Data access through digital Earth
Explore the source record for details and available documents.
SEARCH · Search NASA
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.
Explore the source record for details and available documents.
To address the lack of user-friendly software needed to simplify the utilization of model data across Heliophysics, the Community Coordinated Modeling Center (CCMC) at NASA’s Goddard Space Flight Center has developed a model-agnostic method via Kamodo for users to easily access and utilize model data in their workflows. By abstracting away the broad range of file formats and the intricacies of interpolation on specialized grids, this approach significantly lowers the barrier to model data access and utilization for the community while adding exciting new capabilities to their tool boxes. This paper describes the direct interfaces to the model data, called model readers, and a basic introduction on how to use them. Additionally, we detail the planned approach for including custom interpolation codes, and include current progress on specialized visualization developments. The CCMC is maintaining Kamodo as an official NASA open-sourced software to enable and encourage community collaboration.
GPU performance of the lattice Boltzmann method (LBM) depends heavily on memory access patterns. When LBM is advanced with GPUs on complex computational domains, geometric data is typically accessed indirectly, and lattice data is typically accessed lexicographically in the Structure of Array (SoA) layout. Although there are a variety of existing access patterns beyond the typical choices, no study has yet examined the relative efficacy between them. Here, we compare a suite of memory access schemes via empirical testing and performance modeling. We find strong evidence that semi-direct addressing is the superior addressing scheme for the majority of cases examined: Semi-direct addressing increases computational speed and often reduces memory consumption. For lattice layout, we find that the Collected Structure of Arrays (CSoA) layout outperforms the SoA layout. When compared to state-of-the-art practices, our recommended addressing modifications lead to performance gains between 10-40% across different complex geometries, fluid volume fractions, and resolutions. The modifications also lead to a decrease in memory consumption by as much as 17%. Having discovered these improvements, we examine a highly resolved arterial geometry on a leadership class system. On this system we present the first near-optimal strong results for LBM with arterial geometries run on GPUs. We also demonstrate that the above recommendations remain valid for large scale, many device simulations, which leads to an increased computational speed and average memory usage reductions. To understand these observations, we employ performance modeling which reveals that semi-direct methods outperform indirect methods due to a reduced number of total loads/stores in memory, and that CSoA outperforms SoA and bundling due to improved caching behavior.
Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.
Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.
Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.
Remote access to large-scale scientific datasets, like those generated by combustion simulations or other high-performance computing (HPC) applications, presents a significant challenge. Downloading entire datasets is often impractical due to their size and the bandwidth limitations of typical networks. To address this challenge, we propose a novel approach that enables efficient remote access to large datasets distributed across multiple facilities. Our method enables technologies to download only the data values of a select variable, in a select region of interest, to a user-defined accuracy. For this purpose, we extended the ADIOS IO library to provide read functions with user-defined accuracy, a remote data server that understands multidimensional selections of specific variables, steps and accuracy from an ADIOS dataset, and which uses lossy compression on the remote site to reduce the data to be transferred back to the client. In addition, our extension of the ADIOS library collects metadata from multiple datasets in small files called Campaign Archives, which can be shared among project participants on any HPC, cloud or laptop, and which can easily facilitate the discovery of content and pointers to the data location as well as remote access to the data by local tools as if data was local. This feature called Campaign Management, enables a group of scientists to manage related datasets stored in multiple files, across multiple facilities as if it was in a single file/database. We demonstrate the effectiveness of our approach using a 1.5 TB dataset from the S3D combustion simulation on Frontier at the Oak Ridge Leadership Facility. Even a single variable from this dataset, at 64 GB, is too large to be processed on a standard laptop. We show two different reading patterns for 2D plots and 3D visualization, with careful settings that a scientist studying combustion data would do and show that running the same Python scripts on Frontier directly takes comparable time than running them on the local laptop with remote access to the data on Frontier.
Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to a deterministic data communications network through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and the deterministic data communications network; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.
Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to a deterministic data communications network through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and the deterministic data communications network; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.
A technical description is given of the effort to design, develop, fabricate, and test the two dimensional data processing system, McIDAS. The system has three basic sections: an access and data archive section, a control section, and a display section. Areas reported include hardware, system software, and applications software.
