Speaker: Emmanuelle Saillard

Title: Static/dynamic analyses for validation and improvements of multi-models HPC applications

Abstract: Supercomputing plays in important role in several innovative fields, speeding up prototyping or validating scientific theories. However, supercomputers are evolving rapidly with now millions of processing units, posing the questions of their programmability. Despite the emergence of more widespread and functional parallel programming models, developing correct and effective parallel applications still remain a complex task. Although debugging solutions have emerged to address this issue, they often come with restrictions.

However, programming model evolutions stress the requirement for a convenient validation tool able to handle hybrid applications. Indeed, as current scientific applications mainly rely on the MPI parallel programming model, new hardwares designed for Exascale with higher node-level parallelism clearly advocate for an MPI+X solutions with X a thread-based model such as OpenMP. But integrating two different programming models inside the same application can be error-prone leading to complex bugs – unfortunately mostly detected at runtime. 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.

This thesis aims at developing a combination of static and dynamic analysis to enable a scalable verification of hybrid HPC applications. The first pass statically verifies the thread level required by an MPI+OpenMP application and outlines execution paths leading to potential deadlocks. Thanks to this analysis, is selectively instrumented, displaying an error and synchronously interrupting all processes if the actual scheduling leads to a deadlock situation. Our method as been implemented as a plugin in the GCC compiler to avoid compiler recompilation.

Bio: Emmanuelle Saillard obtained a M.Sc. in Computer Science in 2012 from the University of Versailles. She is in a PhD program at CEA DAM (Military Applications Department of the French Atomic Energy Authority) since september 2012.