Cycles: Fixed compilation of CUDA kernels. Follow-up fix for my last commit.
This commit is contained in:
@@ -73,13 +73,14 @@
|
|||||||
|
|
||||||
/* tunable parameters */
|
/* tunable parameters */
|
||||||
# define CUDA_THREADS_BLOCK_WIDTH 16
|
# define CUDA_THREADS_BLOCK_WIDTH 16
|
||||||
# define CUDA_KERNEL_MAX_REGISTERS 48
|
|
||||||
# define CUDA_KERNEL_BRANCHED_MAX_REGISTERS 63
|
|
||||||
|
|
||||||
/* CUDA 9.0 seems to cause slowdowns on high-end Pascal cards unless we increase the number of registers */
|
/* CUDA 9.0 seems to cause slowdowns on high-end Pascal cards unless we increase the number of registers */
|
||||||
# if __CUDACC_VER_MAJOR__ == 9 && __CUDA_ARCH__ >= 600
|
# if __CUDACC_VER_MAJOR__ == 9 && __CUDA_ARCH__ >= 600
|
||||||
# #define CUDA_KERNEL_MAX_REGISTERS 64
|
# define CUDA_KERNEL_MAX_REGISTERS 64
|
||||||
|
# else
|
||||||
|
# define CUDA_KERNEL_MAX_REGISTERS 48
|
||||||
# endif
|
# endif
|
||||||
|
# define CUDA_KERNEL_BRANCHED_MAX_REGISTERS 63
|
||||||
|
|
||||||
|
|
||||||
/* unknown architecture */
|
/* unknown architecture */
|
||||||
#else
|
#else
|
||||||
|
Reference in New Issue
Block a user