escience2019 has ended
Wednesday, September 25 • 11:00am - 11:30am
Scalable Performance Awareness for In Situ Scientific Applications

Sign up or log in to save this to your schedule and see who's attending!

Matthew Wolf (Oak Ridge National Laboratory), Jong Choi (Oak Ridge National Laboratory), Greg Eisenhauer (Georgia Institute of Technology), Stéphane Ethier (Princeton Plasma Physics Laboratory), Kevin Huck (University of Oregon), Scott Klasky (Oak Ridge National Laboratory), Jeremy Logan (Oak Ridge National Laboratory), Allen Malony (University of Oregon), Chad Wood (University of Oregon), Julien Dominski (Princeton Plasma Physics Laboratory), and Gabriele Merlo (University of Texas, Austin)

Part of the promise of exascale computing and the next generation of scientific simulation codes is the ability to bring together time and spatial scales that have traditionally been treated separately. This enables creating complex coupled simulations and in situ analysis pipelines, encompassing such things as "whole device" fusion models or the simulation of cities from sewers to rooftops. Unfortunately, the HPC analysis tools that have been built up over the preceding decades are ill suited to the debugging and performance analysis of such computational ensembles. In this paper, we present a new vision for performance measurement and understanding of HPC codes, MONitoring Analytics (MONA). MONA is designed to be a flexible, high performance monitoring infrastructure that can perform monitoring analysis in place or in transit by embedding analytics and characterization directly into the data stream, without relying upon delivering all monitoring information to a central database for post-processing. It addresses the trade-offs between the prohibitively expensive capture of all performance characteristics and not capturing enough to detect the features of interest. We demonstrate several uses of MONA; capturing and indexing multi-executable performance profiles to enable later processing, extraction of performance primitives to enable the generation of customizable benchmarks and performance skeletons, and extracting communication and application behaviors to enable better control and placement for the current and future runs of the science ensemble. Relevant performance based on a system for MONA built from ADIOS and SOSFlow technologies are provided for DOE science applications and leadership machines.


Matthew Wolf

Oak Ridge National Laboratory

Wednesday September 25, 2019 11:00am - 11:30am
Boardroom West