In-Memory Graph Databases for Web-Scale Data

Castellana, Vito G.; Morari, Alessandro; Weaver, Jesse R.; Tumeo, Antonino; Haglin, David J.; Villa, Oreste; Feo, John

doi:10.1109/mc.2015.74

Home/Archive/DOE OSTI

DOE OSTI · 1208713

In-Memory Graph Databases for Web-Scale Data

Castellana, Vito G.·Morari, Alessandro·Weaver, Jesse R.·Tumeo, Antonino·Haglin, David J.·Villa, Oreste·Feo, John

View original source ↗Export metadata ↓

Abstract

RDF databases have emerged as one of the most relevant way for organizing, integrating, and managing expo- nentially growing, often heterogeneous, and not rigidly structured data for a variety of scientific and commercial fields. In this paper we discuss the solutions integrated in GEMS (Graph database Engine for Multithreaded Systems), a software framework for implementing RDF databases on commodity, distributed-memory high-performance clusters. Unlike the majority of current RDF databases, GEMS has been designed from the ground up to primarily employ graph-based methods. This is reflected in all the layers of its stack. The GEMS framework is composed of: a SPARQL-to-C++ compiler, a library of data structures and related methods to access and modify them, and a custom runtime providing lightweight software multithreading, network messages aggregation and a partitioned global address space. We provide an overview of the framework, detailing its component and how they have been closely designed and customized to address issues of graph methods applied to large-scale datasets on clusters. We discuss in details the principles that enable automatic translation of the queries (expressed in SPARQL, the query language of choice for RDF databases) to graph methods, and identify differences with respect to other RDF databases.

Explore related subjects

GEMS Graph databases multithreading RDF

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Castellana, Vito G., Morari, Alessandro, Weaver, Jesse R., Tumeo, Antonino, Haglin, David J., Villa, Oreste, Feo, John. 2015-03-01. In-Memory Graph Databases for Web-Scale Data. https://doi.org/10.1109/mc.2015.74

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

NASA NTRS2014

X-Ray Polarization Capabilities of a Small Explorer Mission

X-ray polarization measurements hold great promise for studying the geometry and emission mechanisms in the strong gravitational and magnetic fields that surround black holes and neutron stars. In spite of this, the observational situation remains very limited; the last instrument dedicated to X-ray polarimetry flew decades ago on OSO-8, and the few recent measurements have been made by instruments optimized for other purposes. However, the technical capabilities to greatly advance the observational situation are in hand. Recent developments in micro-pattern gas detectors allow use of the polarization sensitivity of the photo-electric effect, which is the dominant interaction in the band above 2 keV. We present the scientific and technical requirements for an X-ray polarization observatory consistent with the scope of a NASA Small Explorer (SMEX) mission, along with a representative catalog of what the observational capabilities and expected sensitivities for the first year of operation could be. The mission is based on the technically robust design of the Gravity and Extreme Magnetism SMEX (GEMS) which completed a Phase B study and Preliminary Design Review in 2012. The GEMS mission is enabled by time projection detectors sensitive to the photo-electric effect. Prototype detectors have been designed, and provide engineering and performance data which support the mission design. The detectors are further characterized by low background, modest spectral resolution, and sub-millisecond timing resolution. The mission also incorporates high efficiency grazing incidence X-ray mirrors, design features that reduce systematic errors (identical telescopes at different azimuthal angles with respect to the look axis, and mounted on a rotating spacecraft platform), and a moderate capability to perform Target of Opportunity observations. The mission operates autonomously in a low earth, low inclination orbit with one to ten downlinks per day and one or more uplinks per week. Data and calibration products will be made available through the High Energy Astrophysics Science and Archival Research Center (HEASARC).

GEMS↗

NASA NTRS2014

Design Improvements and X-Ray Performance of a Time Projection Chamber Polarimeter for Persistent Astronomical Sources

The design of the Time-Projection Chamber (TPC) Polarimeter for the Gravity and Extreme Magnetism Small Explorer (GEMS) was demonstrated to Technology Readiness Level 6 (TRL-6)3 and the flight detectors fabricated, assembled and performance tested. A single flight detector was characterized at the Brookhaven National Laboratory Synchrotron Light Source with polarized X-rays at 10 energies from 2.3-8.0 keV at five detector positions. The detector met all of the GEMS performance requirements. Lifetime measurements have shown that the existing flight design has 23 years of lifetime4, opening up the possibility of relaxing material requirements, in particular the consideration of the use of epoxy, to reduce risk elsewhere. We report on design improvements to the GEMS detector to enable a narrower transfer gap that, when operated with a lower transfer field, reduces asymmetries in the detector response. In addition, the new design reduces cost and risk by simplifying the assembly and reducing production time. Finally, we report on the performance of the narrow-gap detector in response to polarized and unpolarized X-rays.

GEMS↗