Commit Graph

25 Commits

Author SHA1 Message Date
7f4479da42 Cycles: OpenCL kernel split
This commit contains all the work related on the AMD megakernel split work
which was mainly done by Varun Sundar, George Kyriazis and Lenny Wang, plus
some help from Sergey Sharybin, Martijn Berger, Thomas Dinges and likely
someone else which we're forgetting to mention.

Currently only AMD cards are enabled for the new split kernel, but it is
possible to force split opencl kernel to be used by setting the following
environment variable: CYCLES_OPENCL_SPLIT_KERNEL_TEST=1.

Not all the features are supported yet, and that being said no motion blur,
camera blur, SSS and volumetrics for now. Also transparent shadows are
disabled on AMD device because of some compiler bug.

This kernel is also only implements regular path tracing and supporting
branched one will take a bit. Branched path tracing is exposed to the
interface still, which is a bit misleading and will be hidden there soon.

More feature will be enabled once they're ported to the split kernel and
tested.

Neither regular CPU nor CUDA has any difference, they're generating the
same exact code, which means no regressions/improvements there.

Based on the research paper:

  https://research.nvidia.com/sites/default/files/publications/laine2013hpg_paper.pdf

Here's the documentation:

  https://docs.google.com/document/d/1LuXW-CV-sVJkQaEGZlMJ86jZ8FmoPfecaMdR-oiWbUY/edit

Design discussion of the patch:

  https://developer.blender.org/T44197

Differential Revision: https://developer.blender.org/D1200
2015-05-09 19:52:40 +05:00
ae7d84dbc1 Cycles: Use native saturate function for CUDA
This more a workaround for CUDA optimizer which can't optimize clamp(x, 0, 1)
into a single instruction and uses 4 instructions instead.

Original patch by @lockal with own modification:

  Don't make changes outside of the kernel. They don't make any difference
  anyway and term saturate() has a bit different meaning outside of kernel.

This gives around 2% of speedup in Barcelona file, but in more complex shader
setups with lots of math nodes with clamping speedup could be much nicer.

Subscribers: dingto

Projects: #cycles

Differential Revision: https://developer.blender.org/D1224
2015-04-28 00:38:32 +05:00
ee36e75b85 Cleanup: Fix Cycles Apache header.
This was already mixed a bit, but the dot belongs there.
2014-12-25 02:50:24 +01:00
dc13969e48 Style cleanup: indentation, braces 2014-05-05 02:19:08 +10:00
a41648c1dc Cycles: add pass alpha threshold value to render layers.
Z, Index, normal, UV and vector passes are only affected by surfaces with alpha
transparency equal to or higher than this threshold. With value 0.0 the first
surface hit will always write to these passes, regardless of transparency. With
higher values surfaces that are mostly transparent can be skipped until an opaque
surface is encountered.
2014-02-06 15:24:15 +01:00
c18712e868 Cycles: change __device and similar qualifiers to ccl_device in kernel code.
This to avoids build conflicts with libc++ on FreeBSD, these __ prefixed values
are reserved for compilers. I apologize to anyone who has patches or branches
and has to go through the pain of merging this change, it may be easiest to do
these same replacements in your code and then apply/merge the patch.

Ref T37477.
2013-11-18 08:48:15 +01:00
edde749850 Fix #36741: cycles AO pass giving values > 1.0 with transparency. 2013-09-17 13:22:42 +00:00
b9ce231060 Cycles: relicense GNU GPL source code to Apache version 2.0.
More information in this post:
http://code.blender.org/

Thanks to all contributes for giving their permission!
2013-08-18 14:16:15 +00:00
8cda3264bd Code cleanup:
* Some typo fixes.
2013-08-13 08:43:31 +00:00
5fc6f04fc8 Cycles / SSS:
* Render Passes are now available for Subsurface Scattering (Direct, Indirect and Color pass). 

