This patch causes the render buffers to be copied to the denoiser
device only once before denoising and output/display is then fed
from that single buffer on the denoiser device. That way usually all
but one copy (from all the render devices to the denoiser device)
can be eliminated, provided that the denoiser device is also the
display device (in which case interop is used to update the display).
As such this patch also adds some logic that tries to ensure the
chosen denoiser device is the same as the display device.
Differential Revision: https://developer.blender.org/D15657
This was added for Metal, but also gives good results with CUDA and OptiX.
Also enable it for future Apple GPUs instead of only M1 and M2, since this has
been shown to help across multiple GPUs so the better bet seems to enable
rather than disable it.
Also moves some of the logic outside of the Metal device code, and always
enables the code in the kernel since other devices don't do dynamic compile.
Time per sample with OptiX + RTX A6000:
new old
barbershop_interior 0.0730s 0.0727s
bmw27 0.0047s 0.0053s
classroom 0.0428s 0.0464s
fishy_cat 0.0102s 0.0108s
junkshop 0.0366s 0.0395s
koro 0.0567s 0.0578s
monster 0.0206s 0.0223s
pabellon 0.0158s 0.0174s
sponza 0.0088s 0.0100s
spring 0.1267s 0.1280s
victor 0.0524s 0.0531s
wdas_cloud 0.0817s 0.0816s
Ref D15331, T87836
This patch partitions the active indices into chunks prior to sorting by material in order to tradeoff some material coherence for better locality. On Apple Silicon GPUs (particularly higher end M1-family GPUs), we observe overall render time speedups of up to 15%. The partitioning is implemented by repeating the range of `shader_sort_key` for each partition, and encoding a "locator" key which distributes the indices into sorted chunks.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D15331
This patch adds a new Cycles device with similar functionality to the
existing GPU devices. Kernel compilation and runtime interaction happen
via oneAPI DPC++ compiler and SYCL API.
This implementation is primarly focusing on Intel® Arc™ GPUs and other
future Intel GPUs. The first supported drivers are 101.1660 on Windows
and 22.10.22597 on Linux.
The necessary tools for compilation are:
- A SYCL compiler such as oneAPI DPC++ compiler or
https://github.com/intel/llvm
- Intel® oneAPI Level Zero which is used for low level device queries:
https://github.com/oneapi-src/level-zero
- To optionally generate prebuilt graphics binaries: Intel® Graphics
Compiler All are included in Linux precompiled libraries on svn:
https://svn.blender.org/svnroot/bf-blender/trunk/lib The same goes for
Windows precompiled binaries but for the graphics compiler, available
as "Intel® Graphics Offline Compiler for OpenCL™ Code" from
https://www.intel.com/content/www/us/en/developer/articles/tool/oneapi-standalone-components.html,
for which path can be set as OCLOC_INSTALL_DIR.
Being based on the open SYCL standard, this implementation could also be
extended to run on other compatible non-Intel hardware in the future.
Reviewed By: sergey, brecht
Differential Revision: https://developer.blender.org/D15254
Co-authored-by: Nikita Sirgienko <nikita.sirgienko@intel.com>
Co-authored-by: Stefan Werner <stefan.werner@intel.com>
* Rename "texture" to "data array". This has not used textures for a long time,
there are just global memory arrays now. (On old CUDA GPUs there was a cache
for textures but not global memory, so we used to put all data in textures.)
* For CUDA and HIP, put globals in KernelParams struct like other devices.
* Drop __ prefix for data array names, no possibility for naming conflict now that
these are in a struct.
Move MNEE to own kernel, separate from shader ray-tracing. This does introduce
the limitation that a shader can't use both MNEE and AO/bevel, but that seems
like the better trade-off for now.
We can experiment with bigger kernel organization changes later.
Differential Revision: https://developer.blender.org/D15070
* Float/double promotion warnings were mainly meant for avoiding slow
operatiosn in the kernel. Limit it to that to avoid hard to fix warnings
in Hydra.
* Const warnings in Hydra iterators.
