home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!haven.umd.edu!decuac!pa.dec.com!nntpd2.cxo.dec.com!nntpd.lkg.dec.com!engage.pko.dec.com!e2big.mko.dec.com!cvg.enet.dec.com!pettengill
- From: pettengill@cvg.enet.dec.com ()
- Subject: Re: Request Info Re Bus Trends & Intel 486s
- Message-ID: <1992Jul25.053124.14505@e2big.mko.dec.com>
- Sender: guest@e2big.mko.dec.com (Guest (DECnet))
- Reply-To: pettengill@cvg.enet.dec.com ()
- Organization: Digital Equipment Corporation
- References: <rjmartin.711191773@extro.ucc.su.OZ.AU> <1992Jul20.003506.23290@theus.rain.com> <GLEW.92Jul23192755@pdx007.intel.com>
- Date: Sat, 25 Jul 92 05:31:24 GMT
- Lines: 40
-
- In article <GLEW.92Jul23192755@pdx007.intel.com>, glew@pdx007.intel.com (Andy Glew) writes:
-
- |>[Burkhard Neidecker-Lutz]
- |>Can you explain which *desktop* applications need peer-to-peer communication ?
- |>I.e. what is wrong with going through main memory ?
- |>>
- |>>[John Theus]
- |>>To use today's favorite buzz word: multimedia.
- |>>
- |>[Andy Glew]
- |>First you'll put video on your screen.
- |>
- |>Then you'll want special effects: things like zooming in on a
- |>particular speaker (or the papers on his desk) in a video conference,
- |>things like cropping speakers from different video inputs and
- |>superimposing them into a virtual conference room.
-
- I assume from the tone of his note that Andy is arguing for peer to peer...
-
- I remember the early days of the Unibus, for which one of the selling features
- was peer to peer capability. However, I can't think of any standard or
- specialized device for the Unibus or the Qbus that ever made use of it.
- And, when I look at the graphics processors with special capabilities available
- today, none that I'm aware of do it with peer to peer, but rather have special
- ports.
-
- As someone who has worked on comm technology that can deliver both data and
- full motion video, I must say that I've never figured out a good architecture
- for having some data from the fiber go directly to the video display and other
- data from the fiber go to the memory and thence to the CPU. I'm not saying
- that's not possible, or that it won't happen, but since I haven't figured
- out how to architect it without constraints, I'm skeptical that it can be
- done given the constraints that current communication architectures imply.
-
- (Let's see, we'll make the video display an IP node and have the fiber
- interface adapter route IP packets to either the host CPU or the video
- display, so it might also have an IP address....
-
- mulp
- DEC
-