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).

intern/cycles/kernel/kernel_path_volume.h

@@ -18,8 +18,14 @@ CCL_NAMESPACE_BEGIN
 
 #ifdef __VOLUME_SCATTER__
 
-ccl_device void kernel_path_volume_connect_light(KernelGlobals *kg, RNG *rng,
-	ShaderData *sd, ShaderData *emission_sd, float3 throughput, PathState *state, PathRadiance *L)
+ccl_device_inline void kernel_path_volume_connect_light(
+        KernelGlobals *kg,
+        RNG *rng,
+        ShaderData *sd,
+        ShaderData *emission_sd,
+        float3 throughput,
+        PathState *state,
+        PathRadiance *L)
 {
 #ifdef __EMISSION__
 	if(!kernel_data.integrator.use_direct_light)