Re: SUMMARY: pentium optimized debian discussion
On Tue, Jul 28, 1998 at 11:56:18AM -0700, Joey Hess wrote:
> It's been a long thread. Here's what've come up so far:
>
> Speed increases of pentium optmized binaries:
> - My tests whow around 15%.
> - 50% increase one one program claimed
> - The pgcc group claims 5% to 15%, 30% in some cases. This is probably lower
> for egcs, it's not as aggressive.
[snip]
> I'd suggest, if anyone can find a noticible speed increase on a pentium
> clone, we bypass the whole problem and call it 586. It may be worthwhile to
> call it 586 anyhow so we don't have to worry about intel.
[snip]
> Implementation:
> - We've decicded that it is better implemented by an architecture, rather
> than the Optimization tag hack.
I have looked at this thread on and off...What program benefited by 50%
increase?
If you can tell me how you did these tests...and give some good steps so
I reproduce everything right...I would be happy to test on my AMD K6
system to see if it has any increase.
(I don't have pgcc installed...It doesn't apear to be a debian package?
-after a cursory glance)
--
/* -- Stephen Carpenter <sjc@delphi.com> --- <sjc@debian.org>------------ */
E-mail "Bumper Stickers":
"A FREE America or a Drug-Free America: You can't have both!"
"honk if you Love Linux"
--
To UNSUBSCRIBE, email to debian-devel-request@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
Reply to: