home *** CD-ROM | disk | FTP | other *** search
- Path: nntp.hut.fi!usenet
- From: oahvenla@hyppynaru.cs.hut.fi (Osma Ahvenlampi)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: Difference between 020 & 030 optimisation?
- Date: 07 Mar 1996 19:36:58 +0200
- Organization: What, me, organised?
- Sender: oahvenla@hyppynaru.cs.hut.fi
- Distribution: inet
- Message-ID: <jdj91hcby9x.fsf@hyppynaru.cs.hut.fi>
- References: <4hju8q$mtd@leofric.coventry.ac.uk> <4hkm47$bud@news.sdd.hp.com>
- NNTP-Posting-Host: hyppynaru.cs.hut.fi
- Mime-Version: 1.0
- Content-Type: text/plain; charset=US-ASCII
- In-reply-to: Jeff Grimmett's message of 6 Mar 1996 18:39:03 GMT
- X-Newsreader: Gnus v5.1
-
- In article <4hkm47$bud@news.sdd.hp.com> Jeff Grimmett <jgrimm@bitnova.com> writes:
- >dj@coventry.ac.uk (Dave Jackson) wrote:
- >>What is the difference between an '030 version of a program and an '020
- >>version of the same program? Surely the only difference between the two
- >>processors is that the '030 has a data cache, so does the optimiser
- >>(C/ASM) do anything differently because of it?
- >What I found is that the code for the 020, 030, and 040 were all
- >identical when compiled with SAS/C 6.55. I even went as far as to DIFF
- >the files to find differences other than size, and the only part that was
- >different was the compile time embedded in the library's version.
-
- Did you use OPTSCHED? I would expect there to be differences in the
- order of instructions, since the major difference between these CPUs
- (besides the size of the caches) is the relative execution time
- between instructions.
-
- --
- I didn't know it was impossible when I did it.
- | "Osma Ahvenlampi" <mailto:oa@iki.fi> <http://www.iki.fi/oa/> |
- | Amiga&BeBox&ClassAct&Voodoo&ARTech cool stuff: I-Net225&AWeb |
- --
-