US Patent Issued to Red Hat on Aug. 4 for "Systems and methods for generation of sparse-dense matrix multiplication code for neural network and other applications" (Massachusetts Inventor)

ALEXANDRIA, Va., Aug. 5 -- United States Patent no. 12,699,899, issued on Aug. 4, was assigned to Red Hat Inc. (Raleigh, N.C.).

"Systems and methods for generation of sparse-dense matrix multiplication code for neural network and other applications" was invented by Aleksander Zleteski (Somerville, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Generating computer code to perform a matrix-multiply operation, for use in neural network compute or other applications may include determining parameters Rr (number of rows for a plurality of partitioned matrices A'), Rc (number of registers used for each column of a target matrix C'), and RL (number of processor registers used as a source for targets for vecto...