| 1. |
- de Blanche, Andreas, 1975, et al.
(author)
-
Dual Core Efficiency for Engineering Simulation Applications
- 2008
-
In: International Conference on Parallel and Distributed Processing Techniques and Applications, Las Vegas, NV, USA, 14-17 July 2008. ; , s. 888-894
-
Conference paper (peer-reviewed)abstract
- With the event of multi-core processors the parallel execution of simulation applications has resulted in new problems and possibilities in resource usage in high performance computing (HPC). In this paper we have investigated the impact of execution of engineering applications utilizing one and two cores in an Intel Core 2 Duo based Linux cluster. In engineering industry the number of licenses puts practical and economical constraints on the maximum number of processes. Consequently the issue of how to distribute a given number of processes over the compute nodes in a HPC resource becomes very important. When distributing the application over multiple nodes we found that having N processes on N computer nodes, only using one core on each node, is significantly faster than running N processes on N cores in N/2 computer nodes. Only in one case out of 32 it was beneficial to use both cores. The “one compute node – one simulation process” approach gave an average cost efficiency increase of 16.5%, and for several sub-cases it is actually costbeneficial to run on more nodes than fewer, which decreases the overall run time.
|
|
| 2. |
- de Blanche, Andreas, 1975-, et al.
(author)
-
Multicore Clusters for CFD Simulations : Comparative Study of Three CFD-Softwares
- 2012
-
In: PROCEEDINGS OFTHE 2012 INTERNATIONAL CONFERENCE ONPARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES ANDAPPLICATIONS, PART II. - : CSREA Press. - 1601322275 - 1601322283 ; , s. 855-852
-
Conference paper (peer-reviewed)abstract
- Multicore processors have come to stay, fulfill Moore’s law and might very well revolutionize the computer industry. However, we are now in a transitional period before the new programming models, numerical algorithms and general computer architecture have been developed and the software has been rewritten. This paper focuses on the effects multicore based systems have on industrial computational fluid dynamics (CFD) simulations. The most significant finding was that five of the models ran faster when only one process was executed on each multicore node instead of two. In these cases the execution time was increased by between 6.5% and 64% with a median increase of 10% when utilizing both cores.
|
|
| 3. |
- Namaki, Nima, 1975-, et al.
(author)
-
A Tool for Processor Dependency Characterization of HPC Applications
- 2009
-
In: Proceedings for the HPC Asia & APAN 2009. - Hsinchu, Taiwan : National Center for High-Performance Computing. - 9789868522800 ; , s. 70-76
-
Conference paper (peer-reviewed)abstract
- In this paper we have implemented and verified Cpugen, a tool for characterization of processor resource utilization of HPC applications .Toward this end we implemented Cpugen, an application with good accuracy for processor load generation. Cpugen was verified through three different phases of passive, active and real world application measurements. The measurement results show that our implemented method is a viable option for non-intrusive, stable and robust load generation. The error range for all generated target loads are between 0.00% minimum and 1.04% maximum, with a median deviation of 0.11%. We can conclude that the method utilized in this investigation provides the ability to generate stable and robust processor load.
|
|
| 4. |
- Namaki, Nima, 1975-, et al.
(author)
-
Exhausted Dominated Performance : Basic Proof of Concept
- 2010
-
In: International conference on Parallel and Distributed Processing Techniques and Applications. - Las Vegas : CSREA. - 1601321562 - 1601321570 ; , s. 63-67
-
Conference paper (peer-reviewed)
|
|
| 5. |
- Namaki, Nima, 1975-, et al.
(author)
-
Exhaustion dominated performance : a first attempt
- 2009
-
In: SAC '09. - New York, NY, USA : ACM. - 9781605581668 ; , s. 1011-1012
-
Conference paper (peer-reviewed)abstract
- In this paper we present a first attempt to an analytical method to discover and understand how the available resources influence the execution time. Our method is based on a piecewise linear model for dominating execution limitations and black-box observations. We verify this analysis method by a set of real-world experiments. Finally, we conclude that the different effects follow a linear superposition within a certain range.
|
|
| 6. |
|
|
| 7. |
- Andersson, H. Robert H., et al.
