#include <lapacke.h>
#include "common.h"

Include dependency graph for core_cgeqrt.c:

Functions
int	CORE_cgeqrt (int M, int N, int IB, PLASMA_Complex32_t A, int LDA, PLASMA_Complex32_t T, int LDT, PLASMA_Complex32_t TAU, PLASMA_Complex32_t WORK)
void	QUARK_CORE_cgeqrt (Quark quark, Quark_Task_Flags task_flags, int m, int n, int ib, int nb, PLASMA_Complex32_t A, int lda, PLASMA_Complex32_t T, int ldt)
void	CORE_cgeqrt_quark (Quark *quark)

Detailed Description

PLASMA core_blas kernel PLASMA is a software package provided by Univ. of Tennessee, Univ. of California Berkeley and Univ. of Colorado Denver

Version:: 2.4.5

Author:: Hatem Ltaief; Mathieu Faverge; Jakub Kurzak

Date:: 2010-11-15 c Tue Nov 22 14:35:16 2011

Definition in file core_cgeqrt.c.

Function Documentation

int CORE_cgeqrt	(	int	M,
		int	N,
		int	IB,
		PLASMA_Complex32_t *	A,
		int	LDA,
		PLASMA_Complex32_t *	T,
		int	LDT,
		PLASMA_Complex32_t *	TAU,
		PLASMA_Complex32_t *	WORK
	)

CORE_cgeqrt computes a QR factorization of a complex M-by-N tile A: A = Q * R.

The tile Q is represented as a product of elementary reflectors

Q = H(1) H(2) . . . H(k), where k = min(M,N).

Each H(i) has the form

H(i) = I - tau * v * v'

where tau is a complex scalar, and v is a complex vector with v(1:i-1) = 0 and v(i) = 1; v(i+1:m) is stored on exit in A(i+1:m,i), and tau in TAU(i).

Parameters:

[in]	M	The number of rows of the tile A. M >= 0.
[in]	N	The number of columns of the tile A. N >= 0.
[in]	IB	The inner-blocking size. IB >= 0.
[in,out]	A	On entry, the M-by-N tile A. On exit, the elements on and above the diagonal of the array contain the min(M,N)-by-N upper trapezoidal tile R (R is upper triangular if M >= N); the elements below the diagonal, with the array TAU, represent the unitary tile Q as a product of elementary reflectors (see Further Details).
[in]	LDA	The leading dimension of the array A. LDA >= max(1,M).
[out]	T	The IB-by-N triangular factor T of the block reflector. T is upper triangular by block (economic storage); The rest of the array is not referenced.
[in]	LDT	The leading dimension of the array T. LDT >= IB.
[out]	TAU	The scalar factors of the elementary reflectors (see Further Details).
[out]	WORK

Returns:

Return values:

PLASMA_SUCCESS	successful exit
<0	if -i, the i-th argument had an illegal value

Definition at line 86 of file core_cgeqrt.c.

References coreblas_error, lapack_const, max, min, PLASMA_SUCCESS, PlasmaColumnwise, PlasmaConjTrans, PlasmaForward, and PlasmaLeft.

{
    int i, k, sb;
    /* Check input arguments */
    if (M < 0) {
        coreblas_error(1, "Illegal value of M");
        return -1;
    }
    if (N < 0) {
        coreblas_error(2, "Illegal value of N");
        return -2;
    }
    if ((IB < 0) || ( (IB == 0) && ((M > 0) && (N > 0)) )) {
        coreblas_error(3, "Illegal value of IB");
        return -3;
    }
    if ((LDA < max(1,M)) && (M > 0)) {
        coreblas_error(5, "Illegal value of LDA");
        return -5;
    }
    if ((LDT < max(1,IB)) && (IB > 0)) {
        coreblas_error(7, "Illegal value of LDT");
        return -7;
    }
    /* Quick return */
    if ((M == 0) || (N == 0) || (IB == 0))
        return PLASMA_SUCCESS;
    k = min(M, N);
    for(i = 0; i < k; i += IB) {
        sb = min(IB, k-i);
        LAPACKE_cgeqr2_work(LAPACK_COL_MAJOR, M-i, sb, 
                            &A[LDA*i+i], LDA, &TAU[i], WORK);
        LAPACKE_clarft_work(LAPACK_COL_MAJOR,
            lapack_const(PlasmaForward),
            lapack_const(PlasmaColumnwise),
            M-i, sb,
            &A[LDA*i+i], LDA, &TAU[i],
            &T[LDT*i], LDT);
        if (N > i+sb) {
            LAPACKE_clarfb_work(
                LAPACK_COL_MAJOR,
                lapack_const(PlasmaLeft),
                lapack_const(PlasmaConjTrans),
                lapack_const(PlasmaForward),
                lapack_const(PlasmaColumnwise),
                M-i, N-i-sb, sb,
                &A[LDA*i+i],      LDA,
                &T[LDT*i],        LDT,
                &A[LDA*(i+sb)+i], LDA,
                WORK, N-i-sb);
        }
    }
    return PLASMA_SUCCESS;
}

Here is the caller graph for this function:

void CORE_cgeqrt_quark ( Quark * quark )

Definition at line 181 of file core_cgeqrt.c.

References A, CORE_cgeqrt(), quark_unpack_args_9, T, and TAU.

{
    int m;
    int n;
    int ib;
    PLASMA_Complex32_t *A;
    int lda;
    PLASMA_Complex32_t *T;
    int ldt;
    PLASMA_Complex32_t *TAU;
    PLASMA_Complex32_t *WORK;
    quark_unpack_args_9(quark, m, n, ib, A, lda, T, ldt, TAU, WORK);
    CORE_cgeqrt(m, n, ib, A, lda, T, ldt, TAU, WORK);
}

Here is the call graph for this function:

Here is the caller graph for this function:

void QUARK_CORE_cgeqrt	(	Quark *	quark,
		Quark_Task_Flags *	task_flags,
		int	m,
		int	n,
		int	ib,
		int	nb,
		PLASMA_Complex32_t *	A,
		int	lda,
		PLASMA_Complex32_t *	T,
		int	ldt
	)

Definition at line 155 of file core_cgeqrt.c.

References CORE_cgeqrt_quark(), DAG_CORE_GEQRT, INOUT, OUTPUT, QUARK_Insert_Task(), SCRATCH, and VALUE.

{
    DAG_CORE_GEQRT;
    QUARK_Insert_Task(quark, CORE_cgeqrt_quark, task_flags,
        sizeof(int),                        &m,     VALUE,
        sizeof(int),                        &n,     VALUE,
        sizeof(int),                        &ib,    VALUE,
        sizeof(PLASMA_Complex32_t)*nb*nb,    A,             INOUT,
        sizeof(int),                        &lda,   VALUE,
        sizeof(PLASMA_Complex32_t)*ib*nb,    T,             OUTPUT,
        sizeof(int),                        &ldt,   VALUE,
        sizeof(PLASMA_Complex32_t)*nb,       NULL,          SCRATCH,
        sizeof(PLASMA_Complex32_t)*ib*nb,    NULL,          SCRATCH,
        0);
}

Here is the call graph for this function:

Here is the caller graph for this function:

Functions

Detailed Description

Function Documentation