Message75719
| Author |
vstinner |
| Recipients |
christian.heimes, gregory.p.smith, mark.dickinson, pernici, vstinner |
| Date |
2008年11月11日.02:16:57 |
| SpamBayes Score |
1.5828364e-05 |
| Marked as misclassified |
No |
| Message-id |
<1226369818.63.0.935832912154.issue4294@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
More numbers!
------ 64 bits CPU -------
original: 885.0 ms
fast long: 746.8 ms (+16%) -- issue #3944
--------------------------
+16% only with an optimized multiplicaton, great job Pernici :-)
------ 32 bits CPU -------
original: 1564.3 ms
30 bits: 1497.3 ms (+4%)
fast long: 1591.7 ms (-2%)
GMP: 1564.4 ms (=)
--------------------------
It looks like the operation 32 bits x 32 bits is slower on a 32 bits
CPU, the gain is small (only +4%). fast long and a little bit slower,
and GMP patch doesn't change anything. |
|