7553

iGPU: Exception Support and Speculative Execution on GPUs

Jaikrishnan Menon, Marc de Kruijf, Karthikeyan Sankaralingam
Department of Computer Sciences, University of Wisconsin-Madison
39th International Symposium on Computer Architecture (ISCA), 2012

@inproceedings{isca2012:igpu,

   author={Jaikrishnan Menon and Marc de Kruijf and Karthikeyan Sankaralingam},

   title={iGPU: Exception Support and Speculative Execution on GPUs},

   booktitle={"{Proceedings of 39th International Symposium on Computer Architecture (ISCA)}"},

   year={2012},

   bib_dl_pdf={http://www.cs.wisc.edu/vertical/papers/2012/isca12-igpu.pdf},

   bib_dl_ppt={http://www.cs.wisc.edu/vertical/talks/2012/isca12-igpu.pptx},

   bib_pubtype={Refereed Conference},

   bib_rescat={Architecture},

   month={June}

}

Download Download (PDF)   View View   Source Source   

1032

views

Since the introduction of fully programmable vertex shader hardware, GPU computing has made tremendous advances. Exception support and speculative execution are the next steps to expand the scope and improve the usability of GPUs. However, traditional mechanisms to support exceptions and speculative execution are highly intrusive to GPU hardware design. This paper builds on two related insights to provide a unified lightweight mechanism for supporting exceptions and speculation on GPUs. First, we observe that GPU programs can be broken into code regions that contain little or no live register state at their entry point. We then also recognize that it is simple to generate these regions in such a way that they are idempotent, allowing their entry points to function as program recovery points and enabling support for exception handling, fast context switches, and speculation, all with very low overhead. We call the architecture of GPUs executing these idempotent regions the iGPU architecture. The hardware extensions required are minimal and the construction of idempotent code regions is fully transparent under the typical dynamic compilation framework of GPUs. We demonstrate how iGPU exception support enables virtual memory paging with very low overhead (1% to 4%), and how speculation support enables circuit-speculation techniques that can provide over 25% reduction in energy.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: