GPUPoly, a deep neural network robustness verifier running on GPU. Using sound polyhedra algorithms, it is faster and more precise than prior work.
SGen is a generator capable of producing efficient hardware designs operating on streaming datasets. “Streaming” means that the dataset is divided into several chunks that are processed during several cycles, thus allowing a reduced use of resources. The size of these chunks is referred as the streaming width. It outputs a Verilog file that can be used for FPGAs.
F2Matrix is a linear algebra library for small matrices (of maximal size 8$\times$8) in $\mathbb F_2$, i.e. the Galois field with two elements. It supports matrix addition (and therefore subtraction), multiplication, transposition, inversion and rank computation.
This library aims to provide high performance, an relies heavily on bit manipulation instructions. Particularly, it requires an x64, BMI2 capable processor (e.g. Intel Haswell or newer). It was used for searching optimal Walsh-Hadamard transform algorithms for streaming.