| NSF Org: |
CCF Division of Computing and Communication Foundations |
| Recipient: |
|
| Initial Amendment Date: | February 9, 2017 |
| Latest Amendment Date: | July 7, 2018 |
| Award Number: | 1657175 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Almadena Chtchelkanova
achtchel@nsf.gov (703)292-7498 CCF Division of Computing and Communication Foundations CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | February 15, 2017 |
| End Date: | January 31, 2020 (Estimated) |
| Total Intended Award Amount: | $175,000.00 |
| Total Awarded Amount to Date: | $175,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
3 RUTGERS PLZ NEW BRUNSWICK NJ US 08901-8559 (848)932-0150 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
715, 96 Frelinghuysen Road Piscataway NJ US 08854-8018 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | CRII CISE Research Initiation |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
Sparse numerical computations are at the heart of many science and engineering simulations. However, the complex irregularities in sparse methods limit the performance of many scientific software. This project integrates mathematical reformulation, algorithm redesign, and performance engineering to develop high-performance sparse solvers for heterogeneous parallel platforms. The outcomes of this research are innovative tools and methodologies that advance the field of large-scale scientific simulations. In addition, the project has a broader impact in training graduate students to perform interdisciplinary research.
The project conducts an in-depth investigation of performance bottlenecks in sparse solvers and reformulates their standard variants to deliver end-to-end performance. Cross-layer solutions are developed to improve data locality, reduce communication, and increase inherent parallelism in sparse linear solvers. The solutions involve multi-level algorithm restructuring and performance tuning to significantly improve the scalability and performance of sparse computations while preserving their numerical accuracy, convergence, and stability. The proposed methods and algorithms are implemented as domain-specific high-performance software and a benchmark suite to promote iterative improvements of the developed algorithms and codes.
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.
Sparse numerical computations are at the heart of many science and engineering simulations. However, the complex irregularities in sparse methods limit the performance of many scientific software. In this project we integrated mathematical reformulation, algorithm redesign, and performance engineering to develop high-performance sparse solvers and software for heterogeneous parallel platforms. The outcomes of the project were the invention of novel algorithms and inspection strategies that analyze the irregularity in sparse matrix computations in scientific simulations. The analysis was used to build domain-specific code generators and cloud engines, specifically the MatRox, Sympiler, and ASYNC frameworks. These frameworks use multi-level algorithm restructuring and performance tuning to significantly improve the scalability and performance of sparse computations while preserving their numerical accuracy, convergence, and stability. As a result, practitioners and domain experts that use MatRox, Sympiler, and ASYNC can automatically generate high-performance code in scientific and machine learning applications. The frameworks are developed with a domain-specific language to improve programmer productivity.
The project has produced nine peer-reviewed publications. Code generation frameworks Sympiler and MatRox as well as the cloud computing engine ASYNC are the software artifacts produced from the project. These frameworks are made publicly available. Several graduate and undergraduate students were trained in numerical analysis, compiler development, cloud computing, and optimization methods. The trainees working on the project have won numerous awards such as the ACM Grant Final Student Research Competition award and the 2018 Adobe Research fellowship.
Last Modified: 03/09/2020
Modified by: Narayan Mandayam
Please report errors in award information by writing to: awardsearch@nsf.gov.
