The issue was caused by un-initialized local storage for volume
intersection hits which are supposed to be stored in per-thread
KernelGlobals.
Fix is to make thread_shader() be the same as thread_render() in
respect of KernelGlobals.
Reviewers: brecht
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D5230
The kernel does not use AVX2 vectorization, and trying to use BVH8 was
leading to an empty scenes.
Fixes T64624: Ctest : Win32 + AVX2 fails virtually all cycles tests
This adds our own OSL texture handle, that has info for OIIO textures or our
own custom texture types. A filename to handle hash map is used for lookups.
This is efficient because it happens at OSL compile time, because the optimizer
can figure out constant strings and replace them with texture handles.
It's effectively always enabled, only not on some unsupported OpenCL devices.
For testing those it's not useful to disable these features. This is replaced
by the more fine grained feature toggles that we have now.
This is the internal implementation, not available from the API or
interface yet. The algorithm takes into account past and future frames,
both to get more coherent animation and reduce noise.
Ref D3889.
Prefiltering of feature passes will happen during rendering, which can
then be used for denoising immediately or written as a render pass for
later (animation) denoising.
The number of denoising data passes written is reduced because of this,
leaving out the feature variance passes. The passes are now Normal,
Albedo, Depth, Shadowing, Variance and Intensity.
Ref D3889.
This commit adds a sample-based profiler that runs during CPU rendering and collects statistics on time spent in different parts of the kernel (ray intersection, shader evaluation etc.) as well as time spent per material and object.
The results are currently not exposed in the user interface or per Python yet, to see the stats on the console pass the "--cycles-print-stats" argument to Cycles (e.g. "./blender -- --cycles-print-stats").
Unfortunately, there is no clear way to extend this functionality to CUDA or OpenCL, so it is CPU-only for now.
Reviewers: brecht, sergey, swerner
Reviewed By: brecht, swerner
Differential Revision: https://developer.blender.org/D3892
Note that this is turned off by default and must be enabled at build time with the CMake WITH_CYCLES_EMBREE flag.
Embree must be built as a static library with ray masking turned on, the `make deps` scripts have been updated accordingly.
There, Embree is off by default too and must be enabled with the WITH_EMBREE flag.
Using Embree allows for much faster rendering of deformation motion blur while reducing the memory footprint.
TODO: GPU implementation, deduplication of data, leveraging more of Embrees features (e.g. tessellation cache).
Differential Revision: https://developer.blender.org/D3682
Mainly useful for debugging. Previously, when AVX2 was disabled
in the debug panel but BVH layout was kept on BVH8 nothing was
rendered.
Needed to make it so supported BVH layout mask for devices is
queried in "dynamic", so it is possible to use DebugFlags there.
This allows for extra output passes that encode automatic object and material masks
for the entire scene. It is an implementation of the Cryptomatte standard as
introduced by Psyop. A good future extension would be to add a manifest to the
export and to do plenty of testing to ensure that it is fully compatible with other
renderers and compositing programs that use Cryptomatte.
Internally, it adds the ability for Cycles to have several passes of the same type
that are distinguished by their name.
Differential Revision: https://developer.blender.org/D3538
This is an initial implementation of BVH8 optimization structure
and packated triangle intersection. The aim is to get faster ray
to scene intersection checks.
Scene BVH4 BVH8
barbershop_interior 10:24.94 10:10.74
bmw27 02:41.25 02:38.83
classroom 08:16.49 07:56.15
fishy_cat 04:24.56 04:17.29
koro 06:03.06 06:01.45
pavillon_barcelona 09:21.26 09:02.98
victor 23:39.65 22:53.71
As memory goes, peak usage raises by about 4.7% in a complex
scenes.
Note that BVH8 is disabled when using OSL, this is because OSL
kernel does not get per-microarchitecture optimizations and
hence always considers BVH3 is used.
Original BVH8 patch from Anton Gavrikov.
Batched triangles intersection from Victoria Zhislina.
Extra work and tests and fixes from Maxym Dmytrychenko.
With small tiles, the repeated allocations on GPUs can actually slow down the denoising quite a lot.
Allocating the buffer just once reduces rendertime for the default cube with 16x16 tiles and denoising on a mobile 1050 from 22.7sec to 14.0sec.
This deduplicates the calls for tile (un)mapping and allows to have a target buffer that is different from the source buffer (needed for baking and animation denoising).
The latest clang compiler (at least the one in Xcode 9.4.1) warns about the register keyword and macro expansions using defined().
Since these warnings come from third party code, we can't address them directly in Blender. Silencing them via #pramgas will
at least keep the warnings during a build down to the ones that are relevant to Blender code.
We should actually be using CL_DEVICE_MEM_BASE_ADDR_ALIGN for sub buffers,
previous change in this code was incorrect. Renamed the function now to
make the specific purpose of this alignment clear, it's not required for
data types in general.
This was we can introduce other types of BVH, for example, wider ones, without
causing too much mess around boolean flags.
Thoughs:
- Ideally device info should probably return bitflag of what BVH types it
supports.
It is possible to implement based on simple logic in device/ and mesh.cpp,
rest of the changes will stay the same.
- Not happy with workarounds in util_debug and duplicated enum in kernel.
Maybe enbum should be stores in kernel, but then it's kind of weird to include
kernel types from utils. Soudns some cyclkic dependency.
Reviewers: brecht, maxim_d33
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D3011
Debug flags are to be controlling render behavior, nothing to do with low level
system utilities.
it was simple to hack, but logically is wrong. Lets do things where they are
supposed to be done!
Previously, the NLM kernels would be launched once per offset with one thread per pixel.
However, with the smaller tile sizes that are now feasible, there wasn't enough work to fully occupy GPUs which results in a significant slowdown.
Therefore, the kernels are now launched in a single call that handles all offsets at once.
This has two downsides: Memory accesses to accumulating buffers are now atomic, and more importantly, the temporary memory now has to be allocated for every shift at once, increasing the required memory.
On the other hand, of course, the smaller tiles significantly reduce the size of the memory.
The main bottleneck right now is the construction of the transformation - there is nothing to be parallelized there, one thread per pixel is the maximum.
I tried to parallelize the SVD implementation by storing the matrix in shared memory and launching one block per pixel, but that wasn't really going anywhere.
To make the new code somewhat readable, the handling of rectangular regions was cleaned up a bit and commented, it should be easier to understand what's going on now.
Also, some variables have been renamed to make the difference between buffer width and stride more apparent, in addition to some general style cleanup.
Goal is to reduce OpenCL kernel recompilations.
Currently viewport renders are still set to use 64 closures as this seems to
be faster and we don't want to cause a performance regression there. Needs
to be investigated.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D2775
* Remove tex_* and pixels_* functions, replace by mem_*.
* Add MEM_TEXTURE and MEM_PIXELS as memory types recognized by devices.
* No longer create device_memory and call mem_* directly, always go
through device_only_memory, device_vector and device_pixels.
