Innovative approach for porting existing CPU program to its CUDA program

Yu Liu; Yang Hong; Chung Hung Wang; Sheng Ta Lee; Chun Yuan Lin; Che Lun Hung

doi:10.1109/BIBM.2015.7359898

Innovative approach for porting existing CPU program to its CUDA program

Yu Liu
, Yang Hong
, Chung Hung Wang
, Sheng Ta Lee
, Chun Yuan Lin
, Che Lun Hung^*

^*Corresponding author for this work

Tianjin University
Chang Gung University
Providence University Taiwan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.

Original language	English
Title of host publication	Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
Editors	lng. Matthieu Schapranow, Jiayu Zhou, Xiaohua Tony Hu, Bin Ma, Sanguthevar Rajasekaran, Satoru Miyano, Illhoi Yoo, Brian Pierce, Amarda Shehu, Vijay K. Gombar, Brian Chen, Vinay Pai, Jun Huan
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1503-1508
Number of pages	6
ISBN (Electronic)	9781467367981
DOIs	https://doi.org/10.1109/BIBM.2015.7359898
State	Published - 16 12 2015
Event	IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 - Washington, United States Duration: 09 11 2015 → 12 11 2015

Publication series

Name	Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

Conference

Conference	IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
Country/Territory	United States
City	Washington
Period	09/11/15 → 12/11/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

BLAST
CUDA
GPU
Parallel Processing
Porting method

Access to Document

10.1109/BIBM.2015.7359898

Cite this

Liu, Y., Hong, Y., Wang, C. H., Lee, S. T., Lin, C. Y., & Hung, C. L. (2015). Innovative approach for porting existing CPU program to its CUDA program. In L. M. Schapranow, J. Zhou, X. T. Hu, B. Ma, S. Rajasekaran, S. Miyano, I. Yoo, B. Pierce, A. Shehu, V. K. Gombar, B. Chen, V. Pai, & J. Huan (Eds.), Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 (pp. 1503-1508). Article 7359898 (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2015.7359898

Liu, Yu ; Hong, Yang ; Wang, Chung Hung et al. / Innovative approach for porting existing CPU program to its CUDA program. Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. editor / lng. Matthieu Schapranow ; Jiayu Zhou ; Xiaohua Tony Hu ; Bin Ma ; Sanguthevar Rajasekaran ; Satoru Miyano ; Illhoi Yoo ; Brian Pierce ; Amarda Shehu ; Vijay K. Gombar ; Brian Chen ; Vinay Pai ; Jun Huan. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1503-1508 (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015).

@inproceedings{d9d54131065843fc82d31dcb046efc19,

title = "Innovative approach for porting existing CPU program to its CUDA program",

abstract = "GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.",

keywords = "BLAST, CUDA, GPU, Parallel Processing, Porting method",

author = "Yu Liu and Yang Hong and Wang, \{Chung Hung\} and Lee, \{Sheng Ta\} and Lin, \{Chun Yuan\} and Hung, \{Che Lun\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 ; Conference date: 09-11-2015 Through 12-11-2015",

year = "2015",

month = dec,

day = "16",

doi = "10.1109/BIBM.2015.7359898",

language = "英语",

series = "Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1503--1508",

editor = "Schapranow, \{lng. Matthieu\} and Jiayu Zhou and Hu, \{Xiaohua Tony\} and Bin Ma and Sanguthevar Rajasekaran and Satoru Miyano and Illhoi Yoo and Brian Pierce and Amarda Shehu and Gombar, \{Vijay K.\} and Brian Chen and Vinay Pai and Jun Huan",

booktitle = "Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015",

address = "美国",

}

Liu, Y, Hong, Y, Wang, CH, Lee, ST, Lin, CY & Hung, CL 2015, Innovative approach for porting existing CPU program to its CUDA program. in LM Schapranow, J Zhou, XT Hu, B Ma, S Rajasekaran, S Miyano, I Yoo, B Pierce, A Shehu, VK Gombar, B Chen, V Pai & J Huan (eds), Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015., 7359898, Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015, Institute of Electrical and Electronics Engineers Inc., pp. 1503-1508, IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015, Washington, United States, 09/11/15. https://doi.org/10.1109/BIBM.2015.7359898

