Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)最新文献
Public education in the United States is challenged by the rapidly changing skills and knowledge required by the global workforce. Technology innovation drives the evolution of workforce requirements at a pace that is roughly tied to Moore's law, with significant changes every few months to years. In contrast, significant public K-12 school reform has historically required decades. The conflict between the two evolutionary rates, orders of magnitude apart, creates a crisis for sustaining the US economy requiring urgent, innovative, and sustainable solutions. Insightful, strategic thinkers representing a coalition of national agencies and organizations launched a project designed to infuse innovative computer science curriculum into pre-college public schools through the most expeditious pathway available: creation of a new advanced placement (AP) course. The new AP exam is based on a course taught with many titles at the college level that focuses on learning objectives within computer science (CS) principles. If taught with pedagogy that includes and supports traditionally underrepresented students, the course provides diverse students with foundational understanding of the underlying logic, grammar, communication skills, and problem-solving approaches of computational thinking-- essential skills and knowledge for becoming contributors to the country's economic survival. Pilot high school courses based on college level courses that meet the above learning objectives are being introduced into high schools through a national teacher professional development initiative. The goal of this initiative, the CS 10K project, is to train ten thousand teachers to teach CS Principles in ten thousand secondary schools by the time the new AP exam unrolls in 2016-17. Several NSF projects supporting this initiative are undergoing careful evaluation. This paper describes one of these projects and its teacher, student, and district-level outcomes to date. It also considers ways that the positive outcomes might be scaled and sustained, addressing the larger challenge posed above of creating a sustainable strategy for accelerating the pace of educational adaptation to technology's more rapid global transformation.
{"title":"Clash of the Timelines: Lessons Learned from the Front Lines of CS Education","authors":"Diane A. Baxter, B. Simon","doi":"10.1145/2616498.2616574","DOIUrl":"https://doi.org/10.1145/2616498.2616574","url":null,"abstract":"Public education in the United States is challenged by the rapidly changing skills and knowledge required by the global workforce. Technology innovation drives the evolution of workforce requirements at a pace that is roughly tied to Moore's law, with significant changes every few months to years. In contrast, significant public K-12 school reform has historically required decades. The conflict between the two evolutionary rates, orders of magnitude apart, creates a crisis for sustaining the US economy requiring urgent, innovative, and sustainable solutions.\u0000 Insightful, strategic thinkers representing a coalition of national agencies and organizations launched a project designed to infuse innovative computer science curriculum into pre-college public schools through the most expeditious pathway available: creation of a new advanced placement (AP) course.\u0000 The new AP exam is based on a course taught with many titles at the college level that focuses on learning objectives within computer science (CS) principles. If taught with pedagogy that includes and supports traditionally underrepresented students, the course provides diverse students with foundational understanding of the underlying logic, grammar, communication skills, and problem-solving approaches of computational thinking-- essential skills and knowledge for becoming contributors to the country's economic survival.\u0000 Pilot high school courses based on college level courses that meet the above learning objectives are being introduced into high schools through a national teacher professional development initiative. The goal of this initiative, the CS 10K project, is to train ten thousand teachers to teach CS Principles in ten thousand secondary schools by the time the new AP exam unrolls in 2016-17. Several NSF projects supporting this initiative are undergoing careful evaluation.\u0000 This paper describes one of these projects and its teacher, student, and district-level outcomes to date. It also considers ways that the positive outcomes might be scaled and sustained, addressing the larger challenge posed above of creating a sustainable strategy for accelerating the pace of educational adaptation to technology's more rapid global transformation.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"5 1","pages":"69:1-69:5"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78193999","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}
Ivan Babic, Aaron Weeden, Mobeen Ludin, S. Thompson, Charles Peck, Kristin Muterspaw, Andrew Fitz Gibbon, Jennifer Houchins, Tom Murphy
The LittleFe/BCCD Project is a combination of hardware, software, and curriculum to facilitate the inclusion of high-performance computing (HPC), data-enabled science (DES), and computational science (CS) education in high school, undergraduate, and graduate settings. The hardware is a six-node computational cluster whose parts cost $2800, easily assembled by students in a day, and small enough to be checked on an airline. The software is a Linux distribution called Bootable Cluster CD (BCCD) that will configure a HPC cluster in under five minutes. BCCD was created in conjunction with LittleFe, and continues to be maintained alongside LittleFe. The curriculum modules are written by faculty who use LittleFe in their classrooms and cover a wide range of topics. The combination of these three has proven to be very effective in delivering HPC, DES, and CS education in this environment.
