11 messages in at.iem.pd-dev[PD-dev] amd64: rsqrt~| From | Sent On | Attachments |
|---|---|---|
| Tim Blechmann | Sep 10, 2005 2:36 pm | |
| Thomas Grill | Sep 10, 2005 3:59 pm | |
| IOhannes m zmoelnig | Sep 11, 2005 10:23 am | |
| Mathieu Bouchard | Sep 11, 2005 11:57 am | |
| IOhannes m zmoelnig | Sep 11, 2005 12:10 pm | |
| Tim Blechmann | Sep 11, 2005 12:36 pm | |
| Mathieu Bouchard | Sep 11, 2005 1:47 pm | |
| IOhannes m zmölnig | Sep 11, 2005 1:56 pm | |
| Thomas Grill | Sep 11, 2005 2:30 pm | |
| Tim Blechmann | Sep 11, 2005 4:13 pm | |
| Mathieu Bouchard | Sep 11, 2005 8:06 pm |
| Subject: | [PD-dev] amd64: rsqrt~ | |
|---|---|---|
| From: | Tim Blechmann (TimB...@gmx.net) | |
| Date: | Sep 10, 2005 2:36:05 pm | |
| List: | at.iem.pd-dev | |
hi miller, hi devs ...
the current implementation of rsqrt~ is most likely broken. i was sshing to carmen's amd64 machine ... looked like that filling the lookup table isn't really working ...
static void init_rsqrt(void) { int i; for (i = 0; i < DUMTAB1SIZE; i++) { float f; long l = (i ? (i == DUMTAB1SIZE-1 ? DUMTAB1SIZE-2 : i) : 1)<< 23; *(long *)(&f) = l; rsqrt_exptab[i] = 1./sqrt(f); } for (i = 0; i < DUMTAB2SIZE; i++) { float f = 1 + (1./DUMTAB2SIZE) * i; rsqrt_mantissatab[i] = 1./sqrt(f); } }
couldn't really look into it, but i guess, the wild cast in *(long *)(&f) = l; might be a problem on th x86_64 architecture ...
not really a problem for devel, since devel most likely uses sse instructions to do the rsqrt computation ... but someone who is into vanilla pd might be interested in having a look at it ..
cheers ... tim
-- mailto:TimB...@gmx.de ICQ: 96771783 http://www.mokabar.tk
latest mp3: kMW.mp3 http://mattin.org/mp3.html
latest cd: Gohü Lee Kwang & Tim Blechmann: Drone http://www.geocities.com/gohleekwangtimblechmannduo/
After one look at this planet any visitor from outer space would say "I want to see the manager." William S. Burroughs