Usage of the SCALASCA toolset for scalable performance analysis of large-scale parallel applications

Wolf, Felix; Wylie, Brian J. N.; Ábrahám, Erika; Becker, Daniel; Frings, Wolfgang; Fürlinger, Karl; Geimer, Markus; Hermanns, Marc-André; Mohr, Bernd; Moore, Shirley; Pfeifer, Matthias; Szebenyi, Zoltán

doi:10.1007/978-3-540-68564-7_10

Cited by 45 publications

(25 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several performance tools use measurement for the purposes of offline performance analysis, including TAU [32], HPCToolkit [1], Scalasca [38], Vampir [20], Extrae [27] and others. All are powerful and capable tools in their own right.…”

Section: Related Workmentioning

confidence: 99%

An Autonomic Performance Environment for Exascale

Huck

Porterfield²,

Chaimov

et al. 2015

JSFI

View full text Add to dashboard Cite

Exascale systems will require new approaches to performance observation, analysis, and runtime decision-making to optimize for performance and efficiency. The standard "first-person" model, in which multiple operating system processes and threads observe themselves and record first-person performance profiles or traces for offline analysis, is not adequate to observe and capture interactions at shared resources in highly concurrent, dynamic systems. Further, it does not support mechanisms for runtime adaptation. Our approach, called APEX (Autonomic Performance Environment for eXascale), provides mechanisms for sharing information among the layers of the software stack, including hardware, operating and runtime systems, and application code, both new and legacy. The performance measurement components share information across layers, merging first-person data sets with information collected by third-person tools observing shared hardware and software states at node-and global-levels. Critically, APEX provides a policy engine designed to guide runtime adaptation mechanisms to make algorithmic changes, re-allocate resources, or change scheduling rules when appropriate conditions occur.

show abstract

Section: Related Workmentioning

confidence: 99%

An Autonomic Performance Environment for Exascale

Huck

Porterfield²,

Chaimov

et al. 2015

JSFI

View full text Add to dashboard Cite

show abstract

“…Scalasca [24], Vampir [21] and TAU [23] are performance tools that collect data from OpenMP applications, among other types of applications. OpenMP data collection in these tools can be done through OPARI [19], DynInst [8].…”

Section: Related Workmentioning

confidence: 99%

On the Instrumentation of OpenMP and OmpSs Tasking Constructs

Servat

Teruel

Llort

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Parallelism has become more and more commonplace with the advent of the multicore processors. Although different parallel programming models have arisen to exploit the computing capabilities of such processors, developing applications that take benefit of these processors may not be easy. And what is worse, the performance achieved by the parallel version of the application may not be what the developer expected, as a result of a dubious utilization of the resources offered by the processor.We present in this paper a fruitful synergy of a shared memory parallel compiler and runtime, and a performance extraction library. The objective of this work is not only to reduce the performance analysis life-cycle when doing the parallelization of an application, but also to extend the analysis experience of the parallel application by incorporating data that is only known in the compiler and runtime side. Additionally we present performance results obtained with the execution of instrumented application and evaluate the overhead of the instrumentation.

show abstract

“…Many tools offer the ability to obtain MPI profiles, including Open|SpeedShop [8], TAU [6], and Scalasca [9]. For the following experiments, we used mpiP [10], which provides information such as total time spent in MPI calls versus total application time and also the top MPI calls and their respective call sites where most of the time was spent.…”

Section: B Per-phase Datamentioning

confidence: 99%

“…Again, though, this work only supports visualizations of how the observed data relates to the application source code, and not how it relates to application semantics. Finally, many existing parallel performance tracing frameworks [7], [9], [15], [16], [17] attempt to visualize the behavior of large-scale parallel programs, either by visualizing communication between processes, by visualizing hardware metrics on a torus, or by examining communication traces using three-dimensional views. None of these, however, support the projection of application data into performance domains or vice versa, limiting their ability to pinpoint performance bottlenecks through the kind of correlation analysis presented in this paper.…”

Section: Per-core Per-phase Datamentioning

confidence: 99%

Novel views of performance data to analyze large-scale adaptive applications

Bhatelé

Gamblin

Isaacs

et al. 2012

2012 International Conference for High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

Abstract-Performance analysis of parallel scientific codes is becoming increasingly difficult due to the rapidly growing complexity of applications and architectures. Existing tools fall short in providing intuitive views that facilitate the process of performance debugging and tuning. In this paper, we extend recent ideas of projecting and visualizing performance data for faster, more intuitive analysis of applications. We collect detailed per-level and per-phase measurements for a dynamically load-balanced, structured AMR library and project per-core data collected in the hardware domain on to the application's communication topology. We show how our projections and visualizations lead to a rapid diagnosis of and mitigation strategy for a previously elusive scaling bottleneck in the library that is hard to detect using conventional tools. Our new insights have resulted in a 22% performance improvement for a 65,536-core run of the AMR library on an IBM Blue Gene/P system.

show abstract

Usage of the SCALASCA toolset for scalable performance analysis of large-scale parallel applications

Cited by 45 publications

References 6 publications

An Autonomic Performance Environment for Exascale

An Autonomic Performance Environment for Exascale

On the Instrumentation of OpenMP and OmpSs Tasking Constructs

Novel views of performance data to analyze large-scale adaptive applications

Contact Info

Product

Resources

About