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

Title: Domain Specific Language Support for Exascale. Final Project Report

Abstract

The project developed a domain specific translator enable legacy MPI source code to tolerate communication delays, which are increasing over time due to technological factors. The translator performs source-to-source translation that incorporates semantic information into the translation process. The output of the translator is a C program runs as a data driven program, and uses an existing run time to overlap communication automatically

Authors:
ORCiD logo [1]
  1. Univ. of California, San Diego, CA (United States)
Publication Date:
Research Org.:
Univ. of California, San Diego, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
OSTI Identifier:
1410671
Report Number(s):
1
DOE Contract Number:
SC0008691
Resource Type:
Technical Report
Resource Relation:
Related Information: SoftwareMate project web site, including software release, 2017http://mate.ucsd.edu/Bamboo project web site, including software release,http://bamboo.ucsd.edu/Refereed publications1. Tan Nguyen, Pietro Cicotti, Eric Bylaska, Dan Quinlan, and Scott B. Baden. 2012. Bamboo -- Translating MPI applications to a latency-tolerant, data-driven form. In Proceedings of the 2012 International Conference for High Performance Computing, Networking, Storage and Analysis (SC '12). IEEE Computer Society, Washington, DC, USA, 1-11. DOI=http://dx.doi.org/10.1109/SC.2012.232. Bamboo - Preliminary scaling results on multiple hybrid nodes of Knights Corner and Sandy Bridge processors , Tan Nguyen and Scott Baden, Proc. WOLFHPC: Workshop on Domain-Specific Languages and High-Level Frameworks for HPC, SC13, The International Conference for High Performance Computing, Networking, Storage and Analysis, Denver CO, November 2013.3. LU Factorization: Towards Hiding Communication Overheads With A Lookahead-free Algorithm.Tan Nguyen and Scott Baden. IEEE Cluster 2015, Chicago, IL, Sept 8-11, 2015.4. Tan Nguyen, Pietro Cicotti, Eric Bylaska, Dan Quinlan, Scott Baden, Automatic translation of MPI source into a latency-tolerant, data-driven form, In Journal of Parallel and Distributed Computing, Volume 106, 2017, Pages 1-13, ISSN 0743-7315, https://doi.org/10.1016/j.jpdc.2017.02.0095. Toucan - A Translator for Communication Tolerant MPI Applications.Sergio M. Martin, Marsha J. Berger and Scott B. Baden, 31th International Parallel and Distributed Processing Symposium (IPDPS'17), Orlando, FL, May 29-June 2, 2017.
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Data driven; MPI; source-to-source translation; domain specific translation; communication overlap

Citation Formats

Baden, Scott. Domain Specific Language Support for Exascale. Final Project Report. United States: N. p., 2017. Web. doi:10.2172/1410671.
Baden, Scott. Domain Specific Language Support for Exascale. Final Project Report. United States. doi:10.2172/1410671.
Baden, Scott. 2017. "Domain Specific Language Support for Exascale. Final Project Report". United States. doi:10.2172/1410671. https://www.osti.gov/servlets/purl/1410671.
@article{osti_1410671,
title = {Domain Specific Language Support for Exascale. Final Project Report},
author = {Baden, Scott},
abstractNote = {The project developed a domain specific translator enable legacy MPI source code to tolerate communication delays, which are increasing over time due to technological factors. The translator performs source-to-source translation that incorporates semantic information into the translation process. The output of the translator is a C program runs as a data driven program, and uses an existing run time to overlap communication automatically},
doi = {10.2172/1410671},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2017,
month = 7
}

Technical Report:

Save / Share:
  • Domain-Specific Languages (DSLs) offer an attractive path to Exascale software since they provide expressive power through appropriate abstractions and enable domain-specific optimizations. But the advantages of a DSL compete with the difficulties of implementing a DSL, even for a narrowly defined domain. The DTEC project addresses how a variety of DSLs can be easily implemented to leverage existing compiler analysis and transformation capabilities within the ROSE open source compiler as part of a research program focusing on Exascale challenges. The OSU contributions to the DTEC project are in the area of code generation from high-level DSL descriptions, as well asmore » verification of the automatically-generated code.« less
  • A multi-institutional project known as D-TEC (short for “Domain- specific Technology for Exascale Computing”) set out to explore technologies to support the construction of Domain Specific Languages (DSLs) to map application programs to exascale architectures. DSLs employ automated code transformation to shift the burden of delivering portable performance from application programmers to compilers. Two chief properties contribute: DSLs permit expression at a high level of abstraction so that a programmer’s intent is clear to a compiler and DSL implementations encapsulate human domain-specific optimization knowledge so that a compiler can be smart enough to achieve good results on specific hardware. Domainmore » specificity is what makes these properties possible in a programming language. If leveraging domain specificity is the key to keep exascale software tractable, a corollary is that many different DSLs will be needed to encompass the full range of exascale computing applications; moreover, a single application may well need to use several different DSLs in conjunction. As a result, developing a general toolkit for building domain-specific languages was a key goal for the D-TEC project. Different aspects of the D-TEC research portfolio were the focus of work at each of the partner institutions in the multi-institutional project. D-TEC research and development work at Rice University focused on on three principal topics: understanding how to automate the tuning of code for complex architectures, research and development of the Rosebud DSL engine, and compiler technology to support complex execution platforms. This report provides a summary of the research and development work on the D-TEC project at Rice University.« less
  • This final technical report summarizes the research accomplished under the Expert Science and Engineering (ES E) program by the University of California at Berkeley through Syracuse University. The research effort, entitled Parallel Extensions for Object Oriented Programming, examined communication aspects leading to language support for parallel computation. The work undertaken in this effort has extended concurrent programming languages in their communication primitives. Although many abstraction mechanisms have been used in programming languages, including control abstraction mechanisms (such as procedures) and data abstraction mechanisms (such as data types), communication abstraction mechanisms have been found to be the most useful for parallel/concurrentmore » programming paradigms. Work accomplished in this effort has extended those mechanisms, concentrating on inter-process communication. A formal model for concurrent systems, called the Synchronous Token-based Communicating State (STOCS) model, has been used to model and analyze concurrent systems. Since present concurrent languages do not support any form of analysis of the communication structure of programs, two new constructs based on STOCS formalism have been developed to support high level specification - handshake and unit. A fair and efficient algorithm for execution of multi-process shared events is also presented.« less
  • The goal of this project is to develop a set of techniques and software tools to enhance the matching between memory accesses in dynamic simulations and the prominent features of modern and future manycore systems, alleviating the memory performance issues for exascale computing. In the first three years, the PI and his group have achieves some significant progress towards the goal, producing a set of novel techniques for improving the memory performance and data locality in manycore systems, yielding 18 conference and workshop papers and 4 journal papers and graduating 6 Ph.Ds. This report summarizes the research results of thismore » project through that period.« less
  • This is the final report for the UW-Madison efforts on the PIPER Performance Insight for Programmers and Exascale Runtimes research project.