ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,423,007, issued on Sept. 23, was assigned to NVIDIA Corp. (Santa Clara, Calif.).
"Techniques for tensor memory allocation" was invented by Mahesh Ravishankar (Kenmore, Wash.), Yuan Lin (Cupertino, Calif.) and Vinod Grover (Mercer Island, Wash.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Apparatuses, systems, and techniques to generate a memory allocation plan for a set of tensors. In at least one embodiment, tensor data corresponding to the set of tensors is stored into memory locations at run time based, at least in part, on the memory allocation plan generated at a compile time."
The patent was filed on March 31, 2020, under Application No. 16/83...