Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery最新文献

{"title":"The parallel system for integrating impact models and sectors (pSIMS)","authors":"J. Elliott, David Kelly, N. Best, M. Wilde, M. Glotter, Ian T Foster","doi":"10.1145/2484762.2484814","DOIUrl":"https://doi.org/10.1145/2484762.2484814","url":null,"abstract":"We present a framework for massively parallel simulations of climate impact models in agriculture and forestry: the parallel System for Integrating Impact Models and Sectors (pSIMS). This framework comprises a) tools for ingesting large amounts of data from various sources and standardizing them to a versatile and compact data type; b) tools for translating this standard data type into the custom formats required for point-based impact models in agriculture and forestry; c) a scalable parallel framework for performing large ensemble simulations on various computer systems, from small local clusters to supercomputers and even distributed grids and clouds; d) tools and data standards for reformatting outputs for easy analysis and visualization; and d) a methodology and tools for aggregating simulated measures to arbitrary spatial scales such as administrative districts (counties, states, nations) or relevant environmental demarcations such as watersheds and river-basins. We present the technical elements of this framework and the results of an example climate impact assessment and validation exercise that involved large parallel computations on XSEDE.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131408063","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":"Enhancing the performance of scientific workflow execution in e-science environments by harnessing the standards based parameter sweep model","authors":"M. S. Memon, M. Riedel, Sonja Holl, B. Schuller, A. Grimshaw","doi":"10.1145/2484762.2484820","DOIUrl":"https://doi.org/10.1145/2484762.2484820","url":null,"abstract":"Certain scientific use cases possess complex requirements to have Grid jobs executed in collections where the jobs' request contains only some variation in different parts. These scenarios can easily be tackled by a single job request which abstract this variation and can represent the same collection. The Open Grid Forum (OGF) standards community modeled this requirement through the Job Submission and Description Language (JSDL) Parameter Sweep specification, which takes a modular approach to handle different variations of parameter sweeps (e.g. document and file sweep). In this paper we present the UNICORE server environment implementing this specification build upon its existing JSDL implementation. We also demonstrate the application of UNICORE's parameter sweep extension for optimizing job executions, which are submitted as a sub-activity of a Taverna based scientific workflow. Further we validate our approach by analyzing performance of the workflow with and without using the parameter sweep extension.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116889875","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 framework for flexible and scalable replica-exchange on production distributed CI","authors":"B. Radak, Tai-Sung Lee, Peng He, Melissa Romanus, Ole Weidner, Wei Dai, Emilio Gallicchio, N. Deng, D. York, R. Levy, S. Jha","doi":"10.1145/2484762.2484830","DOIUrl":"https://doi.org/10.1145/2484762.2484830","url":null,"abstract":"Replica exchange represents a powerful class of algorithms used for enhanced configurational and energetic sampling in a range of physical systems. Computationally it represents a type of application with multiple scales of communication. At a fine-grained level there is often communication with a replica, typically an MPI process. At a coarse-grained level, the replicas communicate with other replicas -- both temporally as well as in amount of data exchanged. This paper outlines a novel framework developed to support the flexible execution of large-scale replica exchange. The framework is flexible in the sense that it supports different coupling schemes between replicas and is agnostic to the specific underlying simulation -- classical or quantum, serial or parallel simulation. The scalability of the framework is assessed using standard simulation benchmarks. In spite of the increasing communication and coordination requirements as a function of the number of replicas, our framework supports the execution of hundreds replicas without significant overhead. Although there are several specific aspects that will benefit from further optimization, a first working prototype has the ability to fundamentally change the scale of replica exchange simulations possible on production distributed cyberinfrastructure such as XSEDE, as well as support novel usage modes. This paper also represents the release of the framework to the broader biophysical simulation community and provides details on its usage.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121571113","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":"MuMMI: multiple metrics modeling infrastructure for exploring performance and power modeling","authors":"Xingfu Wu, Hung-Ching Chang, S. Moore, V. Taylor, Chun-Yi Su, D. Terpstra, Charles W. Lively, K. Cameron, Chee Wai Lee","doi":"10.1145/2484762.2484773","DOIUrl":"https://doi.org/10.1145/2484762.2484773","url":null,"abstract":"MuMMI (Multiple Metrics Modeling Infrastructure) environment is an infrastructure that facilitates systematic measurement, modeling, and prediction of performance, power consumption and performance-power tradeoffs for parallel systems. MuMMI builds upon three existing frameworks: Prophesy for performance modeling and prediction of parallel applications, PAPI for hardware performance counter monitoring, and PowerPack for power measurement and profiling. In this paper, we present the MuMMI framework, which consists of an Instrumentor, Databases and Analyzer. The MuMMI Instrumentor provides automatic performance and power data collection and storage with low overhead. The MuMMI Databases extend the databases of Prophesy to store power and energy consumption and hardware performance counters' data with different CPU frequency settings. The MuMMI Analyzer extends the data analysis component of Prophesy to support power consumption and hardware performance counters, and it entails performance and power modeling, performance-power tradeoff and optimizations, and web-based automated modeling system. Currently, our MuMMI online automated performance and power modeling system uses four modeling techniques: curve fitting, parameterization, kernel coupling and performance-counters-based, we discuss the effort to automate the process of developing performance and power models for scientific applications online, and focus on exploring performance-counters-based performance and power modeling. The MuMMI environment is able to aid in performance and power data measurement, storage, modeling and prediction of scientific applications on XSEDE resources in XSEDE community.