Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Open Science”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12

Open Watershed Science by Design: Leveraging Distributed Research Networks to Understand Watershed Systems: Workshop Report

The workshop upon which this report is based was convened in response to a community-recognized need for greater openness and coordination of multiwatershed distributed research efforts that integrate across capabilities within the U.S. Department of Energy’s (DOE) Office of Biological and Environmental Research (BER) and link to those of other agencies. The science enabled by such an approach targets challenges and strategic directions articulated in the Biological and Environmental Research Advisory Committee’s (BERAC) 2017 grand challenges report (BERAC 2017) and the 2018 Climate and Environmental Sciences Division (CESD) strategic plan (U.S. DOE 2018). The BERAC report and CESD strategic plan both focus heavily on the need for integrative research to connect environmental microbes, multiomics, plant system dynamics, biogeochemical interactions, and hydrological processes to understand ecosystem function. The need to develop such connections across scales of space, time, and biological complexity is framed in the context of improving predictions of the Earth system in response to disturbance, including extreme events. This report summarizes the discussions and ideas that came from the watershed systems research community on how to use integrated, coordinated, open, and community-networked watershed science to advance BER’s efforts to link fundamental processes to emergent properties of watershed structure, function, and evolution. The ultimate goal is to enhance predictive capacity across scales up to the integrated Earth system.

54 ENVIRONMENTAL SCIENCES↗

2023 Operational Assessment Report: Argonne Leadership Computing Facility

In 2004, the U.S. Department of Energy’s (DOE’s) Advanced Scientific Computing Research (ASCR) program established the Leadership Computing Facility (LCF) with a mission to provide the world’s most advanced computational resources to the open science community. The LCF is a huge investment in the nation’s scientific and technological future, inspired by a growing demand for large-scale computing and its impact on science and engineering. The LCF operates two world-class centers in support of open science at Argonne National Laboratory (Argonne) and at Oak Ridge National Laboratory (Oak Ridge) and deploys diverse machines that are among the most powerful systems in the world today. The LCF ranks among the top U.S. scientific facilities delivering impactful science. The work performed at these centers informs policy decisions and advances innovations in far-reaching areas such as energy assurance, ecological sustainability, and global security. The leadership-class systems at Argonne and Oak Ridge operate around the clock every day of the year. The high level of services these centers provide and the exceptional science they produce justify their existence to the DOE Office of Science and the U.S. Congress

97 MATHEMATICS AND COMPUTING↗

Biomass Harmonization and SAR Analysis with the Multi-mission Algorithm and Analysis Platform (MAAP)

