short-paper

Extending SHAPES for SIMD Architectures: An approach to native support for Struct of Arrays in languages

Authors:

Susan EisenbachAuthors Info & Claims

ICOOOLPS '18: Proceedings of the 13th Workshop on Implementation, Compilation, Optimization of Object-Oriented Languages, Programs and Systems

Pages 23 - 29

https://doi.org/10.1145/3242947.3242951

Published: 17 July 2018 Publication History

Get Access

Abstract

SIMD (Single Instruction, Multiple Data) instruction sets are ubiquitous on modern hardware, but rarely used in software projects. A major reason for this is that efficient SIMD code requires data to be laid out in memory in an unconventional manner, forcing developers to explicitly refactor their code and data structures in order to make use of SIMD.

In previous work, we proposed SHAPES, an abstract layout specification for enabling memory optimisations for managed, object-oriented languages. In this paper, we explain how, by extending SHAPES with well-known constructs from the literature, which are not specific to SIMD, we can extend SHAPES to compile programs to use SIMD instructions.

The resulting language (sketch) seems able to exploit SIMD capabilities without sacrificing ease of development.

References

[1]

Franco, Juliana, et al. "You Can Have it All: Abstraction and Good Cache Performance." Proceedings of the 2017 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software. ACM, 2017.

Digital Library

Google Scholar

[2]

Pharr, Matt, and William R. Mark. "ISPC: A SPMD Compiler for High-Performance CPU Programming." Innovative Parallel Computing (InPar), 2012. IEEE, 2012.

Google Scholar

[3]

Rodriguez, Jose. A Jai Primer. URL: https://github.com/BSVino/JaiPrimer/blob/fc9ff9e722c190eeabe33a78d50d2588ae6b7e49/JaiPrimer. md Accessed: 2018-05-18.

Google Scholar

[4]

Leißa, Roland, Immanuel Haffner, and Sebastian Hack. "Sierra: a SIMD Extension for C++." Proceedings of the 2014 Workshop on Programming models for SIMD/Vector processing. ACM, 2014.

Google Scholar

[5]

Kornblith, Simon. Julia Structs of Arrays. URL: https://github.com/simonster/StructsOfArrays.jl/blob/v0.0.3/src/StructsOfArrays.jl Accessed: 2018-05-18.

Google Scholar

[6]

Fog, Agner. "The Microarchitecture of Intel, AMD and VIA CPUs: An Optimization Guide for Assembly Programmers and Compiler Makers." Copenhagen University College of Engineering (2012): 02--29.

Google Scholar

[7]

Van Waveren, J. M. P. "From Quaternion to Matrix and Back." Id Software, Inc (2005).

Google Scholar

[8]

Henry, David. "MD5Mesh and MD5Anim Files Formats." URL: http://tfc.duke.free.fr/coding/md5-specs-en.html. Accessed: 2018-05-18.

Google Scholar

[9]

John Hogg. Islands: Aliasing Protection in Object-oriented Languages." SIGPLAN Not. 26(11):271--285. 1991.

Digital Library

Google Scholar

[10]

John Boyland. "Alias burying: Unique variables without destructive reads." Software: Practice and Experience, 31(6):533--553. 2001.

Digital Library

Google Scholar

[11]

Mattis, Toni, Johannes Henning, Patrick Rein, Robert Hirschfeld, and Malte Appeltauer. "Columnar objects: Improving the performance of analytical applications." In 2015 ACM International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software (Onward!), pp. 197--210. ACM, 2015.

Digital Library

Google Scholar

Cited By

View all

Castegren EWrigstad T(2024)Encore: CodaActive Object Languages: Current Research Trends10.1007/978-3-031-51060-1_3(59-91)Online publication date: 29-Jan-2024
https://doi.org/10.1007/978-3-031-51060-1_3
Tasos AFranco JDrossopoulou SWrigstad TEisenbach S(2020)Reshape your layouts, not your programs: A safe language extension for better cache localityScience of Computer Programming10.1016/j.scico.2020.102481(102481)Online publication date: May-2020
https://doi.org/10.1016/j.scico.2020.102481

Recommendations

Dynamic translation of structured Loads/Stores and register mapping for architectures with SIMD extensions
LCTES '17

More and more modern processors have been supporting non-contiguous SIMD data accesses. However, translating such instructions has been overlooked in the Dynamic Binary Translation (DBT) area. For example, in the popular QEMU dynamic binary translator, ...
Dynamic translation of structured Loads/Stores and register mapping for architectures with SIMD extensions
LCTES 2017: Proceedings of the 18th ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems

More and more modern processors have been supporting non-contiguous SIMD data accesses. However, translating such instructions has been overlooked in the Dynamic Binary Translation (DBT) area. For example, in the popular QEMU dynamic binary translator, ...
Avoiding conversion and rearrangement overhead in SIMD architectures

Single-Instruction Multiple-Data (SIMD) instructions provide an inexpensive way to exploit the Data-Level Parallelism in multimedia applications. However, the performance improvement obtained by employing SIMD instructions is often limited because ...

Comments

Information & Contributors

Information

Published In

ICOOOLPS '18: Proceedings of the 13th Workshop on Implementation, Compilation, Optimization of Object-Oriented Languages, Programs and Systems

July 2018

43 pages

ISBN:9781450358040

DOI:10.1145/3242947

Permission to make digital or hard copies of all or part 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 components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

In-Cooperation

AITO: Assoc Internationale por les Technologies Objects

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 July 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Short-paper
Research
Refereed limited

Conference

ECOOP '18

ECOOP '18: European Conference on Object Oriented Programming

July 17, 2018

Amsterdam, Netherlands

Acceptance Rates

ICOOOLPS '18 Paper Acceptance Rate 5 of 6 submissions, 83%;

Overall Acceptance Rate 11 of 14 submissions, 79%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
85
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)1

Reflects downloads up to 15 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Castegren EWrigstad T(2024)Encore: CodaActive Object Languages: Current Research Trends10.1007/978-3-031-51060-1_3(59-91)Online publication date: 29-Jan-2024
https://doi.org/10.1007/978-3-031-51060-1_3
Tasos AFranco JDrossopoulou SWrigstad TEisenbach S(2020)Reshape your layouts, not your programs: A safe language extension for better cache localityScience of Computer Programming10.1016/j.scico.2020.102481(102481)Online publication date: May-2020
https://doi.org/10.1016/j.scico.2020.102481

View Options

Get Access

Login options

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

Cited By

Recommendations

Dynamic translation of structured Loads/Stores and register mapping for architectures with SIMD extensions

Dynamic translation of structured Loads/Stores and register mapping for architectures with SIMD extensions

Avoiding conversion and rearrangement overhead in SIMD architectures

Comments

Published In

In-Cooperation

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Conference

Acceptance Rates

Other Metrics

Article Metrics

Other Metrics

Cited By

Login options

Full Access

PDF

eReader

Abstract

References

Cited By

Recommendations

Dynamic translation of structured Loads/Stores and register mapping for architectures with SIMD extensions

Dynamic translation of structured Loads/Stores and register mapping for architectures with SIMD extensions

Avoiding conversion and rearrangement overhead in SIMD architectures

Comments

Information

Published In

In-Cooperation

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Get Access

Login options

Full Access

View options

PDF

eReader

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations