News for hackers. Stuff that matters.
Re:High Performance Correctly Rounded Math Libraries for 32-... by gpderetta on Thursday August 26, 2021 @08:22PM (#28322795)
For scalar computations 32 bit floats are not going to be faster except maybe divisions. There are second order effects due the reduced memory usage.

For anything that is vectorizable or otherwise amenable to SIMD optimizations you can get up to 2x speedup.

Re:High Performance Correctly Rounded Math Libraries for 32-... by adgjlsfhk1 on Thursday August 26, 2021 @10:37PM (#28323728)
All the transcendental functions are also an extra 2-4x slower for Float64 since you need higher order approximations, and the compensated arithmetic is slower.