Cycles: Use native saturate function for CUDA

This more a workaround for CUDA optimizer which can't optimize clamp(x, 0, 1)
into a single instruction and uses 4 instructions instead.

Original patch by @lockal with own modification:

  Don't make changes outside of the kernel. They don't make any difference
  anyway and term saturate() has a bit different meaning outside of kernel.

This gives around 2% of speedup in Barcelona file, but in more complex shader
setups with lots of math nodes with clamping speedup could be much nicer.

Subscribers: dingto

Projects: #cycles

Differential Revision: https://developer.blender.org/D1224

1 files changed, 9 insertions, 0 deletions

diff --git a/intern/cycles/util/util_math.h b/intern/cycles/util/util_math.h
index 6208608a233..f48625ec95d 100644
--- a/intern/cycles/util/util_math.h
+++ b/intern/cycles/util/util_math.h
@@ -175,6 +175,15 @@ ccl_device_inline float clamp(float a, float mn, float mx)
 
 #endif
 
+#ifndef __KERNEL_CUDA__
+
+ccl_device_inline float saturate(float a)
+{
+	return clamp(a, 0.0f, 1.0f);
+}
+
+#endif
+
 ccl_device_inline int float_to_int(float f)
 {
 	return (int)f;