Message77747
| Author |
mark.dickinson |
| Recipients |
fredrikj, loewis, mark.dickinson, pitrou, rhettinger, terry.reedy, vstinner |
| Date |
2008年12月13日.15:34:43 |
| SpamBayes Score |
0.034726728 |
| Marked as misclassified |
No |
| Message-id |
<1229182530.86.0.839512898967.issue3439@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
I think I've found the happy medium:
bit_length7_opt2.patch achieves nearly the same performance gains as
bit_length7_opt.patch (around 7% for uniformly-distributed inputs, 3.5%
for uniformly-distributed outputs), but is much more straightforward and
readable. It's pretty much what Raymond suggested in the first place,
plus a table lookup. |
|