Exemple #1
0
/**
    Purpose
    -------
    CGETRF_NOPIV computes an LU factorization of a general M-by-N
    matrix A without pivoting.

    The factorization has the form
       A = L * U
    where L is lower triangular with unit diagonal elements (lower
    trapezoidal if m > n), and U is upper triangular (upper
    trapezoidal if m < n).

    This is the right-looking Level 3 BLAS version of the algorithm.

    Arguments
    ---------
    @param[in]
    m       INTEGER
            The number of rows of the matrix A.  M >= 0.

    @param[in]
    n       INTEGER
            The number of columns of the matrix A.  N >= 0.

    @param[in,out]
    A       COMPLEX array, dimension (LDA,N)
            On entry, the M-by-N matrix to be factored.
            On exit, the factors L and U from the factorization
            A = P*L*U; the unit diagonal elements of L are not stored.

    @param[in]
    lda     INTEGER
            The leading dimension of the array A.  LDA >= max(1,M).

    @param[out]
    info    INTEGER
      -     = 0:  successful exit
      -     < 0:  if INFO = -i, the i-th argument had an illegal value
      -     > 0:  if INFO = i, U(i,i) is exactly zero. The factorization
                  has been completed, but the factor U is exactly
                  singular, and division by zero will occur if it is used
                  to solve a system of equations.

    @ingroup magma_cgesv_comp
    ********************************************************************/
extern "C" magma_int_t
magma_cgetrf_nopiv(
    magma_int_t m, magma_int_t n,
    magmaFloatComplex *A, magma_int_t lda,
    magma_int_t *info)
{
    #define A(i_,j_) (A + (i_) + (j_)*lda)
    
    magmaFloatComplex c_one = MAGMA_C_ONE;
    magmaFloatComplex c_neg_one = MAGMA_C_NEG_ONE;
    
    magma_int_t min_mn, i__3, i__4;
    magma_int_t j, jb, nb, iinfo;

    A -= 1 + lda;

    /* Function Body */
    *info = 0;
    if (m < 0) {
        *info = -1;
    } else if (n < 0) {
        *info = -2;
    } else if (lda < max(1,m)) {
        *info = -4;
    }
    if (*info != 0) {
        magma_xerbla( __func__, -(*info) );
        return *info;
    }

    /* Quick return if possible */
    if (m == 0 || n == 0) {
        return *info;
    }

    /* Determine the block size for this environment. */
    nb = 128;
    min_mn = min(m,n);
    if (nb <= 1 || nb >= min_mn) {
        /* Use unblocked code. */
        magma_cgetf2_nopiv( m, n, A(1,1), lda, info );
    }
    else {
        /* Use blocked code. */
        for (j = 1; j <= min_mn; j += nb) {
            jb = min( min_mn - j + 1, nb );
            
            /* Factor diagonal and subdiagonal blocks and test for exact
               singularity. */
            i__3 = m - j + 1;
            //magma_cgetf2_nopiv( i__3, jb, A(j,j), lda, &iinfo );

            i__3 -= jb;
            magma_cgetf2_nopiv( jb, jb, A(j,j), lda, &iinfo );
            blasf77_ctrsm( "R", "U", "N", "N", &i__3, &jb, &c_one,
                           A(j,j),    &lda,
                           A(j+jb,j), &lda );
            
            /* Adjust INFO */
            if (*info == 0 && iinfo > 0)
                *info = iinfo + j - 1;

            if (j + jb <= n) {
                /* Compute block row of U. */
                i__3 = n - j - jb + 1;
                blasf77_ctrsm( "Left", "Lower", "No transpose", "Unit",
                               &jb, &i__3, &c_one,
                               A(j,j),    &lda,
                               A(j,j+jb), &lda );
                if (j + jb <= m) {
                    /* Update trailing submatrix. */
                    i__3 = m - j - jb + 1;
                    i__4 = n - j - jb + 1;
                    blasf77_cgemm( "No transpose", "No transpose",
                                   &i__3, &i__4, &jb, &c_neg_one,
                                   A(j+jb,j),    &lda,
                                   A(j,j+jb),    &lda, &c_one,
                                   A(j+jb,j+jb), &lda );
                }
            }
        }
    }
    
    return *info;
} /* magma_cgetrf_nopiv */
Exemple #2
0
extern "C" magma_int_t
magma_cgetrf_nopiv(magma_int_t *m, magma_int_t *n, cuFloatComplex *a, 
                   magma_int_t *lda, magma_int_t *info)
{
/*  -- MAGMA (version 1.3.0) --
       Univ. of Tennessee, Knoxville
       Univ. of California, Berkeley
       Univ. of Colorado, Denver
       November 2012

    Purpose   
    =======   
    CGETRF_NOPIV computes an LU factorization of a general M-by-N
    matrix A without pivoting.

