home *** CD-ROM | disk | FTP | other *** search
- Path: comma.rhein.de!serpens!not-for-mail
- From: mlelstv@serpens.rhein.de (Michael van Elst)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: CHIP RAM speed test results
- Date: 23 Mar 1996 14:47:34 +0100
- Organization: dis-
- Message-ID: <4j0vdm$cli@serpens.rhein.de>
- References: <4iogfh$e6i@serpens.rhein.de> <4j0p69$9f6@fizban.solace.mh.se>
- NNTP-Posting-Host: serpens.rhein.de
-
- cmh@lls.se (Magnus Holmgren) writes:
-
- > MvE> This is exactly why the move16 was implemented, to avoid the cost of
- > MvE> the copyback cache when doing bulk copies. Unfortunately it requires
- > MvE> that source and destination are properly aligned, something that is
- > MvE> difficult to achieve under AmigaOS.
-
- >It isn't that difficult if you allocate structs yourself, is it? Allocate
- >some extra bytes, mask, and you're done..
-
- This is surely true. But one major usage of MOVE16 is coyping of
- I/O-Buffers which are rarely aligned.
-
- >On the Amiga, MOVE16 is not supported 100%. Causing an Enforcer hit
- >with a MOVE16 will cause major problems and maybe cause Enforcer or
- >your task to lock.
-
- This isn't a problem because good programs don't cause Enforcer hits :)
-
- >instruction. (Also, watch out for the 68040 CPU bug with MOVE16)
-
- Some revisions of the 040 have bugs and MOVE16 can corrupt data.
-
- Regards,
- --
- Michael van Elst
-
- Internet: mlelstv@serpens.rhein.de
- "A potential Snark may lurk in every tree."
-