diff options
| author | Iliay Katueshenock <Moder> | 2022-07-26 12:06:49 +0300 |
|---|---|---|
| committer | Jacques Lucke <jacques@blender.org> | 2022-07-26 12:10:16 +0300 |
| commit | c94ca54cdafdba15d5a7be55e81d6f7a0da7ed7e (patch) | |
| tree | fe6644d41f65b4e1d5861c33b465b6371b49306c /source/blender/blenkernel | |
| parent | 203e7ba3320e7ed978ec094efa0c1b22137fb12a (diff) | |
BLI: add use_threading parameter to parallel_invoke
`parallel_invoke` allows executing functions on separate threads.
However, creating tasks in tbb has a measurable amount of overhead.
Therefore, it can be benefitial to disable parallelization when
the amount of work done per function is small.
See D15539 for some benchmark results.
Differential Revision: https://developer.blender.org/D15539
Diffstat (limited to 'source/blender/blenkernel')
| -rw-r--r-- | source/blender/blenkernel/intern/curves_geometry.cc | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/source/blender/blenkernel/intern/curves_geometry.cc b/source/blender/blenkernel/intern/curves_geometry.cc index 3050e01e528..6486be4afe0 100644 --- a/source/blender/blenkernel/intern/curves_geometry.cc +++ b/source/blender/blenkernel/intern/curves_geometry.cc @@ -1165,6 +1165,7 @@ static CurvesGeometry copy_with_removed_points(const CurvesGeometry &curves, CurvesGeometry new_curves{new_point_count, new_curve_count}; threading::parallel_invoke( + 256 < new_point_count * new_curve_count, /* Initialize curve offsets. */ [&]() { new_curves.offsets_for_write().copy_from(new_curve_offsets); }, [&]() { @@ -1237,6 +1238,7 @@ static CurvesGeometry copy_with_removed_curves(const CurvesGeometry &curves, CurvesGeometry new_curves{new_tot_points, new_tot_curves}; threading::parallel_invoke( + 256 < new_tot_points * new_tot_curves, /* Initialize curve offsets. */ [&]() { MutableSpan<int> new_offsets = new_curves.offsets_for_write(); |