Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)最新文献

Leveraging Public Cloud Services for CLIA-Certified Personalized Medicine Pipelines 利用公共云服务实现clia认证的个性化医疗管道

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332244

Evan F. Bollig, C. Henzler, H. Lam, S. Munro, R. LaRue, Getiria Onsongo, S. Yohe, A. Nelson, Matthew Bower, Matthew Schomaker, B. Thyagarajan

{"title":"Leveraging Public Cloud Services for CLIA-Certified Personalized Medicine Pipelines","authors":"Evan F. Bollig, C. Henzler, H. Lam, S. Munro, R. LaRue, Getiria Onsongo, S. Yohe, A. Nelson, Matthew Bower, Matthew Schomaker, B. Thyagarajan","doi":"10.1145/3332186.3332244","DOIUrl":"https://doi.org/10.1145/3332186.3332244","url":null,"abstract":"Dating back to 2012, a joint effort between Fairview Hospital's Molecular Diagnostic Lab and the Minnesota Supercomputing Institute introduced the Next-Generation Sequencing Diagnostic Pipeline (NGSDP) [17, 20], a novel cloud-based analysis pipeline that was validated for clinical use to be compliant with the Clinical Laboratory Improvement Amendments (CLIA). Since then, the partnership has grown the portfolio of active pipelines to seven, and expanded the available gene panels to over 6700 genes. Likewise, the design of the backing cloud infrastructure has been significantly overhauled for efficiency, scalability, automation, and fault tolerance. This document introduces our revised cloud-native, scheduled infrastructure solution for containerized applications. The cloud-native infrastructure, deployed on Amazon Web Services, has two core components: a compute cluster of virtual machines, and a simple queue-based job scheduler. The cluster runs analysis pipelines packaged as Docker containers; each with their own resource requirements. The scheduler, akin to products for traditional HPC, allows batch submission of patient samples with a persistent job queue. The scheduler also orchestrates cluster scale-out and -in to match job needs in an effort to minimize idle servers and reduce the cost of computing on a public cloud. Our solution has been successfully running as CLIA-validated pipelines since 2016. Two variants of the solution are presented to address the need for such architecture in both the traditional public cloud space, as well as in Amazon's GovCloud where fewer cloud services are available to handle sensitive or controlled-access data. Furthermore, the innovative solution is driven by a traditional research computing environment; details of which are presented with emphasis on security, monitoring, and user workflow.","PeriodicalId":422540,"journal":{"name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121208612","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}

引用次数: 1

Cultivating the Cyberinfrastructure Workforce via an Intermediate/Advanced Virtual Residency Workshop 通过中级/高级虚拟实习工作坊培养网络基础设施劳动力

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332204

Henry Neeman, Hussein M. Al-Azzawi, D. Brunson, William Burke, D. Colbry, J. Falgout, James W. Ferguson, S. Gesing, Joshua V. Gyllinsky, Christopher S. Simmons, Jason L. Simms, Mohammed Tanash, D. Voss, Jason Wells, Scott Yockel

{"title":"Cultivating the Cyberinfrastructure Workforce via an Intermediate/Advanced Virtual Residency Workshop","authors":"Henry Neeman, Hussein M. Al-Azzawi, D. Brunson, William Burke, D. Colbry, J. Falgout, James W. Ferguson, S. Gesing, Joshua V. Gyllinsky, Christopher S. Simmons, Jason L. Simms, Mohammed Tanash, D. Voss, Jason Wells, Scott Yockel","doi":"10.1145/3332186.3332204","DOIUrl":"https://doi.org/10.1145/3332186.3332204","url":null,"abstract":"Cyberinfrastructure (CI) Facilitation is the process of helping researchers to use research computing systems and services to advance their computing-intensive/data-intensive research goals. The growing need for CI Facilitation isn't being met by traditional academic degree and certificate programs, so informal education is required. The Virtual Residency (VR) is a program that teaches key CI Facilitation skills to CI Facilitators. Using a combination of (a) workshops, (b) biweekly conference calls, (c) a Grant Proposal Writing Apprenticeship and (d) a new Paper Writing Apprenticeship, the VR has been teaching CI Facilitation since 2015. During the summers of 2015-17, the annual VR workshop was at an introductory level, driving demand for a higher level workshop. In 2018, the VR workshop was presented at a level described as intermediate, but in practice it included a great deal of advanced content, concentrated on institutional CI leadership. The 2018 focus areas were: (1) in-depth CI expertise in areas of rapidly changing technology; (2) CI leadership; (3) funding acquisition skills; (4) outreach strategies, techniques, and skills; (5) communication skills. The 2018 VR workshop served 216 participants from 147 institutions in 42 US states and 2 US territories plus 2 other countries.","PeriodicalId":422540,"journal":{"name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125020356","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}

引用次数: 8

Wrangling Rogues: A Case Study on Managing Experimental Post-Moore Architectures Wrangling Rogues:管理实验性后摩尔架构的案例研究

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332223

Will Powell, E. J. Riedy, Jeffrey S. Young, T. Conte

引用次数: 2

Traps, Pitfalls and Misconceptions of Machine Learning applied to Scientific Disciplines 应用于科学学科的机器学习的陷阱、陷阱和误解

