Introducing speculative optimizations in task dataflow with language extensions and runtime support

View/Open
Document typeConference report
Defense date2012
Rights accessOpen Access
Except where otherwise noted, content on this work
is licensed under a Creative Commons license
:
Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
We argue that speculation leads to increased
parallelism in the coarse-grain dataflow paradigm. To do so,
we present a framework for adding speculation in a popular
and well-established framework. We specify a limited set of
additions to the OmpSs language and changes required in its
supporting runtime environment. These modifications enable
speculation across the system in a flexible way. We evaluate
our implementation using a simple benchmark leading to a
promising 10% speedup.
CitationAzuelos, N. [et al.]. Introducing speculative optimizations in task dataflow with language extensions and runtime support. A: Workshop on Data-Flow Execution Models for Extreme Scale Computing. "2nd Workshop on Data-Flow Execution Models for Extreme Scale Computing". Minneapolis: 2012, p. 1-4.
Files | Description | Size | Format | View |
---|---|---|---|---|
Introducing Spe ... ns and Runtime Support.pdf | DFM-2012 | 266,1Kb | View/Open |