diff options
| author | Brecht Van Lommel <brechtvanlommel@gmail.com> | 2014-04-30 12:54:17 +0400 |
|---|---|---|
| committer | Brecht Van Lommel <brechtvanlommel@gmail.com> | 2014-04-30 18:07:27 +0400 |
| commit | 741f17f05b8272abfaf000a403e44b73692ba4c7 (patch) | |
| tree | dafcf851ca51b51b56e947bfb3879d224381cd6d /intern/cycles/device/device_cuda.cpp | |
| parent | 4d1a109ddec02ad7e527d8b65a5cdc8d4a7528a9 (diff) | |
Cycles CUDA: make CUDA toolkit 6.0 the official supported version.
This also updates the configurations to build kernels for compute capability
5.0 cards, when using and older CUDA toolkit version this will be skipped.
Also includes tweaks to improve performance with this version:
* Increase max registers on sm_30, sm_35 and sm_50
* No longer use texture storage on sm_30
Diffstat (limited to 'intern/cycles/device/device_cuda.cpp')
| -rw-r--r-- | intern/cycles/device/device_cuda.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/intern/cycles/device/device_cuda.cpp b/intern/cycles/device/device_cuda.cpp index 0d2f6cdfe19..72453e83864 100644 --- a/intern/cycles/device/device_cuda.cpp +++ b/intern/cycles/device/device_cuda.cpp @@ -222,7 +222,7 @@ public: /* In order to use full 6GB of memory on Titan cards, use arrays instead * of textures. On earlier cards this seems slower, but on Titan it is * actually slightly faster in tests. */ - use_texture_storage = (cuDevArchitecture < 350); + use_texture_storage = (cuDevArchitecture < 300); cuda_pop_context(); } |