    The factorization has the form   
       A = L * U   
    where L is lower triangular with unit diagonal elements (lower 
    trapezoidal if m > n), and U is upper triangular (upper 
    trapezoidal if m < n).   

    This is the right-looking Level 3 BLAS version of the algorithm.   

    Arguments   
    =========   
    M       (input) INTEGER   
            The number of rows of the matrix A.  M >= 0.   

    N       (input) INTEGER   
            The number of columns of the matrix A.  N >= 0.   

    A       (input/output) COMPLEX*16 array, dimension (LDA,N)   
            On entry, the M-by-N matrix to be factored.   
            On exit, the factors L and U from the factorization   
            A = P*L*U; the unit diagonal elements of L are not stored.   

    LDA     (input) INTEGER   
            The leading dimension of the array A.  LDA >= max(1,M).   

    INFO    (output) INTEGER   
            = 0:  successful exit   
            < 0:  if INFO = -i, the i-th argument had an illegal value   
            > 0:  if INFO = i, U(i,i) is exactly zero. The factorization   
                  has been completed, but the factor U is exactly   
                  singular, and division by zero will occur if it is used   
                  to solve a system of equations.   
    =====================================================================   */
   
    cuFloatComplex c_one = MAGMA_C_ONE;
    
    magma_int_t a_dim1, a_offset, min_mn, i__3, i__4;
    cuFloatComplex z__1;
    magma_int_t j, jb, nb, iinfo;

    a_dim1 = *lda;
    a_offset = 1 + a_dim1;
    a -= a_offset;

    /* Function Body */
    *info = 0;
    if (*m < 0) {
        *info = -1;
    } else if (*n < 0) {
        *info = -2;
    } else if (*lda < max(1,*m)) {
        *info = -4;
    }
    if (*info != 0) {
        magma_xerbla( __func__, -(*info) );
        return *info;
    }

    /* Quick return if possible */
    if (*m == 0 || *n == 0) {
        return *info;
    }

    /* Determine the block size for this environment. */
    nb = 128;
    min_mn = min(*m,*n);
    if (nb <= 1 || nb >= min_mn) 
      {
        /* Use unblocked code. */
        magma_cgetf2_nopiv(m, n, &a[a_offset], lda, info);
      }
    else 
      {
        /* Use blocked code. */
        for (j = 1; j <= min_mn; j += nb)
          {
            /* Computing MIN */
            i__3 = min_mn - j + 1;
            jb = min(i__3,nb);
            
            /* Factor diagonal and subdiagonal blocks and test for exact   
               singularity. */
            i__3 = *m - j + 1;
            //magma_cgetf2_nopiv(&i__3, &jb, &a[j + j * a_dim1], lda, &iinfo);

            i__3 -= jb; 
            magma_cgetf2_nopiv(&jb, &jb, &a[j + j * a_dim1], lda, &iinfo);
            blasf77_ctrsm("R", "U", "N", "N", &i__3, &jb, &c_one, 
                          &a[j + j * a_dim1], lda,
                          &a[j + jb + j * a_dim1], lda);
            
            /* Adjust INFO */
            if (*info == 0 && iinfo > 0)
              *info = iinfo + j - 1;

            if (j + jb <= *n) 
              {
                /* Compute block row of U. */
                i__3 = *n - j - jb + 1;
                blasf77_ctrsm("Left", "Lower", "No transpose", "Unit", &jb, &i__3,
                       &c_one, &a[j + j * a_dim1], lda, &a[j + (j+jb)*a_dim1], lda);
                if (j + jb <= *m) 
                  {
                    /* Update trailing submatrix. */
                    i__3 = *m - j - jb + 1;
                    i__4 = *n - j - jb + 1;
                    z__1 = MAGMA_C_NEG_ONE;
                    blasf77_cgemm("No transpose", "No transpose", &i__3, &i__4, &jb, 
                           &z__1, &a[j + jb + j * a_dim1], lda, 
                           &a[j + (j + jb) * a_dim1], lda, &c_one, 
                           &a[j + jb + (j + jb) * a_dim1], lda);
                  }
              }
          }
      }
    
    return *info;
} /* magma_cgetrf_nopiv */
Exemple #3
0
/* ////////////////////////////////////////////////////////////////////////////
   -- Testing cgetrf
*/
int main( int argc, char** argv)
{
    TESTING_INIT();

