Commit Graph

33 Commits

Author SHA1 Message Date
Sergey Sharybin
a537e7b426 Cycles: Fix strict compilation warnings 2016-11-23 10:59:54 +01:00
Sergey Sharybin
751573ce6f Fix T50034: Blender changes processor affinity unauthorized 2016-11-22 16:03:16 +01:00
Sergey Sharybin
b277ba5c0d Cycles: Fix compilation error on OSX 2016-06-06 13:52:57 +02:00
Sergey Sharybin
b62faa54de Cycles: Add support of processor groups
Currently for windows only, this is an initial commit towards native
support of NUMA.

Current commit makes it so Cycles will use all logical processors on
Windows running on system with more than 64 threads.

Reviewers: juicyfruit, dingto, lukasstockner97, maiself, brecht

Subscribers: LazyDodo

Differential Revision: https://developer.blender.org/D2049
2016-06-06 09:14:37 +02:00
Sergey Sharybin
f25f7c8030 Cycles: Re-implement some utilities to avoid use of boost
The title says it all actually, the idea is to make Cycles
only requiring Boost via 3rd party dependencies like OIIO
and OSL.

So now there are only few places which still uses Boost:

- Foreach, function bindings and threading primitives.

  Those we can easily get rid with C++11 bump (which seems
  inevitable sooner or later if we'll want ot use newer
  LLVM for OSL),

- Networking devices

  There's no quick solution for those currently, but there
  are some patches around which improves serialization.

Reviewers: juicyfruit, mont29, campbellbarton, brecht, dingto

Reviewed By: brecht, dingto

Differential Revision: https://developer.blender.org/D1764
2016-02-06 19:19:20 +01:00
Sergey Sharybin
ac7aefd7c2 Cycles: Use special debug panel to fine-tune debug flags
This panel is only visible when debug_value is set to 256 and has no
affect in other cases. However, if debug value is not set to this
value, environment variables will be used to control which features
are enabled, so there's no visible changes to anyone in fact.

There are some changes needed to prevent devices re-enumeration on
every Cycles session create.

Reviewers: juicyfruit, lukasstockner97, dingto, brecht

Reviewed By: lukasstockner97, dingto

Differential Revision: https://developer.blender.org/D1720
2016-01-12 16:21:30 +05:00
Thomas Dinges
a934730368 Cycles: Remove TM / R and whitespace from OpenCL device names.
Was already done for CPU devices, now we also do this for OpenCL.
2015-05-21 23:43:18 +02:00
Sv. Lockal
c7bccb30bf Cycles: check for F16C support with __cpuid, as we do for BMI and BMI2 2015-05-11 15:49:36 +00:00
Thomas Dinges
f2951c23cf Cleanup: Remove unused Cycles cpuid code. 2015-02-11 11:28:42 +01:00
Sergey Sharybin
4b04a4e2ff Cycles: Control CPU capabilities via environment variables
Purely developers-only feature which allows to disable some of the CPU
capabilities. This way it's easier to test different kernels on the
same machine.
2015-02-11 01:56:58 +05:00
Thomas Dinges
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
Thomas Dinges
866c7fb6e6 Cycles: Add an AVX2 CPU kernel.
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.
2014-06-13 22:26:20 +02:00
Campbell Barton
dc13969e48 Style cleanup: indentation, braces 2014-05-05 02:19:08 +10:00
Martijn Berger
eb4f2b4897 Fix missing brackets in cpuid bitfield check.
concern raised by lukas_t (rBef73d547cc7c663ad180721094c81b3c81482ac3)
2014-02-25 19:52:38 +01:00
Martijn Berger
ef73d547cc Fix T38815
For AVX support we need to check both OS support and CPU support.
2014-02-25 17:57:05 +01:00
Thomas Dinges
de28a4d4b2 Cycles: Add an AVX kernel for CPU rendering.
* AVX is available on Intel Sandy Bridge and newer and AMD Bulldozer and newer.
* We don't use dedicated AVX intrinsics yet, but gcc auto vectorization gives a 3% performance improvement for Caminandes. Tested on an i5-3570, Linux x64.
* No change for Windows yet, MSVC 2008 does not support AVX.

Reviewed by: brecht
Differential Revision: https://developer.blender.org/D216
2014-01-16 17:04:11 +01:00
Martijn Berger
85a0c5d4e1 Cycles: network render code updated for latest changes and improved
This actually works somewhat now, although viewport rendering is broken and any
kind of network error or connection failure will kill Blender.

* Experimental WITH_CYCLES_NETWORK cmake option
* Networked Device is shown as an option next to CPU and GPU Compute
* Various updates to work with the latest Cycles code
* Locks and thread safety for RPC calls and tiles
* Refactored pointer mapping code
* Fix error in CPU brand string retrieval code

This includes work by Doug Gale, Martijn Berger and Brecht Van Lommel.

