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

[Øystein Johansen]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

macherius wrote:
| Hi,
|
| 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.

I got a working snapshot of gcc-4.1 today. was tweaking the optimization
parameters a bit and the ftree-vectorizer option gave me about 5%
performance improvment. I still don't see the speed from your Inten build.

| 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.

Hopefully I have done something wrong. Compared to my previous builds
with gcc-3.4.2 I used to have ~21000 evaluations/second and with gcc-4.1
snapshot I get ~22000 evals/sec.

| So intrinsics would be a quick solution for speed improvement, but
| maybe the GTK 2.6 update is more pressing?

I don't feel anything is pressing.... ;-)

"intrinsics" is my vote, but I don't feel I have the knowledge to
implement that. Anyone?

- -Øystein
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (MingW32)
Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org

iD8DBQFCNyln6kDTFPhwyqYRAhlUAJ4hSBWM/+oWcH8383xB7tZlfUijigCfdsSD
j2l3zmaTTXTThWw77eaPQ3E=
=gLx0
-----END PGP SIGNATURE-----