The Multi‐mission Algorithm and Analysis Platform (MAAP) is a collaborative effort between NASA and the European Space Agency (ESA) to support above ground biomass (AGB) research in an open science framework. MAAP brings together relevant data, algorithms, and computing capabilities in a common cloud environment to address the challenges of sharing and processing data from field, airborne and satellite measurements. MAAP was publicly released in October 2021, providing computing capabilities co-located with the data, a collaborative coding and analysis environment, and a set of interoperable tools and algorithms developed to support the estimation and visualization of data. MAAP has allowed scientists from both North America and Europe to collaborate on the generation and analysis/visualization of data derived from multiple, discipline-adjacent missions in an open, collaborative environment that has reached beyond traditional scientific investigation. MAAP has been used to support multiple scientific activities. To date, existing LiDAR data from multiple platforms has been calibrated with field measurements and combined for more comprehensive and accurate estimates of above ground biomass AGB; these LiDAR platforms include airborne (e.g. LVIS), the International Space Station (NASA’s Global Ecosystem Dynamics Investigation (GEDI), and satellites (e.g. ICESat-2). The current challenge is to effectively and seamlessly combine the aforementioned LiDAR-based data with new data sources such as P-band RADAR from ESA’s upcoming BIOMASS mission, existing ESA Sentinel-1 C-band SAR, and the 30 PB/yr of high cadence global coverage L-band SAR data from the upcoming NASA-ISRO SAR (NISAR) mission. Recent analysis using MAAP merged ICESat-2 and optical data (Harmonized Landsat Sentinel) produced the most comprehensively precise estimate of boreal-wide AGB to date. Another effort using MAAP is the production and open distribution of global comparisons of AGB map estimates, including from ICESat-2 and GEDI, to bolster stakeholder uptake for policy applications. These map estimates will feed into the Intergovernmental Panel on Climate Change (IPCC) database, likely aiding the next Global Carbon Stocktake of the UNFCCC. Furthermore, the biomass retrieval intercomparison exercise BRIX-2 could benefit from the MAAP providing standardized test cases (based on airborne campaign and spaceborne data) allowing the community to develop and apply retrieval algorithms based on these test cases, while forthcoming SAR data training curricula could also use the MAAP as a teaching and learning platform. The MAAP is meeting the challenges inherent in international, open science collaboration and large scale computing with a platform that is entirely open source and cloud native, using open standards for data access, manipulation, protocols, and formats. The MAAP data system consists of a dedicated data store whose data is indexed in an online catalog conforming to established metadata, application programmatic interfaces (APIs), and service interface standards, using an implementation of the open sourced NASA Common Metadata Repository. Federation of user identities allows users from either NASA or ESA to access and consume services from the other using a unified metadata catalog for the data utilized across the ESA and NASA MAAP platforms. Similarly, we are exploring how to increase interoperability to achieve a common approach to packaging, orchestrating and executing algorithms, with interoperable access to data for subsetting, fast browse, and cloud-optimized access, all using interoperable standards such as those from the Open Geospatial Consortium (OGC). Designed for interoperability, ESA and NASA utilize a common architecture for the software platform. It provides a cloud-based algorithm development environment (ADE) that enables scientists to develop algorithms collaboratively with access to the MAAP data catalog as well as other data archives. MAAP provides an Eclipse Che-based ADE supporting both Python and R languages, popular in this biomass community. Algorithms developed and containerized within the ADE can be deployed to run to thousands of computational nodes in the MAAP’s data processing system (DPS), dramatically speeding up processing and giving scientists a rapid, iterative turnaround of results. NASA’s implementation of the DPS is based on the Hybrid Science Data System (HySDS) framework, used by NASA flight projects to produce Earth science standard products.

cloud computing↗

MultiSector Dynamics: Advancing the Science of Complex Adaptive Human-Earth Systems

The field of MultiSector Dynamics (MSD) explores the dynamics and co-evolutionary pathways of human and Earth systems with a focus on critical goods, services, and amenities delivered to people through interdependent sectors. This commentary lays out core definitions and concepts, identifies MSD science questions in the context of the current state of knowledge, and describes ongoing activities to expand capacities for open science, leverage revolutions in data and computing, and grow and diversify the MSD workforce. Central to our vision is the ambition of advancing the next generation of complex adaptive human-Earth systems science to better address interconnected risks, increase resilience, and improve sustainability. This will require convergent research and the integration of ideas and methods from multiple disciplines. Understanding the tradeoffs, synergies, and complexities that exist in coupled human-Earth systems is particularly important in the context of energy transitions and increased future shocks.

Reed, Patrick↗

Langston University - High Energy Physics (LU-HEP)

