Age | Commit message (Expand) | Author |
2014-09-04 | Fix wrong track of the memory when doing device vector resize before freeing it | Sergey Sharybin |
2014-08-26 | Cycles: Add an experimental CUDA kernel. | Thomas Dinges |
2014-08-22 | Cycles: Drop support for CUDA 5.0 Toolkit, only 6.0 and 6.5 (recommended) are... | Thomas Dinges |
2014-08-19 | Fix T41471 Cycles Bake: Setting small tile size results in wrong bake with st... | Dalai Felinto |
2014-08-15 | Revert "Fix T41222 Blender gives weird output when baking (4096*4096) resolut... | Dalai Felinto |
2014-08-09 | Cycles OpenCL error to string removed in favour of the same function in clew. | Martijn Berger |
2014-08-05 | Fix T41222 Blender gives weird output when baking (4096*4096) resolution on GPU | Dalai Felinto |
2014-08-05 | Deduplicate CUDA and OpenCL wranglers | Sergey Sharybin |
2014-08-02 | Spelling | Campbell Barton |
2014-07-29 | Implement get_split_task_count to make device_network compile again. | Martijn Berger |
2014-07-25 | Cycles Bake: show progress bar during bake | Dalai Felinto |
2014-07-25 | Switch to Cuda 4.0 style api for kernel invocation. This is a small clean-up ... | Martijn Berger |
2014-07-05 | Cleanup: Typo fixes. | Thomas Dinges |
2014-07-02 | Cycles: Update CUDA error messages, based on Toolkit 6.0. | Thomas Dinges |
2014-07-02 | Cleanup: Remove unused checks in CUDA device code. | Thomas Dinges |
2014-06-14 | Cycles: Add an AVX2 CPU kernel. | Thomas Dinges |
2014-06-06 | Fix T40370: cycles CUDA baking timeout with high number of AA samples. | Brecht Van Lommel |
2014-06-05 | Fix T40228: cycles CUDA multi GPU + world MIS giving error. | Brecht Van Lommel |
2014-05-27 | Fix T40379: world MIS causing too much CUDA memory usage. | Brecht Van Lommel |
2014-05-26 | Fix T40306: cycles baking not distributing work among CPU cores well. | Brecht van Lommel |
2014-05-19 | Cycles: revert async CUDA changes, these are giving too much trouble still. | Brecht Van Lommel |
2014-05-11 | Cycles / CUDA: Increase maximum image textures on GPU. | Thomas Dinges |
2014-05-10 | Fix T40119, CUDA Toolkit version mismatch | Thomas Dinges |
2014-05-04 | Style cleanup: indentation, braces | Campbell Barton |
2014-05-03 | Code cleanup: style, require ; for cuda_assert, opencl_assert | Campbell Barton |
2014-05-03 | Cycles: CUDA changes for kernel evaluation cancel | Brecht Van Lommel |
2014-05-03 | Cycles Bake | Dalai Felinto |
2014-05-03 | Code cleanup: Add -Werror=float-conversion to Cycles | Campbell Barton |
2014-04-30 | Cycles CUDA: make CUDA toolkit 6.0 the official supported version. | Brecht Van Lommel |
2014-04-21 | Cleanup: Remove OpenCL __MULTI_CLOSURE__ sanity check, not needed anymore aft... | Thomas Dinges |
2014-04-17 | Cycles CUDA: don't use cuLaunchGridAsync at all for display devices. | Brecht Van Lommel |
2014-04-17 | Cycles CUDA: only do async execution for GPUs not used for display. | Brecht Van Lommel |
2014-04-16 | Fix another compile error with recent commit on visual studio. | Brecht Van Lommel |
2014-04-16 | Cycles CUDA: enabled branched path kernel again, with more registers. | Brecht Van Lommel |
2014-04-16 | Cycles code refactor: use __launch_bounds__ instead of -maxrregcount for CUDA. | Brecht Van Lommel |
2014-04-09 | Cycles / CUDA: Increase sm_2x registers to 40. | Thomas Dinges |
2014-04-07 | OpenCL Change opencl_assert to be more like cuda assert where possible. | Martijn Berger |
2014-04-04 | Cycles: Disable Branched Path on all GPUs for now, until we separate the cubins. | Thomas Dinges |
2014-03-29 | Cycles code internals: add CPU kernel support for 3D image textures. | Brecht Van Lommel |
2014-03-27 | Cycles: Raise a proper error message when using Branched Path on sm_30, this ... | Thomas Dinges |
2014-03-26 | Fix T39420: Cycles viewport/preview flickers, when moving mouse across editors | Sergey Sharybin |
2014-03-19 | Fix T39247 | Martijn Berger |
2014-03-08 | Add support for multiple interpolation modes on cycles image textures | Martijn Berger |
2014-03-06 | Cuda use streams and async to avoid busywaiting | Martijn Berger |
2014-02-19 | Cycle CUDA: revert the f1aeb2ccf4 and 84f958754 busywait fixes for now. | Brecht Van Lommel |
2014-02-17 | this is an attempted Fix: T38679 | Martijn Berger |
2014-02-06 | Cycles Network rendering, remove some exception throwing, replace with saner ... | Martijn Berger |
2014-01-28 | Cuda use streams and async to avoid busywaiting | Martijn Berger |
2014-01-16 | Cycles: Add an AVX kernel for CPU rendering. | Thomas Dinges |
2014-01-15 | Code cleanup: move half float functions to separate header file. | Brecht Van Lommel |