Visible to Intel only — GUID: GUID-B29EBCC6-C24B-4842-92CF-DE57E256F493
Visible to Intel only — GUID: GUID-B29EBCC6-C24B-4842-92CF-DE57E256F493
VM Naming Conventions
The VM function names are of mixed (lower and upper) case.
The VM mathematical and pack/unpack function names have the following structure:
v[m]<?><name><mod>
where
v is a prefix indicating vector operations.
[m] is an optional prefix for mathematical functions that indicates additional argument to specify a VM mode for a given function call (see vmlSetMode for possible values and their description).
<?> is a precision prefix that indicates one of the following data types:
- s
-
float.
- d
-
double.
- c
-
MKL_Complex8.
- z
-
MKL_Complex16.
<name> indicates the function short name, with some of its letters in uppercase. See examples in Table "VM Mathematical Functions".
<mod> field (written in uppercase) is present only in the pack/unpack functions and indicates the indexing method used:
- i
-
indexing with a positive increment
- v
-
indexing with an index vector
- m
-
indexing with a mask vector.
The VM service function names have the following structure:
vml<name>
where
<name> indicates the function short name, with some of its letters in uppercase. See examples in Table "VM Service Functions".
To call VM functions from an application program, use conventional function calls. For example, call the vector single precision real exponential function as
vsExp ( n, a, y );