litefe /BCCD项目是硬件、软件和课程的结合，以促进高性能计算(HPC)、数据支持科学(DES)和计算科学(CS)教育在高中、本科和研究生的设置。硬件是一个六节点计算集群，其部件价值2800美元，学生一天就能轻松组装好，而且体积小到可以在飞机上检查。该软件是一个名为Bootable Cluster CD (BCCD)的Linux发行版，可以在五分钟内配置一个HPC集群。BCCD是与little lefe一起创建的，并将继续与little lefe一起维护。课程模块由在课堂上使用littleffe的教师编写，涵盖了广泛的主题。事实证明，在这种环境下，这三者的结合在提供HPC、DES和CS教育方面非常有效。
{"title":"LittleFe and BCCD as a successful on-ramp to HPC","authors":"Ivan Babic, Aaron Weeden, Mobeen Ludin, S. Thompson, Charles Peck, Kristin Muterspaw, Andrew Fitz Gibbon, Jennifer Houchins, Tom Murphy","doi":"10.1145/2616498.2616569","DOIUrl":"https://doi.org/10.1145/2616498.2616569","url":null,"abstract":"The LittleFe/BCCD Project is a combination of hardware, software, and curriculum to facilitate the inclusion of high-performance computing (HPC), data-enabled science (DES), and computational science (CS) education in high school, undergraduate, and graduate settings. The hardware is a six-node computational cluster whose parts cost $2800, easily assembled by students in a day, and small enough to be checked on an airline. The software is a Linux distribution called Bootable Cluster CD (BCCD) that will configure a HPC cluster in under five minutes. BCCD was created in conjunction with LittleFe, and continues to be maintained alongside LittleFe. The curriculum modules are written by faculty who use LittleFe in their classrooms and cover a wide range of topics. The combination of these three has proven to be very effective in delivering HPC, DES, and CS education in this environment.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"32 1","pages":"73:1-73:7"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90399368","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}
The major goals of the XSEDE Campus Bridging pilot were to simplify the transition between resources local to the researcher and those at the national scale, as well as those resources intermediary to them; to put in place software and other resources that facilitate diverse researcher workflows; and to begin resolving programming and usability issues with the software selected for these purposes. In this paper, we situate the pilot within the domain of existing research cyberinfrastructure (and in the context of campus bridging) and examine the process by which the pilot program was completed and evaluated. We then present a status update for the selected software packages and explore further advancements to be made in this realm.
{"title":"XSEDE Campus Bridging Pilot Case Study","authors":"B. Hallock, R. Knepper, J. Ferguson, C. Stewart","doi":"10.1145/2616498.2616570","DOIUrl":"https://doi.org/10.1145/2616498.2616570","url":null,"abstract":"The major goals of the XSEDE Campus Bridging pilot were to simplify the transition between resources local to the researcher and those at the national scale, as well as those resources intermediary to them; to put in place software and other resources that facilitate diverse researcher workflows; and to begin resolving programming and usability issues with the software selected for these purposes. In this paper, we situate the pilot within the domain of existing research cyberinfrastructure (and in the context of campus bridging) and examine the process by which the pilot program was completed and evaluated. We then present a status update for the selected software packages and explore further advancements to be made in this realm.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"11 1","pages":"77:1-77:5"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90767429","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}
This paper presents our experiences and outcomes using Scratch to teach parallel computing concepts to students just learning about computer science. We presented versions of this material to middle school and high school girls during a STEM workshop and then to undergraduate university students enrolled in an introductory computer science course. Using the Scratch development environment, students are able to build, modify and observe the changes in the performance of applications which utilize multi-threaded, concurrent, operations. This includes scenarios which involve more advanced topics such as race conditions and mutex locks. Developing these materials has allowed us to introduce these concepts in a programming environment much earlier than we have previously, giving instructors in down-stream courses the ability to build upon this early exposure. Survey results show that this approach resulted in a significant increase in both of these areas. For example, the number of students in our CS0 course who felt they could apply parallel programming to other problems using Scratch more than doubled, rising from 25 to 55 (out of 61 students that responded to both surveys). Likewise, the number of students who felt they understood what parallel programming means rose from 27 to 56. These results were achieved after just one class period. Similarly, 27 of the 37 girls responding to the workshop survey felt that they were capable of learning to write computer programs and 22 of 41 indicated they had an interest in a job using HPC to solve problems.
