home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!cs.utexas.edu!qt.cs.utexas.edu!yale.edu!yale!mintaka.lcs.mit.edu!ai-lab!case!dmb
- From: dmb@case.ai.mit.edu (David Baggett)
- Newsgroups: comp.sys.atari.st
- Subject: Re: PC VS ST
- Date: 25 Jan 1993 06:24:28 GMT
- Organization: MIT Artificial Intelligence Laboratory
- Lines: 25
- Message-ID: <1k012sINNbf6@life.ai.mit.edu>
- References: <1993Jan19.005142.13777@bsu-ucs> <73872@cup.portal.com> <93024.215308SML108@psuvm.psu.edu>)
- Reply-To: dmb@ai.mit.edu
- NNTP-Posting-Host: case.ai.mit.edu
-
- In article <93024.215308SML108@psuvm.psu.edu> <SML108@psuvm.psu.edu> writes:
- >And what exactly disqualifies the DSP as a general purpose computer?
-
- It's optimized for a fairly restricted set of operations, that's all.
- Yes, it's Turing-equivalent, but that doesn't mean the constant factors
- are small. :) The point is that while you can do "general purpose"
- things on a DSP, you're probably better off doing those things on a CPU
- that is optimized for "general purpose" things. In other words, don't
- use your DSP coprocessor for your B-Tree algorithms; your 68030 will
- run them faster.
-
- The other issue is, of course, I/O. The DSP is clearly a big loser for
- general purpose I/O (e.g., files and screen RAM) when compared to the
- CPU on the motherboard.
-
- >It's going to be a good year for computers. I'd advise anyone ready to
- >upgrade to wait and see what everyone releases this year...
-
- Isn't this always the case? That's what I love about this industry...
-
- Dave Baggett
- __
- dmb@ai.mit.edu Natural Language Processing MIT AI Lab
- ADVENTIONS: We make Kuul text adventures! Ask about Unnkulian 1, 2, 0, 1/2
- PO Box 851 Columbia, MD 21044 USA / CIS: 76440,2671 / GEnie: ADVENTIONS
-