Now ccl_device sets inlining and ccl_device_inline forces inlining.
This matches more closely with what is currently done for cuda and metal
backends.
I've measured from 1% to 6% overall performance improvement in rendering
benchmark scenes on Arc B580, as well as a small decrease in compile
time.
Previously point cloud rendering was disabled on the HIPRT backend due
to unexpected performance regressions introduce by it.
With the recent update to HIP SDK 6.3 and HIPRT 2.5, these performance
regressions have been resolved and so this commit re-enables
point cloud rendering on HIPRT.
Pull Request: https://projects.blender.org/blender/blender/pulls/134902
Dropping the inlining hint for `light_tree_pdf` and reverting to the
default inlining thresholds for DPC++ compiler gives a ~4% speedup on
classroom and other scenes on Arc B580.
Pull Request: https://projects.blender.org/blender/blender/pulls/135042
This implements three improvements to the energy preservation and albedo
scaling logic, which help the Principled BSDF pass the white-furnace test
when using the coat layers at high roughness.
Specifically, at roughness 0.3, the albedo scaling brings it from 60% at
the edge to 95%, and with the energy preservation it's 99.8%.
Pull Request: https://projects.blender.org/blender/blender/pulls/134620
This is an intermediate steps towards making lights actual geometry.
Light is now a subclass of Geometry, which simplifies some code.
The geometry is not added to the BVH yet, which would be the next
step and improve light intersection performance with many lights.
This makes object attributes work on lights.
Co-authored-by: Lukas Stockner <lukas@lukasstockner.de>
Pull Request: https://projects.blender.org/blender/blender/pulls/134846
The attribute handling code in the kernel is currently highly duplicated since
it needs to handle five different data types and we couldn't use templates
back then.
We can now, so might as well make use of it and get rid of ~1000 lines.
There are also some small fixes for the GPU OSL code:
- Wrong derivative for .w component when converting float2/float3->float4
- Different conversion for float2->float (CPU averages, GPU used to take .x)
- Removed useless code for converting to float2, not used by OSL
Pull Request: https://projects.blender.org/blender/blender/pulls/134694
This change brings the following improvements on the user level
- Support of GPUs with gfx12 architecture
- New HIP-RT library which in addition to the gfx12 support brings
various bug-fixes.
The known limitation of gfx12 is that OpenImageDenoiser does not yet
support this GPU architecture. This means that while Cycles will use the
full advantage of the gfx12 (including hardware accelerated ray-tracing),
denoising will only be possible on CPU, or secondary gfx11 or below GPU.
This is something that requires a change in OIDN and it is to late to do
it for Blender 4.4, but it is something to look forward for Blender 4.5.
The gfx12 changes for the pre-compiled kernels is rather trivial,
so it comes together (in the same PR) as the bigger HIP-RT change.
On the development side this change brings the following improvements:
- One step compile and link (much simpler CMake rules)
- Embedding BVH binaries in hiprt dll (which makes it easier to package
and load, without relying on special path configuration)
Co-authored-by: Sahar Kashi <sahar.kashi@amd.com>
Co-authored-by: Sergey Sharybin <sergey@blender.org>
Co-authored-by: Brecht Van Lommel <brecht@blender.org>
Pull Request: https://projects.blender.org/blender/blender/pulls/133129
The issue here is that the individual components of TypeDesc are 8-bit each,
but the code was applying a 4-bit mask. It just so happens that the only
case where this matters is TypeDesc::MATRIX44, since its value is 16.
In Cycles lights can be given a light falloff node to control their
light falloff.
This worked by multiplying the light's strength by different
combinations of the ray length, which would be FLT_MAX for
distant lights. This resulting in almost every configuration of the
light falloff node overflowing when used on distant lights, which is
undesirable.
This commit fixes this issue by ignoring most of the functions of the
light falloff node when used on a distant light.
And in the process fixes a small discrepancy between SVM and OSL when
using the light falloff node on distant lights.
