Adds a descriptor for attributes that can easily be passed around and extended
to contain more data. Will be used for attributes on subdivision meshes.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D2110
This changes actually lead to 2x slowdown. It's getting a bit annoying
because those are the changes to make pre-maxwell cards render with the
same speed.
All the changes are mainly giving explicit tips on inlining functions,
so they match how inlining worked with previous toolkit.
This make kernel compiled by CUDA 8 render in average with same speed
as previous kernels. Some scenes are somewhat faster, some of them are
somewhat slower. But slowdown is within 1% so far.
On a positive side it allows us to enable newer generation cards on
buildbots (so GTX 10x0 will be officially supported soon).
These are complex nodes, and it's conceivable they may end up constant
in some circumstances within node groups, so folding support is useful.
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D2084
This adds support for ngons and attributes on subdivision meshes. Ngons are
needed for proper attribute interpolation as well as correct Catmull-Clark
subdivision. Several changes are made to achieve this:
- new primitive `SubdFace` added to `Mesh`
- 3 more textures are used to store info on patches from subd meshes
- Blender export uses loop interface instead of tessface for subd meshes
- `Attribute` class is updated with a simplified way to pass primitive counts
around and to support ngons.
- extra points for ngons are generated for O(1) attribute interpolation
- curves are temporally disabled on subd meshes to avoid various bugs with
implementation
- old unneeded code is removed from `subd/`
- various fixes and improvements
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D2108
While they prevent legit write past the array boundary error
those fixes introduced regression in behavior when having exact
max_hits transparent intersections and nothing else.
Previous code would have considered such case a totally opaque,
but it's not correct.
Fixes T48941: Some materials don't get transparent shadows anymore
In the triangle intersection refinement code, rays that are parallel to the triangle caused a divide by zero.
These rays might initially hit the triangle due to the watertight intersection test, but are very rare - therefore, just skipping the refinement for them works fine.
Also, a few remaining issues in the MultiGGX code are fixed that were caused by rays parallel to the surface (which happened more often there due to smooth shading).
The issue was caused by SSS intersection code gathering all
intersections without check for duplicated ones. This caused
situations when same intersection will be recorded twice in
the case if triangle is shared by several BVH nodes.
Usually this is handled by checking intersection distance
after sorting intersections (in shadow_blocked for example)
but for SSS we don't do such sorting and using number of
intersections to calculate various things.
Didn't find anything smarter than to check intersection
distance in triangle_intersect_subsurface().
This solves render artifacts in the cost of 1.5% slowdown
of extreme case rendering (SSS object filling in whole
FullHD screen).
Reviewers: brecht
Reviewed By: brecht
Differential Revision: https://developer.blender.org/D2105
- In fresnel_dielectric, the differentials calculation sometimes divided by zero.
- When the normal map was (0.5, 0.5, 0.5), the code would try to normalize a zero vector. Now, it just uses the regular normal as a fallback.
- The approximate error function used in Beckmann sampling sometimes overflowed to inf while calculating r^16. The final value is 1 - 1/r^16, however,
so now it just returns 1 if the computation would overflow otherwise.
Also, this fixes a numerical issue where A would be inf.
Since later G is set to 1 if A is larger than 1.6, the code now checks the reciprocal of A for being smaller than 1/1.6 - same effect, but no inf involved.
It was possible to miss bounces termination criteria in this functions,
mainly when max_hits was set to 0.
Made the check more robust in traversal functions (which should not
affect performance, it's an operation of same complexity AFAIK).
Also avoid doing ray-scene intersection from shadow_blocked when
limit of transparent bounces was already reached.
This way restrict can be used for CUDA and OpenCL as well.
From quick tests in areas i've been testing this it might give some
barely measurable %% of speedup, but it increases registers pressure.
So use of this qualifier is still really limited.
Using camel case for variables is something what didn't came from our original
code, but rather from third party libraries. Let's avoid those as much as possible.
Matches better naming of volume traversal files, where we've got
optimized versions of a single step of volume intersection and
traversal which will gather all volume intersections.
