Mechanism of supporting sub-communicator collectives with o(64) counters as opposed to one counter for each sub-communicator
Abstract
A system and method for enhancing barrier collective synchronization on a computer system comprises 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 being executed by a processor. The system includes providing a plurality of communicators for storing state information for a barrier algorithm. Each communicator designates a master core in a multi-processor environment of the computer system. The system allocates or designates one counter for each of a plurality of threads. The system configures a table with a number of entries equal to the maximum number of threads. The system sets a table entry with an ID associated with a communicator when a process thread initiates a collective. The system determines an allocated or designated counter by searching entries in the table.
- Inventors:
- Issue Date:
- Research Org.:
- GLOBALFOUNDRIES INC., Grand Cayman, KY (Cayman Islands)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1236466
- Patent Number(s):
- 9244734
- Application Number:
- 14/015,098
- Assignee:
- GLOBALFOUNDRIES INC.
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
- DOE Contract Number:
- B554331
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 2013 Aug 30
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING
Citation Formats
Blocksome, Michael, Kumar, Sameer, Mamidala, Amith R., Miller, Douglas, and Ratterman, Joseph D.. Mechanism of supporting sub-communicator collectives with o(64) counters as opposed to one counter for each sub-communicator. United States: N. p., 2016.
Web.
Blocksome, Michael, Kumar, Sameer, Mamidala, Amith R., Miller, Douglas, & Ratterman, Joseph D.. Mechanism of supporting sub-communicator collectives with o(64) counters as opposed to one counter for each sub-communicator. United States.
Blocksome, Michael, Kumar, Sameer, Mamidala, Amith R., Miller, Douglas, and Ratterman, Joseph D.. Tue .
"Mechanism of supporting sub-communicator collectives with o(64) counters as opposed to one counter for each sub-communicator". United States. https://www.osti.gov/servlets/purl/1236466.
@article{osti_1236466,
title = {Mechanism of supporting sub-communicator collectives with o(64) counters as opposed to one counter for each sub-communicator},
author = {Blocksome, Michael and Kumar, Sameer and Mamidala, Amith R. and Miller, Douglas and Ratterman, Joseph D.},
abstractNote = {A system and method for enhancing barrier collective synchronization on a computer system comprises 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 being executed by a processor. The system includes providing a plurality of communicators for storing state information for a barrier algorithm. Each communicator designates a master core in a multi-processor environment of the computer system. The system allocates or designates one counter for each of a plurality of threads. The system configures a table with a number of entries equal to the maximum number of threads. The system sets a table entry with an ID associated with a communicator when a process thread initiates a collective. The system determines an allocated or designated counter by searching entries in the table.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2016},
month = {1}
}
Works referenced in this record:
SMARTMAP: Operating system support for efficient data sharing among processes on a multi-core processor
conference, November 2008
- Brightwell, R.; Pedretti, K.; Hudson, T.
- 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis
Synchronization of a client and a server in a prefetching resource allocation system
patent, October 1999
- Pal, Shankar
- US Patent Document 5,963,945
Multithreaded processor efficiency by pre-fetching instructions for a scheduled thread
patent, November 2005
- Nemawarkar, Shashank
- US Patent Document 6,965,982
Program thread syncronization for instruction cachelines
patent, June 2009
- Collard, Jean-Francois; Jouppi, Norman Paul; Schlansker, Michael
- US Patent Document 7,555,607
Measuring processor use in a hardware multithreading processor environment
patent, June 2009
- Olszewski, Bret R.; Smolders, Luc Rene; Srinivas, Mysore S.
- US Patent Document 7,555,753
Program thread syncronization
patent, July 2011
- Collard, Jean-Francois; Jouppi, Norman Paul; Schlansker, Michael
- US Patent Document 7,984,242
Thread-type-based load balancing in a multithreaded processor
patent, December 2011
- Lindholm, John Erik; Nordquist, Bryon S.; Moy, Simon
- US Patent Document 8,087,029
Thread-type-based resource allocation in a multithreaded processor
patent, January 2012
- Lindholm, John Erik; Nordquist, Bryon S.; Moy, Simon
- US Patent Document 8,108,872
Enhanced control of CPU parking and thread rescheduling for maximizing the benefits of low-power state
patent, February 2012
- Branover, Alexander J.; Steinman, Maurice B.; Rystsov, Denis
- US Patent Document 8,112,648
Method and system for modeling and analyzing computing resource requirements of software applications in a shared and distributed computing environment
patent, November 2013
- Wong, Wai Ming; Hui, Michael C.
- US Patent Document 8,584,131