Re: [2.1.98-9] Bogomips weirdness

James Mastros (root@jennifer-unix.dyn.ml.org)
Sat, 2 May 1998 13:16:45 -0400 (EDT)


On Fri, 1 May 1998, Thomas Pornin wrote:
[...]
> The Bogomips value used to be about 166, not 133. This had already
> appeared in 2.1.92 (or 2.1.93 ?) and disappeared as quickly. Anyway,
> the machine seems fine otherwise.
>
> --Thomas Pornin

All part of the bogosity of bogomips. On some processors, the
time the bogomips loop takes can vary widely. Don't worry about it. The
bogomips function isn't inlined, so it always occours at the same place in
memory, so the difference will cancel itself out. (It depends on exactly
where the compiler puts the bogomips function in memory.)

-=- James Mastros

-- 
True mastery is knowing enough to bullshit the rest.
	-=- Me

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu