Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures

Wasuwee Sodsong, Jingun Hong, Seongwook Chung, Yeongkyu Lim, Shin-Dug Kim, bernd Burgstaller

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

7 Citations (Scopus)

Abstract

With the emergence of social networks and improvements in computational photography, billions of JPEG images are shared and viewed on a daily basis. Desktops, tablets and smartphones constitute the vast majority of hardware plat- forms used for displaying JPEG images. Despite the fact that these platforms are heterogeneous multicores, no approach exists yet that is capable of joining forces of a system's CPU and GPU for JPEG decoding. In this paper we introduce a novel JPEG decoding scheme for heterogeneous architectures consisting of a CPU and an OpenCL-programmable GPU. We employ an offline profiling step to determine the performance of a system's CPU and GPU with respect to JPEG decoding. For a given JPEG image, our performance model uses (1) the CPU and GPU performance characteristics, (2) the image entropy and (3) the width and height of the image to balance the JPEG decoding workload on the underlying hardware. Our run- Time partitioning and scheduling scheme exploits task, data and pipeline parallelism by scheduling the non-parallelizable entropy decoding task on the CPU, whereas inverse cosine transformations (IDCTs), color conversions and upsampling are conducted on both the CPU and the GPU. Our kernels have been optimized for GPU memory hierarchies. We have implemented the proposed method in the context of the libjpeg-turbo library, which is an industrial-strength JPEG encoding and decoding engine. Libjpeg-turbo's hand- optimized SIMD routines for ARM and x86 architectures constitute a competitive yardstick for the comparison to the proposed approach. Retro-fitting our method with libjpeg- Turbo provides insights on the software-engineering aspects of re-engineering legacy code for heterogeneous multicores. We have evaluated our approach for a total of 7194 JPEG images across three high- And middle-end CPU{GPU combi- nations. We achieve speedups of up to 4.2x over the SIMD- version of libjpeg-turbo, and speedups of up to 8.5x over its sequential code. Taking into account the non-parallelizable JPEG entropy decoding part, our approach achieves up to 95% of the theoretically attainable maximal speedup, with an average of 88%. Categories and Subject Descriptors D.1.3 [Programming Techniques]: Concurrent Program- ming|Parallel programming; C.4 [Performance of Systems]: Modeling techniques General Terms Performance, Algorithms, Design.

Original languageEnglish
Title of host publicationProceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014
PublisherAssociation for Computing Machinery
Pages80-91
Number of pages12
ISBN (Print)9781450326551
DOIs
Publication statusPublished - 2014 Jan 1
Event2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014 - Orlando, FL, United States
Duration: 2014 Feb 152014 Feb 15

Publication series

NameProceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014

Other

Other2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014
CountryUnited States
CityOrlando, FL
Period14/2/1514/2/15

