home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.theory.cell-automata
- Path: sparky!uunet!mcsun!ieunet!tcdcs!maths.tcd.ie!chughes
- From: chughes@maths.tcd.ie (Conrad Hughes)
- Subject: Re: Using lookup tables for faster Life Game calculations
- Message-ID: <1992Aug27.102124.5016@maths.tcd.ie>
- Keywords: 8086 real mode lookup table life game
- Organization: Dept. of Maths, Trinity College, Dublin, Ireland.
- References: <a_#n=la.pdh@netcom.com>
- Date: Thu, 27 Aug 1992 10:21:24 GMT
- Lines: 22
-
- pdh@netcom.com (Phil Howard ) writes:
-
- >The original method I examined involved calculating 4 cells in parallel.
- About two years ago I implemented standard-rules life in assembler
- on the ARM (a British RISC machine) - doing 32 cells at a time in
- parallel (the ARM is a 32 bit processor). By constructing a binary
- adder with bits 0, 1, 2 and 3 of the live-neighbours count held in
- separate registers I reduced a 32-cell operation to 45 1-clock cycle
- instructions, with a resulting 3000000 (three million) cells-per-
- second performance out of an 8MHz machine (memory load/store and
- screen DMA overheads account for the remainder of wasted CPU time).
- This compares fairly well with that 33MHz 486' 1.1 million cells-
- per-second.. If you like I could try translating my 2-year-old
- assembler source into C; mail me please - I don't normally ready
- this group.
-
- Conrad
- --
- ,--------------------. Suicide City, Paranoid State. Geddout! trip to, heave'n'
- |chughes@maths.tcd.ie| ho, up, down, to'n'fro you have no word please leave us
- +-=>Conrad Hughes<=-+ here close our eyes to the octopus ride isn't it good to
- `-------<SICK>-------' be lost in the wood isn't it bad so quiet there . . .
-