[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: [Bug-gnubg] Benchmarks, experiments, speedups

From: macherius
Subject: RE: [Bug-gnubg] Benchmarks, experiments, speedups
Date: Sun, 27 Feb 2005 02:54:33 +0100


one more on gcc. I've just compiled myself a gcc 4.0.0 from the snapshot
sources as of 20050220. There is a new "-ftree-vectorize" method that mimics
Intel's vectorizer very closely. Attached is code produced by gcc 4.0.0
snapshot, you'll see the BIG difference to 4.3.x code.

The binary produced by the gcc 4.0.0 snapshot dumped core, but at least
things are moving in gcc-land. If the code generator is stable, the binaries
of gnubg produced by gcc 4.0 should be pretty fast.

So intrinsics would be a quick solution for speed improvement, but maybe the
GTK 2.6 update is more pressing? gcc 4.0 WILL improve the slow binaries
without doubt, and it's in a kind of release candidate state. See:


> -----Original Message-----
> From: address@hidden 
> [mailto:address@hidden On Behalf 
> Of macherius
> Sent: Saturday, February 26, 2005 5:49 PM
> To: 'Ingo Macherius'; address@hidden
> Subject: RE: [Bug-gnubg] Benchmarks, experiments, speedups
> Speedkings,

Attachment: gcc4_asm.txt
Description: Text document

reply via email to

[Prev in Thread] Current Thread [Next in Thread]