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/kernel/kernel_bake.h | |
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/kernel/kernel_bake.h')
-rw-r--r-- | intern/cycles/kernel/kernel_bake.h | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/intern/cycles/kernel/kernel_bake.h b/intern/cycles/kernel/kernel_bake.h index 9ee0b09529e..bfbf73df54f 100644 --- a/intern/cycles/kernel/kernel_bake.h +++ b/intern/cycles/kernel/kernel_bake.h @@ -18,8 +18,12 @@ CCL_NAMESPACE_BEGIN #ifdef __BAKING__ -ccl_device void compute_light_pass(KernelGlobals *kg, ShaderData *sd, PathRadiance *L, RNG rng, - int pass_filter, int sample) +ccl_device_inline void compute_light_pass(KernelGlobals *kg, + ShaderData *sd, + PathRadiance *L, + RNG rng, + int pass_filter, + int sample) { /* initialize master radiance accumulator */ kernel_assert(kernel_data.film.use_light_pass); |