O. Zinenko, C. Bastoul, and S. Huot. International Workshop on Polyhedral Compilation Techniques 2015
(IMPACT), page 8. (2015)
Abstract
Manual program parallelization and optimization may be necessary
to reach a decent portion of the target architecture's peak
performance when automatic tools fail at choosing the best
strategy. While a broad range of languages and libraries provide
convenient ways to express parallelism, the difficult, time
consuming and error-prone parallelism identification and
extraction task is mostly left under the programmer's
responsibility. To address this issue, we introduce a
visualization-based approach to ease parallelism extraction and
expression that leverages polyhedral compilation technologies.
Our interactive tool, Clint, maps direct manipulation of the
visual representation to polyhedral program transformations with
real-time semantics preservation feedback. We conducted two user
studies showing that Clint's visualization can be accurately
understood by both experts and non-expert programmers, and that
the parallelism can be extracted better from Clint's
representation than from the source code in many cases.
%0 Conference Paper
%1 Zinenko2015-zk
%A Zinenko, Oleksandr
%A Bastoul, Cédric
%A Huot, Stéphane
%B International Workshop on Polyhedral Compilation Techniques 2015
(IMPACT)
%D 2015
%K Clint Expose Polyhedral_model Visualization
%P 8
%T Manipulating Visualization, Not Codes
%X Manual program parallelization and optimization may be necessary
to reach a decent portion of the target architecture's peak
performance when automatic tools fail at choosing the best
strategy. While a broad range of languages and libraries provide
convenient ways to express parallelism, the difficult, time
consuming and error-prone parallelism identification and
extraction task is mostly left under the programmer's
responsibility. To address this issue, we introduce a
visualization-based approach to ease parallelism extraction and
expression that leverages polyhedral compilation technologies.
Our interactive tool, Clint, maps direct manipulation of the
visual representation to polyhedral program transformations with
real-time semantics preservation feedback. We conducted two user
studies showing that Clint's visualization can be accurately
understood by both experts and non-expert programmers, and that
the parallelism can be extracted better from Clint's
representation than from the source code in many cases.
@inproceedings{Zinenko2015-zk,
abstract = {Manual program parallelization and optimization may be necessary
to reach a decent portion of the target architecture's peak
performance when automatic tools fail at choosing the best
strategy. While a broad range of languages and libraries provide
convenient ways to express parallelism, the difficult, time
consuming and error-prone parallelism identification and
extraction task is mostly left under the programmer's
responsibility. To address this issue, we introduce a
visualization-based approach to ease parallelism extraction and
expression that leverages polyhedral compilation technologies.
Our interactive tool, Clint, maps direct manipulation of the
visual representation to polyhedral program transformations with
real-time semantics preservation feedback. We conducted two user
studies showing that Clint's visualization can be accurately
understood by both experts and non-expert programmers, and that
the parallelism can be extracted better from Clint's
representation than from the source code in many cases.},
added-at = {2015-05-21T14:21:57.000+0200},
author = {Zinenko, Oleksandr and Bastoul, C\'{e}dric and Huot, St\'{e}phane},
biburl = {https://www.bibsonomy.org/bibtex/2d9c1c96f1ea5907e2e5d383074f4d46b/christophv},
booktitle = {International Workshop on Polyhedral Compilation Techniques 2015
({IMPACT})},
interhash = {1c4efaa622c5c4d1b6185b416fb27680},
intrahash = {d9c1c96f1ea5907e2e5d383074f4d46b},
keywords = {Clint Expose Polyhedral_model Visualization},
pages = 8,
timestamp = {2016-01-04T14:22:08.000+0100},
title = {Manipulating Visualization, Not Codes},
year = 2015
}