Rolf Clauberg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Rolf Clauberg has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
A. Blacha
IBM Res. Div., Ruschlikon, Switzerland
11 shared publicationsH. Beha
IBM Res. Div., Ruschlikon, Switzerland
10 shared publicationsE. Kisker
Institut für Festkörperforschung der Kernforschungsanlage Jülich, D-5170 Jülich, West Germany
7 shared publicationsW. Gudat
Institut für Festkörperforschung der KFA Jülich
6 shared publicationsH. Hopster
Institut für Festkörperforschung, Kernforschungsanlage Jülich, D-5170 Jülich, West Germany, and II Physikalisches Institut, Universität Köln, D-5000 Köln 41, West Germany
5 shared publicationsH.K. Seitz
IBM Res. Div., Ruschlikon, Switzerland
5 shared publications
Latest Publications
- 1 January 2022
- Published by Nizhny Novgorod Linguistics University in Germanic Philology in Russia: Yearbook of the Russian Union of Germanists
- Vol. 19
Swiss German in a Changing World
Dieser Artikel untersucht die besondere Bedeutung der Deutschschweizer Mundart-Dialekte für die Schweiz und insbesondere für die Deutschschweizer. Nach einer kurzen Betrachtung der Bevölkerungsstruktur der Schweiz und der damit verbundenen nationalen Sprachen, konzentrieren wir uns auf die Deutschschweiz als grössten Teil der Schweiz und der Rolle der deutschen bzw. schweizerdeutschen Sprache. Zuerst werden die Schriftsprachen, dann die gesprochenen Sprachen verglichen. Obwohl die Schriftsprachen deutliche Unterschiede erkennen lassen, sind sie immer noch so nahe beieinander, dass die Kommunikation von Deutschschweizern mit Deutschen oder Österreichern damit problemlos ist. Ganz anders sieht es bei der Kommunikation mit den Mundarten aus. Hier ist eine Kommunikation innerhalb der Schweizerdeutschen Dialekte möglich, aber äusserst schwierig zwischen Deutschschweizern und Deutschen. Die Schweizerdeutschen Dialekte spielen eine sehr wichtige Rolle im nationalen Selbstverständnis der Schweizer, speziell als Abgrenzung gegen Deutschland und Definition des Deutschschweizers und sogar des Schweizer...
- 1 January 2022
- Published by Nizhny Novgorod Linguistics University in Germanic Philology in Russia: Yearbook of the Russian Union of Germanists
- Vol. 19
Swiss German in a Changing World
Dieser Artikel untersucht die besondere Bedeutung der Deutschschweizer Mundart-Dialekte für die Schweiz und insbesondere für die Deutschschweizer. Nach einer kurzen Betrachtung der Bevölkerungsstruktur der Schweiz und der damit verbundenen nationalen Sprachen, konzentrieren wir uns auf die Deutschschweiz als grössten Teil der Schweiz und der Rolle der deutschen bzw. schweizerdeutschen Sprache. Zuerst werden die Schriftsprachen, dann die gesprochenen Sprachen verglichen. Obwohl die Schriftsprachen deutliche Unterschiede erkennen lassen, sind sie immer noch so nahe beieinander, dass die Kommunikation von Deutschschweizern mit Deutschen oder Österreichern damit problemlos ist. Ganz anders sieht es bei der Kommunikation mit den Mundarten aus. Hier ist eine Kommunikation innerhalb der Schweizerdeutschen Dialekte möglich, aber äusserst schwierig zwischen Deutschschweizern und Deutschen. Die Schweizerdeutschen Dialekte spielen eine sehr wichtige Rolle im nationalen Selbstverständnis der Schweizer, speziell als Abgrenzung gegen Deutschland und Definition des Deutschschweizers und sogar des Schweizer...
- Open Access
- 15 December 2020
- Published by Peoples' Friendship University of Russia in RUDN Journal of Economics
- Vol. 28 (3) , 556-567
Challenges of digitalization and artificial intelligence for modern economies, societies and management
This study aims at identifying the challenges of digitalization and artificial intelligence for modern economies, societies and business administration. The implementation of digitalization schemes as Industry 4.0 are presently official policy of many developed countries. The goal is optimization of production processes and supply chains. Artificial intelligence is also affecting many fields. Both technologies are expected to substantially change working conditions for many people. It is important to identify the kind and impact of these changes and possible means to minimize negative effects. For this purpose, this study uses previous results about the disappearance of manufacturing jobs in the USA and their impact on different groups of society together with technical information about the new technologies to deduce expected changes caused by digitalization and artificial intelligence. Results are that both technologies will destroy large numbers of jobs and complete job classes while at the same time creating new jobs very different from the ones destroyed. Extensive permanent education and re-education of employees will be necessary to minimize negative effects, probably even changes to a more broad-based education to improve the potential of job changes into completely new fields. In addition, the technical information about digitalization in cyber-physical systems points to dangers that will require solutions on the international level.
