diff options
author | Sergey Sharybin <sergey.vfx@gmail.com> | 2016-08-01 16:40:46 +0300 |
---|---|---|
committer | Sergey Sharybin <sergey.vfx@gmail.com> | 2016-08-01 16:54:29 +0300 |
commit | 6353ecb996898b4ce2fe8065130ed1f5ea3b6989 (patch) | |
tree | b6d620152e4ff7920465d8396fe443dc9b3ffc56 /intern/cycles/util | |
parent | 7065022f7aa23ba13d2999e1e40162a8f480af0e (diff) |
Cycles: Tweaks to support CUDA 8 toolkit
All the changes are mainly giving explicit tips on inlining functions,
so they match how inlining worked with previous toolkit.
This make kernel compiled by CUDA 8 render in average with same speed
as previous kernels. Some scenes are somewhat faster, some of them are
somewhat slower. But slowdown is within 1% so far.
On a positive side it allows us to enable newer generation cards on
buildbots (so GTX 10x0 will be officially supported soon).
Diffstat (limited to 'intern/cycles/util')
-rw-r--r-- | intern/cycles/util/util_math.h | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/intern/cycles/util/util_math.h b/intern/cycles/util/util_math.h index 016f4a6a794..13aba0646d2 100644 --- a/intern/cycles/util/util_math.h +++ b/intern/cycles/util/util_math.h @@ -1477,10 +1477,10 @@ ccl_device bool ray_triangle_intersect( return true; } -ccl_device bool ray_triangle_intersect_uv( - float3 ray_P, float3 ray_D, float ray_t, - float3 v0, float3 v1, float3 v2, - float *isect_u, float *isect_v, float *isect_t) +ccl_device_inline bool ray_triangle_intersect_uv( + float3 ray_P, float3 ray_D, float ray_t, + float3 v0, float3 v1, float3 v2, + float *isect_u, float *isect_v, float *isect_t) { /* Calculate intersection */ float3 e1 = v1 - v0; |