US Patent Issued to RED HAT on Oct. 14 for "Systems and methods for neural network convolutional layer matrix multiplication using cache memory" (Massachusetts Inventor)

ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,443,833, issued on Oct. 14, was assigned to RED HAT INC. (Raleigh, N.C.).

"Systems and methods for neural network convolutional layer matrix multiplication using cache memory" was invented by Rati Gelashvili (Cambridge, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer processor may include a number of cores, a shared cache shared among the cores, and a local cache associated with each core and used by that core only. Input data for a neural network (NN) layer may be partitioned into a set of tiles of size TxT, and the tile set may be partitioned into blocks of R tiles. For each block, a core may perform a transform operation on the tiles ...