- 15 December 2020
- Published by Peoples' Friendship University of Russia in RUDN Journal of Economics
- Vol. 28 (3) , 556-567
Open AccessChallenges of digitalization and artificial intelligence for modern economies, societies and management
This study aims at identifying the challenges of digitalization and artificial intelligence for modern economies, societies and business administration. The implementation of digitalization schemes as Industry 4.0 are presently official policy of many developed countries. The goal is optimization of production processes and supply chains. Artificial intelligence is also affecting many fields. Both technologies are expected to substantially change working conditions for many people. It is important to identify the kind and impact of these changes and possible means to minimize negative effects. For this purpose, this study uses previous results about the disappearance of manufacturing jobs in the USA and their impact on different groups of society together with technical information about the new technologies to deduce expected changes caused by digitalization and artificial intelligence. Results are that both technologies will destroy large numbers of jobs and complete job classes while at the same time creating new jobs very different from the ones destroyed. Extensive permanent education and re-education of employees will be necessary to minimize negative effects, probably even changes to a more broad-based education to improve the potential of job changes into completely new fields. In addition, the technical information about digitalization in cyber-physical systems points to dangers that will require solutions on the international level.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 924-929
Catch It If You Can: Real-Time Network Anomaly Detection with Low False Alarm Rates
Unsupervised anomaly detection (AD) has shown promise against the frequently new cyberattacks. But, as anomalies are not always malicious, such systems generate prodigious false alarm rates. The resulting manual validation workload often overwhelms the IT operators: it slows down the system reaction by orders of magnitude and ultimately thwarts its applicability. Therefore, we propose a real-time network AD system that reduces the manual workload by coupling 2 learning stages. The first stage performs adaptive unsupervised AD using a shallow autoencoder. The second stage uses a custom nearest-neighbor classifier to filter the false positives by modeling the manual classification. We implement a prototype for 10-50Gbps speeds and evaluate it with traffic from a national network operator: we achieve 98.5% true and 1.3% false positive rates, while reducing the human intervention rate by 5x.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 924-929
Catch It If You Can: Real-Time Network Anomaly Detection with Low False Alarm Rates
Unsupervised anomaly detection (AD) has shown promise against the frequently new cyberattacks. But, as anomalies are not always malicious, such systems generate prodigious false alarm rates. The resulting manual validation workload often overwhelms the IT operators: it slows down the system reaction by orders of magnitude and ultimately thwarts its applicability. Therefore, we propose a real-time network AD system that reduces the manual workload by coupling 2 learning stages. The first stage performs adaptive unsupervised AD using a shallow autoencoder. The second stage uses a custom nearest-neighbor classifier to filter the false positives by modeling the manual classification. We implement a prototype for 10-50Gbps speeds and evaluate it with traffic from a national network operator: we achieve 98.5% true and 1.3% false positive rates, while reducing the human intervention rate by 5x.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Real-time security services for SDN-based datacenters
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Real-time security services for SDN-based datacenters
- 11 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 36 (6) , 50-58
Unbiased Quantized Congestion Notification for Scalable Server Fabrics
Ethernet is the predominant layer-2 networking technology in the datacenter, and it is evolving into an economical alternative for high-performance computing clusters. Ethernet traditionally drops packets in the event of congestion, but IEEE introduced lossless class services to enable the convergence of storage and IP networks. Losslessness is a simple, well-known concept, but its application in datacenters is hampered by the fear of ensuing saturation trees. In this article, the authors aim to accelerate the deployment of Quantized Congestion Notification (QCN). In particular, they first eliminate the intrinsic unfairness of QCN under typical fan-in scenarios by installing the congestion points at inputs, instead of at outputs as standard QCN does. They then demonstrate that QCN at input buffers cannot always discriminate between culprit and victim flows. To overcome this limitation, they propose a novel QCN-compatible marking scheme called "occupancy sampling." They have implemented these methods in a server-rack fabric with 640 100-Gigabit Ethernet ports.
- 11 November 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 36 (6) , 50-58
Unbiased Quantized Congestion Notification for Scalable Server Fabrics
Ethernet is the predominant layer-2 networking technology in the datacenter, and it is evolving into an economical alternative for high-performance computing clusters. Ethernet traditionally drops packets in the event of congestion, but IEEE introduced lossless class services to enable the convergence of storage and IP networks. Losslessness is a simple, well-known concept, but its application in datacenters is hampered by the fear of ensuing saturation trees. In this article, the authors aim to accelerate the deployment of Quantized Congestion Notification (QCN). In particular, they first eliminate the intrinsic unfairness of QCN under typical fan-in scenarios by installing the congestion points at inputs, instead of at outputs as standard QCN does. They then demonstrate that QCN at input buffers cannot always discriminate between culprit and victim flows. To overcome this limitation, they propose a novel QCN-compatible marking scheme called "occupancy sampling." They have implemented these methods in a server-rack fabric with 640 100-Gigabit Ethernet ports.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 23813555,p. 1-4
Power measurements and cooling of the DOME 28nm 1.8GHz 24-thread ppc64 μServer compute node
Within the IBM/ASTRON DOME μServer project, we are finishing two types of memory DIMM-like sized compute nodes. The first is based on the 4-core/4-thread 2.2 GHz P5040 45nm SoC and the second on a 12-core/24-thread 1.8 GHz T4240 28nm SoC. Both SoCs employ the 64-bit Power instruction set. We show T4240 Specbench performance results, power consumption, describe the packaging of our first P5040 based 8-way hot-water cooled cluster and provide an outlook.