{"title":"Minimum Time, Maximum Effect: Introducing Parallel Computing in CS0 and STEM Outreach Activities Using Scratch","authors":"Russell Feldhausen, R. Bell, Daniel Andresen","doi":"10.1145/2616498.2616568","DOIUrl":"https://doi.org/10.1145/2616498.2616568","url":null,"abstract":"This paper presents our experiences and outcomes using Scratch to teach parallel computing concepts to students just learning about computer science. We presented versions of this material to middle school and high school girls during a STEM workshop and then to undergraduate university students enrolled in an introductory computer science course. Using the Scratch development environment, students are able to build, modify and observe the changes in the performance of applications which utilize multi-threaded, concurrent, operations. This includes scenarios which involve more advanced topics such as race conditions and mutex locks.\u0000 Developing these materials has allowed us to introduce these concepts in a programming environment much earlier than we have previously, giving instructors in down-stream courses the ability to build upon this early exposure. Survey results show that this approach resulted in a significant increase in both of these areas. For example, the number of students in our CS0 course who felt they could apply parallel programming to other problems using Scratch more than doubled, rising from 25 to 55 (out of 61 students that responded to both surveys). Likewise, the number of students who felt they understood what parallel programming means rose from 27 to 56. These results were achieved after just one class period. Similarly, 27 of the 37 girls responding to the workshop survey felt that they were capable of learning to write computer programs and 22 of 41 indicated they had an interest in a job using HPC to solve problems.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"396 1","pages":"75:1-75:7"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76916665","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}
Joseph P. White, R. L. Deleon, T. Furlani, S. Gallo, Matthew D. Jones, Amin Ghadersohi, Cynthia D. Cornelius, A. Patra, J. Browne, W. Barth, John L. Hammond
When a user requests less than a full node for a job on XSEDE's large resources - Stampede and Lonestar4 -, that is less than 16 cores on Stampede or 12 cores on Lonestar4, they are assigned a full node by policy. Although the actual CPU hours consumed by these jobs is small when compared to the total CPU hours delivered by these resources, they do represent a substantial fraction of the total number of jobs (~18% for Stampede and ~15% for Lonestar4 between January and February 2014). Academic HPC centers, such as the Center for Computational Research (CCR) at the University at Buffalo, SUNY typically have a much larger proportion of small jobs than the large XSEDE systems. For CCR's production cluster, Rush, the decision was made to allow the allocation of simultaneous jobs on the same node. This greatly increases the overall throughput but also raises questions whether the jobs that share the same node will interfere with one another. We present here an analysis that explores this issue using data from Rush, Stampede and Lonestar4. Analysis of usage data indicates little interference.
