Brecht Van Lommel 2851ed4a55 Cycles code refactor: use __launch_bounds__ instead of -maxrregcount for CUDA.
This makes it easier to have per kernel number of registers. Also, all the
tunable parameters for this are now in kernel.cu, rather than spread over cmake,
scons and device_cuda.cpp.
2014-04-16 21:05:04 +02:00
2014-04-15 14:12:22 +02:00
2014-04-15 13:11:48 +10:00
2014-03-10 15:17:22 +06:00
2013-12-24 22:57:27 +06:00
2014-04-15 14:12:22 +02:00
Description
No description provided
926 MiB
Languages
C++ 78.1%
Python 15%
C 2.8%
GLSL 1.8%
CMake 1.2%
Other 0.9%