Blender Git Statistics -> Branches -> temp-cycles-tbb
"Temp-cycles-tbb" branch
Total commits : 7
Total committers : 1
First Commit : June 6, 2020
Latest Commit : June 6, 2020
Commits by Date
Date | Number of Commits | |
---|---|---|
June 6, 2020 | 7 |
Committers
Author | Number of Commits |
---|---|
Brecht Van Lommel | 7 |
Popular Files
Filename | Total Edits |
---|---|
util_task.h | 5 |
util_task.cpp | 4 |
bvh_build.cpp | 3 |
device_cpu.cpp | 3 |
device_optix.cpp | 3 |
device_cuda_impl.cpp | 3 |
device_opencl.h | 3 |
object.cpp | 2 |
bvh_build.h | 2 |
bvh_sort.cpp | 2 |
Latest commits
June 6, 2020, 19:02 (GMT) |
Cycles: use TBB for task pools and task scheduler No significant performance improvement is expected, but it means we have a single thread pool throughout Blender. And it should make adding more parallellization in the future easier. After previous refactoring commits this is basically a drop-in replacement. One difference is that the task pool had a mechanism for scheduling tasks to the front of the queue to minimize memory usage. TBB has a smarter algorithm to balance depth-first and breadth-first scheduling of tasks and we assume that removes the need to manually provide hints to the scheduler. |
June 6, 2020, 19:01 (GMT) |
Cleanup: remove task pool stop() and finished() |
June 6, 2020, 19:01 (GMT) |
Cleanup: use lambdas instead of functors for task pools, remove threadid |
June 6, 2020, 19:01 (GMT) |
Cycles: make TBB a required library dependency, and use in a few places Now that the rest of Blender also relies on TBB, no point in maintaining custom code for paraller_for and thread local storage. |
June 6, 2020, 19:00 (GMT) |
Cleanup: minor refactoring around DeviceTask |
June 6, 2020, 19:00 (GMT) |
Cleanup: use move semantics for task pool functions |
June 6, 2020, 18:59 (GMT) |
Build: upgrade from C++11 to C++14, matching VFX reference platform |
MiikaHweb - Blender Git Statistics v1.06