ISMAX(3S)ISMAX(3S)NAME
ISMAX, IDMAX - Searches a real vector for the first occurrence of the
maximum value
SYNOPSIS
Single precision
Fortran:
integer ISMAX
integer index
index = ISMAX (n, x, incx)
C/C++:
#include <scsl_blas.h>
int ismax (int n, float *x, int incx);
Double precision
Fortran:
integer IDMAX
integer index
index = IDMAX (n, x, incx)
C/C++:
#include <scsl_blas.h>
int idmax (int n, double *x, int incx);
IMPLEMENTATION
These routines are part of the SCSL Scientific Library and can be loaded
using either the -lscs or the -lscs_mp option. The -lscs_mp option
directs the linker to use the multi-processor version of the library.
When linking to SCSL with -lscs or -lscs_mp, the default integer size is
4 bytes (32 bits). Another version of SCSL is available in which integers
are 8 bytes (64 bits). This version allows the user access to larger
memory sizes and helps when porting legacy Cray codes. It can be loaded
by using the -lscs_i8 option or the -lscs_i8_mp option. A program may use
only one of the two versions; 4-byte integer and 8-byte integer library
calls cannot be mixed.
The C and C++ prototypes shown above are appropriate for the 4-byte
integer version of SCSL. When using the 8-byte integer version, the
variables of type int become long long and the <scsl_blas_i8.h> header
file should be included.
DESCRIPTION
These routines search a vector for the first occurrence of the maximum
value.
ISMAX and IDMAX returns the first index i such that
x = MAX x : j = 1, ..., n (j = 0, ..., n-1 for C/C++)
Page 1
ISMAX(3S)ISMAX(3S)
i j
where xj is an element of a real vector.
These functions have the following arguments:
index Integer. (output)
First index of maximum value.
n Integer. (input)
Number of elements to process in the vector to be searched. If
n <= 0, ISMAX and ISMIN return 0 (-1 for C/C++).
x Array x of dimension 1 + (n-1) * |incx|.
ISMAX: Single precision array.
IDMAX: Double precision array.
Array containing the vector to be searched.
incx Integer. (input)
Increment between elements of x.
NOTES
When scanning backward (incx < 0), each routine starts at the end of the
vector and moves backward, as follows:
Fortran:
x(1 - incx * (n-1)), x(1 - incx * (n-2)), ..., x(1)
C/C++:
x[-incx * (n-1)], x[-incx * (n-2)], ..., x(0)
The desired value is at:
Fortran:
|x(1 + incx * (index-1))| when incx > 0
|x(1 - incx * (n-index))| when incx < 0
C/C++:
|x[incx * (index-1)]| when incx > 0
|x[-incx * (n-index)]| when incx < 0
Page 2
ISMAX(3S)ISMAX(3S)
These routines are extensions to the Level 1 Basic Linear Algebra
Subprograms (Level 1 BLAS).
Data Types
The following data types are described in this documentation.
Term Used Data type
Fortran:
Array dimensioned n x(n)
Integer INTEGER (INTEGER*8 for -lscs_i8[_mp])
Single precision REAL
Double precision DOUBLE PRECISION
C/C++:
Array dimensioned n x[n]
Integer int (long long for -lscs_i8[_mp])
Single precision float
Double precision double
SEE ALSOINTRO_SCSL(3S), INTRO_BLAS1(3S), ISAMAX(3S)INTRO_CBLAS(3S) for information about using the C interface to Fortran 77
Basic Linear Algebra Subprograms (legacy BLAS) set forth by the Basic
Linear Algebra Subprograms Technical Forum.
Page 3