    real_Double_t   gflops, gpu_perf, gpu_time, cpu_perf=0, cpu_time=0;
    float          error;
    magmaFloatComplex *h_A;
    magma_int_t     *ipiv;
    magma_int_t     M, N, n2, lda, info, min_mn;
    magma_int_t     status = 0;
    
    magma_opts opts;
    opts.parse_opts( argc, argv );
    
    float tol = opts.tolerance * lapackf77_slamch("E");

    printf("%% ngpu %d, version %d\n", (int) opts.ngpu, (int) opts.version );
    if ( opts.check == 2 ) {
        printf("%%   M     N   CPU Gflop/s (sec)   GPU Gflop/s (sec)   |Ax-b|/(N*|A|*|x|)\n");
    }
    else {
        printf("%%   M     N   CPU Gflop/s (sec)   GPU Gflop/s (sec)   |PA-LU|/(N*|A|)\n");
    }
    printf("%%========================================================================\n");
    for( int itest = 0; itest < opts.ntest; ++itest ) {
        for( int iter = 0; iter < opts.niter; ++iter ) {
            M = opts.msize[itest];
            N = opts.nsize[itest];
            min_mn = min(M, N);
            lda    = M;
            n2     = lda*N;
            gflops = FLOPS_CGETRF( M, N ) / 1e9;
            
            TESTING_MALLOC_CPU( ipiv, magma_int_t, min_mn );
            TESTING_MALLOC_PIN( h_A,  magmaFloatComplex, n2 );
            
            /* =====================================================================
               Performs operation using LAPACK
               =================================================================== */
            if ( opts.lapack ) {
                init_matrix( opts, M, N, h_A, lda );
                
                cpu_time = magma_wtime();
                lapackf77_cgetrf( &M, &N, h_A, &lda, ipiv, &info );
                cpu_time = magma_wtime() - cpu_time;
                cpu_perf = gflops / cpu_time;
                if (info != 0) {
                    printf("lapackf77_cgetrf returned error %d: %s.\n",
                           (int) info, magma_strerror( info ));
                }
            }
            
            /* ====================================================================
               Performs operation using MAGMA
               =================================================================== */
            init_matrix( opts, M, N, h_A, lda );
            if ( opts.version == 2 || opts.version == 3 ) {
                // no pivoting versions, so set ipiv to identity
                for (magma_int_t i=0; i < min_mn; ++i ) {
                    ipiv[i] = i+1;
                }
            }
            
            gpu_time = magma_wtime();
            if ( opts.version == 1 ) {
                magma_cgetrf( M, N, h_A, lda, ipiv, &info );
            }
            else if ( opts.version == 2 ) {
                magma_cgetrf_nopiv( M, N, h_A, lda, &info );
            }
            else if ( opts.version == 3 ) {
                magma_cgetf2_nopiv( M, N, h_A, lda, &info );
            }
            gpu_time = magma_wtime() - gpu_time;
            gpu_perf = gflops / gpu_time;
            if (info != 0) {
                printf("magma_cgetrf returned error %d: %s.\n",
                       (int) info, magma_strerror( info ));
            }
            
            /* =====================================================================
               Check the factorization
               =================================================================== */
            if ( opts.lapack ) {
                printf("%5d %5d   %7.2f (%7.2f)   %7.2f (%7.2f)",
                       (int) M, (int) N, cpu_perf, cpu_time, gpu_perf, gpu_time );
            }
            else {
                printf("%5d %5d     ---   (  ---  )   %7.2f (%7.2f)",
                       (int) M, (int) N, gpu_perf, gpu_time );
            }
            if ( opts.check == 2 ) {
                error = get_residual( opts, M, N, h_A, lda, ipiv );
                printf("   %8.2e   %s\n", error, (error < tol ? "ok" : "failed"));
                status += ! (error < tol);
            }
            else if ( opts.check ) {
                error = get_LU_error( opts, M, N, h_A, lda, ipiv );
                printf("   %8.2e   %s\n", error, (error < tol ? "ok" : "failed"));
                status += ! (error < tol);
            }
            else {
                printf("     ---   \n");
            }
            
            TESTING_FREE_CPU( ipiv );
            TESTING_FREE_PIN( h_A  );
            fflush( stdout );
        }
        if ( opts.niter > 1 ) {
            printf( "\n" );
        }
    }

    opts.cleanup();
    TESTING_FINALIZE();
    return status;
}