This final report is presented by Langston University (LU) for the project entitled "Langston University High Energy Physics" (LUHEP) under the direction of principal investigator (PI) and project director Professor Joel Snow. The project encompassed high energy physics research performed at hadron colliders. The PI is a collaborator on the DZero experiment at Fermi National Accelerator Laboratory in Batavia, IL, USA and the ATLAS experiment at CERN in Geneva, Switzerland and was during the entire project period from April 1, 1999 until May 14, 2012. Both experiments seek to understand the fundamental constituents of the physical universe and the forces that govern their interactions. In 1999 as member of the Online Systems group for Run 2 the PI developed a cross-platform Python-based, Graphical User Interface (GUI) application for monitoring and control of EPICS based devices for control room use. This served as a model for other developers to enhance and build on for further monitoring and control tasks written in Python. Subsequently the PI created and developed a cross-platform C++ GUI utilizing a networked client-server paradigm and based on ROOT, the object oriented analysis framework from CERN. The GUI served as a user interface to the Examine tasks running in the D\O\ control room which monitored the status and integrity of data taking for Run 2. The PI developed the histogram server/control interface to the GUI client for the EXAMINE processes. The histogram server was built from the ROOT framework and was integrated into the D\O\ framework used for online monitoring programs and offline analysis. The PI developed the first implementation of displaying histograms dynamically generated by ROOT in a Web Browser. The PI's work resulted in several talks and papers at international conferences and workshops. The PI established computing software infrastructure at LU and U. Oklahoma (OU) to do analysis of DZero production data and produce simulation data for the experiment. Eventually this included the FNAL SAM data grid system, the SAMGrid (SG) infrastructure, and the Open Science Grid software stacks for computing and storage elements. At the end of 2003 Snow took on the role of global Monte Carlo production coordinator for the DØ experiment. A role which continues til this day. In January of 2004 Snow started working with the SAMGrid development team to help debug, deploy, and integrate SAMGrid with DØ Monte Carlo production. Snow installed and configured SG execution and client sites at LUHEP and OUHEP, and a SG scheduler site at LUHEP. The PI developed a python based GUI (DAJ) that acts as a front end for job submission to SAMGrid. The GUI interfaces to the DZero Mone Carlo (MC) request system that uses SAM to manage MC requests by the physics analysis groups. DAJ significantly simplified SG job submission and was deployed in DZero in an effort to increase the user base of SG. The following year was the advent of SAMGrid job submission to the Open Science Grid (OSG) and LHC Computing Grid (LCG) through a forwarding mechanism. The PI oversaw the integration of these grids into the existing production infrastructure. The PI developed an automatic MC (Automc) request processing system capable of operating without user intervention (other than getting grid credentials), and able to submit to any number of sites on various grids. The system manages production at all but 2 sites. The system was deployed at Fermilab and remains operating there today. The PI's work in distributed computing resulted in several talks at international conferences. UTA, OU, and LU were chosen as the collaborating institutions that form the Southwest Tier 2 Center (SWT2) for ATLAS. During the project period the PI contributed to the online and offline software infrastructure through his work with the Run 2 online group, and played a major role in Monte Carlo production for DZero. During the part of the project period in which the PI served as MC production coordinator MC production increased very significantly. In the first year of the PI's tenure as production coordinator production was 159M events and 6.7~TB of data. During the last year of the project period production was 2,342~M events and 262~TB of data. That is a factor of 15 increase in events and 39 in data volume. The increase occurred with improvements in computer hardware and networks, through the use of grid technology on diverse resources, and through increased automation and efficiency of the production process. LU HEP developed and deployed the automatic MC request processing system in use at FNAL. The complementary strategies of automation and grid production served DZero well. Fermilab has recognized LU HEP's contribution to DZero by allowing the PI to devote full time to research activities by appointing him a guest scientist for the last six years of the project period.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

The Nasa SRA Process as It Relates to Open-Source Workflows Developed for GeneLab Data Processing

To release open, standards-compliant processed data sets in the Open Science Data Repository (OSDR), the GeneLab Data Processing team works with the scientific community through the OSDR Analysis Working Groups to design and build open-source data processing pipelines. Once baselined internally, these pipelines are wrapped into workflows and published on the NASA GeneLab Data Processing public GitHub repository along with detailed instructions for installation and use. Each workflow must be approved through NASA's Software Release Authorization (SRA) process prior to publishing. However, the SRA process lacks sufficient documentation and clarity regarding which forms are applicable for new open-source software that utilizes publicly available 3rd party tools, and the SRA process can take several months to complete, making sharing software outside of NASA cumbersome and in contradiction with the concept of Open Science. Furthermore, the SRA process was designed as a one-size fits all approach and thus many of the questions asked are not applicable to our open-source workflows. Here we describe the software provided on the NASA GeneLab Data Processing GitHub repository, summarize our experiences with the SRA process to release these software, and propose a more stream-lined approach for review of open-source projects.

Software Release Authorization↗

The NASA SRA Process as it Relates to Open-Source Workflows Developed for GeneLab Data Processing

To release open, standards-compliant processed data sets in the Open Science Data Repository (OSDR), the GeneLab Data Processing team works with the scientific community through the OSDR Analysis Working Groups to design and build open-source data processing pipelines. Once baselined internally, these pipelines are wrapped into workflows and published on the NASA GeneLab Data Processing public GitHub repository along with detailed instructions for installation and use. Each workflow must be approved through NASA's Software Release Authorization (SRA) process prior to publishing. However, the SRA process lacks sufficient documentation and clarity regarding which forms are applicable for new open-source software that utilizes publicly available 3rd party tools, and the SRA process can take several months to complete, making sharing software outside of NASA cumbersome and in contradiction with the concept of Open Science. Furthermore, the SRA process was designed as a one-size fits all approach and thus many of the questions asked are not applicable to our open-source workflows. Here we describe the software provided on the NASA GeneLab Data Processing GitHub repository, summarize our experiences with the SRA process to release these software, and propose a more stream-lined approach for review of open-source projects.

