Developer Reference for Intel® oneAPI Math Kernel Library for Fortran

ID 766686
Date 3/31/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

p?amax

Computes the global index of the element of a distributed vector with maximum absolute value.

Syntax

call psamax(n, amax, indx, x, ix, jx, descx, incx)

call pdamax(n, amax, indx, x, ix, jx, descx, incx)

call pcamax(n, amax, indx, x, ix, jx, descx, incx)

call pzamax(n, amax, indx, x, ix, jx, descx, incx)

Include Files
  • mkl_pblas.h
Description

The functions p?amax compute global index of the maximum element in absolute value of a distributed vector sub(x),

where sub(x) denotes X(ix, jx:jx+n-1) if incx=m_x, and X(ix: ix+n-1, jx) if incx= 1.

Input Parameters
n

(global) INTEGER. The length of distributed vector sub(x), n0.

x

(local) REAL for psamax

DOUBLE PRECISION for pdamax

COMPLEX for pcamax

DOUBLE COMPLEX for pzamax

Array, size (jx-1)*m_x + ix+(n-1)*abs(incx)).

This array contains the entries of the distributed vector sub(x).

ix, jx

(global) INTEGER. The row and column indices in the distributed matrix X indicating the first row and the first column of the submatrix sub(X), respectively.

descx

(global and local) INTEGER array of dimension 9. The array descriptor of the distributed matrix X.

incx

(global) INTEGER. Specifies the increment for the elements of sub(x). Only two values are supported, namely 1 and m_x. incx must not be zero.

Output Parameters
amax

(global)REAL for psamax.

DOUBLE PRECISION for pdamax.

COMPLEX for pcamax.

DOUBLE COMPLEX for pzamax.

Maximum absolute value (magnitude) of elements of the distributed vector only in its scope.

indx

(global) INTEGER. The global index of the maximum element in absolute value of the distributed vector sub(x) only in its scope.