Fix T43511: Major slow down with many instanced objects in cycles GPU

Slowdown was caused by watertight intersection commit and follow-up workaorund
for compiler crash which uninlined utility function which rotates the ray.

Now it's only uninlined for sm_50 and sm_52 experimental kernels which are the
only ones which failed to compile.

Rendering still might be a bit slower but at least shouldn't be that dramatic.
This commit is contained in:
Sergey Sharybin 2015-02-02 17:06:15 +05:00
parent 81f97692ae
commit 31263192bb

@ -50,7 +50,7 @@ typedef struct IsectPrecalc {
} IsectPrecalc;
/* Workaround for CUDA toolkit 6.5.16. */
#ifdef __KERNEL_CPU__
#if defined(__KERNEL_CPU__) || !defined(__KERNEL_CUDA_EXPERIMENTAL__) || __CUDA_ARCH__ < 500
ccl_device_inline
#else
ccl_device_noinline