Software Release Authorization↗

Earth and Space Science Informatics Perspectives on Integrated, Coordinated, Open, Networked (ICON) Science

Abstract This article is composed of three independent commentaries about the state of Integrated, Coordinated, Open, Networked (ICON) principles (Goldman, et al., 2021b, https://doi.org/10.1029/2021EO153180 ) in Earth and Space Science Informatics (ESSI) and includes discussion on the opportunities and challenges of adopting them. Each commentary focuses on a different topic: (Section 2) Global collaboration, cyberinfrastructure, and data sharing; (Section 3) Machine learning for multiscale modeling; (Section 4) Aerial and satellite remote sensing for advancing Earth system model development by integrating field and ancillary data. ESSI addresses data management practices, computation and analysis, and hardware and software infrastructure. Our role in ICON science therefore involves collaborative work to assess, design, implement, and promote practices and tools that enable effective data management, discovery, integration, and reuse for interdisciplinary work in Earth and space science disciplines. Networks of diverse people with expertise across Earth, space, and data science disciplines are essential for efficient and ethical exchanges of findable, accessible, interoperable, and reusable (FAIR) research products and practices. Our challenge is then to coordinate the development of standards, curation practices, and tools that enable integrating and reusing multiple data types, software, multi‐scale models, and machine learning approaches across disciplines in a way that is as open and/or FAIR as ethically possible. This is a major endeavor that could greatly increase the pace and potential of interdisciplinary scientific discovery.

58 GEOSCIENCES↗

Transcriptomics Processing Pipelines for Space Biology: An Open Source and Consensus-Driven Approach

Transcriptomics holds significant value in elucidating the relationship between gene expression, experimental factors, biological factors, and various types of omics data. Enhancing our understanding of these connections is paramount for foundational biology, which plays a pivotal role in devising solutions for challenges pertinent to both space travel and terrestrial life. The NASA GeneLab project, part of the Open Science Data Repository (OSDR.nasa.gov), seeks to accelerate space biology research through cataloging and democratizing ‘omics data, including transcriptomics. Since raw omics data are largely inaccessible to non-bioinformaticians, GeneLab works with the scientific community via the Open Science Analysis Working Groups (AWGs) to develop standard processing pipelines to generate and publish processed data. Unlike raw data, processed data have greater immediate value to diverse users with varying technical backgrounds and computational capabilities. Standardizing processing workflows is essential to match the pace of raw data generation, ensure reproducibility, and enable standardized processed data for comparison across datasets. As of June 2023, transcriptomics studies comprise over half of GeneLab datasets hosted on the OSDR, including data from bulk RNA-seq and Affymetrix or Agilent 1-Channel DNA microarray assays. In collaboration with the AWGs, GeneLab developed consensus processing pipelines for these transcriptomics data types that includes quality control, background correction (microarray only), data normalization and quantification, culminating in the detection and annotation of differentially expressed genes. The work presented here describes Nextflow implementations of GeneLab’s consensus transcriptomics pipelines that automates and accelerates processing of these datasets. In addition to the core data processing, these workflows also include raw data staging and a robust verification and validation program to identify errors in real-time, stop additional downstream computation, and preserve computational resources. These workflows are used to generate GeneLab processed data hosted on the OSDR, and are publicly available as open source software for others to use at: https://github.com/nasa/GeneLab_Data_Processing.

Jonathan Oribello↗

AI Foundation Models for Science: An Open Collaborative Initiative

Foundation Models (FMs), AI models designed to replace task-specific models, are increasingly being recognized for their versatility across numerous downstream applications. These models, trained using self-supervised techniques on any type of sequence data, circumvent the need for large annotated datasets, a major bottleneck in traditional AI model development. FMs can be applied to downstream tasks using few-shot learning and fine-tuning, significantly reducing the need for large labeled training datasets and computational resources. However, the development of FMs requires substantial resources, including access to data and compute power, expertise in the latest models, and specialized scientific knowledge for systematic evaluation. It is challenging for a single group to possess all these capabilities. To address this, NASA IMPACT has initiated an open collaborative effort, leveraging partnerships with the private sector and other groups within and outside NASA, to jointly build FMs. The overarching goal is to develop a consistent and collaborative approach to building FMs for high-value science datasets. This initiative has fostered collaboration within NASA and with external partners, including IBM Research, Clark University, DOE’s ORNL, ESA, and USGS. The effort focuses on identifying key datasets with a wide range of downstream applications, pretraining and building FMs using modified transformer architectures, evaluating compute infrastructure needs, and sharing models, pretraining and fine-tuning code, and data with the community. Furthermore, it aims to train the Earth science community to fine-tune these models for various downstream applications. Our initial effort resulted in the creation of a 100 million parameter HLS Geospatial Model within six months, which was released on HuggingFace. We are now expanding our scope to include data from weather and climate models and investigating multimodal models. We invite those interested in participating in this effort to join us by sharing their use cases, expertise, or data.