* Unused variable warnings when building without glog.
* Wrong camera enum comparisons in assert.
* PASS_UNUSED is not a pass type, only for pass offsets.
Propagate the fp settings from the main thread to all the worker threads (the fp settings includes the FZ settings among other things) - this guarantees consistency in execution of floating point math regardless if its executed in tbb thread arena or on main thread
Add FZ mode to arm64/aarch64 in parallel to the way its been done on intel processors, currently compiling for arm target does not set this mode at all, hence potentially runs slower and with possible results mismatch with intel x86.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D14454
Light groups are a type of pass that only contains lighting from a subset of light sources.
They are created in the View layer, and light sources (lamps, objects with emissive materials
and/or the environment) can be assigned to a group.
Currently, each light group ends up generating its own version of the Combined pass.
In the future, additional types of passes (e.g. shadowcatcher) might be getting their own
per-lightgroup versions.
The lightgroup creation and assignment is not Cycles-specific, so Eevee or external render
engines could make use of it in the future.
Note that Lightgroups are identified by their name - therefore, the name of the Lightgroup
in the View Layer and the name that's set in an object's settings must match for it to be
included.
Currently, changing a Lightgroup's name does not update objects - this is planned for the
future, along with other features such as denoising for light groups and viewing them in
preview renders.
Original patch by Alex Fuller (@mistaed), with some polishing by Lukas Stockner (@lukasstockner97).
Differential Revision: https://developer.blender.org/D12871
This patch adds a Hydra render delegate to Cycles, allowing Cycles to be used for rendering
in applications that provide a Hydra viewport. The implementation was written from scratch
against Cycles X, for integration into the Blender repository to make it possible to continue
developing it in step with the rest of Cycles. For this purpose it follows the style of the rest of
the Cycles code and can be built with a CMake option
(`WITH_CYCLES_HYDRA_RENDER_DELEGATE=1`) similar to the existing standalone version
of Cycles.
Since Hydra render delegates need to be built against the exact USD version and other
dependencies as the target application is using, this is intended to be built separate from
Blender (`WITH_BLENDER=0` CMake option) and with support for library versions different
from what Blender is using. As such the CMake build scripts for Windows had to be modified
slightly, so that the Cycles Hydra render delegate can e.g. be built with MSVC 2017 again
even though Blender requires MSVC 2019 now, and it's possible to specify custom paths to
the USD SDK etc. The codebase supports building against the latest USD release 22.03 and all
the way back to USD 20.08 (with some limitations).
Reviewed By: brecht, LazyDodo
Differential Revision: https://developer.blender.org/D14398
When new display driver is given to the PathTrace ensure that there are
no GPU resources used from it by the work. This solves graphics interop
descriptors leak.
This aqlso fixes Invalid graphics context in cuGraphicsUnregisterResource
error when doing final render on the display GPU.
Fixes T95837: Regression: GPU memory accumulation in Cycles render
Fixes T95733: Cycles Cuda/Optix error message with multi GPU devices. (Invalid graphics context in cuGraphicsUnregisterResource)
Fixes T95651: GPU error (Invalid graphics context in cuGraphicsUnregisterResource)
Fixes T95631: VRAM is not being freed when rendering (Invalid graphics context in cuGraphicsUnregisterResource)
Fixes T89747: Cycles Render - Textures Disappear then Crashes the Render
Maniphest Tasks: T95837, T95733, T95651, T95631, T89747
Differential Revision: https://developer.blender.org/D14146
* Replace license text in headers with SPDX identifiers.
* Remove specific license info from outdated readme.txt, instead leave details
to the source files.
* Add list of SPDX license identifiers used, and corresponding license texts.
* Update copyright dates while we're at it.
Ref D14069, T95597
Use a shorter/simpler license convention, stops the header taking so
much space.
Follow the SPDX license specification: https://spdx.org/licenses
- C/C++/objc/objc++
- Python
- Shell Scripts
- CMake, GNUmakefile
While most of the source tree has been included
- `./extern/` was left out.