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122859593","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":"Exploring Twitter networks in parallel computing environments","authors":"Bo Xu, Yun Huang, N. Contractor","doi":"10.1145/2484762.2484811","DOIUrl":"https://doi.org/10.1145/2484762.2484811","url":null,"abstract":"Millions of users follow each other on Twitter and form a large and complex network. The size of the network creates statistical and computational challenges on exploring and examining individual behavior on Twitter. Using a sample of 697,628 Korean Twitter users and 34 million relations, this study investigates the patterns of unfollow behavior on Twitter, i.e. people removing others from their Twitter follow lists. We use Exponential Random Graph Models (p*/ERGMs) and Statnet in R to examine the impacts of reciprocity, status, embeddedness, homophily, and informativeness on tie dissolution. We perform data processing, statistics calculation, network sampling, and Markov chain Monte Carlo (MCMC) simulation on Gordon, a unique supercomputer at the San Diego Supercomputer Center (SDSC). The process demonstrates the role of advanced computing technologies in social science studies.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"138 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128770216","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":"Integration of science gateways: a case study with CyberGIS and OpenTopography","authors":"Anand Padmanabhan, C. Youn, Myunghwa Hwang, Yan Y. Liu, Shaowen Wang, Nancy Wilkins-Diehr, C. Crosby","doi":"10.1145/2484762.2484808","DOIUrl":"https://doi.org/10.1145/2484762.2484808","url":null,"abstract":"Science gateways are collaborative software environments designed to enable community-driven development and use of cyberinfrastructure services, software tools, applications, and data through common interfaces, typically an online portal, customized to meet the needs of individual communities [1]. By abstracting the assemblage of cyberinfrastructure needed by the research communities and democratizing access to high-end computational resources, science gateways (e.g. those on XSEDE) provide a shared problem-solving environment and promote collaborations among community users. The integration work presented here represents a cutting-edge approach to coupling two independent geospatial software environments developed separately, namely CyberGIS [2] and OpenTopography [3]. CyberGIS -- defined as cyberinfrastructure-based geographic information systems (GIS) -- represents a new generation of GIS based on seamless synthesis of cyberinfrastructure, geographic information science, and spatial analysis and modeling [4]. Funded by the National Science Foundation (NSF), the CyberGIS project (http://cybergis.org) advances the science of CyberGIS, with a particular focus on enabling the analysis of big spatial datasets, computationally intensive spatial analysis and modeling, and collaborative geospatial problem solving and decision making [2]. The CyberGIS Gateway provides an online, high-performance and collaborative geospatial problem-solving environment to allow for the contribution, sharing of and access to CyberGIS services and tools by a broad community of geospatial scientists and GIS users. As a NSF cyberinfrastructure-based data facility, OpenTopography (http://opentopography.org) provides its community with access to high-resolution Earth science oriented topography data, related tools and geoprocessing applications published as a suite of Web services. All Web services are built and deployed by leveraging the open source Opal toolkit (http://www2.nbcr.net/data/docs/opal/), which provides a mechanism to streamline the process of encapsulating existing scientific applications as Web services. CyberGIS and OpenTopography represent two software environments that complement each other; with CyberGIS providing access to cyberinfrastructure-based spatial data and related analytics and OpenTopography serving as a data source of LiDAR-based high-resolution terrain data. Hence, integrating these software environments will extend their capabilities, improve their usability and bring benefits to the science communities by enabling large-scale geospatial problem solving through shared interoperable analytical and data services. The goal of this integration is to make seamless access to OpenTopography data when an analysis is planned on the CyberGIS Gateway and vice versa. More importantly, this work demonstrates multiple innovative aspects of software integration research and development that could serve as a template for integrating other such independently","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"71 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120892555","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 Maya use case: adaptable scientific workflows with ADIOS for general relativistic astrophysics","authors":"M. Slawinska, Michael Clark, M. Wolf, Tanja Bode, Hongbo Zou, P. Laguna, Jeremy S. Logan, Matthew Kinsey, S. Klasky","doi":"10.1145/2484762.2484795","DOIUrl":"https://doi.org/10.1145/2484762.2484795","url":null,"abstract":"There are many