Commit Graph

15 Commits

Author SHA1 Message Date
Campbell Barton
48c1e0c0fc spelling: use American spelling for canceled 2013-10-26 01:06:19 +00:00
Brecht Van Lommel
60e5abe71f Fix a few issues reported by coverity scan. 2013-09-03 22:39:21 +00:00
Brecht Van Lommel
6785874e7a Fix #36137: cycles render not using all GPU's when the number of GPU's is larger
than the number of CPU threads
2013-08-30 23:09:22 +00:00
Brecht Van Lommel
b9ce231060 Cycles: relicense GNU GPL source code to Apache version 2.0.
More information in this post:
http://code.blender.org/

Thanks to all contributes for giving their permission!
2013-08-18 14:16:15 +00:00
Thomas Dinges
636b314677 Code cleanup / Cycles:
* Remove useless else branch, after recent changes.
2013-07-21 10:30:22 +00:00
Thomas Dinges
9732c6283e Cycles / CPU Rendering:
* "Auto Detect" now again uses the umber of cores, instead number of cores + 1.

This was added before we had Tile rendering and benchmarks on several systems showed that there is no gain with this now. There might be some slight difference (0.5% or so) slower/faster depending on the scene, but this is negligible.
2013-07-20 00:40:03 +00:00
Brecht Van Lommel
2d0a586c29 Cycles OpenCL: keep the opencl context and program around for quicker rendering
the second time, as for example Intel CPU startup time is 9 seconds.

* Adds an cache for contexts and programs for each platform and device pair,
  which also ensure now no two threads try to compile and write the binary cache
  file at the same time.
* Change clFinish to clFlush so we don't block until the result is done, instead
  it will block at the moment we copy back memory.
* Fix error in Cycles time_sleep implementation, does not affect any active code
  though.
* Adds some (disabled) debugging code in the task scheduler.

Patch #35559 by Doug Gale.
2013-05-31 16:19:03 +00:00
Brecht Van Lommel
38c94e9194 Fix cycles crash that happened with mesh emission and diffuse/glossy ray
visibility disabled on some objects.
2013-01-25 02:00:57 +00:00
Brecht Van Lommel
204113b791 Fix #33107: cycles fixed threads 1 was still having two cores do work,
because main thread works as well.
2012-11-07 21:00:49 +00:00
Lukas Toenne
efaf512406 Revert r50528: "Performance fix for Cycles: Don't wait in the main UI thread when resetting devices."
This commit leads to random freezes in Cycles rendering:
https://projects.blender.org/tracker/index.php?func=detail&aid=32545&group_id=9&atid=498

The goal of this commit was to remove UI lag for OSL, but since that is not officially supported yet, better revert it until a proper fix can be implemented in 2.65.
2012-09-17 12:07:06 +00:00
Lukas Toenne
31ed71cb6b Performance fix for Cycles: Don't wait in the main UI thread when resetting devices.
When the scene is updated Cycles resets the renderer device, cancelling
all existing tasks. The main thread would wait for all running tasks to
finish before continuing. This is ok when tasks can actually cancel in a
timely fashion. For OSL however, this does not work, since the OSL
shader group optimization takes quite a bit of time and can not be
easily be cancelled once running (on my crappy machine in full debug
mode: ~0.12 seconds for simple node trees). This would lead to very
laggy UI behavior and make it difficult to accurately control elements
such as sliders.

This patch removes the wait condition from the device->task_cancel
method. Instead it just sets the do_cancel flag and returns. To avoid
backlog in the task pool of the device it will return early from the
BlenderSession::sync function while the reset is going on (tested in
Session::resetting). Once all existing tasks have finished the do_cancel
flag is finally cleared again (checked in TaskPool::num_decrease).

Care has to be taken to avoid race conditions on the do_cancel flag,
since it can now be modified outside the TaskPool::cancel function
itself. For this purpose the scope of the TaskPool::num_mutex locks has
been extended, in most cases the mutex is now locked by the TaskPool
itself before calling TaskScheduler methods, instead of only locking
inside the num_increase/num_decrease functions themselves. The only
occurrence of a lock outside of the TaskPool methods is in
TaskScheduler::thread_run.

