brad@looking.UUCP (Brad Templeton) (11/04/84)
While the 6809 is a superior chip to generate code for (by machine) it can't even touch the 6502 in speed for hand-written assembler code. Nor can the z-80 or any other 8 bit micro I've seen. Commodore chooses the 6502 mainly because they designed it, or rather Chuck Peddle, designer of the first PET, designed it. But he did a good job if you remember he wanted a fast, optimized 8-bit processor. It's been proven time and time again that when coded properly, z-80 programs that do the same thing are twice as big and several times slower than 6502 programs. -- Brad Templeton, Looking Glass Software Ltd. - Waterloo, Ontario 519/884-7473
bahilchie@water.UUCP (Brian Hilchie) (11/04/84)
[] > I'm not saying the 6809 is a superior micro to the other 8-bitters, > but lots of other people have already.... This may seem blasphemous since I am a C64 owner, but the 6809 IS superior to the 6502 (6510) in almost every way. A few examples: the 6809 has 16 bit arithmetic and move instructions, 16 bit index and stack registers, auto increment/decrement, movable zero page (direct page), multiply, etc, etc, etc. I wish Commodore had gone with this chip; it sure would have made life easier for us C64 programmers. > Commodore 64 C: 28 sec in original posting > Coco OS-9 C: 21 sec > Bear in mind three things: (1) The Color COmputer clock rate is only 0.895 MHz; > I'm sure the C-64 runs faster, so my result is even better than it looks. A minor correction: my C runs the sieve in 26 seconds. This may be nit picking, but when the times are this close every second counts. Anyway, the superior architecture of the 6809 seems to compensate more than enough for the slightly slower clock. I will be interested in hearing the assembler results. Brian Hilchie {decvax|utzoo|ihnp4|allegra|clyde}!watmath!water!bahilchie
e-smith@utah-cs.UUCP (Eric L. Smith) (11/08/84)
In article <208@looking.UUCP> brad@looking.UUCP (Brad Templeton) writes: >While the 6809 is a superior chip to generate code for (by machine) it >can't even touch the 6502 in speed for hand-written assembler code. >-- >Brad Templeton, Looking Glass Software Ltd. - Waterloo, Ontario 519/884-7473 I take this as a challenge. Provide me with any non-trivial piece of code for the 6502 (or even the newer CMOS versions with the added instructions) and I will give you back an optimized 6809 version that will perform an equivalent function in less bytes and using less clock cycles to run. I have been a 6502 programmer since early '77, and a 6809 programmer since mid '80, and while I have to admit that Motorola's byte ordering is completely bass-ackwards from an efficiency viewpoint, the advanced features more than make up for it. -- --------------------------------------------------------------------------- Reality (for those who can't face computers): Eric L. Smith UUCP/UseNet: ...decvax!utah-cs!e-smith ARPA: e-smith@utah-20 U.S.Snail: 230 S. 500 W. Suite 133, Salt Lake City, UT, 84101 AT&T and suchlike: (801) 581-8100 (work), (801) 582-3371 (home) --------------------------------------------------------------------------- The opinions expressed herein do not necessarily represent those of the University of Utah, my friends, enemies, computer, or even me. I make no warranty, express or implied, as to the accuracy of this information of its fitness for any particular purpose. I assume no liability for any damages, actual or alleged, directly or indirectly resulting from the use of or inability to use this information. So there!