skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Final Report from The University of Texas at Austin for DEGAS: Dynamic Global Address Space programming environments

Abstract

The Dynamic, Exascale Global Address Space programming environment (DEGAS) project will develop the next generation of programming models and runtime systems to meet the challenges of Exascale computing. Our approach is to provide an efficient and scalable programming model that can be adapted to application needs through the use of dynamic runtime features and domain-specific languages for computational kernels. We address the following technical challenges: Programmability: Rich set of programming constructs based on a Hierarchical Partitioned Global Address Space (HPGAS) model, demonstrated in UPC++. Scalability: Hierarchical locality control, lightweight communication (extended GASNet), and ef- ficient synchronization mechanisms (Phasers). Performance Portability: Just-in-time specialization (SEJITS) for generating hardware-specific code and scheduling libraries for domain-specific adaptive runtimes (Habanero). Energy Efficiency: Communication-optimal code generation to optimize energy efficiency by re- ducing data movement. Resilience: Containment Domains for flexible, domain-specific resilience, using state capture mechanisms and lightweight, asynchronous recovery mechanisms. Interoperability: Runtime and language interoperability with MPI and OpenMP to encourage broad adoption.

Authors:
ORCiD logo [1];  [2];  [3];  [4]
  1. Univ. of Texas, Austin, TX (United States)
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  3. Rice Univ., Houston, TX (United States)
  4. Univ. of California, Berkeley, CA (United States)
Publication Date:
Research Org.:
Univ. of Texas, Austin, TX (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
OSTI Identifier:
1421939
Report Number(s):
DOE-UTEXAS-08671
DOE Contract Number:  
SC0008671
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; HPC; Resilience; programming models

Citation Formats

Erez, Mattan, Yelick, Katherine, Sarkar, Vivek, and Demmel, James. Final Report from The University of Texas at Austin for DEGAS: Dynamic Global Address Space programming environments. United States: N. p., 2018. Web. doi:10.2172/1421939.
Erez, Mattan, Yelick, Katherine, Sarkar, Vivek, & Demmel, James. Final Report from The University of Texas at Austin for DEGAS: Dynamic Global Address Space programming environments. United States. doi:10.2172/1421939.
Erez, Mattan, Yelick, Katherine, Sarkar, Vivek, and Demmel, James. Wed . "Final Report from The University of Texas at Austin for DEGAS: Dynamic Global Address Space programming environments". United States. doi:10.2172/1421939. https://www.osti.gov/servlets/purl/1421939.
@article{osti_1421939,
title = {Final Report from The University of Texas at Austin for DEGAS: Dynamic Global Address Space programming environments},
author = {Erez, Mattan and Yelick, Katherine and Sarkar, Vivek and Demmel, James},
abstractNote = {The Dynamic, Exascale Global Address Space programming environment (DEGAS) project will develop the next generation of programming models and runtime systems to meet the challenges of Exascale computing. Our approach is to provide an efficient and scalable programming model that can be adapted to application needs through the use of dynamic runtime features and domain-specific languages for computational kernels. We address the following technical challenges: Programmability: Rich set of programming constructs based on a Hierarchical Partitioned Global Address Space (HPGAS) model, demonstrated in UPC++. Scalability: Hierarchical locality control, lightweight communication (extended GASNet), and ef- ficient synchronization mechanisms (Phasers). Performance Portability: Just-in-time specialization (SEJITS) for generating hardware-specific code and scheduling libraries for domain-specific adaptive runtimes (Habanero). Energy Efficiency: Communication-optimal code generation to optimize energy efficiency by re- ducing data movement. Resilience: Containment Domains for flexible, domain-specific resilience, using state capture mechanisms and lightweight, asynchronous recovery mechanisms. Interoperability: Runtime and language interoperability with MPI and OpenMP to encourage broad adoption.},
doi = {10.2172/1421939},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2018},
month = {2}
}