Except that f is made of floating points, is there any trick I can use to use take profit of HVX using floating points? I mean using vectorization or parallelization.
Unfortunately, no, you'll have to find a way to express your algorithm without floats. I think Hexagon can do scalar floating point math, but that's probably not what you want (it's not HVX).
Hi,
I'd like to do this:
Except that f is made of floating points, is there any trick I can use to use take profit of HVX using floating points? I mean using vectorization or parallelization.