Alle 00:13, venerdà 14 novembre 2003, William Kenworthy ha scritto:
> you might also look at -falign-functions=8/16/32 as well. On an athlon
> tbird 1.4, 4 had zero gain, 8 and 16 were slower than 4, but 32 was
> consistantly a little better. Possibly because its a 32 bit system
Align functions to as much as 32-byte boundaries? Please show your results,
I'm a bit curious
> Also, did you use an offline machine with no services running - Ive
> found that can be a killer for repeatbility (~10 runs needed, with spike
> removal, *before* averaging to see a true figure)
Yes, there were only the kernel, init, devfsd, bash and my test running. Isn't
it enough? ;-P
I didn't understand your last sentence. If appropriate, I will repost my
results showing standard deviation. Ask me privately if you want to see the
whole collected data.
BTW, the tests ran respectively 100 and 40 times.
Regards,
Danilo
--
Danilo Piazzalunga <[EMAIL PROTECTED]> | Linux User #245762 |
| ICQ #105550412 |
Public key: search.keyserver.net +--------------------+
Fingerprint: D018 815E 8C7F 2AE2 5565 0C36 B5F6 DB20 B800 CB9F |
--
[EMAIL PROTECTED] mailing list