BVH traversal is not really that much a geometry and we've got
quite some traversals now. Makes sense to keep them separate in
the name of source structure clarity.
This commit implements traversal of unaligned BVH nodes.
QBVH traversal is fully SIMD optimized and calculates orientation
for all 4 children at a time, regular BVH might probably be optimized
a bit more.
This is a special builder type which is allowed to orient nodes to
strands direction, hence minimizing their surface area in comparison
with axis-aligned nodes. Such nodes are much more efficient for hair
rendering.
Implementation of BVH builder is based on Embree, and generally idea
there is to calculate axis-aligned SAH and oriented SAH and if SAH
of oriented node is smaller than axis-aligned SAH we create unaligned
node.
We store both aligned and unaligned nodes in the same tree (which
seems to be different from what Embree is doing) so we don't have
any any extra calculations needed to set up hair ray for BVH
traversal, hence avoiding any possible negative effect of this new
BVH nodes type.
This new builder is currently not in use, still need to make BVH
traversal code aware of unaligned nodes.
This seems to be straightforward way to support heterogeneous nodes
in the same tree.
There is some penalty related on 4gig limit of the address space now,
but here's are the thing:
Traversal code was already using ints to store final offset, so
there can't be regressions really.
This is a required commit to make it possible to encode both aligned
and unaligned nodes in the same array. Also, in the future we can use
this to get rid of __leaf_nodes array (which is a bit tricky to do since
trickery in pack_instances().
There are several internal changes for this:
First idea is to make __tri_verts to behave similar to __tri_storage,
meaning, __tri_verts array now contains all vertices of all triangles
instead of just mesh vertices. This saves some lookup when reading
triangle coordinates in functions like triangle_normal().
In order to make it efficient needed to store global triangle offset
somewhere. So no __tri_vindex.w contains a global triangle index which
can be used to read triangle vertices.
Additionally, the order of vertices in that array is aligned with
primitives from BVH. This is needed to keep cache as much coherent as
possible for BVH traversal. This causes some extra tricks needed to
fill the array in and deal with True Displacement but those trickery
is fully required to prevent noticeable slowdown.
Next idea was to use this __tri_verts instead of __tri_storage in
intersection code. Unfortunately, this is quite tricky to do without
noticeable speed loss. Mainly this loss is caused by extra lookup
happening to access vertex coordinate.
Fortunately, tricks here and there (i,e, some types changes to avoid
casts which are not really coming for free) reduces those losses to
an acceptable level. So now they are within couple of percent only,
On a positive site we've achieved:
- Few percent of memory save with triangle-only scenes. Actual save
in this case is close to size of all vertices.
On a more fine-subdivided scenes this benefit might become more
obvious.
- Huge memory save of hairy scenes. For example, on koro.blend
there is about 20% memory save. Similar figure for bunny.blend.
This memory save was the main goal of this commit to move forward
with Hair BVH which required more memory per BVH node. So while
this sounds exciting, this memory optimization will become invisible
by upcoming Hair BVH work.
But again on a positive side, we can add an option to NOT use Hair
BVH and then we'll have same-ish render times as we've got currently
but will have this 20% memory benefit on hairy scenes.
It was initially unsupported because initial idea of checking visibility
of all children was slowing scenes down a lot. Now the idea has changed
and we only perform visibility check of current node. This avoids huge
slowdown (from tests here it seems to be withing 1-2%, but more tests
would never hurt) and gives nice speedup of ray traversal for complex
scenes which utilized ray visibility.
Here's timing of koro.blend:
Without visibility check With visibility check
Original file 4min 20sec 4min 23sec
Camera rays only 1min 43 sec 55sec
Unfortunately, this doesn't come for free and requires extra data in
BVH node, which increases memory usage of BVH nodes by 15%. This we
can solve with some future trickery of avoiding __tri_storage created
for curve segments.
Make sure we don't perform any implicit address space conversion.
A bit annoying, but less intrusive approaches (like using temp private
variable in .cl kernel) do not work correct here.
Using generic address space will help from code side here, but will
be somewhat slower due to extra things happening as far as i know.
