top | item 35244110

(no title)

tgvaughan | 2 years ago

I remember attending a conference presentation back in the early 2000's by one of the FFTW authors. They claimed that the mapping between architecture and optimal FT algorithm was complex enough that the only sensible approach was implementing several and empirically determining the best one at runtime.

discuss

order

magicalhippo|2 years ago

To be fair, this goes for a lot of optimizations. A hand-optimized assembly routine might become slower than the compiler-generated one as CPUs and compilers advance, for example.

blitzar|2 years ago

Today we call that AI.