A graph based approach for MPI deadlock detection

Hilbrich, Tobias; Supinski, Bronis R. de; Schulz, Martin; Müller, Matthias S.

doi:10.1145/1542275.1542319

Cited by 46 publications

(47 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, our generalization of the AND⊕OR model [2] extends work on the AND-OR graph-theoretic deadlock model [9], [10], [11]. Visualizations of the AND-OR model, where processes may specify a Boolean equation as their wait-for condition, are difficult to visualize, while our work demonstrates that the AND⊕OR model is equivalent and supports intuitive visualization.…”

Section: Related Workmentioning

confidence: 81%

“…Thus, we restrict our approach to only consider deadlocks that manifest themselves in a given run. As a result, we use the AND⊕OR model [2] that enables a graph-based deadlock detection, to implement a runtime deadlock detection approach in the Marmot Umpire Scalable Tool (MUST), which extends and scales the functionality of its predecessors: Marmot [6] and Umpire [7].…”

Section: Must and The And⊕or Modelmentioning

confidence: 99%

“…We follow a graph-based approach that uses the AND⊕OR model [2] to represent wait-for dependencies of active MPI calls. This model simplifies the AND-OR model, which can model wait-for conditions of the most general type.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MPI runtime error detection with MUST: Advances in deadlock detection

Hilbrich¹,

Protze²,

Schulz³

et al. 2012

2012 International Conference for High Performance Computing, Networking, Storage and Analysis

Self Cite

View full text Add to dashboard Cite

Abstract-The widely used Message Passing Interface (MPI) is complex and rich. As a result, application developers require automated tools to avoid and to detect MPI programming errors. We present the Marmot Umpire Scalable Tool (MUST) that detects such errors with a significantly increased scalability. We present improvements to our graph-based deadlock detection approach for MPI, which cover complex MPI constructs, as well as future MPI extensions. Further, our enhancements check complex MPI constructs that no previous graph-based detection approach handled correctly. Finally, we present optimizations for the processing of MPI operations that reduce runtime deadlock detection overheads. Existing approaches could require O(p) analysis time per MPI operation, for p processes, where our improvements lead to an O(log p) complexity or better for real world applications. We present overhead measurements for two major benchmark suites with up to 1024 cores to demonstrate our improvements for real world scenarios.

show abstract

Section: Related Workmentioning

confidence: 81%

Section: Must and The And⊕or Modelmentioning

confidence: 99%

See 1 more Smart Citation

MPI runtime error detection with MUST: Advances in deadlock detection

Hilbrich¹,

Protze²,

Schulz³

et al. 2012

2012 International Conference for High Performance Computing, Networking, Storage and Analysis

Self Cite

View full text Add to dashboard Cite

show abstract

“…A key feature of MUST is its graph-based deadlock detection [8]. It creates a waitfor graph and then uses this graph to identify existing deadlock conditions.…”

Section: Example: Pinpointing Deadlocksmentioning

confidence: 99%

MPI Runtime Error Detection with MUST: Advanced Error Reports

Protze

Hilbrich

Supinski

et al. 2013

Tools for High Performance Computing 2012

Self Cite

View full text Add to dashboard Cite

“…The Umpire tool [9,10] Intel's thread checker [14] and Sun Microsystems' thread analyzer [2] are tools for debugging OpenMP run-time errors. The authors are not aware of any run-time error detection tools for Unified Parallel C (UPC).…”

Section: Introductionmentioning

confidence: 99%

The Importance of Run-Time Error Detection

Luecke

Coyle²,

Hoekstra³

et al. 2010

Tools for High Performance Computing 2009

View full text Add to dashboard Cite

Abstract. The ability of system software to detect and issue error messages that help programmers quickly fix serial and parallel run-time errors is an important productivity criterion for developing and maintaining application programs. Over ten thousand run-time error tests and a run-time error detection (RTED) evaluation tool has been developed for the automatic evaluation of run-time error detection capabilities for serial errors and for parallel errors in MPI, OpenMP and UPC programs. Evaluation results, tests and the RTED evaluation tool are freely available at http://rted.public.iastate.edu. Many compilers, tools and run-time systems scored poorly on these tests. The authors make recommendations for providing better RTED in the future.

show abstract

A graph based approach for MPI deadlock detection

Cited by 46 publications

References 8 publications

MPI runtime error detection with MUST: Advances in deadlock detection

MPI runtime error detection with MUST: Advances in deadlock detection

MPI Runtime Error Detection with MUST: Advanced Error Reports

The Importance of Run-Time Error Detection

Contact Info

Product

Resources

About