Rahul Ramachandran↗

The 2017 Bioinformatics Open Source Conference (BOSC)

The Bioinformatics Open Source Conference (BOSC) is a meeting organized by the Open Bioinformatics Foundation (OBF), a non-profit group dedicated to promoting the practice and philosophy of Open Source software development and Open Science within the biological research community. The 18th annual BOSC ( http://www.open-bio.org/wiki/BOSC_2017 ) took place in Prague, Czech Republic in July 2017. The conference brought together nearly 250 bioinformatics researchers, developers and users of open source software to interact and share ideas about standards, bioinformatics software development, open and reproducible science, and this year’s theme, open data. As in previous years, the conference was preceded by a two-day collaborative coding event open to the bioinformatics community, called the OBF Codefest.

59 BASIC BIOLOGICAL SCIENCES↗

The FIFE Project at Fermilab

The FabrIc for Frontier Experiments (FIFE) project is an initiative within the Fermilab Scientific Computing Division designed to steer the computing model for non-LHC Fermilab experiments across multiple physics areas. FIFE is a collaborative effort between experimenters and computing professionals to design and develop integrated computing models for experiments of varying size, needs, and infrastructure. The major focus of the FIFE project is the development, deployment, and integration of solutions for high throughput computing, data management, database access and collaboration management within an experiment. To accomplish this goal, FIFE has developed workflows that utilize Open Science Grid compute sites along with dedicated and commercial cloud resources. The FIFE project has made significant progress integrating into experiment computing operations several services including a common job submission service, software and reference data distribution through CVMFS repositories, flexible and robust data transfer clients, and access to opportunistic resources on the Open Science Grid. The progress with current experiments and plans for expansion with additional projects will be discussed. FIFE has taken the leading role in defining the computing model for Fermilab experiments, aided in the design of experiments beyond those hosted at Fermilab, and will continue to define the future direction of high throughput computing for future physics experiments worldwide.

Box, D.↗

WorkJournalMaker (WJMaker) v0.5

The software generates and maintains daily work journal entries in text format, via a web browser. The journal entries are saved in a structured directory file tree on the system running the software. The software also incorporates a database so that it can track the location of files in the file system and various other metadata. The software allows the users to access their journal entries either through the browser or as discrete text files, facilitating sharing and open science. Additionally, to assist with the yearly PMP process, this tool connects to LLM APIs to provide summarization of the journal entries on a month-by-month or weekly basis. The advantage over similar technologies such as Apple Notes (extremely popular for notetaking) is that the instant software does not force the user to stay inside the Apple ecosystem, since it allows for export of the user's text files. This facilitates open science, so that researchers who use the tool can easily transfer their research notes to any other system. The WebJournalMaker repository is here: https://github.com/lbnl-science-it/WorkJournalMaker The WebJournalMaker repository is forked from the JournalSummarizer: https://github.com/tyfong-lbl/JournalSummarizer and builds on its code. I wrote the code for both of these software repos, using generative AI.

Fong, Timothy [Lawrence Berkeley National Laborato↗

KBase Credit Metadata Schema

As part of KBase’s commitment to promote open science, we offer users the ability to obtain a DOI (Digital Object Identifier) for their work, which can then be cited in an associated science publication. To further support the community-wide shift towards FAIR (Findable, Accessible, Interoperable, Reusable) data, KBase is expanding our data descriptors so that KBase DOIs have comprehensive citations for datasets, in addition to referencing publications or software used in the workflow. This helps encourage a culture of giving attribution for all research inputs and outputs; standard practice for literature, but still relatively new for software products or datasets. It also promotes open science by building trust that contributors get credit for their work, and accelerates knowledge discovery by supporting and incentivizing the release of data.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Definition and implementation of a SAML-XACML profile for authorization interoperability across Grid middleware implementations in OSG and EGEE.

