Biomaterial Database

Efficient heterogeneous execution of Monte Carlo shielding calculations on a Beowulf cluster. 2005

David Dewar, and Paul Hulse, and Andrew Cooper, and Nigel Smith

BNFL, Risley, Warrington, Cheshire, UK. david.dewar@bnfl.com

Recent work has been done in using a high-performance 'Beowulf' cluster computer system for the efficient distribution of Monte Carlo shielding calculations. This has enabled the rapid solution of complex shielding problems at low cost and with greater modularity and scalability than traditional platforms. The work has shown that a simple approach to distributing the workload is as efficient as using more traditional techniques such as PVM (Parallel Virtual Machine). In addition, when used in an operational setting this technique is fairer with the use of resources than traditional methods, in that it does not tie up a single computing resource but instead shares the capacity with other tasks. These developments in computing technology have enabled shielding problems to be solved that would have taken an unacceptably long time to run on traditional platforms. This paper discusses the BNFL Beowulf cluster and a number of tests that have recently been run to demonstrate the efficiency of the asynchronous technique in running the MCBEND program. The BNFL Beowulf currently consists of 84 standard PCs running RedHat Linux. Current performance of the machine has been estimated to be between 40 and 100 Gflop s(-1). When the whole system is employed on one problem up to four million particles can be tracked per second. There are plans to review its size in line with future business needs.

UI	MeSH Term	Description	Entries
D009010	Monte Carlo Method	In statistics, a technique for numerically approximating the solution of a mathematical problem by studying the distribution of some random variable, often generated by a computer. The name alludes to the randomness characteristic of the games of chance played at the gambling casinos in Monte Carlo. (From Random House Unabridged Dictionary, 2d ed, 1993)	Method, Monte Carlo
D009862	Online Systems	Computer-based Information systems having real-time remote access to information or processes.	On-Line Systems,On Line Systems,On-Line System,Online System,System, On-Line,System, Online,Systems, On-Line,Systems, Online
D011829	Radiation Dosage	The amount of radiation energy that is deposited in a unit mass of material, such as tissues of plants or animal. In RADIOTHERAPY, radiation dosage is expressed in gray units (Gy). In RADIOLOGIC HEALTH, the dosage is expressed by the product of absorbed dose (Gy) and quality factor (a function of linear energy transfer), and is called radiation dose equivalent in sievert units (Sv).	Sievert Units,Dosage, Radiation,Gray Units,Gy Radiation,Sv Radiation Dose Equivalent,Dosages, Radiation,Radiation Dosages,Units, Gray,Units, Sievert
D011835	Radiation Protection	Methods and practices adopted to protect against RADIATION.	Protection, Radiation
D011874	Radiometry	The measurement of radiation by photography, as in x-ray film and film badge, by Geiger-Mueller tube, and by SCINTILLATION COUNTING.	Geiger-Mueller Counters,Nuclear Track Detection,Radiation Dosimetry,Dosimetry, Radiation,Geiger Counter,Geiger-Mueller Counter Tube,Geiger-Mueller Probe,Geiger-Mueller Tube,Radiation Counter,Counter Tube, Geiger-Mueller,Counter Tubes, Geiger-Mueller,Counter, Geiger,Counter, Radiation,Counters, Geiger,Counters, Geiger-Mueller,Counters, Radiation,Detection, Nuclear Track,Dosimetries, Radiation,Geiger Counters,Geiger Mueller Counter Tube,Geiger Mueller Counters,Geiger Mueller Probe,Geiger Mueller Tube,Geiger-Mueller Counter Tubes,Geiger-Mueller Probes,Geiger-Mueller Tubes,Probe, Geiger-Mueller,Probes, Geiger-Mueller,Radiation Counters,Radiation Dosimetries,Tube, Geiger-Mueller,Tube, Geiger-Mueller Counter,Tubes, Geiger-Mueller,Tubes, Geiger-Mueller Counter
D003195	Computer Communication Networks	A system containing any combination of computers, computer terminals, printers, audio or visual display devices, or telephones interconnected by telecommunications equipment or cables: used to transmit or receive information. (Random House Unabridged Dictionary, 2d ed)	Cognitive Radio,Computer Network Management,Databases, Distributed,Distributed Systems,Extranets,Intranets,Network Communication Protocols,Telecommunication Networks,Cognitive Radios,Communication Network, Computer,Communication Networks, Computer,Communication Protocol, Network,Communication Protocols, Network,Computer Communication Network,Database, Distributed,Distributed Database,Distributed Databases,Distributed System,Extranet,Intranet,Management, Computer Network,Network Communication Protocol,Network Management, Computer,Network, Computer Communication,Network, Telecommunication,Protocol, Network Communication,Radio, Cognitive,System, Distributed,Telecommunication Network
D003198	Computer Simulation	Computer-based representation of physical systems and phenomena such as chemical processes.	Computational Modeling,Computational Modelling,Computer Models,In silico Modeling,In silico Models,In silico Simulation,Models, Computer,Computerized Models,Computer Model,Computer Simulations,Computerized Model,In silico Model,Model, Computer,Model, Computerized,Model, In silico,Modeling, Computational,Modeling, In silico,Modelling, Computational,Simulation, Computer,Simulation, In silico,Simulations, Computer
D003205	Computing Methodologies	Computer-assisted analysis and processing of problems in a particular area.	High Performance Computing,Methodologies, Computing,Computing Methodology,Computing, High Performance,Methodology, Computing,Performance Computing, High
D015233	Models, Statistical	Statistical formulations or analyses which, when applied to data and found to fit the data, are then used to verify the assumptions and parameters used in the analysis. Examples of statistical models are the linear model, binomial model, polynomial model, two-parameter model, etc.	Probabilistic Models,Statistical Models,Two-Parameter Models,Model, Statistical,Models, Binomial,Models, Polynomial,Statistical Model,Binomial Model,Binomial Models,Model, Binomial,Model, Polynomial,Model, Probabilistic,Model, Two-Parameter,Models, Probabilistic,Models, Two-Parameter,Polynomial Model,Polynomial Models,Probabilistic Model,Two Parameter Models,Two-Parameter Model