Innovative approach for porting existing CPU program to its CUDA program. / Liu, Yu; Hong, Yang; Wang, Chung Hung et al.
Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. ed. / lng. Matthieu Schapranow; Jiayu Zhou; Xiaohua Tony Hu; Bin Ma; Sanguthevar Rajasekaran; Satoru Miyano; Illhoi Yoo; Brian Pierce; Amarda Shehu; Vijay K. Gombar; Brian Chen; Vinay Pai; Jun Huan. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1503-1508 7359898 (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Innovative approach for porting existing CPU program to its CUDA program

AU - Liu, Yu

AU - Hong, Yang

AU - Wang, Chung Hung

AU - Lee, Sheng Ta

AU - Lin, Chun Yuan

AU - Hung, Che Lun

PY - 2015/12/16

Y1 - 2015/12/16

N2 - GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.

AB - GPU computing has gradually become the mainstream to do high-speed computing fields, such as the meteorology, image and video processing, fluid dynamics simulation, seismic analysis, and etc. How to efficiently port an existing program on CPU to its CUDA program on GPU is an important issue. From the previous works, the porting approach can be generalized and classified into two categories: Rewrite Parallel Algorithm (abbreviate to RPA) and Modify Original Library (abbreviate to MOL). For the RPA, the programmers need to understand the original sequential or parallel algorithm on CPU absolutely and then write the CUDA program on GPU directly. For the MOL, the programmers need to analyze (profile) the existing program on CPU at first to find the most spend time libraries (or functions), then they are modified greatly (rewritten in general) to become CUDA programs (kernel functions). There are several disadvantages for the RPA and MOL, especially for the porting time and executing results. Hence, in this paper, a new approach, called innovative systematic contract (abbreviate to ISC), is proposed to allow programmers to port an existing CPU program to its CUDA program by modifying the libraries lightly. The program, BLASTN v2.2.27, was ported into a CUDA version, called CUDA-BLASTN v1, by the ISC. From the experimental results, by comparing with BLASTN v2.2.27, CUDA-BLASTN v1 achieves 5x speedup ratio and obtains almost the same executing results.

KW - BLAST

KW - CUDA

KW - GPU

KW - Parallel Processing

KW - Porting method

UR - https://www.scopus.com/pages/publications/84962448822

U2 - 10.1109/BIBM.2015.7359898

DO - 10.1109/BIBM.2015.7359898

M3 - 会议稿件

AN - SCOPUS:84962448822

T3 - Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

SP - 1503

EP - 1508

BT - Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

A2 - Schapranow, lng. Matthieu

A2 - Zhou, Jiayu

A2 - Hu, Xiaohua Tony

A2 - Ma, Bin

A2 - Rajasekaran, Sanguthevar

A2 - Miyano, Satoru

A2 - Yoo, Illhoi

A2 - Pierce, Brian

A2 - Shehu, Amarda

A2 - Gombar, Vijay K.

A2 - Chen, Brian

A2 - Pai, Vinay

A2 - Huan, Jun

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

Y2 - 9 November 2015 through 12 November 2015

ER -

Liu Y, Hong Y, Wang CH, Lee ST, Lin CY, Hung CL. Innovative approach for porting existing CPU program to its CUDA program. In Schapranow LM, Zhou J, Hu XT, Ma B, Rajasekaran S, Miyano S, Yoo I, Pierce B, Shehu A, Gombar VK, Chen B, Pai V, Huan J, editors, Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1503-1508. 7359898. (Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015). doi: 10.1109/BIBM.2015.7359898

Innovative approach for porting existing CPU program to its CUDA program

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this