Compiler-Aided Type Correctness of Hybrid MPI-OpenMP Applications

Hybrid MPI–OpenMP applications employ message-passing interface (MPI)-enabled process-level, distributed computations on many compute nodes in conjunction with OpenMP shared-memory, thread-level parallelism for the most efficient computation. This poses challenges on the dynamic MPI correctness tool...

Full description

Saved in:
Bibliographic Details
Published inIT professional Vol. 24; no. 2; pp. 45 - 51
Main Authors Huck, Alexander, Kreutzer, Sebastian, Protze, Joachim, Lehr, Jan-Patrick, Bischof, Christian, Terboven, Christian, Muller, Matthias S.
Format Journal Article
LanguageEnglish
Published Washington IEEE 01.03.2022
IEEE Computer Society
Subjects
Adaptation models
Codes
Compilers
Dynamic scheduling
Memory management
Message passing
Parallel processing
Program processors
Run time (computers)
Runtime
Runtime library
Tracking
Online AccessGet full text

Cover

More Information
Summary:Hybrid MPI–OpenMP applications employ message-passing interface (MPI)-enabled process-level, distributed computations on many compute nodes in conjunction with OpenMP shared-memory, thread-level parallelism for the most efficient computation. This poses challenges on the dynamic MPI correctness tool MUST and TypeART, its memory allocation tracking sanitizer extension based on the LLVM compiler framework. In particular, at the thread-level granularity of a process, MPI calls and memory allocations, which are both tracked for our analysis, can occur concurrently. To correctly handle this situation, we: 1) extended our compiler extension to handle OpenMP and 2) introduced thread-safety mechanisms to our runtime libraries, thus keeping the tracking of data consistent and avoiding data races. Our approach exhibits acceptable runtime and memory overheads, both typically below 30%.
ISSN:1520-9202
1941-045X
DOI:10.1109/MITP.2021.3093949