Autotuning Wavefront Abstractions for Heterogenous Architectures

M. Cole; S. Mohanty

doi:10.1109/WAMCA.2012.14

Autotuning Wavefront Abstractions for Heterogenous Architectures

M. Cole, S. Mohanty

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

Abstract / Description of output

We present our auto tuned heterogeneous parallel programming abstraction for the wave front pattern. An exhaustive search of the tuning space indicates that correct setting of tuning factors can average 37x speedup over a sequential baseline. Our best automated machine learning based heuristic obtains 92% of this ideal speedup, averaged across our full range of wave front examples.

Original language	English
Title of host publication	Applications for Multi-Core Architectures (WAMCA), 2012 Third Workshop on
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	42-47
Number of pages	6
ISBN (Print)	978-1-4673-5025-9
DOIs	https://doi.org/10.1109/WAMCA.2012.14
Publication status	Published - 2012

Access to Document

10.1109/WAMCA.2012.14

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6374751

Science and Innovation: Numerical Algorithms and Intelligent Software for the Evolving HPC Platform
Leimkuhler, B.
EPSRC
1/08/09 → 31/07/14
Project: Research

Cite this

@inproceedings{f05cd3ca8fa64cc786f96855f233b9e0,

title = "Autotuning Wavefront Abstractions for Heterogenous Architectures",

abstract = "We present our auto tuned heterogeneous parallel programming abstraction for the wave front pattern. An exhaustive search of the tuning space indicates that correct setting of tuning factors can average 37x speedup over a sequential baseline. Our best automated machine learning based heuristic obtains 92% of this ideal speedup, averaged across our full range of wave front examples.",

author = "M. Cole and S. Mohanty",

year = "2012",

doi = "10.1109/WAMCA.2012.14",

language = "English",

isbn = "978-1-4673-5025-9",

pages = "42--47",

booktitle = "Applications for Multi-Core Architectures (WAMCA), 2012 Third Workshop on",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

TY - GEN

T1 - Autotuning Wavefront Abstractions for Heterogenous Architectures

AU - Cole, M.

AU - Mohanty, S.

PY - 2012

Y1 - 2012

N2 - We present our auto tuned heterogeneous parallel programming abstraction for the wave front pattern. An exhaustive search of the tuning space indicates that correct setting of tuning factors can average 37x speedup over a sequential baseline. Our best automated machine learning based heuristic obtains 92% of this ideal speedup, averaged across our full range of wave front examples.

AB - We present our auto tuned heterogeneous parallel programming abstraction for the wave front pattern. An exhaustive search of the tuning space indicates that correct setting of tuning factors can average 37x speedup over a sequential baseline. Our best automated machine learning based heuristic obtains 92% of this ideal speedup, averaged across our full range of wave front examples.

U2 - 10.1109/WAMCA.2012.14

DO - 10.1109/WAMCA.2012.14

M3 - Conference contribution

SN - 978-1-4673-5025-9

SP - 42

EP - 47

BT - Applications for Multi-Core Architectures (WAMCA), 2012 Third Workshop on

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Autotuning Wavefront Abstractions for Heterogenous Architectures

Abstract / Description of output

Access to Document

Fingerprint

Projects

Science and Innovation: Numerical Algorithms and Intelligent Software for the Evolving HPC Platform

Cite this