Parallelizing heavyweight debugging tools with mpiecho

Journal Article · Mon Dec 10 00:00:00 EST 2012 · Parallel Computing

DOI:https://doi.org/10.1016/j.parco.2012.11.002· OSTI ID:1784617

Rountree, Barry ^[1]; Gamblin, Todd ^[1]; de Supinski, Bronis R. ^[1]; Schulz, Martin ^[1]; Lowenthal, David K. ^[2]; Cobb, Guy ^[3]; Tufo, Henry ^[4]

---

1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
2. Univ. of Arizona, Tucson, AZ (United States)
3. Google, Inc. (United States)
4. Univ. of Colorado, Boulder, CO (United States)

Idioms created for debugging execution on single processors and multicore systems have been successfully scaled to thousands of processors, but there is little hope that this class of techniques can continue to be scaled out to tens of millions of cores. In order to allow development of more scalable debugging idioms we introduce mpiecho, a novel runtime platform that enables cloning of MPI ranks. Given identical execution on each clone, we then show how heavyweight debugging approaches can be parallelized, reducing their overhead to a fraction of the serialized case. We also show how this platform can be useful in isolating the source of hardware-based nondeterministic behavior and provide a case study based on a recent processor bug at LLNL.

• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA)
• Grant/Contract Number: AC52-07NA27344
• OSTI ID: 1784617
• Alternate ID(s): OSTI ID: 1090002
• Report Number(s): LLNL-JRNL--604292; 699892
• Journal Information: Parallel Computing, Journal Name: Parallel Computing Journal Issue: 3 Vol. 39; ISSN 0167-8191
• Publisher: Elsevier
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING