CUDABlock

A GUI Programming Tool for CUDA

Hsih Hsin Lin, ChiaHeng Tu, Yuan Shin Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Recent advances in graphics processing units (GPUs) have resulted in massively parallel hardware that is widely available to achieve high performance in desktop, notebook, and even mobile computer systems. While multicore technology has become the norm of modern computers, programming such systems requires the understanding of underlying hardware architecture and hence posts a great challenge for average joe programmers, who might be professionals in specific domains, but not experts in parallel programming. This paper presents a GUI tool called CUDA Block that can facilitate parallel programming on multicore computer systems. CUDA Block is developed based on the Open Blocks framework, an extendable tool for graphical programming, to construct the GUI-based programming environment for CUDA parallel computing platform. Programmers simply need to drag-n-drop blocks, fill the fields of the blocks, and connect them according to array or matrix computations that are specified by algorithms. CUDA Block can then export block-based code to CUDA programs. Furthermore, a couple of optimization constructs have also been also offered for rapid program optimization. Preliminary experimental results have shown that the generated CUDA programs can achieve reasonable speedups on GPUs. Consequently, CUDA Block can be used as a tool for fast prototyping of GPU applications or a platform for education of parallel programming.

Original languageEnglish
Title of host publicationProceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages37-42
Number of pages6
ISBN (Electronic)9781467375894
DOIs
Publication statusPublished - 2015 Dec 8
Event44th Annual Conference of the International Conference on Parallel Processing Workshops, ICPPW 2015 - Beijing, China
Duration: 2015 Sep 12015 Sep 4

Publication series

NameProceedings of the International Conference on Parallel Processing Workshops
Volume2015-January
ISSN (Print)1530-2016

Other

Other44th Annual Conference of the International Conference on Parallel Processing Workshops, ICPPW 2015
CountryChina
CityBeijing
Period15-09-0115-09-04

Fingerprint

Parallel programming
Parallel Programming
Graphics Processing Unit
Graphical user interfaces
Programming
Computer systems
Hardware
Matrix Computation
Computer systems programming
Programming Environments
Hardware Architecture
Optimization
Prototyping
Parallel processing systems
Parallel Computing
Drag
High Performance
Education
Norm
Experimental Results

All Science Journal Classification (ASJC) codes

  • Software
  • Mathematics(all)
  • Hardware and Architecture

Cite this

Lin, H. H., Tu, C., & Hwang, Y. S. (2015). CUDABlock: A GUI Programming Tool for CUDA. In Proceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015 (pp. 37-42). [7349891] (Proceedings of the International Conference on Parallel Processing Workshops; Vol. 2015-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPPW.2015.15
Lin, Hsih Hsin ; Tu, ChiaHeng ; Hwang, Yuan Shin. / CUDABlock : A GUI Programming Tool for CUDA. Proceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 37-42 (Proceedings of the International Conference on Parallel Processing Workshops).
@inproceedings{88beb39a351f41c7aa3fbc30c34990c2,
title = "CUDABlock: A GUI Programming Tool for CUDA",
abstract = "Recent advances in graphics processing units (GPUs) have resulted in massively parallel hardware that is widely available to achieve high performance in desktop, notebook, and even mobile computer systems. While multicore technology has become the norm of modern computers, programming such systems requires the understanding of underlying hardware architecture and hence posts a great challenge for average joe programmers, who might be professionals in specific domains, but not experts in parallel programming. This paper presents a GUI tool called CUDA Block that can facilitate parallel programming on multicore computer systems. CUDA Block is developed based on the Open Blocks framework, an extendable tool for graphical programming, to construct the GUI-based programming environment for CUDA parallel computing platform. Programmers simply need to drag-n-drop blocks, fill the fields of the blocks, and connect them according to array or matrix computations that are specified by algorithms. CUDA Block can then export block-based code to CUDA programs. Furthermore, a couple of optimization constructs have also been also offered for rapid program optimization. Preliminary experimental results have shown that the generated CUDA programs can achieve reasonable speedups on GPUs. Consequently, CUDA Block can be used as a tool for fast prototyping of GPU applications or a platform for education of parallel programming.",
author = "Lin, {Hsih Hsin} and ChiaHeng Tu and Hwang, {Yuan Shin}",
year = "2015",
month = "12",
day = "8",
doi = "10.1109/ICPPW.2015.15",
language = "English",
series = "Proceedings of the International Conference on Parallel Processing Workshops",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "37--42",
booktitle = "Proceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015",
address = "United States",

