Argonne National Laboratory

Durango: Scalable Synthetic Workload Generation for Extreme-Scale Application Performance Modeling and Simulation

TitleDurango: Scalable Synthetic Workload Generation for Extreme-Scale Application Performance Modeling and Simulation
Publication TypeConference Paper
Year of Publication2017
AuthorsCarothers, CD, Vetter, J, Meredith, JS, Mubarak, M, Moore, S, Blanco, MP, LaPre, J
Conference NameSIGSIM-PADS '17
Date Published05/2017
PublisherACM
Conference LocationSingapore
AbstractPerformance modeling of extreme-scale applications on accurate representations of potential architectures is critical for designing next generation supercomputing systems because it is impractical to construct prototype systems at scale with new network hardware in order to explore designs and policies. However, these simulations often rely on static application traces that can be difficult to work with because of their size and lack of flexibility to extend or scale up without rerunning the original application. To address this problem, we have created a new technique for generating scalable, flexible workloads from real applications, we have implemented a prototype, called Durango, that combines a proven analytical performance modeling language, Aspen, with the massively parallel HPC network modeling capabilities of the CODES framework.  
URLhttp://dl.acm.org/citation.cfm?id=30649230.1145/3064911.3064923
DOI10.1145/3064911.3064923
PDFhttp://www.mcs.anl.gov/papers/P7024-0317.pdf