Re:Revisiting the postcard pathtracer with CUDA and Optix
by xmmrm on Monday May 18, 2020 @06:34PM
(#23229171)
Surprisingly [sincosf fusion] only happened with -Ofast and not with -O3.
As noted, -Ofast turns on -ffast-math which turns on -funsafe-math-optimizations which "enables optimizations that allow arbitrary reassociations and transformations with no accuracy guarantees."[0] In this case, sincosf by itself is probably more accurate.
As noted, -Ofast turns on -ffast-math which turns on -funsafe-math-optimizations which "enables optimizations that allow arbitrary reassociations and transformations with no accuracy guarantees."[0] In this case, sincosf by itself is probably more accurate.
[0] https://gcc.gnu.org/wiki/FloatingPointMath