Tensor Algebra on an Optoelectronic Microchip
share
Tensor algebra lies at the core of computational science and machine learning. Due to its high usage, entire libraries exist dedicated to improving its performance. Conventional tensor algebra performance boosts focus on algorithmic optimizations, which in turn lead to incremental improvements. In this paper, we describe a method to accelerate tensor algebra a different way: by outsourcing operations to an optical microchip. We outline a numerical programming language developed to perform tensor algebra computations that is designed to leverage our optical hardware's full potential. We introduce the language's current grammar and go over the compiler design. We then show a new way to store sparse rank-n tensors in RAM that outperforms conventional array storage (used by C++, Java, etc.). This method is more memory-efficient than Compressed Sparse Fiber (CSF) format and is specifically tuned for our optical hardware. Finally, we show how the scalar-tensor product, rank-n Kronecker product, tensor dot product, Khatri-Rao product, face-splitting product, and vector cross product can be compiled into operations native to our optical microchip through various tensor decompositions.
READ FULL TEXT