PARCOACH Extension for Hybrid Applications with Interprocedural Analysis

Abstract

Supercomputers are rapidly evolving with now millions of processing units, posing the questions of their programmability. Despite the emergence of more widespread and functional programming models, developing correct and effective parallel applications still remains a complex task. Although debugging solutions have emerged to address this issue, they often come with restrictions. Furthermore, programming model evolutions stress the requirement for a validation tool able to handle hybrid applications. Indeed, as current scientific applications mainly rely on MPI (Message-Passing Interface), new hardwares designed with a larger node-level parallelism advocate for an MPI+X solution with X a shared-memory model like OpenMP. But integrating two different approaches inside the same application can be error-prone leading to complex bugs. In an MPI+X program, not only the correctness of MPI should be ensured but also its interactions with the multi-threaded model. For example, identical MPI collective operations cannot be performed by multiple non-synchronized threads. In this paper, we present an extension of the PARallel COntrol flow Anomaly CHecker (PARCOACH) to enable verification of hybrid HPC applications. Relying on a GCC plugin that combines static and dynamic analysis, the first pass statically verifies the thread level required by an MPI+OpenMP application and outlines execution paths leading to potential deadlocks. Based on this analysis, the code is selectively instrumented, displaying an error and interrupting all processes if the actual scheduling leads to a deadlock situation.Emmanuelle Saillard CEA, DAM,

PARCOACH Extension for a Full-Interprocedural Collectives Verification

“…In [5], we propose a light improvement of PARCOACH static analysis to handle interprocedural information. The method keeps and reuses summaries of functions.…”

“…PARCOACH [3], [5] was designed to take the best of static and dynamic methods. It combines a scalable static analysis based on the study of programs control flow with an instrumentation of the code that verifies potential deadlocks at execution-time.…”

“…PARCOACH only checks if the sequence of collectives is deterministic and supposes all MPI blocking and nonblocking collectives are called with compatible arguments. In [5], we compute summaries of functions in addition to the original static analysis. As shown in section II with MPI codes 4 and 5, even if this solution can improve the intraprocedural static analysis, it reports incomplete root causes of deadlocks.…”