The float (or double if optional double is supported)
value given by data
is first converted to a half value using
the appropriate rounding mode. The half value is then written to address computed
as (p
+ offset
). The address computed as
(p
+ offset
) must be 16-bit aligned.
vstore_half
uses the current rounding mode. The default current
rounding mode is round to nearest even.
Vector Data Load and Store Functions allow you to read and write vector types from a pointer to memory.
The generic type gentype is used to indicate the built-in data types char, uchar, short, ushort, int, uint, long, ulong, float, or double.
The generic type name gentypen
represents n
-element vectors of gentype
elements. The suffix n
is also used in the
function names (i.e. vload
,
n
vstore
, etc.), where
n
n
= 2, 3, 4, 8, or 16.
The results of vector data
load and store functions are undefined if the address being read from or written to is
not correctly aligned. The pointer argument p
can be a pointer to
__global,
__local, or
__private
memory for store functions. The pointer argument
p
can be a pointer to __global, __local, __constant or __private
memory for load functions.