}

Lin, HH, Tu, C & Hwang, YS 2015, CUDABlock: A GUI Programming Tool for CUDA. in Proceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015., 7349891, Proceedings of the International Conference on Parallel Processing Workshops, vol. 2015-January, Institute of Electrical and Electronics Engineers Inc., pp. 37-42, 44th Annual Conference of the International Conference on Parallel Processing Workshops, ICPPW 2015, Beijing, China, 15-09-01. https://doi.org/10.1109/ICPPW.2015.15

CUDABlock : A GUI Programming Tool for CUDA. / Lin, Hsih Hsin; Tu, ChiaHeng; Hwang, Yuan Shin.

Proceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 37-42 7349891 (Proceedings of the International Conference on Parallel Processing Workshops; Vol. 2015-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - CUDABlock

T2 - A GUI Programming Tool for CUDA

AU - Lin, Hsih Hsin

AU - Tu, ChiaHeng

AU - Hwang, Yuan Shin

PY - 2015/12/8

Y1 - 2015/12/8

N2 - Recent advances in graphics processing units (GPUs) have resulted in massively parallel hardware that is widely available to achieve high performance in desktop, notebook, and even mobile computer systems. While multicore technology has become the norm of modern computers, programming such systems requires the understanding of underlying hardware architecture and hence posts a great challenge for average joe programmers, who might be professionals in specific domains, but not experts in parallel programming. This paper presents a GUI tool called CUDA Block that can facilitate parallel programming on multicore computer systems. CUDA Block is developed based on the Open Blocks framework, an extendable tool for graphical programming, to construct the GUI-based programming environment for CUDA parallel computing platform. Programmers simply need to drag-n-drop blocks, fill the fields of the blocks, and connect them according to array or matrix computations that are specified by algorithms. CUDA Block can then export block-based code to CUDA programs. Furthermore, a couple of optimization constructs have also been also offered for rapid program optimization. Preliminary experimental results have shown that the generated CUDA programs can achieve reasonable speedups on GPUs. Consequently, CUDA Block can be used as a tool for fast prototyping of GPU applications or a platform for education of parallel programming.

AB - Recent advances in graphics processing units (GPUs) have resulted in massively parallel hardware that is widely available to achieve high performance in desktop, notebook, and even mobile computer systems. While multicore technology has become the norm of modern computers, programming such systems requires the understanding of underlying hardware architecture and hence posts a great challenge for average joe programmers, who might be professionals in specific domains, but not experts in parallel programming. This paper presents a GUI tool called CUDA Block that can facilitate parallel programming on multicore computer systems. CUDA Block is developed based on the Open Blocks framework, an extendable tool for graphical programming, to construct the GUI-based programming environment for CUDA parallel computing platform. Programmers simply need to drag-n-drop blocks, fill the fields of the blocks, and connect them according to array or matrix computations that are specified by algorithms. CUDA Block can then export block-based code to CUDA programs. Furthermore, a couple of optimization constructs have also been also offered for rapid program optimization. Preliminary experimental results have shown that the generated CUDA programs can achieve reasonable speedups on GPUs. Consequently, CUDA Block can be used as a tool for fast prototyping of GPU applications or a platform for education of parallel programming.

UR - http://www.scopus.com/inward/record.url?scp=84954545989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954545989&partnerID=8YFLogxK

U2 - 10.1109/ICPPW.2015.15

DO - 10.1109/ICPPW.2015.15

M3 - Conference contribution

T3 - Proceedings of the International Conference on Parallel Processing Workshops

SP - 37

EP - 42

BT - Proceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lin HH, Tu C, Hwang YS. CUDABlock: A GUI Programming Tool for CUDA. In Proceedings - 2015 International Conference on Parallel Processing Workshops, The 44th Annual Conference, ICPPW 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 37-42. 7349891. (Proceedings of the International Conference on Parallel Processing Workshops). https://doi.org/10.1109/ICPPW.2015.15