{"title":"An Analysis of Node Sharing on HPC Clusters using XDMoD/TACC_Stats","authors":"Joseph P. White, R. L. Deleon, T. Furlani, S. Gallo, Matthew D. Jones, Amin Ghadersohi, Cynthia D. Cornelius, A. Patra, J. Browne, W. Barth, John L. Hammond","doi":"10.1145/2616498.2616533","DOIUrl":"https://doi.org/10.1145/2616498.2616533","url":null,"abstract":"When a user requests less than a full node for a job on XSEDE's large resources - Stampede and Lonestar4 -, that is less than 16 cores on Stampede or 12 cores on Lonestar4, they are assigned a full node by policy. Although the actual CPU hours consumed by these jobs is small when compared to the total CPU hours delivered by these resources, they do represent a substantial fraction of the total number of jobs (~18% for Stampede and ~15% for Lonestar4 between January and February 2014). Academic HPC centers, such as the Center for Computational Research (CCR) at the University at Buffalo, SUNY typically have a much larger proportion of small jobs than the large XSEDE systems. For CCR's production cluster, Rush, the decision was made to allow the allocation of simultaneous jobs on the same node. This greatly increases the overall throughput but also raises questions whether the jobs that share the same node will interfere with one another. We present here an analysis that explores this issue using data from Rush, Stampede and Lonestar4. Analysis of usage data indicates little interference.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"13 1","pages":"31:1-31:8"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85051787","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}
The demand for virtualization within high-performance computing is rapidly growing as new communities, driven by both new application stacks and new computing modalities, continue to grow and expand. While virtualization has traditionally come with significant penalties in I/O performance that have precluded its use in mainstream large-scale computing environments, new standards such as Single Root I/O Virtualization (SR-IOV) are emerging that promise to diminish the performance gap and make high-performance virtualization possible. To this end, we have evaluated SR-IOV in the context of both virtualized InfiniBand and virtualized 10 gigabit Ethernet (GbE) using micro-benchmarks and real-world applications. We compare the performance of these interconnects on non-virtualized environments, Amazon's SR-IOV-enabled C3 instances, and our own SR-IOV-enabled InfiniBand cluster and show that SR-IOV significantly reduces the performance losses caused by virtualization. InfiniBand demonstrates less than 2% loss of bandwidth and less than 10% increase in latency when virtualized with SR-IOV. Ethernet also benefits, although less dramatically, when SR-IOV is enabled on Amazon's cloud.
{"title":"SR-IOV: Performance Benefits for Virtualized Interconnects","authors":"Glenn K. Lockwood, M. Tatineni, R. Wagner","doi":"10.1145/2616498.2616537","DOIUrl":"https://doi.org/10.1145/2616498.2616537","url":null,"abstract":"The demand for virtualization within high-performance computing is rapidly growing as new communities, driven by both new application stacks and new computing modalities, continue to grow and expand. While virtualization has traditionally come with significant penalties in I/O performance that have precluded its use in mainstream large-scale computing environments, new standards such as Single Root I/O Virtualization (SR-IOV) are emerging that promise to diminish the performance gap and make high-performance virtualization possible.\u0000 To this end, we have evaluated SR-IOV in the context of both virtualized InfiniBand and virtualized 10 gigabit Ethernet (GbE) using micro-benchmarks and real-world applications. We compare the performance of these interconnects on non-virtualized environments, Amazon's SR-IOV-enabled C3 instances, and our own SR-IOV-enabled InfiniBand cluster and show that SR-IOV significantly reduces the performance losses caused by virtualization. InfiniBand demonstrates less than 2% loss of bandwidth and less than 10% increase in latency when virtualized with SR-IOV. Ethernet also benefits, although less dramatically, when SR-IOV is enabled on Amazon's cloud.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"92 1","pages":"47:1-47:7"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84094715","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}
"Tell me, I'll forget, Show me, I may remember, Involve me, I'll understand." - Confucius This proverb describes the essence of our paper and the motivation behind the development of the Interactive Parallelization Tool (IPT) that can transform serial applications into multiple parallel variants. The end-users of IPT must have an understanding of the basic concepts involved in parallel programming (e.g., data distribution and data gathering). After developing an understanding of the basic parallel programming concepts, IPT can be used by its target audience (domain-experts and students) to semi-automatically generate parallel programs using multiple parallel programming paradigms (MPI, OpenMP, and CUDA), and learn about these paradigms through observation and comparison. This IPT-based personalized learning approach complements the traditional methods of learning and training that usually emphasize the syntax and semantics of one or more programming standards. The main benefit of IPT is that it provides a jumpstart to the domain-experts in using modern HPC platforms for their research and development needs, and hence lowers the adoption barriers to HPC.
