Age | Commit message (Collapse) | Author | |
---|---|---|---|
2014-01-17 | Fix T37706: avoid cycles crash when using a stack that exceeds SVM stack limits. | Brecht Van Lommel | |
This should be pretty rare, the shader in question had many parallel node links because of copying the nodes many times, which is inefficient to run anyway. | |||
2014-01-16 | Workaround for avx assembler not compiling with vanilla gcc ( with openMP case ) | Jens Verwiebe | |
2014-01-16 | Fix compilation of Cycles AVX kernel with cmake. | Thomas Dinges | |
2014-01-16 | Cycles: Add an AVX kernel for CPU rendering. | Thomas Dinges | |
* 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 | |||
2014-01-15 | Code cleanup: move half float functions to separate header file. | Brecht Van Lommel | |
2014-01-15 | Code cleanup: some reshuffling of SIMD defines moving more code to ↵ | Brecht Van Lommel | |
util_optimization.h. | |||
2014-01-15 | Fix compilation error with stricg GCC flags | Sergey Sharybin | |
2014-01-15 | Fix a bunch of UI string issues... | Bastien Montagne | |
2014-01-15 | Cycles: Disable SSE41 kernel on 32bit, we don't use intrinsics here anyway. ↵ | Thomas Dinges | |
Also disable it for Visual Studio < 2012, broken blendv instruction. | |||
2014-01-15 | OS X linker does not like empty compilation unit by itself in a library. ↵ | Martijn Berger | |
Scons creates one library (.a) per kernel. This fixes that | |||
2014-01-15 | Cycles: Build SSE41 kernel per default, remove build option. This hopefully ↵ | Thomas Dinges | |
also fixes some compile errors on various systems. | |||
2014-01-15 | DingTo forgot to make sure kernel_sse41 is compiled in even when empty | Martijn Berger | |
2014-01-14 | Cycles: Skip the compilation of the dedicated SSE2 kernel on x86-64, we can ↵ | Thomas Dinges | |
assume SSE2 here, so just re-use the regular one. Saves 500kb in the blender binary. Reviewed by: brecht Differential Revision: https://developer.blender.org/D199 | |||
2014-01-14 | Further fix for T37817: non-ascii paths fix in Cycles broke OSL rendering. | Brecht Van Lommel | |
Not quite sure yet what is going on here, but this works for me. | |||
2014-01-14 | Cycles, Code cleanup: simplify code for color linear interpolation and float ↵ | Sv. Lockal | |
math Reviewed By: brecht Differential Revision: https://developer.blender.org/D215 | |||
2014-01-14 | Fix T38192: OSL got incorrectly enabled in preview render when GPU was selected | Brecht Van Lommel | |
for rendering of the main scene. | |||
2014-01-14 | Cycles: Fix Wave texture difference between OSL and SVM, OSL wasn't using ↵ | Thomas Dinges | |
the "Scale" properly for distortion. | |||
2014-01-14 | Code cleanup / Cycles: Don't pass scale to texture functions, do the ↵ | Thomas Dinges | |
multiplication in the function call already. | |||
2014-01-13 | Fix T38190: Linux tablet: Issue with XInput/GHOST? | Bastien Montagne | |
With edits by Campbell, thanks! Looks like in some cases (driver dependent?), `XDeviceMotionEvent` get generated with only part of expected data (e.g. only x coordinate, only pressure, etc.), data which did not change since last event being NULL. We know which data to actually handle with `XDeviceMotionEvent.first_axis` and `XDeviceMotionEvent.axes_count` values. Reviewed by: campbellbarton Differential Revision: https://developer.blender.org/D208 | |||
2014-01-13 | Fix cycles texture crash on win x86-64 + msvc 11 | Sv. Lockal | |
Use union for __m128 aliasing; while gcc supports no-strict-aliasing attribute, unions are the most common way to deal with __m128 in msvc. | |||
2014-01-13 | Fix cycles standalone compile on some systems, CMAKE_DL_LIBS should be enough. | Marcus von Appen | |
Reviewed By: brecht Differential Revision: https://developer.blender.org/D205 | |||
2014-01-13 | Fix some harmless warnings that mostly appeared on MinGW64 | Antony Riakiotakis | |
2014-01-12 | Fix compilation for OpenCL (and small stype fixes) | Sv. Lockal | |
2014-01-12 | Cycles: SSE for Voronoi textures (targeted for Haswell CPUs) | Sv. Lockal | |
Gives up to 15% speedup scenes with voronoi-based textures (up to 25% with volumes) on Haswell. The performance change for other CPUs is much smaller: 1-2%. Reviewed By: brecht Differential Revision: https://developer.blender.org/D203 | |||
2014-01-11 | Code Cleanup: in Cycles SSE replace macros with templates, skip unused code ↵ | Sv. Lockal | |