(author)
-
Flipping the Data Center Network : Increasing East-West Capacity Using Existing Hardware
- 2017
-
In: 2017 IEEE 42nd Conference on Local Computer Networks (LCN), 9-12 Oct. 2017. - : IEEE. - 9781509065233 - 9781509065226 ; , s. 211-214
-
Conference paper (peer-reviewed)abstract
- In today's datacenters, there is an increasing demand for more network traffic capacity. The majority of the increase in traffic is internal to the datacenter, i.e., it flows between different servers within the datacenter. This category of traffic is often referred to as east-west traffic and traditional hierarchical architectures are not well equipped to handle this type of traffic. Instead, they are better suited for the north-southbound traffic between hosts and the Internet. One suggested solution for this capacity problem is to adopt a folded CLOS topology, also known as spine-leaf, which often relies on software defined network (SDN) controllers to manage traffic. This paper shows that it is possible to implement a spine-leaf network using commodity-ofthe-shelf switches and thus improve the east-west traffic capacity. This can be obtained using low complexity configuration and edgerouting for load balancing, eliminating the need for a centralized SDN controller.
|
|
| 8. |
- de Blanche, Andreas, 1975-, et al.
(author)
-
A methodology for estimating co-scheduling slowdowns due to memory bus contention on multicore nodes
- 2014
-
In: Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2014. - : ACTA Press. - 9780889869677 - 9780889869653 ; , s. 216-223
-
Conference paper (peer-reviewed)abstract
- When two or more programs are co-scheduled on the same multicore computer they might experience a slowdown due to the limited off-chip memory bandwidth. According to our measurements, this slowdown does not depend on the total bandwidth use in a simple way. One thing we observe is that a higher memory bandwidth usage will not always lead to a larger slowdown. This means that relying on bandwidth usage as input to a job scheduler might cause non-optimal scheduling of processes on multicore nodes in clusters, clouds, and grids. To guide scheduling decisions, we instead propose a slowdown based characterization approach. Real slowdowns are complex to measure due to the exponential number of experiments needed. Thus, we present a novel method for estimating the slowdown programs will experience when co-scheduled on the same computer. We evaluate the method by comparing the predictions made with real slowdown data and the often used memory bandwidth based method. This study show that a scheduler relying on slowdown based categorization makes fewer incorrect co-scheduling choices and the negative impact on program execution times is less than when using a bandwidth based categorization method.
|
|
| 9. |
- de Blanche, Andreas, 1975-, et al.
(author)
-
Addressing characterization methods for memory contention aware co-scheduling
- 2015
-
In: Journal of Supercomputing. - : Springer Science and Business Media LLC. - 0920-8542 .- 1573-0484. ; 71:4, s. 1451-1483
-
Journal article (peer-reviewed)abstract
- The ability to precisely predict how memory contention degrades performance when co-scheduling programs is critical for reaching high performance levels in cluster, grid and cloud environments. In this paper we present an overview and compare the performance of state-of-the-art characterization methods for memory aware (co-)scheduling. We evaluate the prediction accuracy and co-scheduling performance of four methods: one slowdown-based, two cache-contention based and one based on memory bandwidth usage. Both our regression analysis and scheduling simulations find that the slowdown based method, represented by Memgen, performs better than the other methods. The linear correlation coefficient (Formula presented.) of Memgen's prediction is 0.890. Memgen's preferred schedules reached 99.53 % of the obtainable performance on average. Also, the memory bandwidth usage method performed almost as well as the slowdown based method. Furthermore, while most prior work promote characterization based on cache miss rate we found it to be on par with random scheduling of programs and highly unreliable.
|
|
| 10. |
- de Blanche, Andreas, 1975-, et al.
(author)
-
Artificial and human aspects of Industry 4.0: an industrial work-integrated-learning research agenda
- 2021
-
In: VILÄR. - 9789189325036
-
Conference paper (other academic/artistic)abstract
- The manufacturing industry is currently under extreme pressure to transform their organizations and competencies to reap the benefits of industry 4.0. The main driver for industry 4.0 is digitalization with disruptive technologies such as artificial intelligence, machine learning, internet of things, digital platforms, etc. Industrial applications and research studies have shown promising results, but they rarely involve a human-centric perspective. Given this, we argue there is a lack of knowledge on how disruptive technologies take part in human decision-making and learning practices, and to what extent disruptive technologies may support both employees and organizations to “learn”. In recent research the importance and need of including a human-centric perspective in industry 4.0 is raised including a human learning and decision-making approach. Hence, disruptive technologies, by themselves, no longer consider to solve the actual problems.Considering the richness of this topic, we propose an industrial work-integrated-learning research agenda to illuminate a human-centric perspective in Industry 4.0. This work-in-progress literature review aims to provide a research agenda on what and how application areas are covered in earlier research. Furthermore, the review identifies obstacles and opportunities that may affect manufacturing to reap the benefits of Industry 4.0. As part of the research, several inter-disciplinary areas are identified, in which industrial work-integrated-learning should be considered to enhance the design, implementation, and use of Industry 4.0 technologies. In conclusion, this study proposes a research agenda aimed at furthering research on how industrial digitalization can approach human and artificial intelligence through industrial work-integrated-learning for a future digitalized manufacturing.
|
|
