International Business Machines Corporation

Globalfoundries Inc.

James Lee Van Oosten

Michael K Gschwind

Valentina Salapura

Dong Chen

Paul William Coteus

Michael A Blocksome

Alan G Gara

Erik John Burckart

Joseph D Ratterman

Philip Heidelberger

Adam James Muff

Todd Edward Takken

Martin Ohmacht

Bruce Martin Fleischer

Alexandre E Eichenberger

Robert William Wisniewski

Thomas M Gooding

John A Gunnels

Mark Edwin Giampapa

Burkhard Steinmacher-Burow

Kathryn Mary O'Brien

Mark Gregory Megerian

Sameh W Asaad

Matthias Augustin Blumrich

Shawn Anthony Hall

John Kevin O'Brien

Thomas Winters Fox

Chen-Yong Cher

Barry Marshall Trager

William Thomas Newport

Peng Wu

Charles David Wait

Sameer Kumar

James Anthony Marcella

George L Chiu

Todd Alan Inglett

Krishnan Sugavanam

Gerard Vincent Kopcsay

Jeffrey John Parker

Craig Andrew Lanzen

Robert Matthew Senger

Noel A Eisley

David L Satterfield

Douglas R Miller

Craig Brian Stunkel

Rudolf Adriaan Haring

Amith R Mamidala

Yutaka Sugawara

Kristan D Davis

Jose R Brunheroto

Michael B Mundy

Matthew Roger Ellavsky

Robert E Walkup

Stephen M Fontes

Samuel J Miller

Gabor J Dozsa

Ruth Janine Poole

Brant L Knudson

Ralph E Bellofatto

Peter Boyle

Norman Christ

Kahn C Evans

Robert H High

William Maupin Stockdell

Alfred Thomas Watson, Iii

Brian E Smith

Naresh Nayar

Gregory Louis Truty

James Xenidis

John Joseph Stecher

Prabhakar Nandavar Kudva

Robert Howard High, Jr

James Irwin Knutson

Rohit Kapoor

Pia Naoko Sanda

Chris D Johnson

Subbarao K Meduri

Thomas Edward Musta

Daniel James Henderson

David W Siegel

Kristi Paula Peterson

Tim Alan Fors

An install factory creates install packages used to install complex applications onto multiple data processing systems in a reliable and reproducible manner. The install factory takes a variety of inputs to build a custom installation package. The custom install package may be used repeatedly for installs, using the same install package, a full install on a first data processing system, an updated install on a second data processing system, a fix or service pack on a third data processing system, and also configure an application on a fourth data processing system. Thereafter, all data processing systems have the desired level of the application installed. In addition, the install factory may create install packages that are modified in accordance with user preferences.

Method and apparatus for creation of customized install packages for installation of software

A Multi-Petascale Highly Efficient Parallel Supercomputer of 100 petaflop-scale includes node architectures based upon System-On-a-Chip technology, where each processing node comprises a single Application Specific Integrated Circuit (ASIC). The ASIC nodes are interconnected by a five dimensional torus network that optimally maximize the throughput of packet communications between nodes and minimize latency. The network implements collective network and a global asynchronous network that provides global barrier and notification functions. Integrated in the node design include a list-based prefetcher. The memory system implements transaction memory, thread level speculation, and multiversioning cache that improves soft error rate at the same time and supports DMA functionality allowing for parallel processing message-passing.

Multi-petascale highly efficient parallel supercomputer

A Multi-Petascale Highly Efficient Parallel Supercomputer of 100 petaOPS-scale computing, at decreased cost, power and footprint, and that allows for a maximum packaging density of processing nodes from an interconnect point of view. The Supercomputer exploits technological advances in VLSI that enables a computing model where many processors can be integrated into a single Application Specific Integrated Circuit (ASIC). Each ASIC computing node comprises a system-on-chip ASIC utilizing four or more processors integrated into one die, with each having full access to all system resources and enabling adaptive partitioning of the processors to functions such as compute or messaging I/O on an application by application basis, and preferably, enable adaptive partitioning of functions in accordance with various algorithmic phases within an application, or if I/O or other processors are underutilized, then can participate in computation or communication nodes are interconnected by a five dimensional torus network with DMA that optimally maximize the throughput of packet communications between nodes and minimize latency.

An attribute of a descriptor associated with a task informs a runtime environment of which instructions a processor is to run to schedule a plurality if resources for completion of the task in accordance with a level of quality of service in a service level agreement.

Tunable error resilience computing

A method for augmenting a hierarchy of layered applications and corresponding protocols can include applying a discrimination algorithm to a selection process in which a particular application/protocol layer in a listing of adjacent application/protocol layers is selected to receive traffic flowing through the hierarchy. A new application/protocol layer is inserted adjacent to the particular application/protocol layer in the hierarchy. Also, a new application/protocol layer is added to the listing, and the discrimination algorithm is replaced with another discrimination algorithm programmed to consider the new application/protocol layer during the selection process. Each of the steps of performing the inserting, adding and replacing steps are performed without decoupling or disabling other applications and protocols in the hierarchy.

Unobtrusive port and protocol sharing among server processes

Computer implemented method, system and computer program product for searching for a class in a data processing system having classloaders organized in both a classloader hierarchy and a classloader network. A computer implemented method for searching for a class in a data processing system having classloaders organized in both a classloader hierarchy and a classloader network includes receiving a request to load a class at a request receiving classloader in the classloader hierarchy. The request to load a class is forwarded to a gateway classloader in the classloader network, wherein the gateway classloader is also in the classloader hierarchy. The requested class is then searched for in the classloader network.

Collaborative classloader system and method

A method, system, and computer program product for enabling efficient start up of an application server with the components required for complete operation of the supported application. A pre-processor autonomically determines the specific services that are required by the application to be initiated within the application server during start up of the application. The specific services are selected from a comprehensive list of available services for start up of the application server. The application server is then started up with only the specific services required by the application, rather than the full list of services.

Autonomic application server unneeded process disablement

In a hierarchy of layered applications and corresponding protocols, a port and protocol sharing method is disclosed. Traffic is received over a single shared logical port, and the traffic is routed to an interlayer communications process disposed between two layers in the hierarchy. A discrimination algorithm is applied to select a particular application/protocol layer in a higher one of the two layers to which the traffic is to be routed. The traffic is routed to the selected particular application/protocol layer. An additional application/protocol layer is added to the hierarchy. The discrimination algorithm is replaced with another discrimination algorithm program to consider the additional application/protocol layer during the selection process. The additional application/protocol layer is considered in the selecting step. When selected, the traffic is routed to the additional application/protocol layer. The adding and replacing steps are performed without decoupling or disabling other applications and protocols in the hierarchy.

A software wrapper for interfacing to pre-existing software code is provided. The software wrapper is capable of inheriting from a first application program interface (API) and a second API. For calls to the first API, the software wrapper delegates to a pre-existing enumeration of objects. The wrapper creates a vector identifying elements of the enumeration. Iterators provided by the wrapper maintain positional cursors for calls to the second API. A comparison is made between each of the positional cursors and the vector. If a positional cursor exceeds the size of the vector, additional elements are extracted from the enumeration, placed in the vector, and returned on the second API. Otherwise, if the positional cursor is smaller than the vector size, the wrapper delegates directly to the vector. The first API can be a java-based enumeration API and the second API can be a java-based collection API.

Method and system for implementing collection program interface for accessing a collection of data associated with a legacy enumeration application interface

Growing community of inventors

Rochester, MN, United States of America

James Lee Van Oosten