with preprocessor, simplify casts | |||
2014-01-11 | Cycles: mix hair minimum width code with SSE intersection code | Sv. Lockal | |
Gives 6.5% speedup for hair.blend from testsuite. Reviewed By: brecht Differential Revision: https://developer.blender.org/D197 | |||
2014-01-11 | Events: support for buttons 6 & 7 (some trackballs have these) X11 only | Campbell Barton | |
Patch by Marcus von Appen Note: this patch makes ISMOUSE accept INBETWEEN_MOUSEMOVE as a mouse event where before it didnt. | |||
2014-01-11 | Ghost: update multitest for changes in BLF | Campbell Barton | |
2014-01-11 | Fix T38129: cycles viewport render display with very bright colors turning ↵ | Brecht Van Lommel | |
black. This happened when exceeding the maximum value representable by half floats. | |||
2014-01-11 | Fix T37817: cycles CUDA detection problem on Windows with non-ascii paths. | Brecht Van Lommel | |
2014-01-10 | Fix T38143: pressing F12 key in the text editor on OS X would type an ↵ | Brecht Van Lommel | |
invalid character. | |||
2014-01-09 | Fix T38134: missing cycles update when removing world volume scatter shader. | Brecht Van Lommel | |
2014-01-09 | Fix T38134: cycles viewport render not updating when adding a world volume ↵ | Brecht Van Lommel | |
shader. | |||
2014-01-08 | Cycles: workaround for noise performance regression in CUDA 5.5 | Sv. Lockal | |
Use manual ternary operation widening in grad(). Without it nvcc 5.5 produces multiple branch splits with very big branches (because of inlining). This solves 19% performance regression for BMW1M-MikePan.blend. Also remove one redundant instruction in perlin SSE (when h == 12 or h == 14, then h is always >= 4). Reviewed By: brecht Differential Revision: https://developer.blender.org/D190 | |||
2014-01-08 | Cycles: Fix World Homogeneous volume setting, had no influence. | Thomas Dinges | |
Thanks to "storm" for noticing this! | |||
2014-01-07 | Cycles: Update Integrator Presets and Total Samples info for latest changes. | Thomas Dinges | |
2014-01-07 | Fix CUDA/OpenCL compile errors in scattering commit. | Brecht Van Lommel | |
2014-01-07 | Cycles Volume Render: scattering support. | Brecht Van Lommel | |
This is done by adding a Volume Scatter node. In many cases you will want to add together a Volume Absorption and Volume Scatter node with the same color and density to get the expected results. This should work with branched path tracing, mixing closures, overlapping volumes, etc. However there's still various optimizations needed for sampling. The main missing thing from the volume branch is the equiangular sampling for homogeneous volumes. The heterogeneous scattering code was arranged such that we can use a single stratified random number for distance sampling, which gives less noise than pseudo random numbers for each step. For volumes where the color is textured there still seems to be something off, needs to be investigated. | |||
2014-01-07 | Code cleanup: defines for statfs were getting out of hand for BSD's. | Campbell Barton | |
add __DragonFly__ and internal defines to avoid copy-pasting checks. also remove __CYGWIN32__ check, since cygwin is no longer supported. | |||
2014-01-07 | Added scons option to actually build the sse41 kernel. CMake already has it | Martijn Berger | |
2014-01-07 | Cycles: Don't include SIMD util file for OpenCL/CUDA, this fixes OpenCL ↵ | Thomas Dinges | |
compilation. | |||
2014-01-06 | Take back last header copy, due it is for native only, must be a runtime ↵ | Jens Verwiebe | |
solution, todo: do by definitions | |||
2014-01-06 | Cmake: fix kernelcompile after introduction of util_simd.h | Jens Verwiebe | |
2014-01-06 | Cycles: Minor optimization (~1%) for texture access on CPU | Sv. Lockal | |
2014-01-06 | Cleanup: use blend() in perlin noise (gives 12 less instructions on SSE4.1) | Sv. Lockal | |
2014-01-06 | Cycles: SSE optimization for sRGB conversion (gives 7% speedup on CPU for ↵ | Sv. Lockal | |
pavillon_barcelone scene) Thanks brecht/dingto/juicyfruit et al. for testing and reviewing this patch in T38034. | |||
2014-01-06 | Code Cleanup: osl style | Campbell Barton | |
2014-01-06 | Code cleanup / Cycles: else/if for SSE41 kernel functions. | Thomas Dinges | |
2014-01-04 | CMake: cleanup and add include | Campbell Barton | |
2014-01-03 | Fix gcc compile error in last commit. | Brecht Van Lommel | |