home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.mac.programmer
- Path: sparky!uunet!pipex!harlqn.co.uk!harlqn!bear
- From: bear@harlqn.co.uk (Andy Edwards)
- Subject: Re: WARNING! WARNING! REMOVE A/ROSE!!!
- In-Reply-To: bwilliam@iat.holonet.net's message of Sat, 24 Oct 1992 05:09:28 GMT
- Message-ID: <BEAR.92Nov10201127@eve.harlqn.co.uk>
- Lines: 53
- Sender: news@harlqn.co.uk (Usenet News Account)
- Organization: Harlequin Limited, Cambridge, England
- References: <1992Oct20.155243.10181@gallant.apple.com> <BwM0zt.GDq@iat.holonet.net>
- Date: Tue, 10 Nov 1992 20:11:27 GMT
-
-
- Hi Bill,
-
- >The facts are in:
- >
- >To get back the 37% of speed with the A/ROSE 1.1.7 on a IIci or IIfx...
- >Just turn on virtual memory! Wow! Who would have thought to try that
- >(slightly counter-intuitive)
-
- Wo, hold on:
-
- >But there is more to the story ...
- >
- >It seems Apple ..[double click here to expand news item]..
- >
- >"Release notes for A/ROSE 1.1.8
- >
- >+ Implemented a workaround for a severe performance slowdown affecting
- >68030-based Macintoshes. The slowdown is caused by the poor
- >resolution--or lack--of memory page tables when Virtual Memory is disabled
- >on 68030-based Macintoshes, beginning with the Macintosh IIci. This
- >causes large blocks of memory (one-megabyte blocks or even all of
- >motherboard RAM) to be made non-cachable when memory is locked using the
- >Mac OS LockMemory routine in the MemoryDispatch trap.
- >The slowdown did not affect pre-Mac IIci 68030-based Macintoshes (which
- >did not implement the MemoryDispatch trap) or 68000-, 68020-, or
- >68040-based Macintoshes.
- >"
- >
- >According to Apple Dave, in a way it is related to VM Voodoo.
-
- Nah, I don't think that's got anything to do with VM being switched on
- at all, it's who gets to configure the MMU first that is the solution
- in this case!
-
- I bet what happens during boot up: before all the diddly inits & cdevs
- are run the VM system initialises the MMU with a sufficient number of
- page table entries. A/Rose doesn't get a sniff at reconfiguring the
- MMU (because it's already initialised), when it's init gets runned.
-
- >Bill Williams
-
- Best Regards,
- andy
-
- +--: Andy Edwards :----------*=================*------------------------------+
- | Macintosh fire fighter, | Harlequin Ltd. | uucp: bear@harlqn.uucp |
- | Deity, PostScript language | Barrington Hall | janet: bear@uk.co.harlqn |
- | level 2 porter and PAP | Barrington | applelink: harlequin |
- | server clone originator. | Cambridge | voice: 0223 872522 |
- | *They that have power to | CB2 5RG | +44-223-872-522 |
- | hurt, and will do none* | England | fax: 0223 872519 |
- +----------------------------*=================*------------------------------+
-