kannonier8/blender
1
0
Fork 0
forked from bartvdbraak/blender
Code Pull Requests Activity
d83bcf7071
blender/intern/cycles/device
History
Brecht Van Lommel e360d003ea Cycles: schedule more work for non-display and compute preemption CUDA cards. 
This change affects CUDA GPUs not connected to a display or connected to a
display but supporting compute preemption so that the display does not
freeze. I couldn't find an official list, but compute preemption seems to be
only supported with GTX 1070+ and Linux (not GTX 1060- or Windows).

This helps improve small tile rendering performance further if there are
sufficient samples x number of pixels in a single tile to keep the GPU busy.
2017-10-08 21:12:16 +02:00
..
opencl Code refactor: make texture code more consistent between devices. 2017-10-07 14:53:14 +02:00
CMakeLists.txt Cycles: Pack kernel textures into buffers for OpenCL 2017-08-08 07:12:04 -04:00
device_cpu.cpp Code refactor: use DeviceInfo to enable QBVH and decoupled volume shading. 2017-10-08 13:17:33 +02:00
device_cuda.cpp Cycles: schedule more work for non-display and compute preemption CUDA cards. 2017-10-08 21:12:16 +02:00
device_denoising.cpp Cycles Denoising: Merge outlier heuristic and confidence interval test 2017-06-09 03:46:11 +02:00
device_denoising.h Cycles Denoising: Merge outlier heuristic and confidence interval test 2017-06-09 03:46:11 +02:00
device_intern.h Cycles: Refactor Device selection to allow individual GPU compute device selection 2016-11-07 03:19:29 +01:00
device_memory.h Code refactor: add WorkTile struct for passing work to kernel. 2017-10-04 21:11:14 +02:00
device_multi.cpp Code refactor: split displace/background into separate kernels, remove luma. 2017-10-05 17:57:58 +02:00
device_network.cpp Code refactor: use DeviceInfo to enable QBVH and decoupled volume shading. 2017-10-08 13:17:33 +02:00
device_network.h Code refactor: split displace/background into separate kernels, remove luma. 2017-10-05 17:57:58 +02:00
device_opencl.cpp Code refactor: use DeviceInfo to enable QBVH and decoupled volume shading. 2017-10-08 13:17:33 +02:00
device_split_kernel.cpp Cycles: Faster split branched path tracing by sharing samples with inactive threads 2017-06-10 04:08:49 -04:00
device_split_kernel.h Cycles: Pass string by const reference rather than by value 2017-07-05 12:27:41 +02:00
device_task.cpp Code refactor: split displace/background into separate kernels, remove luma. 2017-10-05 17:57:58 +02:00
device_task.h Code refactor: split displace/background into separate kernels, remove luma. 2017-10-05 17:57:58 +02:00
device.cpp Fix T53017: Cycles not detecting AMD GPU when there is an NVidia GPU too. 2017-10-08 18:36:02 +02:00
device.h Code refactor: use DeviceInfo to enable QBVH and decoupled volume shading. 2017-10-08 13:17:33 +02:00