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

Chapter 1 Introduction to VECLIB 25
Data type and byte length
Data type and byte length
There is a relationship between the data type of a subprogram, designated by
the first character of its name (refer to T in Table 1-3), and the byte lengths of
its arguments. This relationship is shown in Table :
MLIB Argument Lengths
Operator arguments
Some BLAS routines take input-only arguments called operators that allow for
the specification of multiple related operations to be performed by a single
function. Operator arguments used by the BLAS Standard routines are NORM,
SORT, SIDE, UPLO, TRANS, CONJ, DIAG
, and JROT. Their meanings are
defined as follows:
norm Used by routines computing the norm of a vector or
matrix. There are seven valid values that specify the
norm to be computed, namely one-norm, real one-norm,
infinity-norm and real infinity-norm for vectors and
matrices, two-norm for vectors, and Frobenius-norm,
max-norm, and real max-norm for matrices.
sort Used by sorting routines.There are two valid values
that specify whether the data should be specified in
increasing or decreasing order.
side Used by functions computing the product of two
matrices A and B. There are two valid values that
specify whether A*B or B*A should be computed.
T
MLIB Argument Lengths
VECLIB
INTEGER
LOGICAL
VECLIB8
INTEGER
LOGICAL
REAL COMPLEX
S4 8 4 8
D4 8 8 16
C4 8 4 8
Z4 8 8 16