Age | Commit message (Collapse) | Author | |
---|---|---|---|
2017-10-06 | Merge branch 'master' into blender28 | Campbell Barton | |
2017-10-05 | Fix T53001: more workarounds for crash in AMD compiler with recent drivers. | Brecht Van Lommel | |
2017-09-22 | Merge branch 'master' into blender2.8 | Sergey Sharybin | |
2017-09-20 | Fix T52368: Cycles OSL trace() failing on Windows 32 bit. | Brecht Van Lommel | |
2017-09-05 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-09-04 | Cycles: Fix compilation warning | Sergey Sharybin | |
2017-08-31 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-29 | Fix Cycles Windows render errors with BVH2 CPU rendering. | Brecht Van Lommel | |
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. | |||
2017-08-26 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-25 | Cycles: Add utility function to query current value of scoped timer | Sergey Sharybin | |
2017-08-25 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-24 | Cycles: FIx issue with -0 being considered a non-finite value | Sergey Sharybin | |
2017-08-23 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-23 | Fix implementation of atomic update max and move to a central location | Mai Lavelle | |
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. | |||
2017-08-22 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-21 | Cycles: reorganize Performance panel layout, move viewport BVH type to debug. | Brecht Van Lommel | |
2017-08-19 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-19 | Fix T52443: Cycles OpenCL build error after recent mesh lights changes. | Brecht Van Lommel | |
2017-08-14 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-12 | Fix T52372: CUDA build error after recent changes. | Brecht Van Lommel | |
2017-08-12 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-12 | Fix T52368: OSL trace() crash after recent changes. | Brecht Van Lommel | |
2017-08-11 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-11 | Fix T52322: denoiser broken on Windows after recent changes. | Brecht Van Lommel | |
It's not clear why this only happened on Windows, but the code was wrong and should do a bitcast here instead of conversion. | |||
2017-08-08 | Merge branch 'master' into blender2.8 | Bastien Montagne | |
Conflicts: source/blender/depsgraph/intern/builder/deg_builder_relations.cc source/blender/editors/object/object_add.c source/blender/python/intern/bpy_app_handlers.c | |||
2017-08-08 | Cycles: Add utility macro ccl_ref | Sergey Sharybin | |
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. | |||
2017-08-07 | Fix Windows build errors with recent Cycles SIMD refactoring. | Brecht Van Lommel | |
2017-08-07 | Merge branch 'master' into blender2.8 | Brecht Van Lommel | |
2017-08-07 | Fix Windows build errors with recent Cycles SIMD refactoring. | Brecht Van Lommel | |
2017-08-07 | Merge branch 'master' into blender2.8 | Bastien Montagne | |
2017-08-07 | Cycles: Cleanup, space after keyword | Sergey Sharybin | |
2017-08-07 | Code refactor: use float4 instead of intrinsics for CPU denoise filtering. | Brecht Van Lommel | |
Differential Revision: https://developer.blender.org/D2764 | |||
2017-08-07 | Code refactor: add, remove, optimize various SSE functions. | Brecht Van Lommel | |
* 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 | |||
2017-08-07 | Code refactor: split defines into separate header, changes to SSE type headers. | Brecht Van Lommel | |
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 | |||
2017-08-04 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-03 | Cycles: Extra tweaks to performance of header expansion | Sergey Sharybin | |
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). | |||
2017-08-03 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-08-02 | Cycles: Avoid some expensive operations in header expansions | Sergey Sharybin | |
Basically gather lines as-is during traversal, avoiding allocating memory for all the lines in headers. Brings additional performance improvement abut 20%. | |||
2017-08-02 | Cycles: Support "precompiled" headers in include expansion algorithm | Sergey Sharybin | |
The idea here is that it is possible to mark certain include statements as "precompiled" which means all subsequent includes of that file will be replaced with an empty string. This is a way to deal with tricky include pattern happening in single program OpenCL split kernel which was including bunch of headers about 10 times. This brings preprocessing time from ~1sec to ~0.1sec on my laptop. | |||
2017-08-02 | Cycles: Speed up #include expansion algorithm | Sergey Sharybin | |
The idea is to re-use files which were already processed. Gives about 4x speedup of processing time (~4.5sec vs 1.0sec) on my laptop for the whole OpenCL kernel. For users it will mean lower delay before OpenCL rendering might start. | |||
2017-07-25 | Merge branch 'master' into blender2.8 | Campbell Barton | |
2017-07-25 | Fix T51450: viewport render time keeps increasing after render is done. | Jeff Knox | |
Reviewed By: brecht Differential Revision: https://developer.blender.org/D2747 | |||
2017-07-21 | Merge branch 'master' into blender2.8 | Sergey Sharybin | |
2017-07-21 | Fix a few harmless maybe uninitialized warnings with GCC 5.4. | Brecht Van Lommel | |
GCC seems to detect uninitialized into function calls now, but then isn't always smart enough to see that it is actually initialized. Disabling this warning entirely seems a bit too much, so initialize a bit more now. | |||
2017-07-06 | Merge branch 'master' into blender2.8 | Sergey Sharybin | |
2017-07-06 | Cycles: Add artificial memory limit debug option for OpenCL | Mai Lavelle | |
2017-07-06 | Revert "Cycles: use std::min and max for extra overloads" | Mai Lavelle | |
We already have this in util_algorithm.h This reverts commit cff172c7621d89773baa99a9460f19056efb5f1e. | |||
2017-07-06 | Cycles: use std::min and max for extra overloads | Mai Lavelle | |
2017-07-05 | Merge branch 'master' into blender2.8 | Sybren A. Stüvel | |
2017-07-05 | Cycles: Fix compilation error after recent logging changes | Sergey Sharybin | |
This file uses std::ostream for helper << operators, so need to make sure corresponding header is included. |