Fingerprint

Program processors
Decoding
Entropy
Computer programming
Scheduling
Hardware
Parallel programming
Smartphones
Photography
Graphics processing unit
Joining
Software engineering
Pipelines
Engines
Color
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Sodsong, W., Hong, J., Chung, S., Lim, Y., Kim, S-D., & Burgstaller, B. (2014). Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures. In Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014 (pp. 80-91). (Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014). Association for Computing Machinery. https://doi.org/10.1145/2560683.2560684
Sodsong, Wasuwee ; Hong, Jingun ; Chung, Seongwook ; Lim, Yeongkyu ; Kim, Shin-Dug ; Burgstaller, bernd. / Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures. Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014. Association for Computing Machinery, 2014. pp. 80-91 (Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014).
@inproceedings{12f70f8b0b324b65b3a4f21f5d10d7e8,
title = "Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures",
abstract = "With the emergence of social networks and improvements in computational photography, billions of JPEG images are shared and viewed on a daily basis. Desktops, tablets and smartphones constitute the vast majority of hardware plat- forms used for displaying JPEG images. Despite the fact that these platforms are heterogeneous multicores, no approach exists yet that is capable of joining forces of a system's CPU and GPU for JPEG decoding. In this paper we introduce a novel JPEG decoding scheme for heterogeneous architectures consisting of a CPU and an OpenCL-programmable GPU. We employ an offline profiling step to determine the performance of a system's CPU and GPU with respect to JPEG decoding. For a given JPEG image, our performance model uses (1) the CPU and GPU performance characteristics, (2) the image entropy and (3) the width and height of the image to balance the JPEG decoding workload on the underlying hardware. Our run- Time partitioning and scheduling scheme exploits task, data and pipeline parallelism by scheduling the non-parallelizable entropy decoding task on the CPU, whereas inverse cosine transformations (IDCTs), color conversions and upsampling are conducted on both the CPU and the GPU. Our kernels have been optimized for GPU memory hierarchies. We have implemented the proposed method in the context of the libjpeg-turbo library, which is an industrial-strength JPEG encoding and decoding engine. Libjpeg-turbo's hand- optimized SIMD routines for ARM and x86 architectures constitute a competitive yardstick for the comparison to the proposed approach. Retro-fitting our method with libjpeg- Turbo provides insights on the software-engineering aspects of re-engineering legacy code for heterogeneous multicores. We have evaluated our approach for a total of 7194 JPEG images across three high- And middle-end CPU{GPU combi- nations. We achieve speedups of up to 4.2x over the SIMD- version of libjpeg-turbo, and speedups of up to 8.5x over its sequential code. Taking into account the non-parallelizable JPEG entropy decoding part, our approach achieves up to 95{\%} of the theoretically attainable maximal speedup, with an average of 88{\%}. Categories and Subject Descriptors D.1.3 [Programming Techniques]: Concurrent Program- ming|Parallel programming; C.4 [Performance of Systems]: Modeling techniques General Terms Performance, Algorithms, Design.",
author = "Wasuwee Sodsong and Jingun Hong and Seongwook Chung and Yeongkyu Lim and Shin-Dug Kim and bernd Burgstaller",
year = "2014",
month = "1",
day = "1",
doi = "10.1145/2560683.2560684",
language = "English",
isbn = "9781450326551",
series = "Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014",
publisher = "Association for Computing Machinery",
pages = "80--91",
booktitle = "Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014",

}

Sodsong, W, Hong, J, Chung, S, Lim, Y, Kim, S-D & Burgstaller, B 2014, Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures. in Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014. Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014, Association for Computing Machinery, pp. 80-91, 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014, Orlando, FL, United States, 14/2/15. https://doi.org/10.1145/2560683.2560684

Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures. / Sodsong, Wasuwee; Hong, Jingun; Chung, Seongwook; Lim, Yeongkyu; Kim, Shin-Dug; Burgstaller, bernd.

Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014. Association for Computing Machinery, 2014. p. 80-91 (Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014).

