Resource-Management Study in HPC Runtime-Stacking Context

Arthur Loussert (1, 2) , Benoît Welterlen (3) , Patrick Carribault (1) , Julien Jaeger (1) , Marc Pérache (1) , Raymond Namyst (2)

1 DAM/DIF - DAM Île-de-France
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
3 Bull atos technologies

With the advent of multicore and manycore processors as building blocks of HPC supercomputers, many applications shift from relying solely on a distributed programming model (e.g., MPI) to mixing distributed and shared-memory models (e.g., MPI+OpenMP), to better exploit shared-memory communications and reduce the overall memory footprint. One side effect of this programming approach is runtime stacking: mixing multiple models involve various runtime libraries to be alive at the same time and to share the underlying computing resources. This paper explores different configurations where this stacking may appear and introduces algorithms to detect the misuse of compute resources when running a hybrid parallel application. We have implemented our algorithms inside a dynamic tool that monitors applications and outputs resource usage to the user. We validated this tool on applications from CORAL benchmarks. This leads to relevant information which can be used to improve runtime placement, and to an average overhead lower than 1% of total execution time.

Domaines: Calcul parallèle, distribué et partagé [cs.DC]

Arthur Loussert, Benoît Welterlen, Patrick Carribault, Julien Jaeger, Marc Pérache, et al.. Resource-Management Study in HPC Runtime-Stacking Context. SBAC-PAD 2017 - 29th International Symposium on Computer Architecture and High Performance Computing, Oct 2017, Campinas, Brazil. pp.177-184, ⟨10.1109/SBAC-PAD.2017.30⟩. ⟨hal-01682286⟩