It turns out that the new Beckmann sampling function doesn't work well with
Quasi Monte Carlo sampling, mainly near normal incidence where it can be worse
than the previous sampler. In the new sampler the random number pattern gets
split in two, warped and overlapped, which hurts the stratification, see the
visualization in the differential revision.
Now we use a precomputed table, which is much better behaved. GGX does not seem
to benefit from using a precomputed table.
Disadvantage is that this table adds 1MB of memory usage and 0.03s startup time
to every render (on my quad core CPU).
Differential Revision: https://developer.blender.org/D614
This way util_simd.cpp would not require modifications
if/when SSE2 is suddenly supported on 32bit platforms.
This also allowed to unleash some issues with util_simd.h
related on the fact that there size_t and int are actually
the same types.
* Anisotropic BSDF now supports GGX and Beckmann distributions, Ward has been
removed because other distributions are superior.
* GGX is now the default distribution for all glossy and anisotropic nodes,
since it looks good, has low noise and is fast to evaluate.
* Ashikhmin-Shirley is now available in the Glossy BSDF.
* Ashikhmin-Shirley anisotropic BSDF was added as closure
* Anisotropic BSDF node now has two distributions
Reviewers: brecht, dingto
Differential Revision: https://developer.blender.org/D549
Samples render slower than before, but hopefully this is made up for with
reduced noise in most cases. The main slowdown comes from samples that would
previously be wasted and turn out black, which are now continued.
GGX sampling is about the same speed as before, while for Beckmann it is slower
still. Perhaps optimizations are still possible there, but didn't find anything
easy.
Code from this paper, which comes with sample code:
Importance Sampling Microfacet-Based BSDFs using the Distribution of Visible Normals.
E. Heitz and E. d'Eon, EGSR 2014
Differential Revision: https://developer.blender.org/D572
This gives you "Multiple Importance", "Distance" and "Equiangular" choices.
What multiple importance sampling does is make things more robust to certain
types of noise at the cost of a bit more noise in cases where the individual
strategies are always better.
So if you've got a pretty dense volume that's lit from far away then distance
sampling is usually more efficient. If you've got a light inside or near the
volume then equiangular sampling is better. If you have a combination of both,
then the multiple importance sampling will be better.
* Volume multiple importace sampling support to combine equiangular and distance
sampling, for both homogeneous and heterogeneous volumes.
* Branched path "Sample All Direct Lights" and "Sample All Indirect Lights" now
apply to volumes as well as surfaces.
Implementation note:
For simplicity this is all done with decoupled ray marching, the only case we do
not use decoupled is for distance only sampling with one light sample. The
homogeneous case should still compile on the GPU because it only requires fixed
size storage, but the heterogeneous case will be trickier to get working.
* Added support for uchar4 attributes to Cycles' attribute system.
* This is used for Vertex Colors now, which saves some memory (4 unsigned characters, instead of 4 floats).
* GPU Texture Limit on sm_20 and sm_21 decreased from 95 to 94, because we need a new texture for the uchar4 attributes. This is no problem for sm_30 or newer.
Part of my GSoC 2014.
This kernel is compiled with AVX2, FMA3, and BMI compiler flags. At the moment only Intel Haswell benefits from this, but future AMD CPUs will have these instructions as well.
Makes rendering on Haswell CPUs a few percent faster, only benchmarked with clang on OS X though.
Part of my GSoC 2014.
Instead of pre-calculation and storage, we now calculate the face normal during render.
This gives a small slowdown (~1%) but decreases memory usage, which is especially important for GPUs,
where you have limited VRAM.
Part of my GSoC 2014.
This makes the code a bit easier to understand, and might come in handy
if we want to reuse more Embree code.
Differential Revision: https://developer.blender.org/D482
Code by Brecht, with fixes by Lockal, Sergey and myself.
This gives around 30% of speedup for gaussian blur node.
Pretty much straightforward implementation inside the node
itself, but needed to implement some additional things:
- Aligned malloc. It's needed to load data onto SSE registers
faster. based on the aligned_malloc() from Libmv with
some additional trickery going on to support arbitrary
alignment (this magic is needed because of MemHead).
In the practice only 16bit alignment is supported because
of the lack of aligned malloc with arbitrary alignment
for OSX. Not a bit deal for now because we need 16 bytes
alignment at this moment only. Could be tweaked further
later.
- Memory buffers in compositor are now aligned to 16 bytes.
Should be harmless for non-SSE cases too. just mentioning.
Reviewers: campbellbarton, lukastoenne, jbakker
Reviewed By: campbellbarton
CC: lockal
Differential Revision: https://developer.blender.org/D564
