home *** CD-ROM | disk | FTP | other *** search
- Path: columba.udac.uu.se!not-for-mail
- From: trulsson@student.docs.uu.se (Erik Trulsson)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: Difference between 020 & 030 optimisation?
- Date: 12 Mar 1996 11:33:05 GMT
- Organization: Uppsala Universitet
- Message-ID: <4i3ndh$2bvs@columba.udac.uu.se>
- References: <38232880@kone.fipnet.fi> <Do4DHD.By3@cix.compulink.co.uk>
- NNTP-Posting-Host: minsk.docs.uu.se
- X-Newsreader: TIN [UNIX 1.3 950824BETA PL0]
-
- Jolyon Ralph (jralph@cix.compulink.co.uk) wrote:
- > > They have the same timings..
- >
- > In that case, I can't see any reason for 020/030 code being different
- > (which is what i suspected all along...)
- >
- > Jolyon
-
- As far as I know the only real differences between the 020 and 030
- (from a programmers point of view) apart from the MMU (that application
- writers shouldn't touch anyway) is that the 030 has a data cache and
- that the 020 has the CALLM/RETM instructions (that nobody uses anyway).
-
- The presence of a data cahe on the 030 might make a couple of
- extra optimizations possible but I don't think that they would make
- enough of a difference to be worth caring about.
-
- In short , making separate 020/030 version is certainly overkill.
- (Unless you are making something really lowlevel that *requires*
- stuff like messing with strange stackframes or using the MMU)
-