Re: Doom Conversion (was Dragons Lair

[jd-wong@uxa.cso.uiuc.edu (Jim Wong)]

Leslie M. Barstow III <wdphoenix@delphi.com> writes:
> 
>Here's my basis...
>A GS's average cycle count is about 3-4.
>A Mac's average cycle count (excluding the PowerPC) is about 8
>A 386 (relative to a Mac) uses about 3 times more average.
>The 486 reduced this by half.
>Therefore, a GS should run things about 3 times faster than a 486 of equivalent
>speed, if both are optimized equally.
>The GS-Mac, Mac-386, GS-386, and 386-486 comparisons are all out there...

You're ignoring two important factors in your analysis:

1) They don't make 66, 50, or even 33 MHz 65816 processors.
2) Even assuming your analysis of the CPIs of the 816 and 486 is correct,
   you have to account for the fact that the instruction counts for 
   accomplishing tasks on the two processors may be very different.
   Considering the 486 can move data around in 32-bit chunks and, I believe,
   has a richer instruction set than the 65816, this may very well be the
   case.

-- 
Jim Wong (jd-wong@uiuc.edu)