The idea is to support following: allow doing parallel for on a small range,
each iteration of which takes lots of compute power, but limit such range to
a subset of threads.
For example, on a machine with 44 threads we can occupy 4 threads to handle
range of 64 elements, 16 elements per thread, where each block of 16 elements
is very complex to compute.
The idea should be to use this setting instead of global use_threading flag,
which is only based on size of array. Proper use of the new flag will improve
threadability.
This commit only contains internal task scheduler changes, this setting is not
used yet by any areas.
Now all the fine-tuning is happening using parallel range settings structure,
which avoid passing long lists of arguments, allows extend fine-tuning further,
avoid having lots of various functions which basically does the same thing.
The idea is to avoid any threading overhead when we start pushing tasks in a
loop. Similarly to how we do it from the new dependency graph. Gives couple of
percent of speedup here, but also improves scalability.
For some blend modes there would be no effect with factor 1.0, even if factor
0.999 would give a very different image. Now the result should have no
discontinuity.
Differential Revision: https://developer.blender.org/D2925
It merely uses the new thread-safe iterators system of mempool, quite
straight forward.
Note that to avoid possible confusion with two void pointers as
parameters of the callback, a dummy opaque struct pointer is used
instead for the second parameter (pointer generated by iteration over
mempool), callback functions must explicitely convert it to expected
real type.
Also added a basic gtest for this new feature.
This will allow threaded tasks to 'consume' all mempool items in
parallel tasks, each one working on a whole chunk at once (to reduce
concurrency managing overhead).
Adapted from http://www.pixelbeat.org/programming/gcc/static_assert.html.
Note that this macro just discards error message, so error when building
is much less nice than with gcc's _Static_assert... But error log will
point to right place in code, so should still be OK.
This reverts commit d749320e3b.
It's possible the container struct is larger,
we could do sizeof checks that falls back to memmove
but rather avoid complicating things.
The issue was caused by SpinLock implementation in old pthreads we ar eusing on
Windows. Using newer one (2.10-rc) demonstrates same exact behavior. But likely
using own atomics and memory barrier based implementation solves the issue.
A bit annoying that we need to change such a core part of Blender just to make
specific CPU happy, but it's better to have artists happy on all computers.
There is no expected downsides of this change, but it is so called "works for
me" category. Let's see how it all goes.
The legacy algorithm only considers two adjacent points when computing
the bezier handles, which cannot produce satisfactory results. Animators
are often forced to manually adjust all curves.
The new approach instead solves a system of equations to trace a cubic spline
with continuous second derivative through the whole segment of auto points,
delimited at ends by keyframes with handles set by other requirements.
This algorithm also adjusts Vector handles that face ordinary bezier keyframes
to achieve zero acceleration at the Vector keyframe, instead of simply pointing
it at the adjacent point.
Original idea and implementation by Benoit Bolsee <benoit.bolsee@online.be>;
code mostly rewritten to improve code clarity and extensibility.
Reviewers: aligorith
Differential Revision: https://developer.blender.org/D2884
