US Patent Issued to Groq on April 15 for "Software-defined tensor streaming multiprocessor for large-scale machine learning" (American, Canadian Inventors)

ALEXANDRIA, Va., June 5 -- United States Patent no. 12,277,444, issued on April 15, was assigned to Groq Inc. (Mountain View, Calif.).

"Software-defined tensor streaming multiprocessor for large-scale machine learning" was invented by Dennis Charles Abts (Eau Claire, Wis.), Jonathan Ross (Palo Alto, Calif.), Garrin Kimmell (Mountain View, Calif.), Michael Bye (Chippewa Falls, Wis.), Matthew Boyd (Gresham, Ore.) and Andrew Ling (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system contains a network of processors arranged in a plurality of nodes. Each node comprises a respective plurality of processors connected via local links, and different nodes are connected via global links. The processors of ...