International Business Machines Corporation

Intel Corporation

Globalfoundries Inc.

Mark Edwin Giampapa

Alan G Gara

Philip Heidelberger

Dong Chen

Matthias Augustin Blumrich

Martin Ohmacht

Pavlos Michael Vranas

Paul William Coteus

Dirk Hoenicke

Burkhard D Steinmacher-Burow

Todd Edward Takken

Valentina Salapura

Burkhard Steinmacher-Burow

Thomas M Gooding

Dong Chen Chen

Krishnan Sugavanam

Gerard Vincent Kopcsay

Blake G Fitch

George L Chiu

Jeffrey John Parker

Rudolf Adriaan Haring

Ralph E Bellofatto

Hubertus Franke

Peng Wu

Sameer Kumar

Gyan Vatsaraja Bhanot

Michael A Blocksome

Bulent Abali

Thomas Mario Cipolla

Mark Gregory Megerian

Shawn Anthony Hall

David L Satterfield

Matthew Roger Ellavsky

Michael K Gschwind

Joseph D Ratterman

Adam James Muff

Lawrence Shungwei Mok

Bruce Martin Fleischer

Alexandre E Eichenberger

Pratap Chandra Pattnaik

Robert William Wisniewski

John A Gunnels

Kathryn Mary O'Brien

Sameh W Asaad

John Kevin O'Brien

Thomas Winters Fox

Raul Esteban Silvera

Chen-Yong Cher

Barry Marshall Trager

Kai-Ting Amy Wang

Douglas James Joseph

Charles David Wait

James Anthony Marcella

Todd Alan Inglett

Jon K Kriegel

Robert Matthew Senger

Noel A Eisley

Douglas R Miller

Craig Brian Stunkel

Amith R Mamidala

Yutaka Sugawara

Gheorghe Almasi

Xiaotong Zhuang

Kristan D Davis

Jose R Brunheroto

Michael B Mundy

Robert E Walkup

Samuel J Miller

James Lee Van Oosten

Gabor J Dozsa

Ruth Janine Poole

Peter Boyle

Brant L Knudson

Norman Christ

Kahn C Evans

William Maupin Stockdell

Alfred Thomas Watson, Iii

Phillip Heidelberger

Dror Gershon Feitelson

Charles J Archer

Brian E Smith

Joefon Jann

Paul Gregory Crumley

John Eric Attinella

Don Darrell Reed

Sandra Johnson Baylor

Richard A Swetz

Lance G Hehenberger

Peter Frank Corbett

Sarabjeet Singh

Dozsa Gabor

Gerard V Kopscay

Todd E c/o Ibm United Kingdom Limited Takken

Gerald V Kopscay

Dong c/o Ibm United Kingdom Limited Chen

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices are included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network and class structures. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to needs of a processing algorithm.

Collective network for computer structures

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

An error-recovery method to enable error-free message transfer between nodes of a computer network. A first node of the network sends a packet to a second node of the network over a link between the nodes, and the first node keeps a copy of the packet on a sending end of the link until the first node receives acknowledgment from the second node that the packet was received without error. The second node tests the packet to determine if the packet is error free. If the packet is not error free, the second node sets a flag to mark the packet as corrupt. The second node returns acknowledgement to the first node specifying whether the packet was received with or without error. When the packet is received with error, the link is returned to a known state and the packet is sent again to the second node.

Error recovery to enable error-free message transfer between nodes of a computer network

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.

In an embodiment, if a self thread has more than one conflict, a transaction of the self thread is aborted and restarted. If the self thread has only one conflict and an enemy thread of the self thread has more than one conflict, the transaction of the self thread is committed. If the self thread only conflicts with the enemy thread and the enemy thread only conflicts with the self thread and the self thread has a key that has a higher priority than a key of the enemy thread, the transaction of the self thread is committed. If the self thread only conflicts with the enemy thread, the enemy thread only conflicts with the self thread, and the self thread has a key that has a lower priority than the key of the enemy thread, the transaction of the self thread is aborted.