- 1 June 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 23813555,p. 1-4
Power measurements and cooling of the DOME 28nm 1.8GHz 24-thread ppc64 μServer compute node
Within the IBM/ASTRON DOME μServer project, we are finishing two types of memory DIMM-like sized compute nodes. The first is based on the 4-core/4-thread 2.2 GHz P5040 45nm SoC and the second on a 12-core/24-thread 1.8 GHz T4240 28nm SoC. Both SoCs employ the 64-bit Power instruction set. We show T4240 Specbench performance results, power consumption, describe the packaging of our first P5040 based 8-way hot-water cooled cluster and provide an outlook.
- 1 February 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
4.4 Energy-efficient microserver based on a 12-core 1.8GHz 188K-CoreMark 28nm bulk CMOS 64b SoC for big-data applications with 159GB/S/L memory bandwidth system density
MicroServers integrate an entire server motherboard into a single Server-on-a-Chip (SoC), excluding DRAM, NOR-boot and power conversion circuits. This technology has evolved to 64b processing able to run server-class operating systems (OS), and the newest SoCs also target cloud computing and business SW [1]. The DOME μServer [2] packages the T4240 SoC in a dense node.
- 1 February 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
4.4 Energy-efficient microserver based on a 12-core 1.8GHz 188K-CoreMark 28nm bulk CMOS 64b SoC for big-data applications with 159GB/S/L memory bandwidth system density
MicroServers integrate an entire server motherboard into a single Server-on-a-Chip (SoC), excluding DRAM, NOR-boot and power conversion circuits. This technology has evolved to 64b processing able to run server-class operating systems (OS), and the newest SoCs also target cloud computing and business SW [1]. The DOME μServer [2] packages the T4240 SoC in a dense node.
- 19 March 2014
- Published by Springer Nature in Design Automation for Embedded Systems
- Vol. 18 (3-4) , 183-197
Tandem queue weighted fair smooth scheduling
- 19 March 2014
- Published by Springer Nature in Design Automation for Embedded Systems
- Vol. 18 (3-4) , 183-197
Tandem queue weighted fair smooth scheduling
- Open Access
- 23 January 2013
- Published by Association for Computing Machinery (ACM)
- p. 5-8
Arbitration of many thousand flows at 100G and beyond
- 23 January 2013
- Published by Association for Computing Machinery (ACM)
- p. 5-8
Open AccessArbitration of many thousand flows at 100G and beyond
- 1 August 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15504794,p. 64-71
Occupancy Sampling for Terabit CEE Switches
One consequential feature of Converged Enhanced Ethernet (CEE) is loss lessness, achieved through L2 Priority Flow Control (PFC) and Quantized Congestion Notification (QCN). We focus on QCN and its effectiveness in identifying congestive flows in input-buffered CEE switches. QCN assumes an idealized, output-queued switch, however, as future switches scale to higher port counts and link speeds, purely output-queued or shared-memory architectures lead to excessive memory bandwidth requirements, moreover, PFC typically requires dedicated buffers per input. Our objective is to complement PFC's coarse per-port/priority granularity with QCN's per-flow control. By detecting buffer overload early, QCN can drastically reduce PFC's side effects. We install QCN congestion points (CPs) at input buffers with virtual output queues and demonstrate that arrival-based marking cannot correctly discriminate between culprits and victims. Our main contribution is occupancy sampling (QCN-OS), a novel, QCN-compatible marking scheme. We focus on random occupancy sampling, a practical method not requiring any per-flow state. For CPs with arbitrarily scheduled buffers, QCN-OSis shown to correctly identify congestive flows, improving buffer utilization, switch efficiency, and fairness.
- 1 August 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15504794,p. 64-71
Occupancy Sampling for Terabit CEE Switches
One consequential feature of Converged Enhanced Ethernet (CEE) is loss lessness, achieved through L2 Priority Flow Control (PFC) and Quantized Congestion Notification (QCN). We focus on QCN and its effectiveness in identifying congestive flows in input-buffered CEE switches. QCN assumes an idealized, output-queued switch, however, as future switches scale to higher port counts and link speeds, purely output-queued or shared-memory architectures lead to excessive memory bandwidth requirements, moreover, PFC typically requires dedicated buffers per input. Our objective is to complement PFC's coarse per-port/priority granularity with QCN's per-flow control. By detecting buffer overload early, QCN can drastically reduce PFC's side effects. We install QCN congestion points (CPs) at input buffers with virtual output queues and demonstrate that arrival-based marking cannot correctly discriminate between culprits and victims. Our main contribution is occupancy sampling (QCN-OS), a novel, QCN-compatible marking scheme. We focus on random occupancy sampling, a practical method not requiring any per-flow state. For CPs with arbitrarily scheduled buffers, QCN-OSis shown to correctly identify congestive flows, improving buffer utilization, switch efficiency, and fairness.