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

TY - GEN

T1 - Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures

AU - Sodsong, Wasuwee

AU - Hong, Jingun

AU - Chung, Seongwook

AU - Lim, Yeongkyu

AU - Kim, Shin-Dug

AU - Burgstaller, bernd

PY - 2014/1/1

Y1 - 2014/1/1

N2 - With the emergence of social networks and improvements in computational photography, billions of JPEG images are shared and viewed on a daily basis. Desktops, tablets and smartphones constitute the vast majority of hardware plat- forms used for displaying JPEG images. Despite the fact that these platforms are heterogeneous multicores, no approach exists yet that is capable of joining forces of a system's CPU and GPU for JPEG decoding. In this paper we introduce a novel JPEG decoding scheme for heterogeneous architectures consisting of a CPU and an OpenCL-programmable GPU. We employ an offline profiling step to determine the performance of a system's CPU and GPU with respect to JPEG decoding. For a given JPEG image, our performance model uses (1) the CPU and GPU performance characteristics, (2) the image entropy and (3) the width and height of the image to balance the JPEG decoding workload on the underlying hardware. Our run- Time partitioning and scheduling scheme exploits task, data and pipeline parallelism by scheduling the non-parallelizable entropy decoding task on the CPU, whereas inverse cosine transformations (IDCTs), color conversions and upsampling are conducted on both the CPU and the GPU. Our kernels have been optimized for GPU memory hierarchies. We have implemented the proposed method in the context of the libjpeg-turbo library, which is an industrial-strength JPEG encoding and decoding engine. Libjpeg-turbo's hand- optimized SIMD routines for ARM and x86 architectures constitute a competitive yardstick for the comparison to the proposed approach. Retro-fitting our method with libjpeg- Turbo provides insights on the software-engineering aspects of re-engineering legacy code for heterogeneous multicores. We have evaluated our approach for a total of 7194 JPEG images across three high- And middle-end CPU{GPU combi- nations. We achieve speedups of up to 4.2x over the SIMD- version of libjpeg-turbo, and speedups of up to 8.5x over its sequential code. Taking into account the non-parallelizable JPEG entropy decoding part, our approach achieves up to 95% of the theoretically attainable maximal speedup, with an average of 88%. Categories and Subject Descriptors D.1.3 [Programming Techniques]: Concurrent Program- ming|Parallel programming; C.4 [Performance of Systems]: Modeling techniques General Terms Performance, Algorithms, Design.

AB - With the emergence of social networks and improvements in computational photography, billions of JPEG images are shared and viewed on a daily basis. Desktops, tablets and smartphones constitute the vast majority of hardware plat- forms used for displaying JPEG images. Despite the fact that these platforms are heterogeneous multicores, no approach exists yet that is capable of joining forces of a system's CPU and GPU for JPEG decoding. In this paper we introduce a novel JPEG decoding scheme for heterogeneous architectures consisting of a CPU and an OpenCL-programmable GPU. We employ an offline profiling step to determine the performance of a system's CPU and GPU with respect to JPEG decoding. For a given JPEG image, our performance model uses (1) the CPU and GPU performance characteristics, (2) the image entropy and (3) the width and height of the image to balance the JPEG decoding workload on the underlying hardware. Our run- Time partitioning and scheduling scheme exploits task, data and pipeline parallelism by scheduling the non-parallelizable entropy decoding task on the CPU, whereas inverse cosine transformations (IDCTs), color conversions and upsampling are conducted on both the CPU and the GPU. Our kernels have been optimized for GPU memory hierarchies. We have implemented the proposed method in the context of the libjpeg-turbo library, which is an industrial-strength JPEG encoding and decoding engine. Libjpeg-turbo's hand- optimized SIMD routines for ARM and x86 architectures constitute a competitive yardstick for the comparison to the proposed approach. Retro-fitting our method with libjpeg- Turbo provides insights on the software-engineering aspects of re-engineering legacy code for heterogeneous multicores. We have evaluated our approach for a total of 7194 JPEG images across three high- And middle-end CPU{GPU combi- nations. We achieve speedups of up to 4.2x over the SIMD- version of libjpeg-turbo, and speedups of up to 8.5x over its sequential code. Taking into account the non-parallelizable JPEG entropy decoding part, our approach achieves up to 95% of the theoretically attainable maximal speedup, with an average of 88%. Categories and Subject Descriptors D.1.3 [Programming Techniques]: Concurrent Program- ming|Parallel programming; C.4 [Performance of Systems]: Modeling techniques General Terms Performance, Algorithms, Design.

UR - http://www.scopus.com/inward/record.url?scp=84897725863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897725863&partnerID=8YFLogxK

U2 - 10.1145/2560683.2560684

DO - 10.1145/2560683.2560684

M3 - Conference contribution

SN - 9781450326551

T3 - Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014

SP - 80

EP - 91

BT - Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014

PB - Association for Computing Machinery

ER -

Sodsong W, Hong J, Chung S, Lim Y, Kim S-D, Burgstaller B. Dynamic partitioning-based JPEG decompression on heterogeneous multicore architectures. In Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014. Association for Computing Machinery. 2014. p. 80-91. (Proceedings of the 2014 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2014). https://doi.org/10.1145/2560683.2560684