Logo des Repositoriums

Auflistung nach Schlagwort "Java Virtual Machine"

1 - 2 von 2
  • Konferenzbeitrag
    Analysis and Optimization of Task Granularity on the Java Virtual Machine
    (Software Engineering 2020, 2020) Rosà, Andrea; Rosales, Eduardo; Binder, Walter
    Our article published in ACM Transactions on Programming Languages and Systems (TOPLAS) (which extends our work published in the proceedings of the 2018 IEEE/ACM International Symposium on Code Generation and Optimization (CGO 2018))presents a new methodology to accurately and efficiently collect the granularity of each executed task. Task granularity, i.e., the amount of work performed by parallel tasks, is a key performance attribute of parallel applications. On the one hand, fine-grained tasksmay introduce considerable parallelization overheads. On the other hand, coarse-grained tasks may not fully utilize the available CPU cores, leading to missed parallelization opportunities. We implement our methodology in tgp, a novel task-granularity profiler that collects carefully selected metrics from the whole system stack with low overhead, and helps developers locate performance and scalability problems. We analyze task granularity in the DaCapo, ScalaBench, and Spark Perf benchmark suites, revealing inefficiencies related to fine-grained and coarse-grained tasks in several applications We demonstrate that the collected task-granularity profiles are actionable by optimizing task granularity in several applications, achieving speedups up to a factor of 5.9x. tgp is available open-source at https://github.com/fithos/tgp/
  • Konferenzbeitrag
    Post-Debugging in Large Scale Big Data Analytic Systems
    (Datenbanksysteme für Business, Technologie und Web (BTW 2017) - Workshopband, 2017) Bergen, Eduard; Edlich, Stefan
    Data scientists often need to fine tune and resubmit their jobs when processing a large quantity of data in big clusters because of a failed behavior of currently executed jobs. Consequently, data scientists also need to filter, combine, and correlate large data sets. Hence, debugging a job locally helps data scientists to figure out the root cause and increases efficiency while simplifying the working process. Discovering the root cause of failures in distributed systems involve a different kind of information such as the operating system type, executed system applications, the execution state, and environment variables. In general, log files contain this type of information in a cryptic and large structure. Data scientists need to analyze all related log files to get more insights about the failure and this is cumbersome and slow. Another possibility is to use our reference architecture. We extract remote data and replay the extraction on the developer’s local debugging environment.