home *** CD-ROM | disk | FTP | other *** search
- Path: comma.rhein.de!serpens!not-for-mail
- From: mlelstv@serpens.rhein.de (Michael van Elst)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: CHIP RAM speed test resul
- Date: 15 Apr 1996 09:16:05 +0200
- Organization: dis-
- Message-ID: <4kst3l$oi7@serpens.rhein.de>
- References: <4j6jv0$1im@serpens.rhein.de> <5827.6659T112T770@mbox.vol.it> <1996Apr2.234528.8971@scala.scala.com> <4k1kk3$i2q@sunsystem5.informatik.tu-muenchen.de> <peterk.0mvy@combo.ganesha.com>
- NNTP-Posting-Host: serpens.rhein.de
-
- peterk@combo.ganesha.com (Dr. Peter Kittel) writes:
-
- >In article <4k1kk3$i2q@sunsystem5.informatik.tu-muenchen.de> fischerj@Informatik.TU-Muenchen.DE (Juergen "Rally" Fischer) writes:
- >>
- >>BTW imho it should cost almost nothing to add a A3000-alike chipmembuffer,
-
- >Oops, that Amber chip was one of the most expensive parts in the A3000!
- >No, not at all like "cost almost nothing".
-
- Sorry, Juergen meant something completely different.
-
- >>: >It would be sufficient to modify the interface CPU <->chipram<-> Alice.
-
- >To explain it: This would mean a *complete* redesign of the AA chipset.
-
- Sorry, the modification wouldn't require changes in the chipset. It
- requires extra logic for the CPU data path and a few address bits.
- You could save on the address logic if Alice would generate double-cas
- cycles for the CPU too.
-
- Regards,
- --
- Michael van Elst
-
- Internet: mlelstv@serpens.rhein.de
- "A potential Snark may lurk in every tree."
-