International Business Machines Corporation

Asahi Kasei Kabushiki Kaisha

Winfried W Wilcke

Arvind Kumar

Robert Barton Garner

Harald Huels

Robert Dennis Miller

Toshiaki Kirihata

Subramanian Srikanteswara Iyer

Ahmet Serkan Ozcan

Ho-Cheol Kim

Mark Whitney Hart

John Campbell Scott

Troy Lawrence Graves-Abe

Charles Edwin Cox

Daniel George Berger

Bryan D McCloskey

Naga Phani B Aetukuri

Leslie E Krupp

Shintaro Kitajima

Xiao Hu Liu

Robert K Montoye

Aaron Roger Cox

Steven Alan Cordes

Ronald A Smith

Pritish Narayanan

Robert Edward Steinbugler

Matthew J Farinelli

Barry Jay Rubin

Claudio Fleiner

Ralph Attila Becker-Szendy

J Campbell Scott

Edward Scott Kirkpatrick

Manfred Ries

Eric P Kronstadt

Kenneth Richard Fernandez

Richard Michael Williams

Howard Kahn

A method includes dispensing ion-conducting particles on a substrate comprising an adhesive to which the ion-conducting particles adhere; overcoating the ion conducting particles with a polymer; removing the substrate and the adhesive from the ion conducting particles; and removing a polymer overburden on the ion conducting particles to form a device that includes: (i) the polymer or a derivative thereof, and (ii) ion-conducting particles. At least a portion of the ion-conducting particles extend through the polymer or its derivative.

Ion conducting hybrid membranes

A connectivity look up structure is maintained for a network that comprises a plurality of nodes, each node is connectable to one or more other nodes, and nodes that are connected tend to be local to one another in the network, and the number of node connections in the network tends to be sparse in relation to the number of potential node connections in the network. The connectivity look up structure stores, for a given node, an address of each other node that is connected to the given node, wherein the stored address for the other node is represented as a run-length encoded difference between a full network address of the given node and a full network address of the other node.

Space-efficient dynamic addressing in very large sparse networks

A processor-memory system, a stacked-wafer processor-memory system, and a method of fabricating a processor-memory system are disclosed. In an embodiment, the invention provides a processor-memory system comprising a memory area, a multitude of specialized processors, and a management processor. The specialized processors are embedded in the memory area, and each of the specialized processors is configured for performing a specified set of operations using an associated memory domain in the memory area. The management processor is provided to control operations of an associated set of the specialized processors. In one embodiment, each of the specialized processors controls a respective one associated memory domain in the memory area. In an embodiment, the processor-memory system further comprises a specialized processor wafer. The specialized processor wafer includes the memory area, and the multitude of specialized processors are embedded in the specialized processor wafer.

Architecture and implementation of cortical system, and fabricating an architecture using 3D wafer scale integration

A method is provided to supply power to wafer-scale ICs. The method includes receiving a wafer containing ICs placed on the top of the wafer. The wafer has through-silicon vias to provide power from the bottom to the ICs. The method also includes a printed circuit board, which has power rails in a pattern on the top of the printed circuit board, where the rails provide voltage and ground. The method continues with placing metal solder spheres between the bottom of the wafer and the top of the printed circuit board, where the spheres provide connections between the two, and where the spheres are free to move and operate as mechanical springs to resist clamping forces. The method also includes applying clamping pressure to the structure to establish connections by compressing the spheres, where no soldering is required.

Wafer-scale power delivery

Three-dimensional (3D) neuromorphic computing systems are provided. A system includes a logic wafer having a plurality of processors. The system further includes a double-sided interposer bonded to the logic wafer and incorporating a signal port ring for sending and receiving signals. The system also includes a plurality of 3D memory modules bonded to the double-sided interposer. The double-sided interposer is a wafer scale or a panel scale providing communication between the plurality of processors and the plurality of 3D memory modules.

High memory bandwidth neuromorphic computing system

A method is provided to supply power to wafer-scale ICs. The method includes receiving a wafer containing ICs placed on the top of the wafer. The wafer has through-hole vias to provide power from the bottom to the ICs. The method also includes a printed circuit board, which has power rails in a pattern on the top of the printed circuit board, where the rails provide voltage and ground. The method continues with placing metal solder spheres between the bottom of the wafer and the top of the printed circuit board, where the spheres provide connections between the two, and where the spheres are free to move and operate as mechanical springs to resist clamping forces. The method also includes applying clamping pressure to the structure to establish connections by compressing the spheres, where no soldering is required.

A device includes a membrane that is: (i) impermeable to oxygen, and (ii) insoluble in at least one polar solvent; and ion conducting particles in the membrane. At least some of the particles extend from a first side of the membrane to an opposed second side of the membrane. The thickness of the membrane is 15 &#x3bc;m to 100 &#x3bc;m.

A method and apparatus for storing data is provided. One implementation involves providing a fiber medium for storing data, wherein the fiber medium has a characteristic configured to irreversibly change when exposed to write irradiation. The fiber medium is logically partitioned into cells along the length of the fiber medium. Data is stored in a cell of the fiber medium by exposing the cell to write irradiation to irreversibly change characteristic of the bulk of the cell.

Storing data on fiber data storage media

According to the present invention, there is provided a system for removing heat from server blades densely packaged in a rack of server blades. The system includes a liquid distribution manifold. In addition, the system includes a plurality of cold blades attached to the liquid distribution manifold, wherein liquid is circulated through the liquid distribution manifold and the cold blades. Moreover, the system includes at least one server blade attached to each of the cold blades.

Method for high-density packaging and cooling of high-powered compute and storage server blades

A flexible capacitive coupler assembly includes a flexible dielectric substrate assembly having a front surface and a rear surface, the front surface having thereon a macroscopic metal capacitive pad. A package supports the flexible dielectric substrate. An electrical connection is made to package wiring or leads on the flexible dielectric substrate to establish electrical contact with a computer subsystem.

Flexible capacitive coupler assembly and method of manufacture

A three-dimensional computer infrastructure cooling system is provided. The three-dimensional computer infrastructure cooling system includes at least one compute, storage, or communications brick. In addition, the three-dimensional computer infrastructure cooling system includes at least one coldrail to facilitate the removal of heat from the at least one compute, storage, or communications brick. Also, the three-dimensional computer infrastructure includes a brick-internal carrier within the at least one compute, storage, communications brick, wherein the brick-internal carrier is attached to the at least one coldrail. Moreover, the three-dimensional computer infrastructure includes a power dissipating electronic element within the at-least-one compute, storage, or communications brick, wherein the power dissipating element is attached to the brick-internal carrier.

System and method for providing cooling in a three-dimensional infrastructure for massively scalable computers

A mechanism that automatically achieves alignment of the communications elements during assembly of a modular computer system, without the need for human intervention. The mechanism comprises an alignment frame provided with bumps and depressions. The bumps in the alignment frames mate with the depressions on adjacent alignment frames. Each depression comprises an entrance opening that is wider than the diameter of the bumps. The diameter of the entrance opening is determined by the expected accuracy of the alignment of subsystems or bricks within the modular electronic system. When it is desired to align the communication elements, the alignment frames are brought into engagement by causing alignment guides to slide past each other, and to guide the bumps in the alignment frames into the depressions in the adjacent alignment frames. The mechanism further comprises a set of springs that force the allow the alignment frames to be retained securely by the communications elements.

Mechanism for self-alignment of communications elements in a modular electronic system

Growing community of inventors

Yorktown Heights, NY, United States of America

Winfried W Wilcke