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).

1 files changed, 6 insertions, 6 deletions

diff --git a/intern/cycles/kernel/svm/svm_ramp.h b/intern/cycles/kernel/svm/svm_ramp.h
index f959d90f309..368740f64c7 100644
--- a/intern/cycles/kernel/svm/svm_ramp.h
+++ b/intern/cycles/kernel/svm/svm_ramp.h
@@ -21,12 +21,12 @@ CCL_NAMESPACE_BEGIN
 
 /* NOTE: svm_ramp.h, svm_ramp_util.h and node_ramp_util.h must stay consistent */
 
-ccl_device float4 rgb_ramp_lookup(KernelGlobals *kg,
-                                  int offset,
-                                  float f,
-                                  bool interpolate,
-                                  bool extrapolate,
-                                  int table_size)
+ccl_device_inline float4 rgb_ramp_lookup(KernelGlobals *kg,
+                                         int offset,
+                                         float f,
+                                         bool interpolate,
+                                         bool extrapolate,
+                                         int table_size)
 {
 	if((f < 0.0f || f > 1.0f) && extrapolate) {
 		float4 t0, dy;