Re: CPU specific/optimized Debian builds ?
On 29 May 2002 22:58:41 +1200,
James Kahn <jkahn@paradise.net.nz> wrote:
> On Wed, 2002-05-29 at 22:16, Andrew Suffield wrote:
> > If you are trying to do a benchmark on processor-related performance
> > changes (which it seems like you are), you will have to construct a
> > benchmark which actually measures that (no, I don't have any
> > suggestions offhand).
> Ray tracing tends to be pretty CPU intensive, how about using povray?
> Of course, to get "real" results, you'll need it to trace a rather large
> scene a few times with each buildarch, throw away any outliers and draw
> the mean of the rest.
How about john? Here is my result:
$ echo 'exec -a john debian/tmp/usr/sbin/john-any -test' | sh
* Debian default (-O2 -fomit-frame-pointer)
Benchmarking: Standard DES [24/32 4K]... DONE
Many salts: 164531 c/s real, 166193 c/s virtual
Only one salt: 152396 c/s real, 152396 c/s virtual
Benchmarking: BSDI DES (x725) [24/32 4K]... DONE
Many salts: 5868 c/s real, 5868 c/s virtual
Only one salt: 5779 c/s real, 5779 c/s virtual
Benchmarking: FreeBSD MD5 [32/32]... DONE
Raw: 2603 c/s real, 2603 c/s virtual
Benchmarking: OpenBSD Blowfish (x32) [32/32]... DONE
Raw: 208 c/s real, 208 c/s virtual
Benchmarking: Kerberos AFS DES [24/32 4K]... DONE
Short: 148224 c/s real, 148224 c/s virtual
Long: 258252 c/s real, 258252 c/s virtual
Benchmarking: NT LM DES [24/32 4K]... DONE
Raw: 815219 c/s real, 815219 c/s virtual
* no optimization
Benchmarking: Standard DES [24/32 4K]... DONE
Many salts: 162892 c/s real, 163219 c/s virtual
Only one salt: 140697 c/s real, 140697 c/s virtual
Benchmarking: BSDI DES (x725) [24/32 4K]... DONE
Many salts: 5872 c/s real, 5872 c/s virtual
Only one salt: 5609 c/s real, 5609 c/s virtual
Benchmarking: FreeBSD MD5 [32/32]... DONE
Raw: 2459 c/s real, 2588 c/s virtual
Benchmarking: OpenBSD Blowfish (x32) [32/32]... DONE
Raw: 191 c/s real, 191 c/s virtual
Benchmarking: Kerberos AFS DES [24/32 4K]... DONE
Short: 131123 c/s real, 131123 c/s virtual
Long: 127948 c/s real, 127948 c/s virtual
Benchmarking: NT LM DES [24/32 4K]... DONE
Raw: 685875 c/s real, 685875 c/s virtual
* overkill optimization (gcc-3.1, -O3 -fomit-frame-pointer -mcpu=pentium4)
Benchmarking: Standard DES [24/32 4K]... DONE
Many salts: 166272 c/s real, 166272 c/s virtual
Only one salt: 152038 c/s real, 152648 c/s virtual
Benchmarking: BSDI DES (x725) [24/32 4K]... DONE
Many salts: 5777 c/s real, 5835 c/s virtual
Only one salt: 5777 c/s real, 5777 c/s virtual
Benchmarking: FreeBSD MD5 [32/32]... DONE
Raw: 2616 c/s real, 2616 c/s virtual
Benchmarking: OpenBSD Blowfish (x32) [32/32]... DONE
Raw: 207 c/s real, 207 c/s virtual
Benchmarking: Kerberos AFS DES [24/32 4K]... DONE
Short: 144640 c/s real, 144640 c/s virtual
Long: 256256 c/s real, 256256 c/s virtual
Benchmarking: NT LM DES [24/32 4K]... DONE
Raw: 847820 c/s real, 847820 c/s virtual
I don't think CPU-specific optimization is much better
than non-CPU-specific optimization.
--
Oohara Yuuma <oohara@libra.interq.or.jp>
Debian developer
PGP key (key ID F464A695) http://www.interq.or.jp/libra/oohara/pub-key.txt
Key fingerprint = 6142 8D07 9C5B 159B C170 1F4A 40D6 F42E F464 A695
I always put away what I take.
--- Ryuji Akai, "Star away"
--
To UNSUBSCRIBE, email to debian-devel-request@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
Reply to: