around the volume.
We generate a tight mesh around the active voxels of the volume in order
to effectively skip empty space, and start volume ray marching as close
to interesting volume data as possible. See code comments for details on
how the mesh generation algorithm works.
This gives up to 2x speedups in some scenes.
Reviewed by: brecht, dingto
Reviewers: #cycles
Subscribers: lvxejay, jtheninja, brecht
Differential Revision: https://developer.blender.org/D3038
It is basically brute force volume scattering within the mesh, but part
of the SSS code for faster performance. The main difference with actual
volume scattering is that we assume the boundaries are diffuse and that
all lighting is coming through this boundary from outside the volume.
This gives much more accurate results for thin features and low density.
Some challenges remain however:
* Significantly more noisy than BSSRDF. Adding Dwivedi sampling may help
here, but it's unclear still how much it helps in real world cases.
* Due to this being a volumetric method, geometry like eyes or mouth can
darken the skin on the outside. We may be able to reduce this effect,
or users can compensate for it by reducing the scattering radius in
such areas.
* Sharp corners are quite bright. This matches actual volume rendering
and results in some other renderers, but maybe not so much real world
objects.
Differential Revision: https://developer.blender.org/D3054
This patch changes the huge list of projects in visual studio into a nice tree matching the source folder structure. see D2823 for details.
Differential Revision: http://developer.blender.org/D2823
This was disabled to avoid updating the geometry every time when the
material includes displacement, because there was no way to distinguish
between surface shader and displacement updates.
As a solution, we now compute an MD5 hash of the nodes linked to the
displacement socket, and only update the mesh if that changes.
Differential Revision: https://developer.blender.org/D3018
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!
In that case it can now fall back to CPU memory, at the cost of reduced
performance. For scenes that fit in GPU memory, this commit should not
cause any noticeable slowdowns.
We don't use all physical system RAM, since that can cause OS instability.
We leave at least half of system RAM or 4GB to other software, whichever
is smaller.
For image textures in host memory, performance was maybe 20-30% slower
in our tests (although this is highly hardware and scene dependent). Once
other type of data doesn't fit on the GPU, performance can be e.g. 10x
slower, and at that point it's probably better to just render on the CPU.
Differential Revision: https://developer.blender.org/D2056
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.
There was some changes about namespaces, which causes ambiguities.
Replaces using namespace with an explicit symbols we need. Is good idea to NOT
pull in the whole namespace anyway!
* 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.
* Use common TextureInfo struct for all devices, except CUDA fermi.
* Move image sampling code to kernels/*/kernel_*_image.h files.
* Use arrays for data textures on Fermi too, so device_vector<Struct> works.
One problem is that it was always using __mm_blendv_ps emulation even if the
instruction was supported. The other that the emulation function was wrong.
Thanks a lot to Ray Molenkamp for tracking this one down.
While unlikely to have had any serious effects because of limited use, the
previous implementation was not actually atomic due to a data race and
incorrectly coded CAS loop. We also had duplicates of this code in a few
places, it's now been moved to a single location with all other atomic
operations.
It is defined to & for CPU side compilation, and defined to an empty for any GPU
platform. The idea here is to use this macro instead of #ifdef block with bunch
of duplicated lines just to make it so CPU code is efficient.
Eventually we might switch to references on CUDA as well, but that would require
some intensive testing.
* Remove some unnecessary SSE emulation defines.
* Use full precision float division so we can enable it.
* Add sqrt(), sqr(), fabs(), shuffle variations, mask().
* Optimize reduce_add(), select().
Differential Revision: https://developer.blender.org/D2764
I need to use some macros defined in util_simd.h for float3/float4, to emulate
SSE4 instructions on SSE2. But due to issues with order of header includes this
was not possible, this does some refactoring to make it work.
Differential Revision: https://developer.blender.org/D2764
Two main things here:
1. Replace all unsafe for #line directive characters into a single loop,
avoiding multiple iterations and multiple temporary strings created.
2. Don't merge token char by char but calculate start and end point and
then copy all substring at once.
This gives about 15% speedup of source processing time. At this point
(with all previous commits from today) we've shrinked down compiled
sources size from 108 MB down to ~5.5 MB and lowered processing time
from 4.5 sec down to 0.047 sec on my laptop running Linux (this was a
constant time which Blender will always spent first time loading kernel,
even if we've got compiled clbin).
Basically gather lines as-is during traversal, avoiding allocating
memory for all the lines in headers.
Brings additional performance improvement abut 20%.
