SkelCL: a high-level extension of OpenCL for multi-GPU systems

Steuwer, Michel; Gorlatch, Sergei

doi:10.1007/s11227-014-1213-y

“…Besides, SLoC is typically used to predict the amount of effort required to develop a program. As a software metric, SLoC measures the size of a computer program by counting the number of lines in the text of the program's source code and it has been used in most of the existing approaches using skeleton frameworks [24], [42], [48].…”

Section: Software Metricsmentioning

confidence: 99%

Reusable Algorithmic Skeleton Framework for Clustering Algorithms in Wireless Sensor Network (SCW)

Taheri

¹

,

Savadi

²

,

Abrishami

³

2023

Preprint

0

View full text Add to dashboard Cite

In Wireless Sensor Networks (WSNs), clustering is often used to improve communication and routing. Therefore, clustering approaches highly attract several researchers since performing clustering saves energy, and energy efficiency is a significant goal in WSN. To beneficially adopt WSN technology, efficient application development is necessary. Therefore, a user-friendly programming abstraction is required to simplify the programming chore without sacrificing efficiency. Using suitable higher-level programming abstraction, it is neither obligatory for a programmer to be an expert in most fields related to WSN nor to be distracted from the application logic by focusing on low-level system issues. To ease the development of new clustering algorithms, a prefabricated algorithmic skeleton, namely SCW, is presented which only requires two functions to be filled in, i.e., to be implemented. The rest of the work (e.g., synchronization, sensing the environment, data aggregation, nodes’ energy calculations, and routing) will be handled by the proposed framework. Hence, SCW has the capability of performing a level of optimization in the background without user interference. By considering software metrics such as Lines of Code (LoC), Halstead metrics, and McCabe complexity while employing the proposed framework, one can implement a WSN clustering algorithm with fewer source lines of code, less programming effort, and difficulty, less time to understand and implement when compared to a built-from-scratch implementation. Although this algorithmic skeleton framework is proposed for implementation, to show its efficiency in this paper, we use the simulation environment.

show abstract

“…The SkelCL backend translates each skeleton into an OpenCL kernel, and enables the SkelCL codes to run on both multi-core CPUs and heterogeneous GPUs. This framework also supports automatic mapping of tasks onto multiple devices (Steuwer and Gorlatch 2014).…”

Section: Skeleton-based Programming Modelsmentioning

confidence: 99%

Parallel programming models for heterogeneous many-cores: a comprehensive survey

Fang

¹

,

Huang

²

,

Tang

³

et al. 2020

View full text Add to dashboard Cite

Heterogeneous many-cores are now an integral part of modern computing systems ranging from embedding systems to supercomputers. While heterogeneous many-core design offers the potential for energy-efficient high-performance, such potential can only be unlocked if the application programs are suitably parallel and can be made to match the underlying heterogeneous platform. In this article, we provide a comprehensive survey for parallel programming models for heterogeneous many-core architectures and review the compiling techniques of improving programmability and portability. We examine various software optimization techniques for minimizing the communicating overhead between heterogeneous computing devices. We provide a road map for a wide variety of different research areas. We conclude with a discussion on open issues in the area and potential research directions. This article provides both an accessible introduction to the fast-moving area of heterogeneous programming and a detailed bibliography of its main achievements.

show abstract

“…The SkelCL backend translates each skeleton into an OpenCL kernel, and enables the SkelCL codes to run on both multi-core CPUs and heterogeneous GPUs. This framework also supports automatic mapping of tasks onto multiple devices [176].…”

Section: Skeleton-based Programming Modelsmentioning

confidence: 99%

Parallel Programming Models for Heterogeneous Many-Cores : A Survey

Fang¹,

Huang²,

Tang³

et al. 2020

Preprint

0

View full text Add to dashboard Cite

Heterogeneous many-cores are now an integral part of modern computing systems ranging from embedding systems to supercomputers. While heterogeneous many-core design offers the potential for energy-efficient high-performance, such potential can only be unlocked if the application programs are suitably parallel and can be made to match the underlying heterogeneous platform. In this article, we provide a comprehensive survey for parallel programming models for heterogeneous many-core architectures and review the compiling techniques of improving programmability and portability. We examine various software optimization techniques for minimizing the communicating overhead between heterogeneous computing devices. We provide a road map for a wide variety of different research areas. We conclude with a discussion on open issues in the area and potential research directions. This article provides both an accessible introduction to the fast-moving area of heterogeneous programming and a detailed bibliography of its main achievements.

show abstract

SkelCL: a high-level extension of OpenCL for multi-GPU systems

Cited by 25 publications

References 8 publications

Reusable Algorithmic Skeleton Framework for Clustering Algorithms in Wireless Sensor Network (SCW)

Reusable Algorithmic Skeleton Framework for Clustering Algorithms in Wireless Sensor Network (SCW)

Parallel programming models for heterogeneous many-cores: a comprehensive survey

Parallel Programming Models for Heterogeneous Many-Cores : A Survey

Contact Info

Product

Resources

About