| NSF Org: |
PHY Division Of Physics |
| Recipient: |
|
| Initial Amendment Date: | September 22, 2010 |
| Latest Amendment Date: | July 1, 2012 |
| Award Number: | 1005530 |
| Award Instrument: | Continuing Grant |
| Program Manager: |
James Shank
jshank@nsf.gov (703)292-4516 PHY Division Of Physics MPS Directorate for Mathematical and Physical Sciences |
| Start Date: | October 1, 2010 |
| End Date: | September 30, 2014 (Estimated) |
| Total Intended Award Amount: | $437,445.00 |
| Total Awarded Amount to Date: | $437,445.00 |
| Funds Obligated to Date: |
FY 2011 = $145,815.00 FY 2012 = $145,815.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
2600 CLIFTON AVE CINCINNATI OH US 45220-2872 (513)556-4358 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
2600 CLIFTON AVE CINCINNATI OH US 45220-2872 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | PHYSICS GRID COMPUTING |
| Primary Program Source: |
01001112DB NSF RESEARCH & RELATED ACTIVIT 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
One of the newest areas of computational research is in utilizing GPU (Graphical Processing Units) based technology taken from the "gaming" world and utilizing them in high impact science applications. This work will extend current work using GPU based resources to enhance research capabilities in experimental and theoretical Physics. This work proposes to expand and generalize the toolkits now available, targeting certain Physics applications at the colliders BaBar and Belle, but more generally making these tools available to the larger community.
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.
The primary goal of the project was to develop a GPU library to implement the MINUIT maximum likelihood fitting algorithm used in experimental particle physics. The result, GooFit, is a thread-parallel, GPU-friendly function evaluation library. It is nominally designed for use with MINUIT. In this use case, it provides highly parallel calculations of normalization integrals and log (likelihood) sums. A key feature of the design is its use of the Thrust library to manage all parallel kernel launches. This allows GooFit to execute on any architecture for which Thrust has a backend, currently, including CUDA for nVidia GPUs and OpenMP for single- and multicore CPUs. Running on an nVidia C2050, GooFit executes 300 times more quickly for a complex high energy physics problem than does the prior (algorithmically equivalent) code running on a single CPU core. The table posted with this report provides a more complete summary of benchmark results for two test cases for a variety of architectures.
The GooFit design and implementation choices are discussed in detail in Implementation of a Thread-Parallel,GPU-Friendly Function Evaluation Library, Digital Object Identifier 10.1109/ACCESS.2014.2306895. This publication can help guide developers of other highly parallel, compute-intensive libraries.
GooFit is an open-source project: Permission to use and redistribute is granted under terms of the GNU Lesser Public License, version 3.0. The code and documentation are maintained in github at
https://github.com/GooFit/GooFit
Last Modified: 01/26/2015
Modified by: Michael D Sokoloff
Please report errors in award information by writing to: awardsearch@nsf.gov.
