Files
jemalloc/include/jemalloc/internal
Kevin Svetlitski 6841110bd6 Make edata_cmp_summary_comp 30% faster
`edata_cmp_summary_comp` is one of the very hottest functions, taking up
3% of all time spent inside Jemalloc. I noticed that all existing
callsites rely only on the sign of the value returned by this function,
so I came up with this equivalent branchless implementation which
preserves this property. After empirical measurement, I have found that
this implementation is 30% faster, therefore representing a 1% speed-up
to the allocator as a whole.

At @interwq's suggestion, I've applied the same optimization to
`edata_esnead_comp` in case this function becomes hotter in the future.
2023-05-04 09:59:17 -07:00
..
2022-09-16 15:04:59 -07:00
2022-09-16 15:04:59 -07:00
2022-09-16 15:04:59 -07:00
…
2020-07-09 13:41:04 -07:00
2021-12-20 15:37:53 -08:00
2021-02-04 14:10:43 -08:00
2020-05-11 14:51:24 -07:00
2023-05-01 10:21:17 -07:00
…
2020-05-12 08:23:15 -07:00
…
2021-12-15 10:39:17 -08:00
2023-05-04 09:59:17 -07:00
2021-09-26 16:30:15 -07:00
2020-05-11 14:51:24 -07:00
2020-11-13 13:42:33 -08:00
2022-04-25 11:29:00 -07:00
2021-02-04 20:58:31 -08:00
…
2022-05-18 17:01:09 -07:00
2023-03-10 11:25:47 -08:00
…
2022-04-25 11:29:00 -07:00
2020-05-12 08:23:15 -07:00
…
2020-05-11 14:51:24 -07:00
2021-06-24 14:55:49 -07:00
2021-01-07 20:39:49 -08:00
2021-12-23 10:55:08 -08:00
2022-04-25 11:29:00 -07:00
2022-03-22 17:45:55 -07:00
2021-12-15 10:39:17 -08:00
2023-03-31 14:35:31 -07:00
2020-10-05 19:55:57 -07:00
2021-09-22 15:04:01 -07:00
2021-07-12 17:59:18 -07:00
2020-04-11 10:32:11 -07:00
2020-04-11 10:32:11 -07:00
2021-05-12 11:14:23 -07:00
2022-04-25 11:29:00 -07:00
…
…
2020-10-23 11:14:34 -07:00
2023-04-05 10:16:37 -07:00
…
2021-02-04 14:10:43 -08:00
2021-12-15 10:39:17 -08:00