*m]), Wl, m1*sizeof(PLASMA_Complex32_t));
    }
    else
        plasma_barrier(plasma);

    /* Restore leftover pieces */
    CORE_clacpy( PlasmaUpperLower, m0, bs, W, m0, &(A[(int64_t)start*m+m1]), m );

    plasma_private_free(plasma, W);
    plasma_private_free(plasma, Wl);
}