Speculative thread execution with hardware transactional memory

A system and method for accessing memory are provided. The system comprises a lookup buffer for storing one or more page table entries, wherein each of the one or more page table entries comprises at least a virtual page number and a physical page number; a logic circuit for receiving a virtual address from said processor, said logic circuit for matching the virtual address to the virtual page number in one of the page table entries to select the physical page number in the same page table entry, said page table entry having one or more bits set to exclude a memory range from a page.

Optimizing TLB entries for mixed page size storage in contiguous memory

An apparatus and method for tracking coherence event signals transmitted in a multiprocessor system. The apparatus comprises a coherence logic unit, each unit having a plurality of queue structures with each queue structure associated with a respective sender of event signals transmitted in the system. A timing circuit associated with a queue structure controls enqueuing and dequeuing of received coherence event signals, and, a counter tracks a number of coherence event signals remaining enqueued in the queue structure and dequeued since receipt of a timestamp signal. A counter mechanism generates an output signal indicating that all of the coherence event signals present in the queue structure at the time of receipt of the timestamp signal have been dequeued. In one embodiment, the timestamp signal is asserted at the start of a memory synchronization operation and, the output signal indicates that all coherence events present when the timestamp signal was asserted have completed. This signal can then be used as part of the completion condition for the memory synchronization operation.

Method and apparatus for efficiently tracking queue entries relative to a timestamp

A method and apparatus for supporting cache coherency in a multiprocessor computing environment having multiple processing units, each processing unit having one or more local cache memories associated and operatively connected therewith. The method comprises providing a snoop filter device associated with each processing unit, each snoop filter device having a plurality of dedicated input ports for receiving snoop requests from dedicated memory writing sources in the multiprocessor computing environment. Each snoop filter device includes a plurality of parallel operating port snoop filters in correspondence with the plurality of dedicated input ports, each port snoop filter implementing one or more parallel operating sub-filter elements that are adapted to concurrently filter snoop requests received from respective dedicated memory writing sources and forward a subset of those requests to its associated processing unit.

Snoop filter for filtering snoop requests

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices are included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to needs of a processing algorithm.

A system and method for enhancing performance of a computer which includes a computer system including a data storage device. The computer system includes a program stored in the data storage device and steps of the program are executed by a processer. The processor processes instructions from the program. A wait state in the processor waits for receiving specified data. A thread in the processor has a pause state wherein the processor waits for specified data. A pin in the processor initiates a return to an active state from the pause state for the thread. A logic circuit is external to the processor, and the logic circuit is configured to detect a specified condition. The pin initiates a return to the active state of the thread when the specified condition is detected using the logic circuit.

Pausing and activating thread state upon pin assertion by external logic monitoring polling loop exit time condition

A novel massively parallel supercomputer of hundreds of teraOPS-scale includes node architectures based upon System- On-a-Chip technology, i.e., each processing node comprises a single Application Specific Integrated Circuit (ASIC). Within each ASIC node is a plurality of processing elements each of which consists of a central processing unit (CPU) and plurality of floating point processors to enable optimal balance of computational performance, packaging density, low cost, and power and cooling requirements. The plurality of processors within a single node individually or simultaneously work on any combination of computation or communication as required by the particular algorithm being solved. The system-on-a-chip ASIC nodes are interconnected by multiple independent networks that optimally maximizes packet communications throughput and minimizes latency. The multiple networks include three high-speed networks for parallel algorithm message passing including a Torus, Global Tree, and a Global Asynchronous network that provides global barrier and notification functions.

Massively parallel supercomputer

Call stack protection, including executing at least one application program on the one or more computer processors, including initializing threads of execution, each thread having a call stack, each call stack characterized by a separate guard area defining a maximum extent of the call stack, dispatching one of the threads of the process, including loading a guard area specification for the dispatched thread's call stack guard area from thread context storage into address comparison registers of a processor; determining by use of address comparison logic in dependence upon a guard area specification for the dispatched thread whether each access of memory by the dispatched thread is a precluded access of memory in the dispatched thread's call stack's guard area; and effecting by the address comparison logic an address comparison interrupt for each access of memory that is a precluded access of memory in the dispatched thread's guard area.

Call stack protection

Growing community of inventors

Irvington, NY, United States of America

Mark Edwin Giampapa