Engineering Algorithms for Scalability through Continuous Validation of Performance Expectations

Autor: Yannick Berens, Torsten Hoefler, Alexandru Calotoiu, Felix Wolf, Alexandre Strube, Sergei Shudler

Publikováno v: IEEE Transactions on Parallel and Distributed Systems. 30:1768-1785

Many libraries in the HPC field use sophisticated algorithms with clear theoretical scalability expectations. However, hardware constraints or programming bugs may sometimes render these expectations inaccurate or even plainly wrong. While algorithm

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::96decec1f3bb7557097e86dab074f8ec
https://doi.org/10.1109/tpds.2019.2896993

Remote Sensing Big Data Classification with High Performance Distributed Deep Learning

Autor: Alexandre Strube, Jenia Jitsev, Jon Atli Benediktsson, Gabriele Cavallaro, Rocco Sedona, Morris Riedel

Publikováno v: Remote Sensing
Volume 11
Issue 24
Pages: 3056
Remote sensing 11(24), 3056-(2019). doi:10.3390/rs11243056

High-Performance Computing (HPC) has recently been attracting more attention in remote sensing applications due to the challenges posed by the increased amount of open data that are produced daily by Earth Observation (EO) programs. The unique parall

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf4ec77e311adfae00c7b955a017ae58

Automatic Performance Modeling of HPC Applications

Autor: Christian Iwainsky, Torsten Hoefler, Andreas Vogel, Grzegorz Kwasniewski, Felix Wolf, Alexandru Calotoiu, Alexandre Strube, Christian Bischof, Bernd Mohr, Sergei Shudler, Gabriel Wittum

Publikováno v: Lecture Notes in Computational Science and Engineering ISBN: 9783319405261
Software for Exascale Computing

Many existing applications suffer from inherent scalability limitations that will prevent them from running at exascale. Current tuning practices, which rely on diagnostic experiments, have drawbacks because (i) they detect scalability problems relat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::453913a867078ba4a598d063d5b36ebd
https://doi.org/10.1007/978-3-319-40528-5_20

How Many Threads will be too Many? On the Scalability of OpenMP Implementations

Autor: Michael Knobloch, Alexandru Calotoiu, Christian Iwainsky, Christian Bischof, Alexandre Strube, Sergei Shudler, Felix Wolf

Publikováno v: Lecture Notes in Computer Science ISBN: 9783662480953
Euro-Par

Exascale systems will exhibit much higher degrees of parallelism both in terms of the number of nodes and the number of cores per node. OpenMP is a widely used standard for exploiting parallelism on the level of individual nodes. Although successfull

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2f68cc8f0ca579654cb8050aa8aa1e56
https://doi.org/10.1007/978-3-662-48096-0_35

Extending Scalasca's analysis features

Autor: Daniel Lorenz, David Böhme, Bernd Mohr, Alexandre Strube, Zoltán Szebenyi

Publikováno v: Berlin : Springer 200 S (2013). doi:10.1007/978-3-642-37349-7_8
Tools for High Performance Computing 2012
Tools for High Performance Computing 20126th International Parallel Tools Workshop, Stuttgart, Germany, 2012-09-25-2012-09-28
Tools for High Performance Computing 2012 ISBN: 9783642373480

Scalasca is a performance analysis tool, which parses the trace of an application run for certain patterns that indicate performance inefficiencies. In this paper, we present recently developed new features in Scalasaca. In particular, we describe tw

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c1166910f688a2e6a72a17e43bfcf3d
https://juser.fz-juelich.de/record/128962