Environmental data is often complex, and it can be difficult to provide proper context to fully understand and comprehensively analyze the data. One tool identified to better present complicated data is the use of web-based Geographic Information Systems (GIS). Web-based GIS provides much-needed visual context to the complex data collected at Los Alamos National Laboratory (LANL). By overlaying environmental data atop relevant geographical features, such as topography, surface or subsurface geology, hydrogeological features, buildings, roads, and technical areas, LANL's diverse group of stakeholders are better able to understand environmental data collected at the LANL site within the framework of the surrounding geography. Since 2012, Los Alamos has utilized a web-based GIS module in the Intellus New Mexico data-sharing web site. This web site provides unfettered public access to LANL and New Mexico Environment Department (NMED) - Department of Energy (DOE) Oversight Bureau environmental data. Through the past five years of real world experience, LANL identified areas where questions and confusion arose, particularly for those not directly associated with the site's environmental cleanup mission. In order to query the millions of records in Intellus in a meaningful way, users had to have substantial knowledge of the data organization and nomenclature ahead of time. While this was not a challenge for LANL and NMED environmental scientists, it proved to be a substantial barrier for members of the general public to utilize Intellus. In 2017, LANL initiated an Intellus redesign with the goal of deconstructing the type of questions people asked and identifying the types of user personas accessing the site to engineer a simpler path to desired data sets. Greatly simplified click paths ('Quick Paths') were created that walk the user through the basics with a minimum of jargon and a strong reliance on mapping results for easy visualization. The improved mapping was enabled by an upgraded online GIS functionality that allowed LANL to easily integrate their own base-maps to provide users the most up to date views of their data. The integrated Intellus GIS was enhanced to assimilate with LANL's dynamic base maps and site information in relation to data collection activities, to avoid outdated presentations. A simplified user interface (UI) was added and easier data querying was designed. A more robust visual presentation was created that allowed better viewing of spatial data. All data queries in the new simplified 'Quick Path' give the users the option to map the results and save their results to their optional accounts. This brings the power of GIS visualization to all users without the need for GIS knowledge or extensive training. By integrating with Esri{sup R} technologies, base-map layers in ArcGIS Online{sup R} can be updated by LANL or other data providers at any time and reflected immediately in the Intellus mapping application called GIS+ 1. Users can even load additional map layers to GIS+ that contain their own spatial data or information shared from over a million users on ArcGIS Online{sup R}, such as ecological information from the Fish and Wildlife Service, or geology layers from the USGS. The results from the improved quick path search in Intellus can be viewed in GIS+ and analyzed using Esri's{sup R} Smart Mapping technology, which makes it easy to classify results with its visual representation of the results in an interactive histogram, where sliders can be dragged to look at various intervals for each color range for that query. With enhanced GIS+, Los Alamos National Laboratory is able to observe improve Stakeholder engagement and positive Stakeholder interactions within its public environmental database, Intellus New Mexico. (authors)
Explore the source record for details and available documents.
A data processing system is disclosed which comprises a data processor and memory control device for controlling the access of information from the memory. The memory control device includes temporary storage and decision ability for determining what order to execute the memory accesses. The compiler detects the requirements of the data processor and selects the data to stream to the memory control device which determines a memory access order. The order in which to access said information is selected based on the location of information stored in the memory. The information is repeatedly accessed from memory and stored in the temporary storage until all streamed information is accessed. The information is stored until required by the data processor. The selection of the order in which to access information maximizes bandwidth and decreases the retrieval time.
The NSLS-II network and computing infrastructure has been significantly updated recently. The re-IP process in 2020-2021 enabled the NSLS-II network to be routable to the rest of the BNL campus. Then, standardization of the operating systems and deployment procedures helped to deliver a consistent environment to workstations and servers used by all NSLS-II beamlines. In particular, the RedHat Enterprise Linux 8 was deployed to 700+ machines using the RedHat Satellite infrastructure management product, and all critical services (IOCs, databases, etc.) were migrated to the new OS. NFS users’ home directories are consistent across all of the machines, which eliminates the need for the individual configuration of the user environment on each host. The standard suite of software packages is available to the beamline staff and users, which includes the system packages (deployed via RPM) as well as the conda environments for data acquisition and analysis. Security measures were implemented to comply with the industry standards, which include multi-factor authentication (using Duo), secure screen lock for the beamline machines, and advanced access control to the experimental data that is stored in shared central storage available on all hosts. These major enhancements facilitated sharing the experimental data (currently for a number of selected beamlines, with a plan to extend it to the whole facility in the nearest future) with the users via an externally facing JupyterHub instance. The beamlines keep using the Bluesky data acquisition framework to orchestrate their experiments, and the new infrastructure enabled them to use a next-generation data access library called tiled.
Large-scale scientific research programs such as the EGS Collab experiments and the FORGE program play extremely important roles in advancing geothermal technologies. Such efforts involve a large number of researchers from multiple institutions, last multiple years, and generate large, complex datasets. The value of the research efforts is only realized when the datasets are used by a large community of researchers in the decades to come. A challenge is that due to the complexity of the data, it could require a user to devote a serious effort into understanding the data before the data can be effectively utilized. In the EGS Collab experiments, the team has devoted remarkable efforts and developed many innovative solutions to make the data more accessible to broader team members and future users. This paper documents the experience gained and lessons learned by the EGS Collab team in disseminating the data in the most informative and inspiring forms to maximize the value of this precious dataset. "Accessibility"in the title does not only mean making the raw data available for download. Particularly, we want to emphasize the importance of organizing, annotating, and presenting the data in ways to make it easy to digest by prospective consumers of the data.
In today's heterogeneous computing environment of proliferating platforms and operating systems, the Internet, through the World Wide Web (WWW), is becoming the preferred interface to much of the world's archive of digital data.
The XIO system is a set of subroutines that provide generalized data management capability for FORTRAN programs using a direct access file. Arrays of integer, real, double precision, and character data may be stored, each logical group of data identified by a unique matrix number. A matrix may be organized and stored as batches to reduce core requirements. Batches may be accessed randomly or sequentially. The file may be checkpointed and retained, allowing for restarts with stored values. The XIO subroutines operate on either IBM 360-370/OS/VS or DEC PDP-11/RSX computing systems.
The ATLAS Distributed Computing system uses the Frontier system to access the Conditions, Trigger, and Geometry database data stored in the Oracle Offline Database at CERN by means of the HTTP protocol. All ATLAS computing sites use Squid web proxies to cache the data, greatly reducing the load on the Frontier servers and the databases. One feature of the Frontier client is that in the event of failure, it retries with different services. While this allows transient errors and scheduled maintenance to happen transparently, it does open the system up to cascading failures if the load is high enough. Throughout LHC Run 2 there has been an ever increasing demand on the Frontier service. There have been multiple incidents where parts of the service failed due to high load. A significant improvement in the monitoring of the Frontier service was required. The monitoring was needed to identify both problematic tasks, which could then be killed or throttled, and to identify failing site services as the consequence of a cascading failure is much higher. This presentation describes the implementation and features of the monitoring system.