Nebo: An efficient, parallel, and portable domain-specific language for numerically solving partial differential equations

Journal Article · Tue Jan 26 00:00:00 EST 2016 · Journal of Systems and Software

DOI:https://doi.org/10.1016/j.jss.2016.01.023· OSTI ID:1440722

Earl, Christopher ^[1]; Might, Matthew ^[2]; Bagusetty, Abhishek ^[3]; Sutherland, James C.  ^[2]

---

1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
2. Univ. of Utah, Salt Lake City, UT (United States)
3. Univ. of Pittsburgh, Pittsburgh, PA (United States)

This study presents Nebo, a declarative domain-specific language embedded in C++ for discretizing partial differential equations for transport phenomena on multiple architectures. Application programmers use Nebo to write code that appears sequential but can be run in parallel, without editing the code. Currently Nebo supports single-thread execution, multi-thread execution, and many-core (GPU-based) execution. With single-thread execution, Nebo performs on par with code written by domain experts. With multi-thread execution, Nebo can linearly scale (with roughly 90% efficiency) up to 12 cores, compared to its single-thread execution. Moreover, Nebo’s many-core execution can be over 140x faster than its single-thread execution.

• Research Organization: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA)
• Grant/Contract Number: AC52-07NA27344
• OSTI ID: 1440722
• Alternate ID(s): OSTI ID: 1398661
• Report Number(s): LLNL-JRNL-665611; 787107
• Journal Information: Journal of Systems and Software, Vol. 125, Issue C; ISSN 0164-1212
• Publisher: Elsevier
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
Domain-specific language embedded in C++
GPGPU