This patch is most useful in combination with the OSL renderer mode, so
it can probably wait until after the 2.64 release. SVM tasks tend to be
cancelled quickly, so the effect is less noticeable.
2012-09-11 11:41:51 +00:00
Campbell Barton
0fbb6bff27 style cleanup: block comments 2012-06-09 17:22:52 +00:00
Brecht Van Lommel
8148d7b1df Cycles: reviewed the task scheduler code and fixed (hopefully all) windows threading problems. 2012-05-10 22:31:16 +00:00
Brecht Van Lommel
8103381ded Cycles: threading optimizations
* Multithreaded image loading, each thread can load a separate image.
* Better multithreading for multiple instanced meshes, different threads can now
  build BVH's for different meshes, rather than all cooperating on the same mesh.
  Especially noticeable for dynamic BVH building for the viewport, gave about
  2x faster build on 8 core in fairly complex scene with many objects.
* The main thread waiting for worker threads can now also work itself, so
  (num_cores + 1) threads will be working, this supposedly gives better
  performance on some operating systems, but did not measure performance for
  this very detailed yet.
2012-05-05 19:44:33 +00:00
Brecht Van Lommel
07b2241fb1 Cycles: merging features from tomato branch.
=== BVH build time optimizations ===

* BVH building was multithreaded. Not all building is multithreaded, packing
  and the initial bounding/splitting is still single threaded, but recursive
  splitting is, which was the main bottleneck.

* Object splitting now uses binning rather than sorting of all elements, using
  code from the Embree raytracer from Intel.
  http://software.intel.com/en-us/articles/embree-photo-realistic-ray-tracing-kernels/

* Other small changes to avoid allocations, pack memory more tightly, avoid
  some unnecessary operations, ...

These optimizations do not work yet when Spatial Splits are enabled, for that
more work is needed. There's also other optimizations still needed, in
particular for the case of many low poly objects, the packing step and node
memory allocation.

BVH raytracing time should remain about the same, but BVH build time should be
significantly reduced, test here show speedup of about 5x to 10x on a dual core
and 5x to 25x on an 8-core machine, depending on the scene.

=== Threads ===

Centralized task scheduler for multithreading, which is basically the
CPU device threading code wrapped into something reusable.

Basic idea is that there is a single TaskScheduler that keeps a pool of threads,
one for each core. Other places in the code can then create a TaskPool that they
can drop Tasks in to be executed by the scheduler, and wait for them to complete
or cancel them early.

=== Normal ====

Added a Normal output to the texture coordinate node. This currently
gives the object space normal, which is the same under object animation.

In the future this might become a "generated" normal so it's also stable for
deforming objects, but for now it's already useful for non-deforming objects.

=== Render Layers ===

Per render layer Samples control, leaving it to 0 will use the common scene
setting.

Environment pass will now render environment even if film is set to transparent.

Exclude Layers" added. Scene layers (all object that influence the render,
directly or indirectly) are shared between all render layers. However sometimes
it's useful to leave out some object influence for a particular render layer.
That's what this option allows you to do.

=== Filter Glossy ===

When using a value higher than 0.0, this will blur glossy reflections after
blurry bounces, to reduce noise at the cost of accuracy. 1.0 is a good
starting value to tweak.

Some light paths have a low probability of being found while contributing much
light to the pixel. As a result these light paths will be found in some pixels
and not in others, causing fireflies. An example of such a difficult path might
be a small light that is causing a small specular highlight on a sharp glossy
material, which we are seeing through a rough glossy material. With path tracing
it is difficult to find the specular highlight, but if we increase the roughness
on the material the highlight gets bigger and softer, and so easier to find.

Often this blurring will be hardly noticeable, because we are seeing it through
a blurry material anyway, but there are also cases where this will lead to a
loss of detail in lighting.
2012-04-28 08:53:59 +00:00