| NSF Org: |
PHY Division Of Physics |
| Recipient: |
|
| Initial Amendment Date: | September 22, 2011 |
| Latest Amendment Date: | August 6, 2012 |
| Award Number: | 1105572 |
| Award Instrument: | Continuing Grant |
| Program Manager: |
Bogdan Mihaila
bmihaila@nsf.gov (703)292-8235 PHY Division Of Physics MPS Directorate for Mathematical and Physical Sciences |
| Start Date: | October 1, 2011 |
| End Date: | September 30, 2016 (Estimated) |
| Total Intended Award Amount: | $548,546.00 |
| Total Awarded Amount to Date: | $548,546.00 |
| Funds Obligated to Date: |
FY 2012 = $89,666.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1608 4TH ST STE 201 BERKELEY CA US 94710-1749 (510)643-3891 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
1608 4TH ST STE 201 BERKELEY CA US 94710-1749 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): |
CI REUSE, Software Institutes |
| Primary Program Source: |
01001213DB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): | |
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.049 |
ABSTRACT
This award funds the continued operations and further development of Einstein@Home and its software infrastructure, the Berkeley Open Infrastructure for Network Computing (BOINC). Einstein@Home is one of the largest and most powerful computers on the planet. It searches astrophysical data for the weak signals from spinning neutron stars. Unlike a normal supercomputer, the computing power of Einstein@Home comes from ordinary home computers and laptops that have been "signed up" by about 300,000 members of the general public. When otherwise idle, these computers automatically download observational data over the Internet from Einstein@Home servers, search the data for the weak signals from spinning neutron stars, and return the results of the analysis to the servers.
Neutron stars are exotic objects: they represent the most compact form that a star can take before it collapses into a black hole. Since they were discovered in 1967, about two thousand neutron stars have been found (including several discovered in 2010 and 2011 by Einstein@Home). Neutron star observations provide a unique view into the behavior of matter at extreme pressures and densities, and into the nature of gravitation when gravity is very strong. Under certain circumstances, neutron stars can be emitters of pulsing radio waves (pulsars). Einstein@home exploits the unique capabilities of the Arecibo Radio Observatory, the largest and most sensitive single-dish radio telescope in the world, to search for these signals. It is possible that neutron stars can also emit gravitational waves. Gravitational waves were first predicted by Einstein in 1917 but have never been directly detected. Einstein@home can search the data from gravitational wave detectors such as those of the Laser Interferometer Gravitational-wave Observatory (LIGO) for these signals. Einstein@home also supports the BOINC software infrastructure to benefit dozens of computationally intensive projects in other areas of science, that also exploit volunteer distributed computing. And it is a remarkable tool for scientific outreach: Einstein@Home allows hundreds of thousands of ordinary citizens from around the world to participate in and make meaningful contribution to cutting-edge scientific research.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
BOINC is a software platform for volunteer computing. Einstein@Home is based on BOINC, and uses volunteer computing to search for pulsars and gravitational waves. The goal of this project was to enhance BOINC in ways that are useful to Einstein@Home and to other BOINC-based projects.
One focus of this work was adding a "volunteer storage" capability to BOINC: in other words, to let projects like Einstein@Home use the free disk space on volunteer computers as well as the idle CPU and GPU time, without impacting the normal use of the computer. This new capability supports computing projects - like Einstein@Home - that have large input or output files, that want to cache input files across jobs to reduce network traffic, or that want to cache computationally-generated files on the computer. It also supports projects that use volunteer computers as a distributed storage system for archival of large data sets, or as a buffer for large data streams such as radio telescope array data.
We addressed the problem of contention for disk space among multiple projects. If BOINC's disk usage on a computer reaches a user-specified limit, it deletes files in such a way that a project's disk usage is proportional to a user-specified "resource share". This mechanism makes BOINC's disk usage invisible to the volunteer. As the disk becomes full, BOINC automatically clears space.
We developed a mechanism called "locality scheduling" that couples job scheduling to storage: the BOINC scheduler preferentially sends jobs whose input files are already present on the computer. This reduces network traffic at both client and server.
Based on the new storage features, we developed a system called VDA (Volunteer Data Archival) for reliable archival of large data. VDA supports files thousands of times larger than the free space of individual computers. It uses a combination of replication and multi-level erasure coding to reduce the probability of data loss to an arbitrary low level, using minimal space overhead.
In addition to these new capabilities, this award supported general maintenance of BOINC, support for new OS versions and for Android devices, support for new GPU hardware and software, and support for virtualization technologies like VirtualBox and Docker, which allow Linux applications to run on Windows and Mac home computers.
Last Modified: 01/02/2017
Modified by: David P Anderson
Please report errors in award information by writing to: awardsearch@nsf.gov.
