home *** CD-ROM | disk | FTP | other *** search
- Path: nntp.teleport.com!sschaem
- From: sschaem@teleport.com (Stephan Schaem)
- Newsgroups: comp.sys.amiga.programmer
- Subject: Re: TMapping again!
- Date: 26 Jan 1996 01:01:43 GMT
- Organization: Teleport - Portland's Public Access (503) 220-1016
- Message-ID: <4e995n$rk@maureen.teleport.com>
- References: <4d6v0t$3dt@maureen.teleport.com> <4dg4jk$km@news.cs.tu-berlin.de> <4dhvd5$5r2@maureen.teleport.com> <38232113@kone.fipnet.fi> <4e10ol$ck3@maureen.teleport.com> <38232152@kone.fipnet.fi>
- NNTP-Posting-Host: linda.teleport.com
- X-Newsreader: TIN [version 1.2 PL2]
-
- Jyrki Saarinen (jsaarinen@kone.fipnet.fi) wrote:
-
- : > repeat 8
- : > mw D1,D2
- : > mb D0,D2
- : > addx.l d7,D0
- : > movea.l d2,a0
- : > addx.l d6,D1
- : > mw (A0),d3
- : > mw D1,D2
- : > mb D0,D2
- : > movea.l d2,a0
- : > mb (A0),d3
- : > addx.l d7,D0
- : > addx.l d6,D1
- : > mw d3,(a1)+
- : > endr
-
- : How do you have the fraction bits in d7 and d6? Also,
- : how do you do addx correction before the loop with
- : two addx?
-
- yfract/xint d7
- xfract/yint d6 (y is preshifter by 8)
-
- Check my followup to your question in "PPC compiler", it show
- how to setup the loop and correctly order the additions.
-
- : Also, does it really pay off buffering two pixels
- : to a register instead of writing bytewise? At least
- : if I count 020/030 cycles it does not pay off.
-
- Maybe not on papper, but doing this give me a better frame rate.
- (I have a 25mhz 030)
-
- Stephan
-