Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Daniel Hackenberg"'
Publikováno v:
Proceedings of the 2022 ACM/SPEC on International Conference on Performance Engineering.
Modern processors, in particular within the server segment, integrate more cores with each generation. This increases their complexity in general, and that of the memory hierarchy in particular. Software executed on such processors can suffer from pe
Publikováno v:
CLUSTER
Processor stress tests target to maximize processor power consumption by executing highly demanding workloads. They are typically used to test the cooling and electrical infrastructure of compute nodes or larger systems in labs or data centers. While
Autor:
Thomas Ilsche, Mario Bielert, Markus Velten, Markus Schmidl, Daniel Hackenberg, Robert Schöne
Publikováno v:
CLUSTER
In High Performance Computing, systems are evaluated based on their computational throughput. However, performance in contemporary server processors is primarily limited by power and thermal constraints. Ensuring operation within a given power envelo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ba96c98a56597b6d5e630ad089f7321
http://arxiv.org/abs/2108.00808
http://arxiv.org/abs/2108.00808
Autor:
Thomas Ilsche, Daniel Hackenberg, Robert Schone, Mario Bielert, Franz Hopfner, Wolfgang E. Nagel
Publikováno v:
DAAC@SC
In this paper we present MetricQ, a novel infrastructure for collecting, archiving, and analyzing sensor data. Core components of MetricQ are a scalable message broker based on the Advanced Message Queuing Protocol, and a newly developed Hierarchical
Autor:
Daniel Hackenberg, Joseph Schuchart, Thomas Ilsche, Marc Simon, Yiannis Georgiou, Robert Schöne, Wolfgang E. Nagel
Publikováno v:
SICS Software-Intensive Cyber-Physical Systems. 34:45-52
The rising concern for power consumption of large-scale computer systems puts a research focus on the respective measurement methods. Varying workload patterns and energy efficiency optimizations cause highly dynamic power consumption on today’s co
Publikováno v:
HPCS
The overwhelming majority of High Performance Computing (HPC) systems and server infrastructure uses Intel x86 processors. This makes an architectural analysis of these processors relevant for a wide audience of administrators and performance enginee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27685ba771c7f45e064d5c7dcd3b8855
http://arxiv.org/abs/1905.12468
http://arxiv.org/abs/1905.12468
Autor:
Michael K. Patterson, Daniel Hackenberg, Joseph Schuchart, Thomas Ilsche, Ramkumar Nagappan, Robert Schöne
Publikováno v:
Computer Science-Research and Development
The Intel Haswell-EP processor generation introduces several major advancements of power control and energy-efficiency features. For computationally intense applications using advanced vector extension (AVX) instructions, the processor cannot continu
Publikováno v:
Euro-Par 2017: Parallel Processing Workshops ISBN: 9783319751771
Euro-Par Workshops
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Euro-Par 2017: Parallel Processing Workshops
Euro-Par Workshops
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Euro-Par 2017: Parallel Processing Workshops
Sleep states are an important and well-understood feature of modern server and desktop CPUs that enable significant power savings during idle and partial load scenarios. Making proper decisions about how to use this feature remains a major challenge
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e750eeace762cadd66e9df5df6fc8487
https://doi.org/10.1007/978-3-319-75178-8_50
https://doi.org/10.1007/978-3-319-75178-8_50
Autor:
Joseph Schuchart, Daniel Hackenberg, Thomas Ilsche, Wolfgang E. Nagel, Robert Schöne, Ronny Tschüter
Publikováno v:
Tools for High Performance Computing 2016 ISBN: 9783319567013
Tools for High Performance Computing 2016
Niethammer, Christoph, Gracia, José, Hilbrich,Tobias, Knüpfer, Andreas, M. Resch, Michael, Nagel, Wolfgang E. (Hrsg.), Tools for High Performance Computing 2016-Proceedings of the 10th International Workshop on Parallel Tools for High Performance Computing, October 2016, Stuttgart. Cham: Springer International Publishing, 2017. S. 59-82. ISBN: 978-3-319-56702-0
Tools for High Performance Computing 2016
Niethammer, Christoph, Gracia, José, Hilbrich,Tobias, Knüpfer, Andreas, M. Resch, Michael, Nagel, Wolfgang E. (Hrsg.), Tools for High Performance Computing 2016-Proceedings of the 10th International Workshop on Parallel Tools for High Performance Computing, October 2016, Stuttgart. Cham: Springer International Publishing, 2017. S. 59-82. ISBN: 978-3-319-56702-0
Performance measurement and runtime tuning tools are both vital in the HPC software ecosystem and use similar techniques: the analyzed application is interrupted at specific events and information on the current system state is gathered to be either
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::960396614130d7c69961f8b6298fa5a9
https://doi.org/10.1007/978-3-319-56702-0_4
https://doi.org/10.1007/978-3-319-56702-0_4
Autor:
Nico Reissmann, Mohammed Sourouri, Per Gunnar Kjeldsberg, Johannes Langguth, Espen Birger Raknes, Daniel Hackenberg, Robert Schöne
Publikováno v:
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on -SC '17
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on-SC 17
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
SC
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on-SC 17
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
SC
There is a consensus that exascale systems should operate within a power envelope of 20MW. Consequently, energy conservation is still considered as the most crucial constraint if such systems are to be realized. So far, most research on this topic ha