Return to BSD News archive
Received: by minnie.vk1xwt.ampr.org with NNTP id AA245 ; Sun, 31 Jan 93 13:59:10 EST Xref: sserve comp.unix.bsd:10571 comp.sys.ibm.pc.hardware:42632 Newsgroups: comp.unix.bsd,comp.sys.ibm.pc.hardware Path: sserve!manuel.anu.edu.au!munnari.oz.au!spool.mu.edu!sdd.hp.com!elroy.jpl.nasa.gov!ames!pacbell.com!att-out!cbnewsj!dwex From: dwex@cbnewsj.cb.att.com (david.e.wexelblat) Subject: Re: ATI Mach32 and Xfree86 or XS3? Organization: AT&T Date: Fri, 29 Jan 1993 17:55:23 GMT Message-ID: <1993Jan29.175523.13926@cbnewsj.cb.att.com> References: <1993Jan27.052056.23103@informix.com> <1ka60dINNhp3@matt.ksu.ksu.edu> <1993Jan29.052847.11959@netcom.com> Lines: 54 In article <1993Jan29.052847.11959@netcom.com> hasty@netcom.com (Amancio Hasty Jr) writes: > In article <1ka60dINNhp3@matt.ksu.ksu.edu> nan@matt.ksu.ksu.edu (Nan Zou) writes: > >johng@informix.com (John Galloway) writes: > >>hasty@netcom.com (Amancio Hasty Jr) writes: > >we can probably expect 170K Xstones from a Weitek P9000 based-card. WOW! > > Well according to Weitek they are getting 60k xstones... > > As for a server I have the specs here so maybe while I wait around > for the 928 to arrive I can write a weitek p9000 server. :-) > > I am expecting the weitek server to about the same as the 928 server.. > > So folks, we are moving into high-end graphics boards which are becoming > a commodity. > > > Cheers, > Amancio > -- > This message brought to you by the letters X and S and the number 3 > Amancio Hasty | > Home: (415) 495-3046 | ftp-site depository of all my work: > e-mail hasty@netcom.com | sunvis.rtpnc.epa.gov:/pub/386bsd/incoming Word I hear is that the Weitek chip is essentially a Sun GX, and only supports acceleration at 8 bits. It does support a linear mapping of the frame buffer, but you can't accelerate HiColor/TruColor with it. Of course, I don't have the specs on the chip yet. The S3 928, on the otherhand, can support 4M of VRAM, a true 24/32-bit RAMDAC (which is expensive), and acceleration at 4, 8, 16, and 24bpp. I'm saving my money for the high-end 928 boards. Beware the early, inexpensive 928 boards. You won't be able to do 1024x768x24 with them (they seem to only have 2M VRAM), and they have a silly 8-bit RAMDAC, which requires 2 cycles for 16-bit modes and 3 cycles for 24-bit modes. So while it may be cheap, the performance will suffer at the high end of the spectrum. And I have it on good authority (2 independent sources) that Amancio's performance estimates for the 928 are low. Which gives him something to strive for. Of course, when you're getting to 100k+ xStones, the differences aren't that visible. The next generation needs to support things like double-buffering, Z-buffer, overlay planes, hardware implementation of higher-level X concepts (wide lines, etc), hardware lighting/HLHRS, etc, etc. -- David Wexelblat <dwex@mtgzfs3.att.com> (908) 957-5871 AT&T Bell Laboratories, 200 Laurel Ave - 3F-428, Middletown, NJ 07748 "The meaning of life? That's simple. Try to be happy, try not to hurt other people, and hope to fall in love." -- Mallory Keaton