Message157916
| Author |
Jim.Jewett |
| Recipients |
Jim.Jewett, jcon, mark.dickinson, neologix, pitrou, rhettinger, serhiy.storchaka, tim.peters |
| Date |
2012年04月09日.22:38:09 |
| SpamBayes Score |
-1.0 |
| Marked as misclassified |
Yes |
| Message-id |
<1334011090.29.0.185496220618.issue10408@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
FWIW, doing a linear probe only within a cache line (changing the 1's bit) before applying perturb might also be useful -- and the results may change if the size of a dictentry were reduced. (Mark Shannon's now-integrated patch doesn't actually do that for the keys, but it would be doable.) |
|