A comparison should have not just have been against an epsilon,
but relative to the edge length involved.
Thanks to mano-wii for patch on which this is based.
Patch from Richard Erhardt, with some additions & modifications.
Changes bevel profile shape parameter so that can get arbitrarily
near square profile as parameter -> 1.
Adds code to make profile=0 case work, at least for cube corners,
so changed hard min of profile parameter to 0 from 0.15.
Two more 'not really useful' cases (OMP only shows some noticeable
speedup with above 1M elements, and since this is quick operation anyway
compared to even ather basic operators, gain is in the 1% area of total
processing time in best case).
So not worth parallelizing here, we'll gain much more on tackling heavy
operations. ;)
And BMesh is free from OMP now!
Performances tests on this one are quite surprising actually...
Parallelized loop itself is at least 10 times quicker with new BLI_task
code than it was with OMP. And subdividing e.g. a heavy mesh with 3
levels of multires (whole process) takes 8 seconds with new code, while
10 seconds with OMP one. And cherry on top, BLI_task code only uses
about 50% of CPU load, while OMP one was at nearly 100%!
In fact, I suspect OMP code was not properly declaring outside vars,
generating a lot of uneeded locks.
Also, raised the minimum level of subdiv to enable parallelization,
tests here showed that we only start to get significant gain with subdiv
levels of 4, below single threaded one is quicker.
Those three ones were actually giving no significant benefits, in fact
even slowing things down in one case compared to no parallelization at
all (in `BM_mesh_elem_table_ensure()`).
Point being, once more, parallelizing *very* small tasks (like index or
flag setting, etc.) is nearly never worth it.
Also note that we could not easlily use per-item parallel looping in
those three cases, since they are heavily relying on valid
loop-generated index (or are doing non-threadable things like allocation
from a mempool)...
Previously outcome depended on order of edges,
now the longest boundary edges are rotated first,
then the faces connected edges.
This gives more predictable results, allowing regions containing
a vertex fan to be rotated onto the next vertex.
That was a nasty one, Debug build would never have any issue (even tried
with 64 threads!), but Release build would deadlock nearly immediately,
even with only 2 threads!
What happened here (I think) is that gcc optimizer would generate a
specific path endlessly looping when initial value of virtual_lock was
FLT_MAX, by-passing re-assignment from v_no[0] and the atomic cas
completely. Which would have been correct, should v_no[0] not have been
shared (and modified) by multiple threads. ;)
Idea of that (broken) for loop was to avoid completely calling the
atomic cas as long as v_no[0] was locked by some other thread, but...
Guess the avoided/missing memory barrier was the root of the issue here.
Lesson of the evening: Remember kids, do not trust your compiler to
understand all possible threading-related side effects, and be explicit
rather than elegant when using atomic ops!
Side-effect lesson: do check both release and debug builds when messing
with said atomic ops...
Using atomic cas correctly is really hairy... ;)
In this case, the returned value from cas needs to validate *two*
conditions, it must not be FLT_MAX (which is our 'locked' value and
would mean another thread has already locked it), but it also must be
equal to previously stored value...
This means we need two steps per loop here, hence using a 'for' loop
instead of a 'while' one now.
Note that collisions are (as expected) very rare, less than 1 for 10k
typically, so did not catch the issue initially (also because I was
mostly working with release build to check on performances...).
`BM_mesh_normals_update` was converted from OMP to new parallel iterator code,
basic test with heavily subdivided cube (24.5k faces) gives:
- old OMP code: average 10ms per run.
- new BLI_task code: average 6ms per run.
So new code seems to be easily 40% quicker, in addition to getting rid of OMP. ;)
Reviewers: sergey, campbellbarton
Differential Revision: https://developer.blender.org/D2930
Just removing it, such cases are not bottlenecks and not worth the
complication of doing real threading with own BLI_task.
Other (remaining) usages may be relevant, need case-by-case check.
- initialize the cube-size from the bounding box when it's not set.
- no longer wrap faces to keep in 0-1 bounds,
other projection methods don't do this and calculating the scale
prevents the UV's from being too far outside the view.
Recent addition of 'reinsert' didn't match logic for ghash API.
Rename to BLI_heap_node_value_update,
also add BLI_heap_insert_or_update since it's a common operation.
Was using an edge hash for triangle -> edge lookups,
updating triangle indices for each edge-rotation.
Replace this with half-edge which can rotate edges much more simply,
writing triangles back once the solution has been calculated.
Gives ~33% speedup in own tests.
