@inproceedings{WendeSteinkeReinefeld, author = {Wende, Florian and Steinke, Thomas and Reinefeld, Alexander}, title = {The Impact of Process Placement and Oversubscription on Application Performance: A Case Study for Exascale Computing}, series = {Proceedings of the 3rd International Conference on Exascale Applications and Software, EASC 2015}, booktitle = {Proceedings of the 3rd International Conference on Exascale Applications and Software, EASC 2015}, editor = {Gray, A. and Smith, L. and Weiland, M.}, publisher = {The University of Edinburgh}, isbn = {978 -0-9 926615 -1-9}, pages = {13 -- 18}, language = {en} } @misc{WendeSteinkeReinefeld, author = {Wende, Florian and Steinke, Thomas and Reinefeld, Alexander}, title = {The Impact of Process Placement and Oversubscription on Application Performance: A Case Study for Exascale Computing}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-53560}, abstract = {With the growing number of hardware components and the increasing software complexity in the upcoming exascale computers, system failures will become the norm rather than an exception for long-running applications. Fault-tolerance can be achieved by the creation of checkpoints during the execution of a parallel program. Checkpoint/Restart (C/R) mechanisms allow for both task migration (even if there were no hardware faults) and restarting of tasks after the occurrence of hardware faults. Affected tasks are then migrated to other nodes which may result in unfortunate process placement and/or oversubscription of compute resources. In this paper we analyze the impact of unfortunate process placement and oversubscription of compute resources on the performance and scalability of two typical HPC application workloads, CP2K and MOM5. Results are given for a Cray XC30/40 with Aries dragonfly topology. Our results indicate that unfortunate process placement has only little negative impact while oversubscription substantially degrades the performance. The latter might be only (partially) beneficial when placing multiple applications with different computational characteristics on the same node.}, language = {en} } @misc{WendeSteinkeKlemmetal., author = {Wende, Florian and Steinke, Thomas and Klemm, Michael and Reinefeld, Alexander}, title = {Concurrent Kernel Offloading}, series = {High Performance Parallelism Pearls}, journal = {High Performance Parallelism Pearls}, editor = {Reinders, James and Jeffers, Jim}, publisher = {Morgan Kaufman, Elsevier}, isbn = {978-0128021187}, language = {en} } @inproceedings{WeinholdLackorzynskiBierbaumetal., author = {Weinhold, Carsten and Lackorzynski, Adam and Bierbaum, Jan and K{\"u}ttler, Martin and Planeta, Maksym and Weisbach, Hannes and Hille, Matthias and H{\"a}rtig, Hermann and Margolin, Alexander and Sharf, Dror and Levy, Ely and Gak, Pavel and Barak, Amnon and Gholami, Masoud and Schintke, Florian and Sch{\"u}tt, Thorsten and Reinefeld, Alexander and Lieber, Matthias and Nagel, Wolfgang}, title = {FFMK: A Fast and Fault-Tolerant Microkernel-Based System for Exascale Computing}, series = {Software for Exascale Computing - SPPEXA 2016-2019}, booktitle = {Software for Exascale Computing - SPPEXA 2016-2019}, publisher = {Springer}, doi = {10.1007/978-3-030-47956-5_16}, pages = {483 -- 516}, language = {en} } @inproceedings{WeinholdLackorzynskiBierbaumetal., author = {Weinhold, Carsten and Lackorzynski, Adam and Bierbaum, Jan and K{\"u}ttler, Martin and Planeta, Maksym and H{\"a}rtig, Hermann and Shiloh, Amnon and Levy, Ely and Ben-Nun, Tal and Barak, Amnon and Steinke, Thomas and Sch{\"u}tt, Thorsten and Fajerski, Jan and Reinefeld, Alexander and Lieber, Matthias and Nagel, Wolfgang}, title = {FFMK: A Fast and Fault-tolerant Microkernel-based System for Exascale Computing}, series = {SPPEXA Symposium 2016}, booktitle = {SPPEXA Symposium 2016}, doi = {10.1007/978-3-319-40528-5_18}, language = {en} } @misc{VanRoyHaridiReinefeldetal.2010, author = {Van Roy, P. and Haridi, Seif and Reinefeld, Alexander and Stefani, J. B.}, title = {The Clouds of Revolution}, publisher = {Public Service Review 19, pp. 449}, year = {2010}, language = {en} } @incollection{StenderBerlinReinefeld2013, author = {Stender, Jan and Berlin, Michael and Reinefeld, Alexander}, title = {XtreemFS - a File System for the Cloud}, series = {Data Intensive Storage Services for Cloud Environments}, booktitle = {Data Intensive Storage Services for Cloud Environments}, editor = {Kyriazis, D. and Voulodimos, A. and Gogouvitis, S. and Varvarigou, Theodora A.}, publisher = {IGI Global}, doi = {10.4018/978-1-4666-3934-8}, year = {2013}, language = {en} } @inproceedings{SteinkeReinefeld2006, author = {Steinke, Thomas and Reinefeld, Alexander}, title = {Experiences with High-Level Programming of FPGAs on Cray XD1}, series = {CUG Proceedings}, booktitle = {CUG Proceedings}, year = {2006}, language = {en} } @inproceedings{ShafaatMoserGhodsietal.2008, author = {Shafaat, Tallat and Moser, Monika and Ghodsi, Ali and Sch{\"u}tt, Thorsten and Reinefeld, Alexander}, title = {On Consistency of Data in Structured Overlay Networks}, series = {Coregrid Integration Workshop}, booktitle = {Coregrid Integration Workshop}, year = {2008}, language = {en} } @inproceedings{ShafaatMoserGhodsietal.2008, author = {Shafaat, Tallat and Moser, Monika and Ghodsi, Ali and Sch{\"u}tt, Thorsten and Haridi, Seif and Reinefeld, Alexander}, title = {Key-Based Consistency and Availability in Structured Overlay Networks}, series = {International ICST Conference on Scalable Information Systems}, booktitle = {International ICST Conference on Scalable Information Systems}, year = {2008}, language = {en} }