simdpp::sign
From libsimdpp-docs
< fp
template<unsigned N, class E>
Ret<N, _DETAIL_> sign( Vec<N,E> a ); |
||
Extracts the sign bits from the values in a floating-point vector. The implementation behaves as if the following set of overloads is provided:
Ret
|
Vec
|
---|---|
float32 | float32 |
float64 | float64 |
The return type is a vector expression.
Parameters[edit]
a | - | floating-point vector |
Return value[edit]
A vector expression evaluating to the sign bits of a
.
Equivalent operation[edit]
r0 = a0 & 0x800...00 ... rN = aN & 0x800...00
See also[edit]
This section is incomplete |