- `./intern/cycles` & `./intern/atomic` are also excluded because they
use different header conventions.
doc/license/SPDX-license-identifiers.txt has been added to list SPDX all
used identifiers.
See P2788 for the script that automated these edits.
Reviewed By: brecht, mont29, sergey
Ref D14069
Sometime throughout development some checks got lost during refactor.
This change makes it so that if OIDN is not supported on the current
CPU Cycles will report an error and stop rendering. This behavior is
similar to when an OptiX denoiser is requested and there is no OptiX
compatible device available.
The easiest way to verify this change is to force return false from
the `openimagedenoise_supported()`.
Fixes Cycles part of the T94127.
Differential Revision: https://developer.blender.org/D13944
The root of the issue is caused by Cycles ignoring OpenGL limitation on
the maximum resolution of textures: Cycles was allocating texture of the
final render resolution. It was exceeding limitation on certain GPUs and
driver.
The idea is simple: use multiple textures for the display, each of which
will fit into OpenGL limitations.
There is some code which allows the display driver to know when to start
the new tile. Also added some code to allow force graphics interop to be
re-created. The latter one ended up not used in the final version of the
patch, but it might be helpful for other drivers implementation.
The tile size is limited to 8K now as it is the safest size for textures
on many GPUs and OpenGL drivers.
This is an updated fix with a workaround for freezing with the NVIDIA
driver on Linux.
Differential Revision: https://developer.blender.org/D13385
Sample offset was not accounted for in the adaptive sampling code and caused
issues, like immediately applied adaptive filtering, with non-zero values.
Differential Revision: https://developer.blender.org/D13510
Adds hysteresis to the resolution divider algorithm to avoid having the resolution bounce around when on the boundary of two resolutions.
Reviewed By: brecht, leesonw
Differential Revision: https://developer.blender.org/D12385
This reverts commit 5e37f70307.
It is leading to freezing of the entire desktop for a few seconds when stopping
3D viewport rendering on my Linux / NVIDIA system.
The root of the issue is caused by Cycles ignoring OpenGL limitation on
the maximum resolution of textures: Cycles was allocating texture of the
final render resolution. It was exceeding limitation on certain GPUs and
driver.
The idea is simple: use multiple textures for the display, each of which
will fit into OpenGL limitations.
There is some code which allows the display driver to know when to start
the new tile. Also added some code to allow force graphics interop to be
re-created. The latter one ended up not used in the final version of the
patch, but it might be helpful for other drivers implementation.
The tile size is limited to 8K now as it is the safest size for textures
on many GPUs and OpenGL drivers.
Differential Revision: https://developer.blender.org/D13385
This patch adds new arg-type parameters to `DeviceQueue::enqueue` and its overrides. This is in preparation for the Metal backend which needs this information for correct argument encoding.
Ref T92212
Reviewed By: brecht
Maniphest Tasks: T92212
Differential Revision: https://developer.blender.org/D13357
Noticed when was looking into T93155. Steps to reproduce:
- Open the .blend file from the report
- Hit F12 to start rendering
- After some tiles were rendered hit Esc
The issue is caused by "sticky" cancel reported via Progress. This means
that once user hit Esc all further requests for cancel state will return
truth, which was preventing OIDN denoiser from completing the denoising
task.
Now only allow stopping the denoiser when interactive rendering requests
a very fast stopping.
Aiming the fix for 3.0 branch.
Differential Revision: https://developer.blender.org/D13352
With the current code in master, scrambling distance is enabled on non-hardware accelerated ray tracing devices see a measurable performance decrease when compared scrambling distance on vs off. From testing, this performance decrease comes from the large tile sizes scheduled in `tile.cpp`.
This patch attempts to address the performance decrease by using different algorithms to calculate the tile size for devices with hardware accelerated ray traversal and devices without. Large tile sizes for hardware accelerated devices and small tile sizes for others.
Most of this code is based on proposals from @brecht and @leesonw
Reviewed By: brecht, leesonw
Differential Revision: https://developer.blender.org/D13042
