Files
test2/source/blender/blenlib
Jacques Lucke e130903060 BLI: avoid invoking tbb for small workloads
We often call `parallel_for` in places with very variable
sized workloads. When many elements are processed,
using multi-threading is great, but when processing
few elements (possibly many times) using `parallel_for`
can result in significant overhead.

I measured that this improves performance by >20% in
the refactored realize instances code I'm working on
separately. The change might also help with debugging
sometimes, because the stack trace is smaller and contains
fewer irrevelant symbols.
2021-12-02 12:56:47 +01:00
..
2021-11-30 10:15:17 +11:00
2021-08-04 10:03:07 +10:00
2021-10-06 14:54:05 +11:00
2021-03-29 19:11:17 -06:00
2021-07-20 11:12:24 +10:00
2021-01-11 14:59:05 +01:00
2021-01-11 14:59:05 +01:00
2021-01-04 17:38:11 +11:00
2021-10-18 12:13:10 +11:00
2021-10-20 09:19:21 +11:00
2020-08-28 10:04:26 -06:00
2021-05-21 10:25:47 +05:30
2021-10-18 12:13:10 +11:00
2021-01-04 17:38:11 +11:00
2021-01-15 12:17:11 +11:00
2021-01-11 14:59:05 +01:00
2021-07-07 13:42:46 +10:00
2021-10-03 13:44:44 +02:00
2021-09-06 15:51:53 +10:00
2021-09-24 14:42:48 +02:00