{"title":"A Tool for Interactive Parallelization","authors":"R. Arora, Julio C. Olaya, Madhav Gupta","doi":"10.1145/2616498.2616558","DOIUrl":"https://doi.org/10.1145/2616498.2616558","url":null,"abstract":"\"Tell me, I'll forget,\u0000 Show me, I may remember,\u0000 Involve me, I'll understand.\" - Confucius\u0000 This proverb describes the essence of our paper and the motivation behind the development of the Interactive Parallelization Tool (IPT) that can transform serial applications into multiple parallel variants. The end-users of IPT must have an understanding of the basic concepts involved in parallel programming (e.g., data distribution and data gathering). After developing an understanding of the basic parallel programming concepts, IPT can be used by its target audience (domain-experts and students) to semi-automatically generate parallel programs using multiple parallel programming paradigms (MPI, OpenMP, and CUDA), and learn about these paradigms through observation and comparison. This IPT-based personalized learning approach complements the traditional methods of learning and training that usually emphasize the syntax and semantics of one or more programming standards. The main benefit of IPT is that it provides a jumpstart to the domain-experts in using modern HPC platforms for their research and development needs, and hence lowers the adoption barriers to HPC.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"6 1","pages":"51:1-51:8"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84269698","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}
As the availability of computing infrastructure continues to increase, so too does the need for accessible means for utilizing those resources. An effective approach is to enable desktop-oriented scientific software tools and frameworks to support execution on high performance cyberinfrastructure in a way that is transparent to the user. We have found this to be the case in our ongoing environmental modeling study in which we are applying multidisciplinary, integrated models to the study of a depleting aquifer. Our models are linked together using the Open Modeling Interface (OpenMI) which provides a composition framework for the sequential execution of model components. In this work we investigate the potential for incorporating parallelism into the OpenMI as a first-class citizen. We present a general solution in which model components may be executed in parallel without requiring changes to their source code. An alternate solution achieves greater parallelism through simultaneous invocations of individual components, but requires them to be modified in some cases. These can result in significant reductions in simulation runtimes on both multi-core desktop machines as well as in high performance computing environments. We demonstrate this potential speedup in a performance study in which the application of the general solution achieved 86% of linear speedup when executed on a high performance machine with 80 cores.
{"title":"Accessible Parallelization for the Open Modeling Interface","authors":"Tom Bulatewicz, Daniel Andresen","doi":"10.1145/2616498.2616566","DOIUrl":"https://doi.org/10.1145/2616498.2616566","url":null,"abstract":"As the availability of computing infrastructure continues to increase, so too does the need for accessible means for utilizing those resources. An effective approach is to enable desktop-oriented scientific software tools and frameworks to support execution on high performance cyberinfrastructure in a way that is transparent to the user. We have found this to be the case in our ongoing environmental modeling study in which we are applying multidisciplinary, integrated models to the study of a depleting aquifer. Our models are linked together using the Open Modeling Interface (OpenMI) which provides a composition framework for the sequential execution of model components. In this work we investigate the potential for incorporating parallelism into the OpenMI as a first-class citizen. We present a general solution in which model components may be executed in parallel without requiring changes to their source code. An alternate solution achieves greater parallelism through simultaneous invocations of individual components, but requires them to be modified in some cases. These can result in significant reductions in simulation runtimes on both multi-core desktop machines as well as in high performance computing environments. We demonstrate this potential speedup in a performance study in which the application of the general solution achieved 86% of linear speedup when executed on a high performance machine with 80 cores.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"36 1","pages":"52:1-52:8"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81638902","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}
Virginia Kuhn, Michael Simeone, Luigi Marini, Dave Bock, Alan B. Craig, Liana Diesendruck, Sandeep Puthanveetil Satheesan
In this paper we describe our efforts at establishing a software workbench for video analysis, annotation, and visualization, using both current and experimental discovery methods. This project builds upon our previous research with video and image analysis, and joins the emergent field of cultural analytics in the digital humanities. Moving image media is particularly ripe for computational analysis given its increasing ubiquity in contemporary culture. Hoping to make video more legible as a big data format, we employ visual media in the public domain and we focus on crowd-sourced annotation, aural and visual analysis and visualization of extracted image data. Our goal is to fill in existing gaps for asking cultural questions about video archives using computers, we also experiment with transformative methods in video research and analysis. Our long term goal is to allow researchers to move with agility from textual description and collection management, to manual inspection, to automated analysis, to visualization of discrete films as well as whole collections.
