Skip to Content.
Sympa Menu

sm-sorcery-bugs - [SM-Sorcery-Bugs] [Bug 5487] x86-64 (AMD Athlon 64, Athlon 64 FX and Opteron) optimisation

sm-sorcery-bugs AT lists.ibiblio.org

Subject: Bugs for Sorcery are reported here

List archive

Chronological Thread  
  • From: bugzilla-daemon AT metalab.unc.edu
  • To: sm-sorcery-bugs AT lists.ibiblio.org
  • Subject: [SM-Sorcery-Bugs] [Bug 5487] x86-64 (AMD Athlon 64, Athlon 64 FX and Opteron) optimisation
  • Date: Mon, 26 Jan 2004 18:28:23 -0500

http://bugs.sourcemage.org/show_bug.cgi?id=5487





------- Additional Comments From gareth AT caffeinefuelled.com 2004-01-26 18:28
-------
Work at uni has ramped up horribly - we now have five assignments to do all at
the same time, plus lectures, so I'm not going to be able to spend much time
on
this for quite a while, which is rather disappointing!

Anyway, I've been reading around the subject and there seems to be some
controversy over whether it is better to recompile everything in 64-bit mode
or
not for x86-64. On the SPARC chip, no new chip features are enabled when code
runs in 64-bit mode, so you get the expected slowdown due to the extra data
being pumped around the chip. On x86-64 however, double the number of general
purpose registers and double the number of SSE registers are enabled when
running any 64-bit code. This might be enough to negate the performance drop
caused by the larger word size - the guys on the Gentoo forums certainly think
it does. I think it would take some proper benchmarking to really find out
but I
don't have time to do that either - bah!

I'll post again once I've actually done some proper work on this :)



------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.




Archive powered by MHonArc 2.6.24.

Top of Page