home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.amiga.programmer
- Path: sparky!uunet!math.fu-berlin.de!news.netmbx.de!Germany.EU.net!mpifr-bonn.mpg.de!speckled.mpifr-bonn.mpg.de!mlelstv
- From: mlelstv@speckled.mpifr-bonn.mpg.de (Michael van Elst)
- Subject: Re: Chunky Pixels vs. Bitplanes (was: Chunky Chip Set...)
- Message-ID: <1992Dec31.174137.10865@mpifr-bonn.mpg.de>
- Sender: news@mpifr-bonn.mpg.de
- Nntp-Posting-Host: speckled
- Organization: Max-Planck-Institut f"ur Radioastronomie
- References: <1992Dec30.115759.22097@mpifr-bonn.mpg.de> <doiron.0ka3@starpt.UUCP> <1992Dec31.011428.2926@mpifr-bonn.mpg.de> <C03uC5.15o@unix.portal.com>
- Date: Thu, 31 Dec 1992 17:41:37 GMT
- Lines: 50
-
- In <C03uC5.15o@unix.portal.com> danb@shell.portal.com (Dan E Babcock) writes:
- >In article <1992Dec31.011428.2926@mpifr-bonn.mpg.de> mlelstv@specklec.mpifr-bonn.mpg.de (Michael van Elst) writes:
- >>Thus bitplane devices are usually same speed as chunky pixel devices. But
- >>you can scale bitplane devices easily with the obvious performance advantages.
- >>You can never scale chunky pixel devices.
-
- >Well, that's misleading. If you are talking about a blitter-per-plane type of
- >architecture, the only one created (a few years ago from National) was a dismal
- >flop. Too expensive with minimal advantages.
-
- I am talking about a single blitter architecture. The simple point that
- you need less memory for less bitplanes makes an operation faster.
-
- >>>You are doing the same transformations 8 times, once for each bitplane.
- >>>This is not 8x the number of transformations? You deny facts?
- >>
- >>Again, with the example of doubling a bitmap you handle multiple pixels
- >>at a time which exactly compensates for the number of bitplanes.
-
- >No, it can rarely exactly compensate. The bitplane version of the algorithm
- >will require the use of more temporary data, slowing it down. The best
- >case is almost-as-fast.
-
- Why would it need more data ?
-
- >>Special-case optimizations. Right. But the "special cases" cover most graphics
- >>operations.
-
- >Except silly little things like drawing lines. Who'd ever want to draw a line? :-)
-
- And who fill an area by writing single pixels ?
-
- Fortunately, line drawing usually has to handle less data (you won't try to
- fill the screen with vertical lines..).
-
- >No, the VRAMs contain a color register. The "1" expands to whatever color was
- >previously loaded. Again, this allows text writing and polygon filling to be
- >done 4 times faster than usual.
-
- So you write a bitplane to VRAMs and get the whole pixel depth ? Would
- be identical to write to several bitplanes at the same time. I can't seen
- anything chunky or bitplane specific here. Just a method to increase
- bus bandwidth.
-
- Regards,
- --
- Michael van Elst
- UUCP: universe!local-cluster!milky-way!sol!earth!uunet!unido!mpirbn!p554mve
- Internet: p554mve@mpirbn.mpifr-bonn.mpg.de
- "A potential Snark may lurk in every tree."
-