challenges in analyzing and visualizing data from current cutting-edge general relativistic astrophysics simulations. Many of the associated tasks are time-consuming with large performance degradation due to the magnitude and complexity of the data. The Adaptable I/O System (ADIOS) is a componentization of the I/O layer that has demonstrated remarkable I/O performance improvements on applications running on leadership class machines while also offering new in-memory \"staging\" operations for transforming data in-situ. We have been incorporating ADIOS staging technologies into our Maya numerical relativity code based on Cactus infrastructure and Carpet mesh refinement. Incorporating ADIOS into the Maya code is the first step toward enabling a more adaptable Maya workflow. We provide descriptions how we intend to leverage FlexPath (an ADIOS transport method) to provide a richer user experience in real-time visualization and interactive steering.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122480198","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":"HPC university: getting information about computational science professional and educational resources and opportunities for engagement","authors":"Scott A. Lathrop, Ange Mason, S. Gordon, M. Faerman","doi":"10.1145/2484762.2484771","DOIUrl":"https://doi.org/10.1145/2484762.2484771","url":null,"abstract":"This paper describes the HPC University website and how it can be utilized to obtain information about computational science and high performance computing education and training resources, opportunities for student internships, shared educational materials, and news and information about HPC related events. The site provides access to a variety of materials relating to HPC events and education and training at a single site.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127468043","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":"Making campus bridging work for researchers: a case study with mlRho","authors":"A. Thota, B. Haubold, Scott Michael, T. Doak, Sen Xu, R. Henschel","doi":"10.1145/2484762.2484803","DOIUrl":"https://doi.org/10.1145/2484762.2484803","url":null,"abstract":"An increasing number of biologists' computational demands have outgrown the capacity of desktop workstations and they are turning to supercomputers to run their simulations and calculations. Many of today's computational problems, however, require larger resource commitments than even individual universities can provide. XSEDE is one of the first places researchers turn to when they outgrow their campus resources. XSEDE machines are far larger (by at least an order of magnitude) than what most universities offer. Transitioning from a campus resource to an XSEDE resource is seldom a trivial task. XSEDE has taken many steps to make this easier, including the Campus Bridging initiative, the Campus Champions program, the Extended Collaborative Support Service (ECSS) [1] program, and through education and outreach. In this paper, our team of biologists and application support analysts (including a Campus Champion) dissect a computationally intensive biology project and share the insights we gain to help strengthen the programs mentioned above. We worked on a project to calculate population mutation and recombination rates of tens of genome profiles using mlRho [2], a serial, open-source, genome analysis code. For the initial investigation, we estimated that we would need 6.3 million service units (SUs) on the Ranger system. Three of the most important places where the biologists needed help in transitioning to XSEDE were (i) preparing the proposal for 6.3 million SUs on XSEDE, (ii) scaling up the existing workflow to hundreds of cores and (iii) performance optimization. The Campus Bridging initiative makes all of these tasks easier by providing tools and a consistent software stack across centers. Ideally, Campus Champions are able to provide support on (i), (ii) and (iii), while ECSS staff can assist with (ii) and (iii). But (i), (ii) and (iii) are often not part of a Campus Champion's regular job description. To someone writing an XSEDE proposal for the first time, a link to the guidelines and a few pointers may not always be enough for a successful application. In this paper we describe a new role for a campus bridging expert to play in closing the gaps between existing programs and present mlRho as a case study.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"43 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130769839","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":"Scalable online comparative genomics of mononucleosomes: a BigJob","authors":"Jack A. Smith, Y. E. Khamra, Melissa Romanus, T. Bishop, P. Mantha, S. Jha","doi":"10.1145/2484762.2484819","DOIUrl":"https://doi.org/10.1145/2484762.2484819","url":null,"abstract":"Our goal is to develop workflows for simulating arbitrary collections of mononucleosomes in atomic detail as an on demand analysis tool for online comparative genomics. The limiting factor is resource availability. The aim of this paper is to document and share our experiences in providing a general-purpose, easy-to-use and extensible solution for such computations. At the core it involves supporting the execution of high-throughput workloads of high-performance biomolecular simulations on one or more XSEDE machines. Although conceptually simple, it is still a difficult practical problem to solve, especially in a flexible, robust, scalable manner. Specifically, we employ BigJob-- an interoperable Pilot-Job. The bulk of this paper is about our experience in executing a very large number of ensembles including the associated non-trivial data management problem. Our experience suggests that although a nascent and fledgling technology, BigJob provides a flexible and scalable Pilot-Job to support workloads that were hitherto not easy.","PeriodicalId":426819,"journal":{"name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","volume":"232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115120449","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}