{"title":"MOVIE: Large Scale Automated Analysis of MOVing ImagEs","authors":"Virginia Kuhn, Michael Simeone, Luigi Marini, Dave Bock, Alan B. Craig, Liana Diesendruck, Sandeep Puthanveetil Satheesan","doi":"10.1145/2616498.2616529","DOIUrl":"https://doi.org/10.1145/2616498.2616529","url":null,"abstract":"In this paper we describe our efforts at establishing a software workbench for video analysis, annotation, and visualization, using both current and experimental discovery methods. This project builds upon our previous research with video and image analysis, and joins the emergent field of cultural analytics in the digital humanities. Moving image media is particularly ripe for computational analysis given its increasing ubiquity in contemporary culture. Hoping to make video more legible as a big data format, we employ visual media in the public domain and we focus on crowd-sourced annotation, aural and visual analysis and visualization of extracted image data. Our goal is to fill in existing gaps for asking cultural questions about video archives using computers, we also experiment with transformative methods in video research and analysis. Our long term goal is to allow researchers to move with agility from textual description and collection management, to manual inspection, to automated analysis, to visualization of discrete films as well as whole collections.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"77 1","pages":"21:1-21:3"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84449422","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}
The Revision Control System (RCS) is an essential aspect of software development process and software configuration management. While continuing to be an integral component of the real world, it is often left out of the main stream curriculum in most academic institutions. Instead, students are expected to learn it on their own, as a hobby or as an independent study, out of personal interest. The author describes the experiences gained from attempting to implement a distributed Revision Control System, Git, as part of the computational sciences and engineering curriculum at the undergraduate and graduate levels. The author also describes the advantages for both parties involved: improving the competency of students and preparing them for the real world expectations while providing the teacher an opportunity to provide timely feedback to the students and monitor their progress. The availability of free and open source tools used to analyze and visualize the commit history to the repository helps teachers and students observe submission and feedback patterns respectively.
{"title":"Revision Control System (RCS) in computational sciences and engineering curriculum","authors":"S. Gowtham","doi":"10.1145/2616498.2616576","DOIUrl":"https://doi.org/10.1145/2616498.2616576","url":null,"abstract":"The Revision Control System (RCS) is an essential aspect of software development process and software configuration management. While continuing to be an integral component of the real world, it is often left out of the main stream curriculum in most academic institutions. Instead, students are expected to learn it on their own, as a hobby or as an independent study, out of personal interest. The author describes the experiences gained from attempting to implement a distributed Revision Control System, Git, as part of the computational sciences and engineering curriculum at the undergraduate and graduate levels. The author also describes the advantages for both parties involved: improving the competency of students and preparing them for the real world expectations while providing the teacher an opportunity to provide timely feedback to the students and monitor their progress. The availability of free and open source tools used to analyze and visualize the commit history to the repository helps teachers and students observe submission and feedback patterns respectively.","PeriodicalId":93364,"journal":{"name":"Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)","volume":"360 1","pages":"76:1-76:3"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76441356","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}
Proceedings of XSEDE16 : Diversity, Big Data, and Science at Scale : July 17-21, 2016, Intercontinental Miami Hotel, Miami, Florida, USA. Conference on Extreme Science and Engineering Discovery Environment (5th : 2016 : Miami, Fla.)
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：