Reviewers: brecht

Differential Revision: http://developer.blender.org/D36
2013-12-07 12:26:58 +01:00
Martijn Berger
e3a79258d1 Cycles: test code for sse 4.1 kernel and alignment for some vector types.
This is mostly work towards enabling the __KERNEL_SSE__ option to start using
SIMD operations for vector math operations. This 4.1 kernel performes about 8%
faster with that option but overall is still slower than without the option.

WITH_CYCLES_OPTIMIZED_KERNEL_SSE41 is the cmake flag for testing this kernel.

Alignment of int3, int4, float3, float4 to 16 bytes seems to give a slight 1-2%
speedup on tested systems with the current kernel already, so is enabled now.
2013-11-22 14:42:41 +01:00
Brecht Van Lommel
e9d03296c7 Better fix for #36935 and 36316:
* 32 bit GCC builds now have the SSE BVH optimizations turned off, but still
  compile with SSE flags for better performance.

* White color when rendering on Windows seems to have been unrelated to SSE,
  rather it was a graphics driver not supporting half float textures, added a
  check for that now.
2013-10-05 19:56:34 +00:00
Brecht Van Lommel
6737a04061 Attempt to fix #36935: disable SSE optimizations on 32 bit windows too. Something
strange is going on here, but I don't think it can be fixed before the release,
if it is worth at all spending time on this.
2013-10-04 14:47:37 +00:00
Brecht Van Lommel
e308c2f166 Fix #36316: dots in cycles render on certain CPUs with 32 bit linux builds.
There is some sort of problem with the SSE2 code path, but I couldn't find
the cause, maybe a compiler bug due to the large amount of inlining? For
now I've disabled SSE2 optimizatons in 32 bit GCC builds.
2013-10-02 19:00:16 +00:00
Brecht Van Lommel
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
Brecht Van Lommel
649dd6f648 Fix cycles crash on some processors. We actually need S-SSE3 support for this
new BVH traversal code, not just SSE3.
2013-06-18 16:52:02 +00:00
Brecht Van Lommel
3fe117bd3d Fix build error on non-x86 architectures as pointed out by Jochen Schmitt. 2013-06-04 11:21:13 +00:00
Brecht Van Lommel
7c9d993347 Fix cycles intersection issue with overlapping faces on windows 32 bit and CPU
without SSE3 support, due to 80 bit precision float register being used for one
bounding box but not the one next to it.
2013-02-04 16:12:37 +00:00
Campbell Barton
0fbb6bff27 style cleanup: block comments 2012-06-09 17:22:52 +00:00
Campbell Barton
d5032657ed style cleanup 2012-06-06 22:38:39 +00:00
Brecht Van Lommel
efe4ea284a Cycles:
* Fix broken compile of test app.
* Fix some warnings compiling with gcc for 32 bit.
* More tweaks to avoid extended precision issue from #29301.
2011-12-02 14:26:28 +00:00
Brecht Van Lommel
db8024f4b5 Fix #29259: cycles issues on certain processors. Now two versions of the kernel
are compiled, one SSE optimized and the other not, and it will choose between
them at runtime.
2011-11-15 15:13:38 +00:00
Brecht Van Lommel
9b31cba74e Cycles: some warning fixes, cpu device task tweaks, avoid unnecessary
tonemap in non-viewport render, and some utility functions.
2011-09-08 18:58:07 +00:00
Antony Riakiotakis
6edb09fe93 Compile fixes for MinGW, checked with basic initial setup, no CUDA, gcc 4.5.2.
OpenImageIO still gives link-time errors, will try to make a lib for MinGW, see if it is fixed.
2011-09-04 15:39:09 +00:00
Brecht Van Lommel
c18c6056ff Cycles: two 32 bit fixes with help from IRC user Agiofws. 2011-05-05 13:51:33 +00:00
Ton Roosendaal
da376e0237 Cycles render engine, initial commit. This is the engine itself, blender modifications and build instructions will follow later.
Cycles uses code from some great open source projects, many thanks them:

* BVH building and traversal code from NVidia's "Understanding the Efficiency of Ray Traversal on GPUs":
http://code.google.com/p/understanding-the-efficiency-of-ray-traversal-on-gpus/
* Open Shading Language for a large part of the shading system:
http://code.google.com/p/openshadinglanguage/
* Blender for procedural textures and a few other nodes.
* Approximate Catmull Clark subdivision from NVidia Mesh tools:
http://code.google.com/p/nvidia-mesh-tools/
* Sobol direction vectors from:
http://web.maths.unsw.edu.au/~fkuo/sobol/
* Film response functions from:
http://www.cs.columbia.edu/CAVE/software/softlib/dorf.php
2011-04-27 11:58:34 +00:00