Message391560
| Author |
vstinner |
| Recipients |
corona10, erlendaasland, miss-islington, pablogsal, petr.viktorin, phsilva, rhettinger, serhiy.storchaka, shihai1991, vstinner |
| Date |
2021年04月21日.23:27:27 |
| SpamBayes Score |
-1.0 |
| Marked as misclassified |
Yes |
| Message-id |
<1619047647.53.0.541144988327.issue40137@roundup.psfhosted.org> |
| In-reply-to |
| Content |
msg391004 benchmark comparing master with Raymond's optimization (commit 139c232f3851b393798d0ea4e65f1298bfbcd9cf) compared to Python 3.9:
Mean +- std dev: [py39] 38.8 ns +- 0.5 ns -> [obj_cache] 40.3 ns +- 0.1 ns: 1.04x slower
For me, these numbers make no sense :-D Getting kwd_mark from the instance (Raymond's new code) *must* be faster than calling _PyType_GetModuleByDef() on the instance.
As I wrote in my previous comment, my bet is that PGO is not reproducible and so we should not pay too much attention to differences of a few nanoseconds. |
|