A Framework for Megascale Agent Based Model Simulations on Graphics Processing Units

Agent-based modeling is a technique for modeling dynamic systems from the bottom up. Individual elements of the system are represented computationally as agents. The system-level behaviors emerge from the micro-level interactions of the agents. Contemporary state-of-the-art agent-based modeling tool...

Full description

Saved in:
Bibliographic Details
Published in:Journal of artificial societies and social simulation Vol. 11; no. 4
Main Authors: Lysenko, Mikola, D'Souza, Roshan M
Format: Journal Article
Language:English
Published: 01.10.2008
Subjects:
Algorithms
Architecture
Graphs
Innovations
Methodology (Data Collection)
ISSN:1460-7425, 1460-7425
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Agent-based modeling is a technique for modeling dynamic systems from the bottom up. Individual elements of the system are represented computationally as agents. The system-level behaviors emerge from the micro-level interactions of the agents. Contemporary state-of-the-art agent-based modeling toolkits are essentially discrete-event simulators designed to execute serially on the Central Processing Unit (CPU). They simulate Agent-Based Models (ABMs) by executing agent actions one at a time. In addition to imposing an un-natural execution order, these toolkits have limited scalability. In this article, we investigate data-parallel computer architectures such as Graphics Processing Units (GPUs) to simulate large scale ABMs. We have developed a series of efficient, data parallel algorithms for handling environment updates, various agent interactions, agent death and replication, and gathering statistics. We present three fundamental innovations that provide unprecedented scalability. The first is a novel stochastic memory allocator which enables parallel agent replication in O(1) average time. The second is a technique for resolving precedence constraints for agent actions in parallel. The third is a method that uses specialized graphics hardware, to gather and process statistical measures. These techniques have been implemented on a modern day GPU resulting in a substantial performance increase. We believe that our system is the first ever completely GPU based agent simulation framework. Although GPUs are the focus of our current implementations, our techniques can easily be adapted to other data-parallel architectures. We have benchmarked our framework against contemporary toolkits using two popular ABMs, namely, SugarScape and StupidModel. Adapted from the source document.
AbstractList Agent-based modeling is a technique for modeling dynamic systems from the bottom up. Individual elements of the system are represented computationally as agents. The system-level behaviors emerge from the micro-level interactions of the agents. Contemporary state-of-the-art agent-based modeling toolkits are essentially discrete-event simulators designed to execute serially on the Central Processing Unit (CPU). They simulate Agent-Based Models (ABMs) by executing agent actions one at a time. In addition to imposing an un-natural execution order, these toolkits have limited scalability. In this article, we investigate data-parallel computer architectures such as Graphics Processing Units (GPUs) to simulate large scale ABMs. We have developed a series of efficient, data parallel algorithms for handling environment updates, various agent interactions, agent death and replication, and gathering statistics. We present three fundamental innovations that provide unprecedented scalability. The first is a novel stochastic memory allocator which enables parallel agent replication in O(1) average time. The second is a technique for resolving precedence constraints for agent actions in parallel. The third is a method that uses specialized graphics hardware, to gather and process statistical measures. These techniques have been implemented on a modern day GPU resulting in a substantial performance increase. We believe that our system is the first ever completely GPU based agent simulation framework. Although GPUs are the focus of our current implementations, our techniques can easily be adapted to other data-parallel architectures. We have benchmarked our framework against contemporary toolkits using two popular ABMs, namely, SugarScape and StupidModel. Adapted from the source document.
