New Benchmarking Methodology and Programming Model for Big Data Processing

Kos, Anton; Tomažič, Sašo; Salom, Jakob; Trifunović, Nemanja; Valero, Mateo; Milutinović, Veljko

doi:10.1155/2015/271752

Cited by 32 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to solve this problem, many new developments are switching from the control-flow paradigm to the dataflow paradigm. 32,33 Cloud services which rely on FPGA, such as Baidu XPU, still cannot offer performance of today's GPUs or TPUs (tensor processing units), but offer better energy efficiency for training and inference of DNNs. Companies like Baidu, Intel, and Microsoft have cloud services which rely on FPGAs, which under certain conditions of interest could achieve better performance per watt.…”

Section: Dnns In Cloud Computingmentioning

confidence: 99%

Survey of deployment locations and underlying hardware architectures for contemporary deep neural networks

Kotlar

Bojic

Punt

et al. 2019

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

This article overviews the emerging use of deep neural networks in data analytics and explores which type of underlying hardware and architectural approach is best used in various deployment locations when implementing deep neural networks. The locations which are discussed are in the cloud, fog, and dew computing (dew computing is performed by end devices). Covered architectural approaches include multicore processors (central processing unit), manycore processors (graphics processing unit), field programmable gate arrays, and application-specific integrated circuits. The proposed classification in this article divides the existing solutions into 12 different categories, organized in two dimensions. The proposed classification allows a comparison of existing architectures, which are predominantly cloud-based, and anticipated future architectures, which are expected to be hybrid cloud-fog-dew architectures for applications in Internet of Things and Wireless Sensor Networks. Researchers interested in studying trade-offs among data processing bandwidth, data processing latency, and processing power consumption would benefit from the classification made in this article.

show abstract

Section: Dnns In Cloud Computingmentioning

confidence: 99%

Survey of deployment locations and underlying hardware architectures for contemporary deep neural networks

Kotlar

Bojic

Punt

et al. 2019

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…Beyer et al (2015) in the paper "Benchmarking and Resource Management: Application to Automatic Verification" set the goal to establish a technological foundation for performance evaluation of verification tools that is based on modern technology and makes it possible to measure and control resources in an accurate, reliable, and reproducible way in order to obtain scientifically valid experimental data [46]. Kos et al (2015) stresses out that big data processing and big data applications are shifting the computing paradigms, computing concepts, and treatment of data. Also, that managing big data is a many-sided problem.…”

Section: Benefits From the Use Of Benchmarkingmentioning

confidence: 99%

“…Their research resulted in presentation of a new benchmarking methodology based on a measure M defined as the number of unit size computers required to achieve the projected execution. Benefit derived from this research is that by using the new methodology data flow computers would outrank the control flow computers on a top 500 list for a number of big data applications [47].…”

Section: Benefits From the Use Of Benchmarkingmentioning

confidence: 99%

Benchmarking as a Method of Adaptation of Organizations to Dynamic Business Changes

Dobrosavljević¹,

Urošević²

2018

ARTTE

View full text Add to dashboard Cite

Organizations in a modern business environment aim to gain knowledge about best business practice in order to improve performances and to gain competitive advantage on the market. As modern business environment and business opportunities in it can be characterized as turbulent and uncertain, there is an inevitable need for usage of managerial methods and tools that accelerate organization's adaptation to modern business conditions. In order to achieve the desired success it is necessary to introduce the practice that will work on continuous improvement of business. Benchmarking, actually, represents the method for continuous analysis of strategies, functions, processes, products and services, performances and everything else within one organization compared with, compared to "best-in-class" organizations, in order to achieve the best business practice. By using benchmarking organizations are able to manage change more effectively. Literature review included in this paper gives an insight into the latest research papers on benchmarking within change management. Based on it, noticed contributions of the method in in conditions of uncertainty are highlighted and possible directions for further research on this issue are proposed.

show abstract

“…Some technologies that are closely connected to the CPS are IoT, wireless sensor networks, and cloud computing. Wireless sensor networks are regarded to be a vital component of CPS [14]. The Internet technology provides essential approaches to enhancing the performance of cyber-physical systems.…”

Section: Cyber-physical Systemsmentioning

confidence: 99%

Big Data in Cyber-Physical Systems, Digital Manufacturing and Industry 4.0

Wang¹,

Wang²

2016

IJEM

124

View full text Add to dashboard Cite

A cyber physical system (CPS) is a complex system that integrates computation, communication, and physical processes. Digital manufacturing is a method of using computers and related technologies to control an entire production process. Industry 4.0 can make manufacturing more efficient, flexible, and sustainable through communication and intelligence; therefore, it can increase the competitiveness. Key technologies such as the Internet of Things, cloud computing, machine-to-machine (M2M) communications, 3D printing, and Big Data have great impacts on Industry 4.0. Big Data analytics is very important for cyber-physical systems (CPSs), digital manufacturing, and Industry 4.0. This paper introduces technology progresses in CPS, digital manufacturing, and Industry 4.0. Some challenges and future research topics in these areas are also presented.

show abstract

New Benchmarking Methodology and Programming Model for Big Data Processing

Cited by 32 publications

References 14 publications

Survey of deployment locations and underlying hardware architectures for contemporary deep neural networks

Survey of deployment locations and underlying hardware architectures for contemporary deep neural networks

Benchmarking as a Method of Adaptation of Organizations to Dynamic Business Changes

Big Data in Cyber-Physical Systems, Digital Manufacturing and Industry 4.0

Contact Info

Product

Resources

About