2008 22nd International Symposium on High Performance Computing Systems and Applications最新文献

{"title":"Quantum Chromodynamics on a Space-Time Lattice","authors":"H. Trottier","doi":"10.1109/HPCS.2008.34","DOIUrl":"https://doi.org/10.1109/HPCS.2008.34","url":null,"abstract":"Quantum chromodynamics has been accepted as the theory of the strong interactions for more than thirty years, ever since the discovery of asymptotic freedom by Gross, Politzer and Wilczek, whose work was recognized with the 2004 Nobel Prize. Despite many successful quantitative predictions for high-energy processes, applications of QCD to strongly-coupled, low-energy hadronic physics, including such basic quantities as the proton mass, have historically been much less successful. A space-time lattice discretization of QCD (proposed by Ken Wilson the year after asymptotic freedom) lends itself to direct numerical simulation, but the enormous computational burden of lattice QCD has, until recently, precluded accurate simulations of the full theory. Happily, dramatic improvements in the predictive power of lattice QCD have occurred in the past few years, due to major theoretical progress in our understanding of lattice quantum field theories. These developments are having a significant impact, including the use of lattice QCD to constrain the search for physics beyond the so-called standard model. This talk will give a conceptual review of the theory of QCD at high and low energies and the new developments in lattice QCD.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116421377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simulating Exotic Quantum States of Matter","authors":"M. Troyer","doi":"10.1109/HPCS.2008.31","DOIUrl":"https://doi.org/10.1109/HPCS.2008.31","url":null,"abstract":"Summary form only given. Strong quantum effects in correlated materials can give rise to unusual and exotic quantum states of matter. Examples are the so-called supersolid phase (which combines the seemingly contradictory properties of being solid and at the same time superfluid), high-temperature superconductors with exotic superconductivity driven by strong quantum fluctuations, or anyonic quantum liquids. Numerical methods are essential for our understanding of these exotic phases since the strong quantum fluctuations make approximate analytical treatments such as mean-field or weak-coupling approximations unreliable. In this talk I will review the tremendous progress in quantum Monte Carlo algorithms in the past decade, allowing the simulation of millions of quantum spins or bosons with high accuracy and the accurate understanding of phenomena such as supersolidity. I will also explain the origin of the infamous \"negative sign problem\" which prevents simulations of similar accuracy for electronic system and will show that this problem is NP-hard. The simulation of electronic systems will thus remain a big challenge for the foreseeable future.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129356748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SpectroGrid: Providing Simple Secure Remote Access to Scientific Instruments","authors":"A. Charbonneau, V. Terskikh","doi":"10.1109/HPCS.2008.17","DOIUrl":"https://doi.org/10.1109/HPCS.2008.17","url":null,"abstract":"With the availability of high performance networks and the increase in the number of online scientific instruments, remote instrumentation is a topic with much popularity lately, promising better instrument utilization, easier collaboration between distant organizations and diminution of travel-related costs and overhead. At NRC we needed a simple and secure method for researchers to remotely access nuclear magnetic resonance (NMR) instruments located at the National Ultrahigh-Field NMR Facility for Solids for data acquisition and visualization purposes. This paper discusses the design and implementation of SpectroGrid: a simple remote instrumentation solution based on open source technologies. VNC (virtual network computing) is used as the remote control implementation, and security is provided by the grid security infrastructure (GSI) and secure shell (SSH). A discussion about the cost-saving potentials of SpectroGrid for the Canadian research community will also be given. SpectroGrid is currently being used by Canadian researchers to remotely access NMR instruments located at NRC in Ottawa.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129189950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proposal for Modifications to the OSCAR Architecture to Address Challenges in Distributed System Management","authors":"Geoffroy R. Vallée, T. Naughton, S. Scott","doi":"10.1109/HPCS.2008.23","DOIUrl":"https://doi.org/10.1109/HPCS.2008.23","url":null,"abstract":"OSCAR, a tool for the deployment and the management of clusters, has historically provided a simple Graphical User Interface (GUI) that aims to hide technical details associated with the management of such distributed platforms. The OSCAR GUI followed a fairly monolithic architecture, which was difficult to extend. Thankfully, OSCAR developers have made deep modifications to the overall OSCAR architecture to be much more modular, and as a result it is fairly simple to support OSCAR on new Linux distributions. However, a few questions remain. Is the present OSCAR architecture suitable to address current challenges needed for the management of distributed systems? For instance, is OSCAR providing a tool set that answers the needs of system administrators? This document presents a criticism of the present OSCAR architecture in order to identify current challenges related to distributed system management. Based on this analysis, we propose a modified version of the OSCAR architecture that emphasizes simplicity and incremental enhancements.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"251 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113980807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficient Parallel Computing for Laser-Gas Quantum Interaction and Propagation","authors":"E. Lorin, A. Bandrauk","doi":"10.1109/HPCS.2008.14","DOIUrl":"https://doi.org/10.1109/HPCS.2008.14","url":null,"abstract":"We present in this short paper some domain decomposition and high performance numerical techniques for simulating laser-gas interaction and propagation using a multi-scale Maxwell-Schrodinger model. Ionization and high order harmonic generation are in particular taken into account in this micro-macro model, leading to additional simulation difficulties. We propose some benchmarks to validate the presented techniques.