poster

ADHA: automatic data layout framework for heterogeneous architectures

Authors:

Deepak Majeti,

Kuldeep S. Meel,

Rajkishore Barik,

Vivek SarkarAuthors Info & Claims

PACT '14: Proceedings of the 23rd international conference on Parallel architectures and compilation

Pages 479 - 480

https://doi.org/10.1145/2628071.2628122

Published: 24 August 2014 Publication History

Get Access

Abstract

Data layouts play a crucial role in determining the performance of a given application running on a given architecture. Existing parallel programming frameworks for both multicore and heterogeneous systems leave the onus of selecting a data layout to the programmer. Therefore, shifting the burden of data layout selection to optimizing compilers can greatly enhance programmer productivity and application performance. In this work, we introduce ADHA: a two-level hierarchal formulation of the data layout problem for modern heterogeneous architectures. We have created a reference implementation of ADHA in the Heterogeneous Habanero-C (H2C) parallel programming system. ADHA shows significant performance benefits of up to 6.92x compared to manually specified layouts for two benchmark programs running on a CPU+GPU heterogeneous platform.

References

[1]

"CDSC Research Applications." {Online}. Available: http://www.cdsc.ucla.edu/research/.

Google Scholar

[2]

"Heterogeneous Habanero-C." {Online}. Available: http://habanero.rice.edu/Heterogeneous+Habanero-C.

Google Scholar

[3]

Che et al., "Rodinia: A benchmark suite for heterogeneous computing," ser. ISWC'09, Oct 2009.

Digital Library

Google Scholar

[4]

D. Majeti et al., "Compiler Driven Data Layout Transformation for Heterogeneous Platforms," in Proc. HeteroPar, 2013.

Google Scholar

[5]

I.-J. Sung et al., "Data layout transformation exploiting memory-level parallelism in structured grid many-core applications," in Proc. of PACT, 2010.

Digital Library

Google Scholar

Cited By

View all

Hu XYu CLi BTang SXiao JHuang Y(2018)GAIDR: An Efficient Time Series Subsets Retrieval Method for Geo-Distributed Astronomical Data2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)10.1109/HPCC/SmartCity/DSS.2018.00065(258-265)Online publication date: Jun-2018
https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00065
Haine CAumage OBarthou D(2017)Rewriting System for Profile-Guided Data Layout Transformations on BinariesEuro-Par 2017: Parallel Processing10.1007/978-3-319-64203-1_19(260-272)Online publication date: 1-Aug-2017
https://doi.org/10.1007/978-3-319-64203-1_19

Index Terms

ADHA: automatic data layout framework for heterogeneous architectures
1. Software and its engineering
  1. Software notations and tools
    1. Compilers

Recommendations

Automatic data layout generation and kernel mapping for CPU+GPU architectures
CC '16: Proceedings of the 25th International Conference on Compiler Construction

The ubiquity of hybrid CPU+GPU architectures has led to renewed interest in automatic data layout generation owing to the fact that data layouts have a large impact on performance, and that different data layouts yield the best performance on CPUs vs. ...
Accelerating a Climate Physics Model with OpenCL
SAAHPC '11: Proceedings of the 2011 Symposium on Application Accelerators in High-Performance Computing

Open Computing Language (OpenCL) is fast becoming the standard for heterogeneous parallel computing. It is designed to run on CPUs, GPUs, and other accelerator architectures. By implementing a real world application, a solar radiation model component ...
An OpenACC extension for data layout transformation
WACCPD '14: Proceedings of the First Workshop on Accelerator Programming using Directives

OpenACC is gaining momentum as an implicit and portable interface in porting legacy CPU-based applications to heterogeneous, highly parallel computational environment involving many-core accelerators such as GPUs and Intel Xeon Phi. OpenACC provides a ...

Comments

Information & Contributors

Information

Published In

PACT '14: Proceedings of the 23rd international conference on Parallel architectures and compilation

August 2014

514 pages

ISBN:9781450328098

DOI:10.1145/2628071

General Chair:
J. Nelson Amaral
University of Alberta, Canada
,
Program Chair:
Josep Torrellas
University of Illinois, USA

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 August 2014

Check for updates

Author Tags

Qualifiers

Poster

Conference

PACT '14

Sponsor:

IFIP WG 10.3
SIGARCH
IEEE CS TCPP
IEEE CS TCAA

PACT '14: International Conference on Parallel Architectures and Compilation

August 24 - 27, 2014

AB, Edmonton, Canada

Acceptance Rates

PACT '14 Paper Acceptance Rate 54 of 144 submissions, 38%;

Overall Acceptance Rate 121 of 471 submissions, 26%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
120
Total Downloads

Downloads (Last 12 months)7
Downloads (Last 6 weeks)0

Reflects downloads up to 18 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Hu XYu CLi BTang SXiao JHuang Y(2018)GAIDR: An Efficient Time Series Subsets Retrieval Method for Geo-Distributed Astronomical Data2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)10.1109/HPCC/SmartCity/DSS.2018.00065(258-265)Online publication date: Jun-2018
https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00065
Haine CAumage OBarthou D(2017)Rewriting System for Profile-Guided Data Layout Transformations on BinariesEuro-Par 2017: Parallel Processing10.1007/978-3-319-64203-1_19(260-272)Online publication date: 1-Aug-2017
https://doi.org/10.1007/978-3-319-64203-1_19

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Automatic data layout generation and kernel mapping for CPU+GPU architectures

Accelerating a Climate Physics Model with OpenCL

An OpenACC extension for data layout transformation