News for hackers. Stuff that matters.
Re:Swift: Google’s Bet on Differentiable Programming by p1esk on Sunday April 12, 2020 @08:50PM (#22852161)
In that benchmark, was Julia tested against CuDNN accelerated neural network CUDA code? If not, is it possible (and beneficial) to call CuDNN functions from Julia?
Re:Swift: Google’s Bet on Differentiable Programming by ChrisRackauckas on Monday April 13, 2020 @01:30PM (#22857907)
That wasn't a benchmark with CuDNN since it was a benchmark about writing such kernels. However, Julia libraries call into optimized kernels whenever they exist, and things like NNLib.jl (the backbone of Flux.jl) and KNet.jl expose operations like `conv` that dispatch CuArrays to automatically use CuDNN.