kannonier8/blender
1
0
Fork 0
forked from bartvdbraak/blender
Code Pull Requests Activity

Cycles: Another attempt to solve 32bit CUDA kernel

Browse Source 
Previous fix didn't quite work well. For some reason everything worked fine when
using native nvcc in 32bit environment, but cross-compiling from 64bit platform
it was still running out of memory.

For now just made it so all the kernels are slower on 32bit CUDA as a temporary
solution. Either it'll be solved in next CUDA releases (by dropped 32bit? =\) or
we'll find better workaround.
This commit is contained in:
Sergey Sharybin 2015-02-09 16:11:58 +05:00
parent 5544ded2b5
commit b83d851901
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
intern/cycles/kernel/geom/geom_triangle_intersect.h
View File

@ -51,7 +51,7 @@ typedef struct IsectPrecalc {
/* Workaround for CUDA toolkit 6.5.16. */
#if defined(__KERNEL_CPU__) || !defined(__KERNEL_CUDA_EXPERIMENTAL__) || __CUDA_ARCH__ < 500
# if (defined(i386) || defined(_M_IX86)) && (__CUDA_ARCH__ > 500)
# if (defined(i386) || defined(_M_IX86))
ccl_device_noinline
# else
ccl_device_inline