Arithmetic functions in torus and tree networks
- Princeton, NJ
- Ridgefield, CT
- Croton On Hudson, NY
- Mount Kisco, NY
- Irvington, NY
- Cortlandt Manor, NY
- Bedford Hills, NY
Methods and systems for performing arithmetic functions. In accordance with a first aspect of the invention, methods and apparatus are provided, working in conjunction of software algorithms and hardware implementation of class network routing, to achieve a very significant reduction in the time required for global arithmetic operation on the torus. Therefore, it leads to greater scalability of applications running on large parallel machines. The invention involves three steps in improving the efficiency and accuracy of global operations: (1) Ensuring, when necessary, that all the nodes do the global operation on the data in the same order and so obtain a unique answer, independent of roundoff error; (2) Using the topology of the torus to minimize the number of hops and the bidirectional capabilities of the network to reduce the number of time steps in the data transfer operation to an absolute minimum; and (3) Using class function routing to reduce latency in the data transfer. With the method of this invention, every single element is injected into the network only once and it will be stored and forwarded without any further software overhead. In accordance with a second aspect of the invention, methods and systems are provided to efficiently implement global arithmetic operations on a network that supports the global combining operations. The latency of doing such global operations are greatly reduced by using these methods.
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- W-7405-ENG-48
- Assignee:
- International Business Machines Corporation (Armonk, NY)
- Patent Number(s):
- 7,313,582
- Application Number:
- 10/468,991
- OSTI ID:
- 921478
- Country of Publication:
- United States
- Language:
- English
A communication model based on an n-dimensional torus architecture using deadlock-free wormhole routing
|
conference | January 2003 |
Network decontamination with local immunization
|
conference | January 2006 |
Parallel image analysis on recursive Torus architecture
|
conference | January 1993 |
The P-Mesh-a commodity-based scalable network architecture for clusters
|
conference | January 1999 |
Exploiting multiple degrees of BP parallelism on the highly parallel computer AP1000
|
conference | January 1995 |
Polymorphic-torus architecture for computer vision
|
journal | March 1989 |
A Scalable Distributed Parallel Breadth-First Search Algorithm on BlueGene/L
|
conference | January 2005 |
Data level parallel processing for object recognition on Recursive Torus Architecture
|
conference | January 1995 |
A unified formulation of honeycomb and diamond networks
|
journal | January 2001 |
A peer-to-peer network based on multi-mesh architecture
|
conference | January 2003 |
Scalable distributed architecture of the terabit router
|
conference | January 2004 |
Image analysis and computer vision: 1988
|
journal | May 1989 |
Efficient mapping algorithm of multilayer neural network on torus architecture
|
journal | September 2003 |
Similar Records
A novel digital pulse processing architecture for nuclear instrumentation
Fault tolerant matrix arithmetic and signal processing on highly concurrent VLSI systems