Date: Thu, 29 Jul 1999 18:09:57 -0700 (PDT) From: The Utz Family <utz@serv.net> To: "James C. Durham" <durham@w2xo.pgh.pa.us> Cc: freebsd-multimedia@FreeBSD.ORG Subject: Re: Where is Gogo? I cant find it! Re: Gogo vs. Bladeenc, Part II Message-ID: <Pine.BSF.4.02.9907291800050.16307-100000@itchy.serv.net> In-Reply-To: <37A0F791.FB177F58@w2xo.pgh.pa.us>
next in thread | previous in thread | raw e-mail | index | archive | help
Ok, so the final wrapup on this would be to find out if matt's machine shows the same performance ratio enhancement over blade and lame as James' machine does. that would eliminate the additional 4dimensional matrix operations(mmx, 3dnow) as the source for gogo's performance win. *if* it *still* has the same speedup, then one must ask how fast one could do a conversion using code that takes advantage of the hardware matrix ops? just pondering! :-) john On Thu, 29 Jul 1999, James C. Durham wrote: > just matt wrote: > > > > > maybe it wont even work on a non Amd3d now or MMX aware computer???? > > > > It functions correctly on my non-mmx pentium 90. > > > > Matt > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > > with "unsubscribe freebsd-multimedia" in the body of the message > > Yes, as I posted earlier, it's 4 times as fast as > blade, twice as fast as lame on my P200MMX, so it > works on MMX processors. Can someone try on an AMD? > > I'm running about 1.5 to 1 with gogo. Nice job! > -- > Jim Durham > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-multimedia" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-multimedia" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.02.9907291800050.16307-100000>