Chris Elrod is a frequent commenter on the Julia Discourse, Slack, and Zulip, as well as a contributor to the ecosystem, known in particular for LoopVectorization.jl and JuliaSIMD.
Depending on the applications, the requirement for a multivariate polynomial library may be efficient computation of product, division, substitution, evaluation, gcd or even Gröbner bases. It is well understood that the concrete representation to use for these polynomials depends on whether they are sparse or not. In this talk, we show that in Julia, the choice of representation also depends on whether to specialize the compilation on the variables.
SimpleChains is an open source pure-Julia machine learning library developed by PumasAI and JuliaComputing in collaboration with Roche and the University of Maryland, Baltimore.
It is specialized for relatively small-sized models and NeuralODEs, attaining best in class performance for these problems. The performance advantage remains significant when scaling to tens of thousands of parameters, where it's still >5x faster than Flux or Pytorch while all use a CPU, even outperforming GPUs.