[Pixman] Performance of radial gradients

Luca Barbato lu_zero at gentoo.org
Mon Feb 22 09:40:34 PST 2010

On 02/22/2010 05:42 PM, Jonathan Morton wrote:
> On Mon, 2010-02-22 at 18:39 +0200, Siarhei Siamashka wrote:
>> The usage of sqrt is probably not a fatal performance problem.
> Most desktop-style PowerPCs in the wild have a dedicated fsqrt{f}
> instruction (with approximately the same expense as fdiv{f}), and
> Altivec can efficiently use the Newton-Raphson method as well.
> Even x87 has transcendentals covered rather well.  In fact it's one of
> the few things it's genuinely good at, justifying the relatively high
> expense of an FPU in the early days.
> So provided there aren't too many of them, I would not consider sqrt a
> huge problem - just like a divide really.

Right, it isn't something fatal, still if we could do w/out could be nicer.



Luca Barbato

More information about the Pixman mailing list