{"title":"Computational Astrophysics","authors":"H. Couchman","doi":"10.1109/HPCS.2008.38","DOIUrl":"https://doi.org/10.1109/HPCS.2008.38","url":null,"abstract":"Summary form only given. Large-scale computation has achieved a pivotal role in many areas of astrophysics and cosmology. Not only does increasing computational power allow us to better model the huge range of spatial and temporal scales in the universe, but simulations provide in many cases the only laboratory in which we may actively experiment on cosmic phenomena. The talk will highlight some of the significant achievements in numerical astrophysics and cosmology over the past decade and describe some of the key challenges that we must face in the future. It will focus, in particular, on some recent state-of-the-art models of dwarf galaxies and illustrate the subtle interplay between gravitational and astrophysical processes in these systems.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"88 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":"128602116","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":"Stateless Clustering Using OSCAR and PERCEUS","authors":"Abhishek Kulkarni, A. Lumsdaine","doi":"10.1109/HPCS.2008.12","DOIUrl":"https://doi.org/10.1109/HPCS.2008.12","url":null,"abstract":"OSCAR has matured over the years into a very capable, yet simple high-performance clustering platform solution. Ease of building and administrating a cluster, effective resource management and scalable performance are some of the issues which have gathered a lot of focus in the HPC domain lately. This technical paper describes the integration of OSCAR and PERCEUS, which aims to enable the deployment of stateless nodes in a cluster. This promises to fill a much needed niche in performing a diskless cluster installation with OSCAR. The single point of administration and ease-of-use would help novice users as well as experienced cluster administrators to deploy clusters faster.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"57 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":"114778625","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":"Utility Computing and Market-Based Scheduling: Shortcomings for Grid Resources Sharing and the Next Steps","authors":"Nicolas Dubé, M. Parizeau","doi":"10.1109/HPCS.2008.29","DOIUrl":"https://doi.org/10.1109/HPCS.2008.29","url":null,"abstract":"This paper lays out fundamental social and economic principles that must be addressed in order to enable true High-Performance Computing resources sharing at the scale of a national Grid. Focusing on the literature around the concept of a Grid Economy, it starts by a rather exhaustive survey of related work in utility computing, market- based scheduling and other economic approaches in resource allocation. Building on forces and weaknesses of previous work, high-level principles to be followed to establish a sustainable and pervasive Grid sharing framework are detailed.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"27 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":"114783673","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 Investigation of Protein Chemistry: “S-Nitrosohemoglobin”","authors":"D. Koch, A. English, Gilles H. Peslherbe","doi":"10.1109/HPCS.2008.39","DOIUrl":"https://doi.org/10.1109/HPCS.2008.39","url":null,"abstract":"Reliable computational studies of large biological systems have only recently become possible due to the availability of high-performance computing resources. In this contribution, we present large-scale quantum mechanics / molecular mechanics (QM/MM) studies of hemoglobin (Hb) and its derivatives. In recent years, Hb has been reported to play an important role in blood-flow regulation via its reactions with the vasodilator, nitric oxide (NO). \"S-nitrosohemoglobin\" (SNO-Hb) has then emerged as a key player. However, NO-derivatization of the conserved cysteine residue (Cysbeta93) of Hb has been proposed to yield either an S-nitrosothiol (RSNO), an S-hydroxyamino radical (RSN*OH) or a thionitroxide radical (RSNHO*). The relative stabilities of the different proposed chemical forms of \"SNO-Hb\" are being examined using large-scale QM/MM simulations, and the critical role of the protein environment in the relative stabilities of the \"SNO-Hb\" forms is demonstrated. Furthermore, it has been proposed that NO is first attached to the heme iron of the beta subunit of hemoglobin, and it is then displaced from the iron by the presence of molecular oxygen and transported to the Cysbeta93 residue. We also investigate the possible transport channels of NO from the heme to this cysteine residue.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"6 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":"124683183","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":"Parallel Implementation of a Subsystem-by-Subsystem Solver","authors":"Yun Guan, J. Verschelde","doi":"10.1109/HPCS.2008.8","DOIUrl":"https://doi.org/10.1109/HPCS.2008.8","url":null,"abstract":"Solving polynomial systems subsystem-by-subsystem means to solve a system of polynomial equations by first solving subsets of the system and then intersecting the results. The approach leads to numerical representations of all the solution components of a system. The focus of this paper is the development of a parallel implementation to solve large systems involving a recursive divide-and- conquer scheme. Because we concentrate our discussion on the distribution of the path tracking jobs, we have selected applications for which we have optimal homotopies, for which all paths converge to regular solutions.