PTask: operating system abstractions to manage GPUs as compute devices.

DMCA

PTask: operating system abstractions to manage GPUs as compute devices. (2011)

Cached

Download Links

by Christopher J Rossbach , Jon Currey , Mark Silberstein , Baishakhi Ray , Emmett Witchel

Venue:	In Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles,
Citations:	52 - 5 self

BibTeX

@INPROCEEDINGS{Rossbach11ptask:operating,
    author = {Christopher J Rossbach and Jon Currey and Mark Silberstein and Baishakhi Ray and Emmett Witchel},
    title = {PTask: operating system abstractions to manage GPUs as compute devices.},
    booktitle = {In Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles,},
    year = {2011},
    pages = {233--248}
}

OpenURL

Abstract

ABSTRACT We propose a new set of OS abstractions to support GPUs and other accelerator devices as first class computing resources. These new abstractions, collectively called the PTask API, support a dataflow programming model. Because a PTask graph consists of OS-managed objects, the kernel has sufficient visibility and control to provide system-wide guarantees like fairness and performance isolation, and can streamline data movement in ways that are impossible under current GPU programming models. Our experience developing the PTask API, along with a gestural interface on Windows 7 and a FUSE-based encrypted file system on Linux show that the PTask API can provide important systemwide guarantees where there were previously none, and can enable significant performance improvements, for example gaining a 5⇥ improvement in maximum throughput for the gestural interface.

DMCA