Developer Reference

Contents

PBLAS Routine Naming Conventions

The naming convention for PBLAS routines is similar to that used for BLAS routines (see Routine Naming Conventions). A general rule is that each routine name in PBLAS, which has a BLAS equivalent, is simply the BLAS name prefixed by initial letter
p
that stands for "parallel".
The
Intel® oneAPI Math Kernel Library
PBLAS routine names have the following structure:
p <character> <name> <mod> ( )
The <
character
> field indicates the Fortran data type:
s
real, single precision
c
complex, single precision
d
real, double precision
z
complex, double precision
i
integer
Some routines and functions can have combined character codes, such as
sc
or
dz
.
For example, the function
pscasum
uses a complex input array and returns a real value.
The
<name>
field, in PBLAS level 1, indicates the operation type. For example, the PBLAS level 1 routines
p?dot
,
p?swap
,
p?copy
compute a vector dot product, vector swap, and a copy vector, respectively.
In PBLAS level 2 and 3,
<name>
reflects the matrix argument type:
ge
general matrix
sy
symmetric matrix
he
Hermitian matrix
tr
triangular matrix
In PBLAS level 3, the
<name>
=
tran
indicates the transposition of the matrix.
The
<mod>
field, if present, provides additional details of the operation. The PBLAS level 1 names can have the following characters in the
<mod>
field:
c
conjugated vector
u
unconjugated vector
The PBLAS level 2 names can have the following additional characters in the
<mod>
field:
mv
matrix-vector product
sv
solving a system of linear equations with matrix-vector operations
r
rank-1 update of a matrix
r2
rank-2 update of a matrix.
The PBLAS level 3 names can have the following additional characters in the
<mod>
field:
mm
matrix-matrix product
sm
solving a system of linear equations with matrix-matrix operations
rk
rank-
k
update of a matrix
r2k
rank-2
k
update of a matrix.
The examples below show how to interpret PBLAS routine names:
pddot
<p> <d> <dot>
: double-precision real distributed vector-vector dot product
pcdotc
<p> <c> <dot> <c>
: complex distributed vector-vector dot product, conjugated
pscasum
<p> <sc> <asum>
: sum of magnitudes of distributed vector elements, single precision real output and single precision complex input
pcdotu
<p> <c> <dot> <u>
: distributed vector-vector dot product, unconjugated, complex
psgemv
<p> <s> <ge> <mv>
: distributed matrix-vector product, general matrix, single precision
pztrmm
<p> <z> <tr> <mm>
: distributed matrix-matrix product, triangular matrix, double-precision complex.
Product and Performance Information
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.
Notice revision #20201201

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.