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332209

D. D. Vento, A. Fanfarillo

{"title":"Traps, Pitfalls and Misconceptions of Machine Learning applied to Scientific Disciplines","authors":"D. D. Vento, A. Fanfarillo","doi":"10.1145/3332186.3332209","DOIUrl":"https://doi.org/10.1145/3332186.3332209","url":null,"abstract":"In the last decade, Machine Learning has experienced a dramatic increase in performance on a wide variety of tasks, including computer vision, speech recognition, text parsing, and language translation, just to name a few. This has corresponded to an understandable hype especially for the remarkable results achieved in some cases. Therefore, practitioners of Scientific Disciplines have become interested in utilizing new Machine Learning techniques, and have sometimes started doing so with mixed success. The purpose of this paper is to describe some of the common Traps, Pitfalls and Misconceptions of Machine Learning as relevant to the Scientific Discipline, and how to avoid them. In fact, Machine Learning and Deep Learning are fast evolving fields, and some of the astonishing results achieved recently sit on small but important details which have become the state of the art. Some of these details are not broadly known by the scientific community. No new scientific result is presented in this paper, which is a survey and a summary of the best of the field, for the benefit of researchers with limited experience. It is not the intention of the authors to provide any criticism to the work of experienced practitioners, particularly not to the ones working on the cutting edge of what is currently possible: in these cases expert researchers may well be doing exactly what we recommend here to avoid, and for a good reason. However we believe that the advice provided here will be useful, and perhaps even a reference, for the newcomers of the field.","PeriodicalId":422540,"journal":{"name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122202126","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}

引用次数: 8

A Novel Pruning Method for Convolutional Neural Networks Based off Identifying Critical Filters 一种基于识别关键滤波器的卷积神经网络剪枝方法

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3333057

Mihaela Dimovska, T. Johnston

{"title":"A Novel Pruning Method for Convolutional Neural Networks Based off Identifying Critical Filters","authors":"Mihaela Dimovska, T. Johnston","doi":"10.1145/3332186.3333057","DOIUrl":"https://doi.org/10.1145/3332186.3333057","url":null,"abstract":"Convolutional Neural Networks (CNNs) are one of the most extensively used tools in machine learning, but they are still not well understood and in many cases they are over-parameterized, leading to slow inference and impeding their deployment on low-power devices. In the last few years, many methods for decreasing the number of parameters in a network by pruning its output channels have been suggested, but a very recent work has argued that random pruning of channels performs on-par with state-of-the-art pruning methods. While random and other pruning methods might be effectively used for lowering the number of parameters in a CNN, none of these methods can be used to gain any further understanding of the model that the CNN has built. In this work, we propose a novel method for pruning a network, that at the same time can lead to a better understanding of what the individual filters of the network learn about the data. The method proposed aims to keep only the filters that are \"important\" for a class. We define a filter as important for a class if its removal has the highest negative impact on the accuracy for that class. We demonstrate that our method is better than random pruning on two networks used on the EMNIST and CIFAR10 datasets. By analyzing the important filters, we find that the important filters in the pruned networks learn features which are more general across classes. We demonstrate the importance and applicability of that observation in two transfer-learning tasks.","PeriodicalId":422540,"journal":{"name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117037607","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}

引用次数: 2

Harmony 和谐

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332254

Cameron Kuchta, R. Budiardja, V. G. V. Larrea

引用次数: 2

Good Enough Project Management Practices for Researcher Support Projects 研究人员支持项目的足够好的项目管理实践

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332198

C. Maimone

引用次数: 2

Software-Enhanced Teaching and Visualization Capabilities of an Ultra-High-Resolution Video Wall 超高分辨率视频墙的软件增强教学和可视化功能

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3333149

R. Zon, Marcelo Ponce

引用次数: 1

In-situ Analysis and Visualization of Earthquake Simulation 地震模拟的现场分析与可视化

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332201

D. Mu, Jon Moran, Hui Zhou, Yifeng Cui, R. Hawkins, M. Tatineni, Steve Campbell

{"title":"In-situ Analysis and Visualization of Earthquake Simulation","authors":"D. Mu, Jon Moran, Hui Zhou, Yifeng Cui, R. Hawkins, M. Tatineni, Steve Campbell","doi":"10.1145/3332186.3332201","DOIUrl":"https://doi.org/10.1145/3332186.3332201","url":null,"abstract":"Nowadays, numerical simulation has played a vital role in analyzing and assessing earthquakes and their affects. Storage I/O performance and network bandwidth have not kept pace with the growth of computing power; as a result, post-processing has become a bottleneck to end-to-end simulation performance. One approach to solving this performance imbalance is to reduce the amount of output data by implementing in-situ visualization, which constructs the visualization concurrent with the simulation. In this paper, we propose a new software utility named \"awp-odc-insitu\" that is based on the well-known open-source seismic simulation software \"awp-odc-os\" and capable of performing in-situ visualization functionality by employing the open-source data analysis and visualization application \"ParaView\" and its in-situ library \"ParaView Catalyst\". Moreover, the paper discusses the implementation of in-situ functionality and analyzes the performance and efficiency of the \"awp-odc-insitu\" code to demonstrate the code is of potential use in practical seismic research.","PeriodicalId":422540,"journal":{"name":"Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121913886","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}

引用次数: 2

GenApp, Containers and Abaco: Technical Paper GenApp，容器和Abaco:技术论文

Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning) Pub Date : 2019-07-28 DOI: 10.1145/3332186.3332191

E. Brookes, Joe Stubbs

引用次数: 1