Microsoft technology licensing, llc (20240412051). SPARSITY-AWARE NEURAL NETWORK PROCESSING

SPARSITY-AWARE NEURAL NETWORK PROCESSING

Organization Name

microsoft technology licensing, llc

Inventor(s)

Zhuo Ruan of Redmond WA (US)

SPARSITY-AWARE NEURAL NETWORK PROCESSING

This abstract first appeared for US patent application 20240412051 titled 'SPARSITY-AWARE NEURAL NETWORK PROCESSING

Original Abstract Submitted

various embodiments discussed herein are directed to improving hardware consumption and computing performance by performing neural network operations on dense tensors using sparse value information from original tensors. such dense tensors are condensed representations of other original tensors that include zeros or other sparse values. in order to perform these operations, particular embodiments provide an indication, via a binary map, of a position of where the sparse values and non-sparse values are in the original tensors. particular embodiments additionally or alternatively determine shape data of the original tensors so that these operations are accurate.