Zobrazeno 1 - 10
of 119
pro vyhledávání: '"BABAOGLU, OZALP"'
Autor:
Netti, Alessio, Kiziltan, Zeynep, Babaoglu, Ozalp, Sirbu, Alina, Bartolini, Andrea, Borghesi, Andrea
Publikováno v:
Future Generation Computer Systems, Volume 110, September 2020, Pages 1009-1022
As High-Performance Computing (HPC) systems strive towards the exascale goal, failure rates both at the hardware and software levels will increase significantly. Thus, detecting and classifying faults in HPC systems as they occur and initiating corre
Externí odkaz:
http://arxiv.org/abs/2007.14241
Autor:
Netti, Alessio, Kiziltan, Zeynep, Babaoglu, Ozalp, Sirbu, Alina, Bartolini, Andrea, Borghesi, Andrea
As High-Performance Computing (HPC) systems strive towards the exascale goal, studies suggest that they will experience excessive failure rates. For this reason, detecting and classifying faults in HPC systems as they occur and initiating corrective
Externí odkaz:
http://arxiv.org/abs/1810.11208
Autor:
Netti, Alessio, Kiziltan, Zeynep, Babaoglu, Ozalp, Sirbu, Alina, Bartolini, Andrea, Borghesi, Andrea
We present FINJ, a high-level fault injection tool for High-Performance Computing (HPC) systems, with a focus on the management of complex experiments. FINJ provides support for custom workloads and allows generation of anomalous conditions through t
Externí odkaz:
http://arxiv.org/abs/1807.10056
Autor:
Sîrbu, Alina, Babaoglu, Ozalp
Publikováno v:
Cluster Computing, Volume 19, Issue 2, pp 865-878, 2016
Continued reliance on human operators for managing data centers is a major impediment for them from ever reaching extreme dimensions. Large computer systems in general, and data centers in particular, will ultimately be managed using predictive compu
Externí odkaz:
http://arxiv.org/abs/1606.04456
Autor:
Sîrbu, Alina, Babaoglu, Ozalp
For current High Performance Computing systems to scale towards the holy grail of ExaFLOP performance, their power consumption has to be reduced by at least one order of magnitude. This goal can be achieved only through a combination of hardware and
Externí odkaz:
http://arxiv.org/abs/1605.09530
Autor:
Sîrbu, Alina, Babaoglu, Ozalp
Power consumption is a major obstacle for High Performance Computing (HPC) systems in their quest towards the holy grail of ExaFLOP performance. Significant advances in power efficiency have to be made before this goal can be attained and accurate mo
Externí odkaz:
http://arxiv.org/abs/1601.05961
Publikováno v:
Computing, 98(12), Dec 2016, pp. 1225-1249
Current generation of Internet-based services are typically hosted on large data centers that take the form of warehouse-size structures housing tens of thousands of servers. Continued availability of a modern data center is the result of a complex o
Externí odkaz:
http://arxiv.org/abs/1509.00773
Autor:
Sîrbu, Alina, Babaoglu, Ozalp
Continued reliance on human operators for managing data centers is a major impediment for them from ever reaching extreme dimensions. Large computer systems in general, and data centers in particular, will ultimately be managed using predictive compu
Externí odkaz:
http://arxiv.org/abs/1505.04935
Autor:
Sîrbu, Alina, Babaoglu, Ozalp
The complexity and cost of managing high-performance computing infrastructures are on the rise. Automating management and repair through predictive models to minimize human interventions is an attempt to increase system availability and contain these
Externí odkaz:
http://arxiv.org/abs/1410.4449
Publikováno v:
proc. INFORMATIK 2014 Workshop on System Software Support for Big Data (BigSys 2014), Lecture Notes in Informatics (LNI), Volume P-232, pp. 1781-1795, ISBN 78-3-88579-626-8, ISSN 1617-5468
Modern data centers that provide Internet-scale services are stadium-size structures housing tens of thousands of heterogeneous devices (server clusters, networking equipment, power and cooling infrastructures) that must operate continuously and reli
Externí odkaz:
http://arxiv.org/abs/1410.1309