Author D'Souza, Roshan M
Lysenko, Mikola
Author_xml – sequence: 1
  givenname: Mikola
  surname: Lysenko
  fullname: Lysenko, Mikola
– sequence: 2
  givenname: Roshan
  surname: D'Souza
  middlename: M
  fullname: D'Souza, Roshan M
BookMark eNpNzLFOwzAUQFELFYm28A-e2CLZTuIkY6hoQWoFEu1cPdsvweDYJS8Rv88AA9M9012xRUwRr9hSFlpkVaHKxT_fsBXRhxAqV7pcsmPLtyMM-J3GT96lkR-wB7IQkLc9xok_AKHjh-Qw8Dc_zAEmnyLxFPluhMu7t8Rfx2SRyMeen6Kf6JZddxAI7_66Zqft43HzlO1fds-bdp9dZK2nrNMuN1jXJi8bp-pC6c5KBKGNywstLZSlqVwjpBFdA9pUEowy0hijCleBzdfs_vd7GdPXjDSdB08WQ4CIaaazllUlmlLnPyHNUSg
ContentType Journal Article
DBID 7U4
BHHNA
DWI
WZK
DatabaseName Sociological Abstracts (pre-2017)
Sociological Abstracts
Sociological Abstracts
Sociological Abstracts (Ovid)
DatabaseTitle Sociological Abstracts (pre-2017)
Sociological Abstracts
DatabaseTitleList Sociological Abstracts (pre-2017)
DeliveryMethod fulltext_linktorsrc
Discipline Architecture
Social Sciences (General)
EISSN 1460-7425
GroupedDBID 29J
2WC
5GY
5VS
7U4
AAFWJ
AAKPC
ACGFO
ADBBV
ADZJE
AFPKN
AIAGR
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BHHNA
C1A
DWI
E3Z
EBS
EJD
ESI
FRS
GROUPED_DOAJ
KQ8
OK1
OVT
P2P
RNS
TR2
WZK
XSB
ID FETCH-LOGICAL-p186t-f6d3be88b359d28426fc1ea06bd3461ca55b7d901b0f9a6b71ab2b1bbb24d7ac3
ISICitedReferencesCount 71
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000265355200010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1460-7425
IngestDate Thu Jul 10 20:30:54 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-p186t-f6d3be88b359d28426fc1ea06bd3461ca55b7d901b0f9a6b71ab2b1bbb24d7ac3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 61770956
PQPubID 23497
ParticipantIDs proquest_miscellaneous_61770956
PublicationCentury 2000
PublicationDate 20081001
PublicationDateYYYYMMDD 2008-10-01
PublicationDate_xml – month: 10
  year: 2008
  text: 20081001
  day: 01
PublicationDecade 2000
PublicationTitle Journal of artificial societies and social simulation
PublicationYear 2008
SSID ssj0023265
Score 2.123544
Snippet Agent-based modeling is a technique for modeling dynamic systems from the bottom up. Individual elements of the system are represented computationally as...
SourceID proquest
SourceType Aggregation Database
SubjectTerms Algorithms
Architecture
Graphs
Innovations
Methodology (Data Collection)
Title A Framework for Megascale Agent Based Model Simulations on Graphics Processing Units
URI https://www.proquest.com/docview/61770956
Volume 11
WOSCitedRecordID wos000265355200010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: Open Access Journals
  customDbUrl:
  eissn: 1460-7425
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023265
  issn: 1460-7425
  databaseCode: DOA
  dateStart: 19980101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtZ3vT9QwGMcbIb4wJkYRI6LQF2o0y5L96Nbu5UDAF-dpwiD37tJuHRCgO-gdAf96nnbd7ggY9IVvukuz25J9tvbbPr8Q-hhwVvGYcp_XIfdJwkNfZAQaGkgC_-Gl3XA7HNDhkI1G2S9XqVDbcgJUKXZ9nU3-K2roA9gmdPYfcPcXhQ74DdChBezQ_hX43IjR1uHK-hD-kEdcAwnp5SaMytuCeauyNdDOvP2T81nvDKe8PZO92qRtduEDZhvBiFL9Bwlr7u4yUGjr_QnLbm9hJ173l-_9fm60VKdN67B_2pz1k8K3TxHdb2a_Wy3b6GNjRLqzJcF657ZuFCVp4MOauzVXywf6uqE3XHjFyHxK6szww5_j3YPBYFzsjIrPkwvfFAszRnVXOWUJLcUB6dbRbpUNejRpQ8ra-92bZK1yKF6iF-554bxF9Qo9kWoFPc8XLDgraK0Nk8ZuqNX4i8sH_vU1KnLcE8VAFPdEsSWKLVFsieIForhRuCOK50SxJbqKDnZ3iu3vviuG4U9Clk79Oq1iIRkTcZJVoCmitC5DyYNUVDFJw5IniaAVqDsR1BlPBQ25iEQohIhIRXkZv0HLqlHyLcKSmZRMWQTHikQ0E7XgaSySksHHSQOxhja7JzaGwcZYkLiSzUyPQe5Sk7ny3aNnrKNn8zfjPVqeXs7kB_S0vJqe6MsNS-wWq1pUcw
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Framework+for+Megascale+Agent+Based+Model+Simulations+on+Graphics+Processing+Units&rft.jtitle=Journal+of+artificial+societies+and+social+simulation&rft.au=Lysenko%2C+Mikola&rft.au=D%27Souza%2C+Roshan+M&rft.date=2008-10-01&rft.issn=1460-7425&rft.eissn=1460-7425&rft.volume=11&rft.issue=4&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1460-7425&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1460-7425&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1460-7425&client=summon