Re: [Mesa-dev] IROUND, math errors, etc.

2015-07-31 Thread Roland Scheidegger
Am 31.07.2015 um 18:44 schrieb Matt Turner: > On Fri, Jul 31, 2015 at 7:13 AM, Roland Scheidegger > wrote: >> CC mesa-dev. >> >> This looks good to me. I am starting to wonder though why we don't just >> use lrintf() and let the compiler sort it out (for x86 too). >> Though actually some quick ex

Re: [Mesa-dev] IROUND, math errors, etc. (was: Re: proposed patch optimized F_TO_I for powerpc platforms)

2015-07-31 Thread Matt Turner
On Fri, Jul 31, 2015 at 7:13 AM, Roland Scheidegger wrote: > CC mesa-dev. > > This looks good to me. I am starting to wonder though why we don't just > use lrintf() and let the compiler sort it out (for x86 too). > Though actually some quick experiments show that: > - llvm's clang will always use

[Mesa-dev] IROUND, math errors, etc. (was: Re: proposed patch optimized F_TO_I for powerpc platforms)

2015-07-31 Thread Roland Scheidegger
CC mesa-dev. This looks good to me. I am starting to wonder though why we don't just use lrintf() and let the compiler sort it out (for x86 too). Though actually some quick experiments show that: - llvm's clang will always use libm lrintf call. Which then will do (x86_64) cvtss2si %xmm0,%rax as ex