An Extensible Platform Description Language Supporting Retargetable Toolchains and Adaptive Execution

Christoph Kessler, Lu Li, Aras Atalar, Alin Dobre

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

XPDL is a modular, extensible platform description language for heterogeneous multicore systems and clusters. XPDL models provide metadata about hardware and installed system software that are relevant for adaptive static and dynamic optimizations of application programs and system settings for improved performance and energy efficiency. XPDL is based on XML and uses hyperlinks and inheritance to create modular, distributed libraries of platform models. We also provide a retargetable toolchain that browses and processes XPDL models and generates driver code for microbenchmarking to bootstrap empirical performance and energy models at deployment time. A C++ API enables convenient introspection of platform models, even at run-time, which allows for adaptive dynamic program optimizations such as tuned selection of implementation variants.
Original languageEnglish
Title of host publicationProceedings of the 19th International Workshop on Software and Compilers for Embedded Systems
Place of PublicationNew York, NY, USA
PublisherACM
Pages194-196
Number of pages3
ISBN (Print)978-1-4503-4320-6
DOIs
Publication statusPublished - 2016
Event19th International Workshop on Software and Compilers for Embedded Systems - Sankt Goar, Germany
Duration: 23 May 201625 May 2016
https://www.scopesconf.org/scopes-16/index.html

Publication series

NameSCOPES '16
PublisherACM

Conference

Conference19th International Workshop on Software and Compilers for Embedded Systems
Abbreviated titleSCOPES 2016
CountryGermany
CitySankt Goar
Period23/05/1625/05/16
Internet address

Keywords

  • Heterogeneous multi-core systems, System modeling, XML

Fingerprint Dive into the research topics of 'An Extensible Platform Description Language Supporting Retargetable Toolchains and Adaptive Execution'. Together they form a unique fingerprint.

Cite this