home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!haven.umd.edu!decuac!pa.dec.com!granite.pa.dec.com!ajc
- From: ajc@pa.dec.com (AJ Casamento)
- Newsgroups: comp.arch
- Subject: Re: COMPAQ PROPOSED SCALABLE I/O ARCHITECTURE
- Followup-To: comp.arch
- Date: 11 Jan 93 16:42:59
- Organization: Digital Equipment Corporation
- Lines: 69
- Message-ID: <AJC.93Jan11164259@thendara.pa.dec.com>
- References: <AJC.92Dec19132456@thendara.pa.dec.com> <BzoL0q.3zr.2@cs.cmu.edu>
- <AJC.93Jan4073719@thendara.pa.dec.com>
- <dbg-080193174652@kfp-slac-mac.slac.stanford.edu>
- NNTP-Posting-Host: thendara.pa.dec.com
- In-reply-to: dbg@slac.stanford.edu's message of Sat, 9 Jan 1993 02:09:00 GMT
-
-
- In-Reply-To: dbg@slac.stanford.edu's message of Sat, 9 Jan 1993 02:09:00 GM
-
- David,
-
- >>Gee, yet another opportunity to point out that the ANSI/IEEE Std 1596 SCI
- >>Scalable Coherent Interconnect is just what you want!
-
- Hmmm, I can think of a lot of things I "want", I'm not sure that SCI is among
- them. However, it is possible that SCI might be something I "need" at some
- point. ;-)
-
- Thanks for the pointers on the various design tools/implementations.
-
-
- >>But of course I understand that this discussion is futile--any engineer
- >>worth his salt (salary) gets his only pleasure in life from designing his
- >>own new unique solution to this problem! ;-) Sigh. But maybe his
- >>competitors will have higher profits because they get the benefit of the
- >>support infrastructure that grows around standards.
-
-
- Certainly a lot of folks do get a charge out of developing something new, which
- they can have some impact on. I would hazard a guess that this enjoyment might
- have kept you going during what must have surely been some interminable IEEE
- meetings in developing the SCI standard. No? I confess to enjoying this also,
- though I also happen to be a fairly opportunistic character who will "borrow"
- whatever technology/tool happens to fit the need.
-
- Standards can certainly be a good thing. It does not necessarily follow (at
- least for me) that therefore "all" standards are good. True SCI is an IEEE
- standard. So too is Futurebus+, and Sbus, and VME. And SCSI is an ANSI standard
- if we need an entry from that camp. My point is not to equate these to one
- another or stipulate which is better. Just that they all have the attribute of
- being a standard.
-
- Obviously each of these protocols deserves to be judged on its own merit. I
- also believe, personally, that standardization has its hazards. One can end up
- with a standard like ANSI SCSI-1 which "grandfathered" a great deal of very
- interesting behaviors into it based on products which were already shipping (it
- was a problem in reaching any consensus that would make existing shipping SCSI
- products non-compliant to the standard). Or, there is the "Profile" approach
- that Futurebus+ has (Profiles: A,B,D,F,M,T) where you make the protocol fit a
- wide variety of market uses by varying what the implementation looks like. I do
- not offer any judgement on whether one is inherently better than the other. I
- am also not certain that any one protocol is a "panacea" for all needs in the
- market.
-
- Your points on taking advantage of the volume/pricing of a popular standard are
- well taken. However, a standard can become so by popular acclaim rather than
- design by committee (as ISA did, or Sbus; which was popular long before it
- gained IEEE status). And, SCI may become a popular standard that garners a high
- volume of the market. I think it will be interesting to see what does happen.
-
-
- Still just my own opinion, of course.
-
- Thanx,
- AJ
-
-
- **********************************************************************
- * AJ Casamento "The question is not whether or *
- * Digital's TRI/ADD Program not the opinions are mine; but *
- * 529 Bryant Ave. PAG-2 rather, which of my personalities *
- * Palo Alto, CA 94301-1616 do they belong to?" *
- * 415.617.3460 *
- * ajc@pa.dec.com *
- **********************************************************************
-