Skip to main content
10 events
when toggle format what by license comment
Apr 11, 2024 at 18:40 comment added Qwertie @Coder floating point. Fixed point is int math, so it's the same speed as int math. Floating point can be faster if the processor was heavily optimized for that, which I've heard is sometimes so, e.g. the amount of FP hardware could simply be much greater than the amount of int hardware, so it gets deeper pipelining or superior SIMD support.
Apr 7, 2024 at 12:43 comment added Coder You said: " (FP may even be faster) " By FP do you mean fixed point or floating point? And if you mean floating point, why would floating point be faster than integer? In what constellations does this occur?
Dec 23, 2021 at 21:20 history edited Qwertie CC BY-SA 4.0
added 272 characters in body
Jan 23, 2014 at 14:42 comment added crush Amen. Premature optimization is thrown around far too liberally these days by people who try to justify using the wrong tool for the job. If you know the right tool for the job ahead of time, then there is no excuse for not using it.
Oct 27, 2013 at 3:20 history made wiki Post Made Community Wiki by Michael Shaw
May 1, 2012 at 21:58 history edited Qwertie CC BY-SA 3.0
added 543 characters in body
May 1, 2012 at 21:46 history edited Qwertie CC BY-SA 3.0
added 543 characters in body
May 1, 2012 at 21:37 history edited Qwertie CC BY-SA 3.0
added 543 characters in body
May 1, 2012 at 21:24 history edited Qwertie CC BY-SA 3.0
added 356 characters in body
May 1, 2012 at 21:10 history answered Qwertie CC BY-SA 3.0