Practical Model-Checking Method for Verifying Correctness of MPI Programs

Pervez, Salman; Gopalakrishnan, Ganesh; Kirby, Robert M.; Palmer, Robert L.; Thakur, Rajeev; Gropp, William

doi:10.1007/978-3-540-75416-9_46

Cited by 20 publications

(27 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It showed how we can derive the advantages of partial order reduction, as well as completely avoid user effort in modeling MPI primitives, the embedding C++ code, or user level libraries -all advantages compared to [7,8,9]. This paper provides vital measurements missing in [4]. It describes our new implementation, which is a total rewrite of our old implementation, facilitating easy experimentation.…”

Section: In-situ Model Checking Of Mpi Programsmentioning

confidence: 94%

See 1 more Smart Citation

Formal Methods for MPI Programs

Gopalakrishnan

Kirby

2007

Electronic Notes in Theoretical Computer Science

Self Cite

View full text Add to dashboard Cite

High-end computing is universally recognized to be a strategic tool for leadership in science and technology. A significant portion of high-end computing is conducted on clusters running the Message Passing Interface (MPI) library. MPI has become the de facto standard in high performance computing (HPC). Our research addresses the need to avoid bugs in MPI programs through a combination of techniques ranging from the use of formal specifications to the use of in-situ model checking techniques. This paper details an assessment of the efficacy of these techniques, as well as our future work plans.

show abstract

Section: In-situ Model Checking Of Mpi Programsmentioning

confidence: 94%

“…Our first paper on ISP [4] showed how to make DPOR work for MPI on a few small examples. It showed how we can derive the advantages of partial order reduction, as well as completely avoid user effort in modeling MPI primitives, the embedding C++ code, or user level libraries -all advantages compared to [7,8,9].…”

Section: In-situ Model Checking Of Mpi Programsmentioning

confidence: 99%

Formal Methods for MPI Programs

Gopalakrishnan

Kirby

2007

Electronic Notes in Theoretical Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…To avoid this problem, we have developed several in-situ model checkers that work directly on the parallel MPI program and hence avoid the need to create verification models. We reported on the first such dynamic model checking algorithm for MPI in [30]. Techniques to enhance the efficiency of this algorithm were reported in [31].…”

Section: Introductionmentioning

confidence: 99%

Formal methods applied to high‐performance computing software design: a case study of MPI one‐sided communication‐based locking

et al. 2009

Self Cite

View full text Add to dashboard Cite

SUMMARYThere is growing need to address the complexity of verifying the numerous concurrent protocols employed in high performance computing software. Today's approaches for verification consist of testing detailed implementations of these protocols. Unfortunately, this approach can seldom show the absence of bugs, and often results in serious bugs escaping into the deployed software. An approach called Model Checking has been demonstrated to be eminently helpful in debugging these protocols early in the software life cycle by offering the ability to represent and exhaustively analyze simplified formal protocol models. The effectiveness of model checking has yet to be adequately demonstrated in high performance computing. This paper presents a case study of a concurrent protocol that was thought to be sufficiently well tested, but proved to contain two very non-obvious deadlocks in them. These bugs were automatically detected through model checking. The protocol models in which these bugs were detected were also easy to create. Recent work in our group demonstrates that even this tedium of model creation can be eliminated by employing dynamic source-code level analysis methods. Our case study comes from the important domain of Message Passing Interface (MPI) based programming which is universally employed for simulating and predicting anything from the structural integrity of combustion chambers to the path of hurricanes. We argue that model checking must be taught as well as used widely within HPC, given this and similar success stories.

show abstract

“…• Since Fib is implemented as an extension to the dynamic formal verification methodology employed in our tool ISP( [9,13,4]), it is capable of detecting deadlocks, and then aborting its analysis. Here are some example deadlock scenarios that ISP can detect: (i) deadlocks due to a collective barrier being incorrectly placed, (ii) those introduced when the user forgets to issue the (supposed) collective call from within some of the processes, (iii) the user employing the wrong communicator for one of the barrier calls, or (iv) MPI messages not matching.…”

Section: Introductionmentioning

confidence: 99%

A Formal Approach to Detect Functionally Irrelevant Barriers in MPI Programs

Sharma

Vakkalanka

Gopalakrishnan

et al. 2008

Recent Advances in Parallel Virtual Machine and Message Passing Interface

Self Cite

View full text Add to dashboard Cite

Abstract. We examine the unsolved problem of automatically and efficiently detecting functionally irrelevant barriers in MPI programs. A functionally irrelevant barrier is a set of MPI_Barrier calls, one per MPI process, such that their removal does not alter the overall MPI communication structure of the program. Static analysis methods are incapable of solving this problem, as MPI programs can compute many quantities at runtime, including send targets, receive sources, tags, and communicators, and also can have data-dependent control flows. We offer an algorithm called Fib to solve this problem based on dynamic (runtime) analysis. Fib applies to MPI programs that employ 24 widely used twosided MPI operations. We show that it is sufficient to detect barrier calls whose removal causes a wildcard receive statement placed before or after a barrier to now begin matching a send statement with which it did not match before. Fib determines whether a barrier becomes relevant in any interleaving of the MPI processes of a given MPI program. Since the number of interleavings can grow exponentially with the number of processes, Fib employs a sound method to drastically reduce this number, by computing only the relevant interleavings. We show that many MPI programs do not have data dependent control flows, thus making the results of Fib applicable to all the input data the program can accept.

show abstract

Practical Model-Checking Method for Verifying Correctness of MPI Programs

Cited by 20 publications

References 13 publications

Formal Methods for MPI Programs

Formal Methods for MPI Programs

Formal methods applied to high‐performance computing software design: a case study of MPI one‐sided communication‐based locking

A Formal Approach to Detect Functionally Irrelevant Barriers in MPI Programs

Contact Info

Product

Resources

About