United States of America As Represented by the Secretary of the Air Force

University of Pittsburgh

Carnegie Mellon University

Seagate Technology Incorporated

Hai Li

Yiran Chen

Xiaobin Wang

Harry Hongyue Liu

Garrett Rose

Miao Hu

Jian-Gang Zhu

Alan Xuguang Wang

Richard W Linderman

Qing Wu

Zheng Li

Mark D Barnell

Enes Eken

Wujie Wen

Xiuyuan Bi

A two-dimensional accessible non-volatile memory apparatus includes an array comprising a plurality of non-volatile memory cells, the array being a crossbar-based non-volatile memory structure, the memory cells being arranged in a plurality of rows and a plurality of columns. The apparatus further includes row read/write circuitry coupled to the array and structured and configured to provide read and write access to the memory cells in any one of the rows on an individual row basis, and column read/write circuitry coupled to the array and structured and configured to provide read and write access to the memory cells in any one of the columns on an individual column basis.

Two-dimensionally accessible non-volatile memory

A recording head includes a near-field transducer configured to heat one or more portions of a magnetic storage layer to generate a thermal profile in the magnetic storage layer. The recording head includes a write pole configured to generate a magnetization pattern, in the magnetic storage layer, that overlaps with the thermal profile in the magnetic storage layer. The write pole includes a non-uniform surface that faces the magnetic storage layer, the non-uniform surface configured to cause a portion of the magnetization pattern to be approximately linear.

Heat-assisted magnetic recording head having a non-uniform air-bearing surface

Method and apparatus for performing close-loop programming of resistive memory devices in crossbar array based hardware circuits and systems. Invention provides iterative training of memristor crossbar arrays for neural networks by applying voltages corresponding to selected training patterns. Error is detected and measured as a function of the actual response to the training patterns versus the expected response to the training pattern.

Method and apparatus for performing close-loop programming of resistive memory devices in crossbar array based hardware circuits and systems

A method of reading a memory cell of a magneto-resistive random access memory device, wherein the memory cell has a ferromagnetic free layer having a first magnetization orientation and a ferromagnetic reference layer, includes applying a first read current from the ferromagnetic free layer to the ferromagnetic reference layer and storing a first voltage generated by the memory cell in response to the first read current, generating a magnetic field adjacent to the memory cell, the magnetic field having a second magnetization orientation that is not parallel to the first magnetization orientation, while the magnetic field is being generated, applying a second read current from the ferromagnetic free layer to the ferromagnetic reference layer and storing a second voltage generated by the memory cell in response to the second read current, and determining a state of the memory cell based on the first voltage and the second voltage.

Magnetic-assisted nondestructive self-reference sensing method for spin-transfer torque random access memory

Invention provides an apparatus and method for performing signal processing on a crossbar array of resistive memory devices. The invention is implemented using one or multiple crossbar arrays of resistive memory devices in conjunction with devices for converting input real number representations to voltage waveforms, devices for converting current waveforms into voltage waveforms, and devices for converting voltage waveforms to real numbers outputs.

Method and apparatus for performing signal processing on a crossbar array of resistive memory devices

An apparatus that performs the mathematical matrix-vector multiplication approximation operations using crossbar arrays of resistive memory devices (e.g. memristor, resistive random-access memory, spintronics, etc.). A crossbar array formed by resistive memory devices serves as a memory array that stores the coefficients of a matrix. Combined with input and output analog circuits, the crossbar array system realizes the method of performing matrix-vector multiplication approximation operations with significant performance, area and energy advantages over existing methods and designs. This invention also includes an extended method that realizes the auto-associative neural network recall function using the resistive memory crossbar architecture.

Apparatus for performing matrix vector multiplication approximation using crossbar arrays of resistive memory devices

Growing community of inventors

Pittsburgh, PA, United States of America

Hai Li