Method and system for optimal parallel computing performance

Data processing: artificial intelligence – Knowledge processing system

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C712S028000

Reexamination Certificate

active

07953684

ABSTRACT:
A system and method that optimizes reduce operations by consolidating the operation into a limited number of participating processes and then distributing the results back to all processes to optimize large message global reduce operations on non power-of-two processes. The method divides a group of processes into subgroups, performs paired exchange and local reduce operations at some of the processes to obtain half vectors of partial reduce results, consolidates partial reduce results into a set of regaining processes, performs successive recursive halving and recursive doubling at a set of remaining processes until each process in the set of remaining process has a half vector of the complete result, and provides a full complete result at every process.

REFERENCES:
patent: 6212617 (2001-04-01), Hardwick
patent: 6601089 (2003-07-01), Sistare et al.
patent: 6751791 (2004-06-01), Inaba
patent: 6766517 (2004-07-01), Bernardo
patent: 6886031 (2005-04-01), Venkatsubramanian et al.
patent: 2003/0204570 (2003-10-01), Rehof et al.
patent: 2004/0073590 (2004-04-01), Bhanot et al.
patent: 2004/0103218 (2004-05-01), Blumrich et al.
patent: 2005/0091334 (2005-04-01), Chen et al.
“Optimization of Collective Communication Operations in MPICH”, R. Thakur, R. Rabenseifner, W. Gropp, The International Journal of High Performance Computing Applications, vol. 19, No. 1, Spring 2005, pp. 49-66.
“All-to-All Personalized Communication in Multidimensional Torus and Mesh Networks”, Young-Joo Suh, K. G. Shin, IEEE Transactions on Parallel and Distributed Systems, vol. 12, No. 1, Jan. 2001, pp. 38-59.
“Improving the Performance of Collective Operations in MPICH”, R. Thakur, W. D. Gropp, Lecture Notes in Computer Science, vol. 2840, 2003, pp. 257-267.
“Optimization of Collective Reduction Operations”, R. Rabenseifner, ICCS 2004, Lecture Notes in Computer Science 3036, pp. 1-9.
“More Efficient Reduction Algorithms for Non-Power-of-Two Number of Processors in Message-Passing Parallell Systems”, R. Rabenseifner, J. L. Traff, Lecture Notes in Computer Science, vol. 3241, 2004 pp. 309-335.
Gorlatch, Sergel: “Toward Formally-Based Design of Message Passing Programs”, IEEE Transactions of Software Engineering, vol. 26, No. 3, (Mar. 2000), pp. 276-288.
Rabenselfner, et al; “Optimization of MPI—Allreduce and MPI—Reduce”: CUG 2004, pp. 1-10, May 17-21, 2004.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Method and system for optimal parallel computing performance does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and system for optimal parallel computing performance, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for optimal parallel computing performance will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2625078

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.