Abstract:
PDT is the Parallel DebuggingTool of the Annai programming environment developedwithin the Joint CSCS-ETH/NEC Collaboration in Parallel Processing. Similarly to the other components of the integrated environment, PDT provides support for application developers to debug data-parallel programs written in HPF, and message-passingprograms basedon the MPI standard. This paper describes how the PDT source-level debugger addresses three major issues in parallel debugging: execution control (handling of breakpoints, watchpoints, and exceptions), distributed data and data distribution visualization, race detection and deterministic execution replay. We present the algorithms, their implementation, and our latest results regarding intrusiveness and overhead.
Citations
|
1763
|
Time, clocks, and the ordering of events in a distributed system
– Lamport
- 1978
|
|
808
|
Distributed Snapshots: Determining Global States of Distributed Systems
– Chandy, Lamport
- 1985
|
|
221
|
SPARSKIT: a basic tool kit for sparse matrix computations
– Saad
- 1994
|
|
154
|
Consistent Detection of Global Predicates
– Cooper, Marzullo
- 1991
|
|
126
|
A Parallel Programming Environment
– Allen, Kennedy
- 1985
|
|
106
|
Partial Orders for Parallel Debugging
– Fidge
- 1989
|
|
63
|
NAS Parallel Benchmark Results
– Bailey, Barszcz, et al.
- 1994
|
|
61
|
Optimal tracing and replay for debugging a message-passing parallel program
– Netzer, Miller
- 1992
|
|
29
|
Practical data breakpoints: design and implementation
– Wahbe, Lucco, et al.
|
|
18
|
Extending High Performance Fortran for the support of unstructured computations
– Muller, Ruhl
- 1995
|
|
15
|
The "Annai" Environment for Portable Distributed Parallel Programming
– Clemencon, Endo, et al.
- 1995
|
|
12
|
Application-Driven Development of an Integrated Tool Environment for Distributed Memory Parallel Processors
– Clemencon, Decker, et al.
- 1994
|
|
12
|
Design and Realization of the Annai Integrated Parallel Programming Environment Performance Monitor and Analyzer
– Wylie, Endo
- 1994
|
|
12
|
mdb: A semantic race detection tool for pvm
– Damodaran-Kamal, Francioni
- 1994
|
|
5
|
An implementation of race detection and deterministic replay with MPI
– Clemencon, Fritscher, et al.
- 1995
|
|
2
|
Paragon Interactive Parallel Debugger Reference
– Corporation
- 1994
|
|
