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

intern/cycles/render/nodes.cpp

@@ -3752,7 +3752,7 @@ void MathNode::compile(SVMCompiler& compiler)
 		                                 value1_in->value.x,
 		                                 value2_in->value.x);
 		if(use_clamp) {
-			optimized_value = clamp(optimized_value, 0.0f, 1.0f);
+			optimized_value = saturate(optimized_value);
 		}
 		compiler.add_node(NODE_VALUE_F,
 		                  __float_as_int(optimized_value),