In order to ensure interoperability between middleware and authorization infrastructures used in the Open Science Grid (OSG) and the Enabling Grids for E-science (EGEE) projects, an Authorization Interoperability activity was initiated in 2006. The interoperability goal was met in two phases: firstly, agreeing on a common authorization query interface and protocol with an associated profile that ensures standardized use of attributes and obligations; and secondly implementing, testing, and deploying on OSG and EGEE, middleware that supports the interoperability protocol and profile. The activity has involved people from OSG, EGEE, the Globus Toolkit project, and the Condor project. This paper presents a summary of the agreed-upon protocol, profile and the software components involved.

97 MATHEMATICS AND COMPUTING↗

Toward SVOPME, a scalable virtual organization privileges management environment

Grids enable uniform access to resources by implementing standard interfaces to resource gateways. In the Open Science Grid (OSG), privileges are granted on the basis of the user's membership to a Virtual Organization (VO). However, user privilege definitions and enforcements are administered separately by VOs and Grid sites. Such partitioning can potentially introduce inconsistent user privileges throughout the Grid and break the Grid paradigm of uniform access to resources. There is a need for an automated privilege management mechanism for a VO to codify privilege policies granted to its users, to propagate the policies to grid sites, to identity and suggest remedies for non-supported VO privileges at individual sites. The Scalable Virtual Organization Privileges Management Environment (SVOPME) addresses the challenge under the context of the Open Science Grid (OSG). The SVOPME provides tools for VOs to define and publish desired privileges. At a site, SVOPME tools help analyze access policies defined for VO users and verify policy consistency between VOs and sites, and suggest site configurations changes. This paper presents the designs and features of SVOPME tools and the lessons learned in applying SVOPME tools for OSG VOs and sites. Furthermore, we will outline future improvements to SVOPME tools to adapt to a range of different site configurations and new privilege policies.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

RadLab: A Comprehensive Database and Analysis Toolkit for Space Radiation Measurements Relevant to Space Radiation Biology

RadLab, a new addition to the NASA Open Science Data Repository (OSDR), is a public platform for space radiation data relevant to human space exploration. RadLab consists of a database, a submission portal, and user-friendly visualization and data analysis tools, including a graphical user interface (GUI) and an application programming interface (API). Investigators from ISS partners including Germany, Italy, Canada, Hungary, the Czech Republic, Russia, Japan have committed to providing data from their instruments. RadLab will also include data from other spacecraft in LEO: the Space Shuttle, the Mir space station, biosatellites; and beyond LEO: the lunar and the Martian surface, the heliocentric orbit at 1 AU, Mars orbit, and Earth-Mars space. Once fully operational, RadLab will provide open, centralized access to space radiation physics data relevant to human space exploration; a platform for submission of data by agencies and research institutions responsible for radiation detectors deployed in space; analysis tools to facilitate detector and dataset intercomparison to better understand space habitat radiation environments; capabilities for space biology investigators to determine the radiation environment to which samples were exposed. A RadLab Working Group (RLWG) has been formed, modeled on the GeneLab Analysis Working Groups and comprised of data contributors and users. RLWG tasks include identifying data sources, normalizing data from diverse detectors, expanding the analysis toolkit and, perhaps most importantly, sharing ideas for research exploiting capabilities of RadLab. We will provide an overview of RadLab data and capabilities and discuss examples of its potential as a resource for open science.

radiation↗

Reliability Lessons Learned From GPU Experience With The Titan Supercomputer at Oak Ridge Leadership Computing Facility

The high computational capability of graphics processing units (GPUs) is enabling and driving the scientific discovery process at large-scale. The world’s second fastest supercomputer for open science, Titan, has more than 18,000 GPUs that computational scientists use to perform scientific simu- lations and data analysis. Understanding of GPU reliability characteristics, however, is still in its nascent stage since GPUs have only recently been deployed at large-scale. This paper presents a detailed study of GPU errors and their impact on system operations and applications, describing experiences with the 18,688 GPUs on the Titan supercom- puter as well as lessons learned in the process of efficient operation of GPUs at scale. These experiences are helpful to HPC sites which already have large-scale GPU clusters or plan to deploy GPUs in the future.

Tiwari, Devesh↗