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"24 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":"124920270","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":"ATLAS Computing: Dealing with Petabytes of Data per Year","authors":"M. Vetterli","doi":"10.1109/HPCS.2008.36","DOIUrl":"https://doi.org/10.1109/HPCS.2008.36","url":null,"abstract":"ATLAS is a particle physics experiment at CERN in Geneva, which will study proton- proton collisions at the highest energy ever achieved in the laboratory. The main goal of the experiment is to discover the Higgs particle, which is central to the current theory of how subatomic particles attain mass. ATLAS will also search for a variety of phenomena beyond the Standard Model of particle physics. In order to carry out this research program, ATLAS will collect data from millions of collisions per second, recording 200 Hz to tape. This will result in 3.5 PetaBytes (1015 bytes) of data per year, which could double when secondary data sets are produced. This talk will describe the international computing network (WLCG) that has been set up using Grid tools to deal with this avalanche of data. Emphasis will be given to Canada's contributions to WLCG.","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":"124127800","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":"Building and Refining General Purpose Computing Clusters in an Emerging HPCOriented Research Environment","authors":"A. Gazendam","doi":"10.1109/HPCS.2008.13","DOIUrl":"https://doi.org/10.1109/HPCS.2008.13","url":null,"abstract":"The increasing uptake of HPC, and cluster computing in particular, has led many people to develop creative solutions to the technical challenges that they encounter in the establishment of useful HPC facilities. Proven solutions from our experiences in acquiring and building research clusters for general purpose scientific use are presented to a number of such issues, ranging from the performance evaluation of vendor bids to matters of user management. Examples of the latter being techniques for limiting manual SSHing to compute nodes and the use of group accounts that empower user groups to take ownership of their specialized software.","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":"130297837","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":"A Computational Study of External Shear Forces in Biofilm Clusters","authors":"Jiaying Xu, R. Sudarsan, G. Darlington, H. Eberl","doi":"10.1109/HPCS.2008.21","DOIUrl":"https://doi.org/10.1109/HPCS.2008.21","url":null,"abstract":"We conduct a computational study of biofilm exposure to external detachment forces, utilising techniques from computational fluid dynamics and statistics. The results obtained for irregular arrangements of biofilm colonies are compared with those of evenly distributed colonies. This requires a multitude of flow field simulations in irregular domains. Our findings suggest that the biofilm community as an entity is protected better for non-uniform spacing between colonies, while the individual biofilm colony that lives under the worst condition is protected better if neighboring colonies are approximately equidistantly spaced.","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"126 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":"117168026","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":"Performance Driven Partial Checkpoint/Migrate for LAM-MPI","authors":"Rajendra Singh, P. Graham","doi":"10.1109/HPCS.2008.16","DOIUrl":"https://doi.org/10.1109/HPCS.2008.16","url":null,"abstract":"Using idle compute resources is cost-effective and systems like Condor have successfully exploited such resources in limited contexts (e.g. bag of tasks problems). Increasingly, networks in large organizations are becoming more capable and, when combined with latency tolerance mechanisms, can now provide an attractive platform for running some cluster-based parallel programs. In environments where machines are shared, however, load guarantees cannot be made. If one or more machines running an application become overloaded it may negatively impact the performance of the entire application. This provides a strong motivation to be able to checkpoint and migrate processes to new machines. Such performance driven migration normally involves the entire set of application processes. This, however, is wasteful both in terms of lost progress (if other processes can still execute) and overhead (since moving unnecessary processes is costly). To address these issues, we describe an extension of LAM/MPI that provides a partial checkpoint and migrate ability. Our system checkpoints only the subset of MPIprocesses that need to migrate. For long running applications exhibiting moderate communications, this can enhance the usefulness of shared machines for \"cluster\" computing.","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":"128453824","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":"How Do We Simulate Things at the Scale of Molecules and Electrons? An Introduction to the Technology and HPC Aspects of Computational Chemistry","authors":"T. Woo","doi":"10.1109/HPCS.2008.43","DOIUrl":"https://doi.org/10.1109/HPCS.2008.43","url":null,"abstract":"Summary form only given. Computer simulations combined with high performance computing have benefited many areas of science and engineering. Chemistry is no different. Computational chemistry involves simulating systems at the atomic and electronic level. When examining individual molecules at this microscopic scale, quantum mechanical effects are important. As a result, to get the physics 'right' we need to solve the quantum mechanical Schrodinger equation or equivalent to properly describe these systems. In this presentation, a brief introduction to the technology of modern computational chemistry and molecular scale modeling will be given. Additionally, some examples how computational chemistry has provided important insights into chemical processes is presented. A study of how anti-wear engine oil additives function at the molecular level in automobile engines is provided (Mosey, Mueser, Woo Science, 2005, 207, 1612) and our recent efforts to search in silico for new pure nitrogen analogues of diamond at high pressure is given.(Phys. Rev. Lett. 2006, 97, 155503)","PeriodicalId":290167,"journal":{"name":"2008 22nd International Symposium on High Performance Computing Systems and Applications","volume":"63 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132708740","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}