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114850364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using OSCAR to Win the Cluster Challenge","authors":"P. Greidanus, G. Klok","doi":"10.1109/HPCS.2008.22","DOIUrl":"https://doi.org/10.1109/HPCS.2008.22","url":null,"abstract":"This paper discusses using OSCAR (open source cluster administration resource) to compete and win, in the first ever cluster challenge competition at supercomputing 2007. The cluster challenge invited teams of undergraduate students to assemble a cluster and compete for 44 hours on the conference floor. The teams competed in two main areas; (i) achieving the best results on the high performance computing challenge benchmark and (ii) who could complete the most of a selection of data sets for several common scientific applications. In the this document we explain why Team Alberta chose OSCAR, how we feel it contributed to our success and our experiences using it.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133095829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large-Scale Integrative Modeling of the Human Heart","authors":"M. Potse, A. Vinet","doi":"10.1109/HPCS.2008.37","DOIUrl":"https://doi.org/10.1109/HPCS.2008.37","url":null,"abstract":"Summary form only given. The contraction of the heart is triggered by an electrical impulse that propagates from one muscle cell to another. This organized activity generates a potential field that can be measured as an electrocardiogram (ECG) on the body surface, or with a catheter inside the heart. The measured signals provide a wealth of diagnostic information. This information has traditionally been decoded by clinicians in a strictly empirical way. As more and more becomes known about the underlying processes in the cell membrane, it becomes more common to hypothesize links between malfunctions on the cellular level and ECG abnormalities. Due to the startling complexity of the basic processes and the heart's anatomy, large-scale mathematical modeling can be necessary to verify such hypotheses. The dynamics of the heart are described by a coupled system of elliptic and parabolic differential equations. Spatial step sizes have to be as small as 0.1 mm in some cases. This leads to systems of hundreds of millions of linear equations when a whole human heart is modeled. The difficulty of solving such large systems has for some time limited the size of heart models to those of mice and rabbits, requiring only about a million equations. A breakthrough was obtained two years ago when we found a combination of algorithms that could solve a system of 60 million equations. Deployed on a newly arrived SGI Altix system, these methods allowed us to model an entire human heart. This heart model has since then provided important new insights in a wide range of cardiological subjects from myocardial ischemia to repolarisation measurement in the heart. The more recent arrival of a 768-processor Altix 4700 system has allowed us to test our methods on an even larger scale. With its 1.5 TB memory, this machine could handle a model with 2 billion equations. A short test showed convergence with an iteration count that was not much larger than for much smaller systems. Currently, we cannot obtain such resouces for routine work. However, our test shows that it is only a matter of time before heart models with over a billion nodes can be used. We expect that this will have a great impact on the understanding of sudden cardiac death syndromes related to congenital cardiomyopathies degenerative diseases that cause fragmentation of the heart muscle on a sub-millimeter scale.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129816594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational Enzymology: Promises and Challenges","authors":"G. Lamoureux","doi":"10.1109/HPCS.2008.33","DOIUrl":"https://doi.org/10.1109/HPCS.2008.33","url":null,"abstract":"With the steady increase of computing power, it will soon become conceivable to decode the function of an enzyme strictly from its molecular structure. To realize this ambitious goal, progress has to be made on two fronts: (1) the realism of the molecular models used in the simulations and (2) the speed at which these models can be computed. The author discuss aspects of these two problems with work on zinc enzymes and on ammonium transport proteins.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129002012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High Performance Networks for the ATLAS Tier-1 @ TRIUMF","authors":"Chris Payne, D. Deatrich, Simon Y. Liu, S. McDonald, Réda Tafirout, R. Walker, A. Wong, M. Vetterli","doi":"10.1109/HPCS.2008.15","DOIUrl":"https://doi.org/10.1109/HPCS.2008.15","url":null,"abstract":"Networking at an ATLAS Tier-1 (Tl) facility is a demanding aspect which is vital to the overall performance and efficiency of the facility. External connectivity of the facility to other tiers of the large hadron collider optical private network (LHCOPN) is largely via dedicated lightpaths as required to meet memorandum of understanding (MOU) commitments. Our primary dedicated link to CERN has an independent, although smaller capacity, dedicated backup link for redundancy. Dedicated lightpaths to the Canadian Tier-2 facilities, and the international partner Tier-1 facilities failover to national and international research networks in the event of failure. The distance between TRIUMF and CERN, and even TRIUMF to some of it's Tier-2 facilities in Canada is thousands of kilometers. Transferring data at the hundreds of terabytes of data level (per year) over such distances and complex networks requires both dedicated bandwidth and network resiliency. Failure scenario, including both fail- over and fail-back, must be handled efficiently and for the most part automatically. Although modern network routing protocols handle this well, monitoring processes become key to management of the infrastructure as the complexity of our Tier-1 site connectivity grows. Internal networking efficiency is also vital to the ATLAS computing model. Large data sets are moved from onsite storage to local scratch disks before analysis, and proper network scaling is vital for efficient use of compute nodes. Although 10 Gigabit network infrastructure (routers) is well established, server 10 Gigabit network components and drivers are not as mature as their I Gigabit counterparts, and resource issues have been observed during extreme load testing. In this paper, internal facility networking, as well as external connectivity issues will be discussed.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128432180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-Performance Computing Considered Harmful","authors":"G. V. Wilson","doi":"10.1109/HPCS.2008.32","DOIUrl":"https://doi.org/10.1109/HPCS.2008.32","url":null,"abstract":"For more than forty years, discussion of scientific computing has been dominated by a minority who equate it with high performance computing. The result is a culture in which productivity is low, project failure rates are high, and quality is usually unknown. This talk examines how this situation arose, why it persists, and what can be done to fix it.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121620438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}