Re:Accelerated Computing Powering World’s Fastest Supercomputer
by stochastic_monk on Friday June 08, 2018 @11:25PM
(#17271355)
fftw isn't exactly developing an optimal kernel from scratch. It's testing a range of different methods and simply choosing the best for one's parameters.
Facebook's Tensor Comprehensions framework, which generates CUDA kernels through a genetic algorithm, is closer to the sort of approach which would take greatest advantage of the hardware it's on.
There are also a few “software synthesis” and “sketching” approaches that use a constraint solver to find all correct implementations of a high level spec, subject to some implementation pattern. Then they either try them all with brute force or pick the one that optimizes some objective function.