Pull Request: https://projects.blender.org/blender/blender/pulls/134539
This commit fixes a issue where ray depth for emissive objects
(E.g. Lights) was incorrect when using the ray depth output of the
light path node in Cycles OSL.
Pull Request: https://projects.blender.org/blender/blender/pulls/134496
The current usage of software-based texture operations in
the oneAPI implementation puts additional register pressure on
the GPU compiler during register allocation. And it also creates
code that requires maintenance. This commit is intended to address
this situation by utilizing a recently productized SYCL bindless
texture API to enable HW-based texture operations using
Intel GPUs' hardware sampler.
This currently translates to 1-11% rendering speedups (scene-specific)
on my Arc A770 and Arc B580. At the moment, there are small
performance regressions with NanoVDB texture operations on Arc B580
and small performance regressions in shade surface MNEE and Raytrace
kernels on Arc A770, but they look recoverable and will be handled
in the future.
Pull Request: https://projects.blender.org/blender/blender/pulls/133457
There is now a non-experimental API for this_work_item functionality, so
let's use it for better code quality and also to avoid the deprecation
warning during compilation.
No functional or performance changes are expected.
Pull Request: https://projects.blender.org/blender/blender/pulls/133472
This is not a complete solution because there may be indirect changes
to the compiler other than the binary that require a rebuild, but this
should catch the simple cases at least.
To align better with the pixel and reduce the samples needed.
The paper was using gamma because the jacobian |d_gamma/d_h| approaches
infinity at the boundaries, but it seems that clamping at 0.999 is
enough for numerical stability.
In practice I did not notice a change in the noise level, but it
simplifies the range computation and renders faster due to reduced
sample amount.
Co-authored-by: Olivier Maury <omaury@meta.com>
Ref: !129616
Pull Request: https://projects.blender.org/blender/blender/pulls/134130
Enables building of a Cubin for GPUs based on Blackwell architecture
if CUDA toolkit version 12.8 or higher is installed.
Only added sm_120 to the default set, since it is the one relevant for
consumer GPUs (RTX 5090 etc.) that are generally used with Blender.
Pull Request: https://projects.blender.org/blender/blender/pulls/134170
This commit adds the `light:random` attribute to OSL, allowing the
object info node to now match between SVM and OSL when using the
random output on a light.
Pull Request: https://projects.blender.org/blender/blender/pulls/134095
The derivatives of the normal were simply not computed.
The offsetted normals are computed by perturbating the barycentric
coordinates. At triangle boundaries, the normals are extrapolated,
so discontinuities might be visible.
Currently only supported on triangles.
Pull Request: https://projects.blender.org/blender/blender/pulls/133769
Use sub-pixel differentials for bump mapping helps with reducing
artifacts when objects are moving or when textures have high frequency
details.
Currently we scale it by 0.1 because it seems to work good in practice,
we can adjust the value in the future if it turns out to be impractical.
Ref: #122892
Pull Request: https://projects.blender.org/blender/blender/pulls/133991
- Rename dx/dy -> dfdx/dfdy to match the actual computed quantity
- Add template functions to compute dfdx/dfdy on triangles for sharing
among different data types
- Add documentation to some functions
- Some code shuffling that makes it easier to scale dfdx/dfdy in the
future
- Some other trivial changes
The issue here is that originally, the step count for the geometry's
motion and the object transform's motion were tied together, so a
single variable is used to store that step count.
However, when using the velocity attribute, it's possible for the step
counts to differ, which will lead to an incorrect interpolated object
transform in the kernel.
Pull Request: https://projects.blender.org/blender/blender/pulls/133788
That version has a bunch of API changes, so by dropping support for older
versions we can remove old compatibility code.
Also, that version is required for OptiX support, so building a fully-featured
Cycles wasn't possible with older OSL anyways.
Pull Request: https://projects.blender.org/blender/blender/pulls/133746
