Implementing OpenMP 4.0 for the NVIDIA PTX architecture in GCC compiler

The paper describes the approach used in implementing OpenMP offloading to NVIDIA accelerators in GCC. Offloading refers to a new capability in OpenMP 4.0 specification update that allows the programmer to specify regions of code that should be executed on an accelerator device that potentially has...

Ausführliche Beschreibung

Bibliographische Detailangaben
Hauptverfasser: A. V. Monakov, V. A. Ivanishin
Format: Artikel
Sprache:English
Veröffentlicht: Ivannikov Institute for System Programming of the Russian Academy of Sciences 2018-10-01
Schriftenreihe:Труды Института системного программирования РАН
Schlagworte:
Online Zugang:https://ispranproceedings.elpub.ru/jour/article/view/145