>In article <Pine.LNX.3.96.980708184902.17875A-100000@mindmeld.dyn.ml.org>
you write:
>> Someone I know had a 486 DX/100 with 16MB RAM... on an ethernet. Then he
>> replaced the motherboard with a P66... same RAM.
>> The BogoMIPS rating went down quite a bit, yet, the Pentium compiled a
heck
>> of a lot faster. I am thinking it's b/c of advances in overall data
>> throughput... and not as much the instruction execution speed...
>
>BogoMIPS are bogus. They do not mean anything.
>
>Actually, on non-MMX pentiums, the BogoMIPS rating is always rather low,
>because the highly optimized loop triggers a bug in the pentium branch
>prediction. So a p66 is faster than any 486, and yet its BogoMIPS rating
>is lower.
>
Not quite true. 486DX4-100 is faster than P66. 486DX4-133 is faster than
P75. (according to benchmarks under Win95 and lower)
> --Thomas Pornin
>
>-
>To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
>the body of a message to majordomo@vger.rutgers.edu
>
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu