Commit: 38a54f4e01d627bb4489cfdbe9d844a89a9bc656 Author: Thomas Dinges Date: Thu Sep 25 20:03:46 2014 +0200 Branches: master https://developer.blender.org/rB38a54f4e01d627bb4489cfdbe9d844a89a9bc656
Cycles: Make CUDA backend aware of sm_52 (Maxwell). In order to compile the new kernel you need to specify sm_52 in SCons / CMake, and use CUDA Toolkit 6.5.19, from here: https://developer.nvidia.com/cuda-downloads-geforce-gtx9xx Note: sm_52 is not enabled per default yet, so it won't be bundled with the Buildbot builds. That will be addressed later. =================================================================== M intern/cycles/kernel/kernel.cu =================================================================== diff --git a/intern/cycles/kernel/kernel.cu b/intern/cycles/kernel/kernel.cu index d5b5293..9ed4592 100644 --- a/intern/cycles/kernel/kernel.cu +++ b/intern/cycles/kernel/kernel.cu @@ -52,8 +52,8 @@ #define CUDA_KERNEL_MAX_REGISTERS 63 #define CUDA_KERNEL_BRANCHED_MAX_REGISTERS 63 -/* 5.0 */ -#elif __CUDA_ARCH__ == 500 +/* 5.0 and 5.2 */ +#elif __CUDA_ARCH__ == 500 || __CUDA_ARCH__ == 520 #define CUDA_MULTIPRESSOR_MAX_REGISTERS 65536 #define CUDA_MULTIPROCESSOR_MAX_BLOCKS 32 #define CUDA_BLOCK_MAX_THREADS 1024 _______________________________________________ Bf-blender-cvs mailing list [email protected] http://lists.blender.org/mailman/listinfo/bf-blender-cvs
