home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!stanford.edu!rutgers!cbmvax!mks
- From: mks@cbmvax.commodore.com (Michael Sinz)
- Newsgroups: comp.sys.amiga.misc
- Subject: Re: JAM info on A570 & A2200/A2400 (public info!)
- Message-ID: <34401@cbmvax.commodore.com>
- Date: 17 Aug 92 19:04:31 GMT
- References: <jbono.02kx@tension.UUCP> <1992Aug14.222143.770@pro-freedom.cts.com>
- Reply-To: mks@cbmvax.commodore.com (Michael Sinz)
- Organization: Commodore, West Chester, PA
- Lines: 24
-
- eeb@pro-freedom.cts.com (Ed Brown) writes:
- >
- > > An '020 is about 75% of the speed of an '030.
-
- A 68020 is more like 95% of the speed of a 68030 in real
- software use *AS LONG AS THERE IS NO MMU* attached. The 68020 has
- the MMU external and this causes a full wait state for each memory
- access. In real code, the data cache of the 68030 makes rather little
- difference (it does may some difference) and the sligbtly different timings
- of the instructions are also rather small. I am sure that some test cases
- will show that a 68030 is much faster than a 68020 but then test cases are
- not the norm usually and in normal operation it is only a 5% (+/- a bit)
- difference.
-
- Now, with an MMU, the 68030 can be *much* faster than a 68020 with MMU.
- Depending on the memory system, this can be as much as 33%.
-
- /----------------------------------------------------------------------\
- | /// Michael Sinz - Senior Amiga Systems Engineer |
- | /// Operating System Development Group |
- | /// BIX: msinz UUNET: mks@cbmvax.commodore.com |
- |\\\/// "A master's secrets are only as good as the |
- | \XX/ master's ability to explain them to others" - Michael Sinz |
- \----------------------------------------------------------------------/
-