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/svm/svm_tex_coord.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/svm/svm_tex_coord.h')
| -rw-r--r-- | intern/cycles/kernel/svm/svm_tex_coord.h | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/intern/cycles/kernel/svm/svm_tex_coord.h b/intern/cycles/kernel/svm/svm_tex_coord.h index 276b6f26f5e..b39d6a3e009 100644 --- a/intern/cycles/kernel/svm/svm_tex_coord.h +++ b/intern/cycles/kernel/svm/svm_tex_coord.h @@ -99,12 +99,12 @@ ccl_device void svm_node_tex_coord(KernelGlobals *kg, stack_store_float3(stack, out_offset, data); } -ccl_device_inline void svm_node_tex_coord_bump_dx(KernelGlobals *kg, - ShaderData *sd, - int path_flag, - float *stack, - uint4 node, - int *offset) +ccl_device void svm_node_tex_coord_bump_dx(KernelGlobals *kg, + ShaderData *sd, + int path_flag, + float *stack, + uint4 node, + int *offset) { #ifdef __RAY_DIFFERENTIALS__ float3 data; @@ -184,12 +184,12 @@ ccl_device_inline void svm_node_tex_coord_bump_dx(KernelGlobals *kg, #endif } -ccl_device_inline void svm_node_tex_coord_bump_dy(KernelGlobals *kg, - ShaderData *sd, - int path_flag, - float *stack, - uint4 node, - int *offset) +ccl_device void svm_node_tex_coord_bump_dy(KernelGlobals *kg, + ShaderData *sd, + int path_flag, + float *stack, + uint4 node, + int *offset) { #ifdef __RAY_DIFFERENTIALS__ float3 data; |