This is part of my GSoC project, SVN merge of r58587, r58828 and r58835.
2013-08-03 13:12:09 +00:00
bcfff4f190 Cycles: invert mist pass so that 0 is nearby and 1 is far away. This is the
opposite of Blender Internal but it makes more sense I think.
2013-06-08 17:56:40 +00:00
a604fb730d Cycles: mist pass added, with start/depth/falloff control. If the pass is
enabled in a render layer a Mist Pass panel will be shown in the world
properties.
2013-06-07 12:45:26 +00:00
909d64079a Fix #34226: cycles shadow pass got incorrectly influenced by world multiple
importance sampleing.
2013-02-13 16:46:18 +00:00
57cf48e7c6 Cycles Hair: refactoring to support generic attributes for hair curves. There
should be no functional changes yet. UV, tangent and intercept are now stored
as attributes, with the intention to add more like multiple uv's, vertex
colors, generated coordinates and motion vectors later.

Things got a bit messy due to having both triangle and curve data in the same
mesh data structure, which also gives us two sets of attributes. This will get
cleaned up when we split the mesh class.
2013-01-03 12:08:54 +00:00
3a67122aef Fix #33256: cycles Z pass for orthographic camera was not right, now is more
useful for e.g. fog in compositing.
2012-11-21 13:00:57 +00:00
71195b247e Fix #32072: cycles shadow pass gave different results with/without emitting
materials present, even though it's only taking lamp shadows into account.
2012-09-28 13:41:34 +00:00
1d8c798188 Cycles: support for motion vector and UV passes.
Most of the changes are related to adding support for motion data throughout
the code. There's some code for actual camera/object motion blur raytracing
but it's unfinished (it badly slows down the raytracing kernel even when the
option is turned off), so that code it disabled still.

Motion vector export from Blender tries to avoid computing derived meshes
when the mesh does not have a deforming modifier, and it also won't store
motion vectors for every vertex if only the object or camera is moving.
2012-04-30 12:49:26 +00:00
93df58160e Fix #30966: cycles nan mesh vertices got set to (0, 0, 0), now remove them instead. 2012-04-16 08:35:21 +00:00
e12adeb8c9 Fix #30551: cycles passes combining did not always give identical result combined
with antialiasing/defocus, now divide out color at the very end instead of for each
sample.
2012-03-28 12:18:12 +00:00
755f018324 Cycles: shadow pass support. Note that this only takes into account lamps,
emitting objects or world lighting do not contribute to the shadow pass.

Consider this more as a pass useful for some compositing tricks, unlike
other lighting passes this pass can't be used to exactly reconstruct the
combined pass.
2012-03-28 10:39:21 +00:00
22abc63f67 Cycles: ambient occlusion support, with AO factor and distance, and a render pass.
http://wiki.blender.org/index.php/Doc:2.6/Manual/Render/Cycles/World#Ambient_Occlusion
http://wiki.blender.org/index.php/Doc:2.6/Manual/Render/Cycles/Passes#Lighting_Passes
2012-02-28 16:45:08 +00:00
803286dde8 Cycles: render passes for CUDA cards with compute model >= 2.x. 2012-01-26 19:07:01 +00:00
de5d5ded7b Cycles: fixes for OpenCL build after pass changes, patch by Daniel Genrich. 2012-01-26 15:37:33 +00:00
f8bddbd347 Cycles: fix issues rendering second render layer passes, and avoid unnecessary
clear of buffer.
2012-01-26 14:55:25 +00:00
f99343d3b8 Cycles: Render Passes
Currently supported passes:
* Combined, Z, Normal, Object Index, Material Index, Emission, Environment,
  Diffuse/Glossy/Transmission x Direct/Indirect/Color

Not supported yet:
* UV, Vector, Mist

Only enabled for CPU devices at the moment, will do GPU tweaks tommorrow,
also for environment importance sampling.

Documentation:
http://wiki.blender.org/index.php/Doc:2.6/Manual/Render/Cycles/Passes
2012-01-25 17:23:52 +00:00