HP MLIB User's Guide Vol. 1 7th Ed.

368 HP MLIB User’s Guide

F_SGEMVER/F_DGEMVER/F_CGEMVER/F_ZGEMVER Multiple matrix-vector multiply, rank 2 update

Name F_SGEMVER/F_DGEMVER/F_CGEMVER/F_ZGEMVER

Multiple matrix-vector multiply, rank 2 update

Purpose F_xGEMVER precedes a combined matrix-vector and a transpose

matrix-vector multiply with a rank two update.

Matrix A is updated by and . The transpose of the updated matrix is

multiplied by a vector y. The resulting vector is scaled and added to the vector

operand z, and stored in x. The operand x is multiplied by the updated matrix

A. The resulting vector is stored in w. If m or n is less than or equal to zero, this

function returns immediately.

Usage VECLIB

INTEGER*4 INCW, INCX, INCY, INCZ, LDA, M, N

REAL*4 A( LDA, * ), W( * ), X( * ), Y( * ), Z( * )

REAL*4 ALPHA, BETA

REAL*4 U1( * ), V1( * ), U2( * ), V2( * )

SUBROUTINE F_SGEMVER (M, N, A, LDA, U1, V1, U2, V2, ALPHA, X,

INCX, Y, INCY, BETA, W, INCW, Z, INCZ)

INTEGER*4 INCW, INCX, INCY, INCZ, LDA, M, N

REAL*8 A( LDA, * ), W( * ), X( * ), Y( * ), Z( * )

REAL*8 ALPHA, BETA

REAL*8 U1( * ), V1( * ), U2( * ), V2( * )

SUBROUTINE F_DGEMVER (M, N, A, LDA, U1, V1, U2, V2, ALPHA, X,

INCX, Y, INCY, BETA, W, INCW, Z, INCZ)

INTEGER*4 INCW, INCX, INCY, INCZ, LDA, M, N

COMPLEX*8 A( LDA, * ), W( * ), X( * ), Y( * ), Z( * )

COMPLEX*8 ALPHA, BETA

COMPLEX*8 U1( * ), V1( * ), U2( * ), V2( * )

SUBROUTINE F_CGEMVER (M, N, A, LDA, U1, V1, U2, V2, ALPHA, X,

INCX, Y, INCY, BETA, W, INCW, Z, INCZ)

++←

x βA

yz+←

w αA

x←