Fft

[AshtonSBradley]

A naive question, but could LoopVectorization be used to speed up fft?

[chriselrod]

It's probably possible to speed up an FFT implementation with it.
It'll take reinterpreting to Float64 arrays for now and it's also probably worth looking into using vfmaddsub and vfmsubadd, e.g.

LoopVectorization.jl/test/shuffleloadstores.jl

Line 28 in 0d62954

vfmsubadd(vmovsldup(a[i]), b[i], vfmsubadd(vmovshdup(a[i]), vpermilps177(b[i]), reim))

but this will be handled automatically in the rewrite.