Fix Cycles CUDA kernels for Ampere not building with CUDA 11

Running Blender on Ampere cards was already possible with ptx, this fix is
needed to support building CUDA binaries.

Note the CUDA version used for official Blender builds is still 10, this is
merely the change to make it possible for those using CUDA 11 and specifying
the sm_8x kernels to be compiled.

Found by Milan Jaros.
This commit is contained in:
Brecht Van Lommel
2020-09-30 18:26:41 +02:00
parent 443e42d47c
commit 60e5ebdd62

View File

@@ -70,8 +70,8 @@
# endif
# define CUDA_KERNEL_BRANCHED_MAX_REGISTERS 63
/* 7.x */
#elif __CUDA_ARCH__ <= 799
/* 7.x, 8.x */
#elif __CUDA_ARCH__ <= 899
# define CUDA_MULTIPRESSOR_MAX_REGISTERS 65536
# define CUDA_MULTIPROCESSOR_MAX_BLOCKS 32
# define CUDA_BLOCK_MAX_THREADS 1024