home *** CD-ROM | disk | FTP | other *** search
- Path: informatik.tu-muenchen.de!fischerj
- From: fischerj@Informatik.TU-Muenchen.DE (Juergen "Rally" Fischer)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: CHIP RAM speed test results
- Date: 23 Mar 1996 04:33:47 GMT
- Organization: Technische Universitaet Muenchen, Germany
- Distribution: world
- Message-ID: <4ivuvb$s3p@sunsystem5.informatik.tu-muenchen.de>
- References: <38232981@kone.fipnet.fi> <4ico8k$2vau@columba.udac.uu.se> <42116651@phoenix.owl.de>
- NNTP-Posting-Host: hphalle5.informatik.tu-muenchen.de
- X-Newsreader: TIN [version 1.2 PL2]
-
- Frank Wille (frank@phoenix.owl.de) wrote:
-
- : With my 68040/25MHz I'm getting the following results:
-
- : move.l (a0)+,(a1)+ -> 3.99 MB/sec
- : move16 (a0)+,(a1)+ -> 5.91 MB/sec
-
- : So MOVE16 is 50% faster, although the A3640 doesn't support burst
- : transfers.
-
- mhm I always though it's a question of mem-type how fast moves are.
- are there good boards which can squeeze max bandwidth ?
- move16 should be same speed like move on those.
-
- BTW timings of my board:
-
- move020 (a0)+,(a1)+ -> 8.8 MB/sec
-
- so move020 is 50% faster than move16 although the A1201 doesn't
- support burst transfers.
-
- :)
-
- am I right the speed of 3640 compared to other boards alternates
- quite much dependent of the code ?
- all those shifts, branches and reg,reg adds done hi-speed, but if
- a mem read occurs, stall.
-
- Or is the 040 able to have "free instructions" after a read
- if they work on different registers, for example a free
- addx.l d0,d1 after a move.b (a0),d2 ?
-
- : -- _
- : _ // Frank EMail: frank@phoenix.owl.de
- : \X/ IRC: Phx @ #amiga(ger)
- ------------------------------------------------------------------------
- fischerj@Informatik.TU-Muenchen.DE (Juergen "Rally" Fischer) =:)
-
-