Date: Sun, 27 Jul 1997 00:40:57 +0300 (EEST) From: Petri Helenius <pete@sms.fi> To: "Gary T. Corcoran" <garycorc@idt.net> Cc: Anthony.Kimball@East.Sun.COM, multimedia@FreeBSD.ORG Subject: Re: Software MPEG-2 (Was: Posting prefix) Message-ID: <199707262140.AAA00828@silver.sms.fi> In-Reply-To: <33DA685A.446B9B3D@idt.net> References: <199707242045.PAA03915@compound.east.sun.com> <199707242113.OAA15573@rah.star-gate.com> <199707250502.IAA29406@silver.sms.fi> <199707250706.CAA03136@compound.east.sun.com> <33DA685A.446B9B3D@idt.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Gary T. Corcoran writes: > Tony Kimball wrote: > > I heard Intel (first hand) say that a 233MHz MMX Pentium will *almost*, > *but not quite* be fast enough for software MPEG-2 decode (they tried it). > In other words, while it generally worked, for high complexity/high motion > scenes, it hiccuped. So until most of us have 300+ MHz processors, we'll > need to use hardware for MPEG-2 decoding. While I don't want to start a discussion about the benefits of general purpose processors I would say that at the current level of technology it's much cheaper to decode MPEG-2 and to some extent MPEG in hardware since the cost of general purpose processor to do that is at least fivefold to the chip doing the job at full rates. > > Of course, if you'd like to get a head start and start writing code for > future processors, be my guest... ;-) > > Or maybe you can find a "trick" that Intel didn't think of... ??? > Pete
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199707262140.AAA00828>