Improving GPU robustness by making use of faulty parts

Artem Durytskyy, Mohamed Zahran, Ramesh Karri

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

Abstract

With hundreds of processing units in current state-of-the-art graphics processing units (GPUs), the probability that one or more processing units fail due to permanent faults, during fabrication or post deployment, increases drastically. In our experiments we found that the loss of a single streaming multiprocessor (SM) in an 8-SM GPU resulted in as much as 16%performance loss. The default method for dealing with faulty SMs is to turn them off. Although faulty SMs cannot be trusted to completely execute a single kernel (program assigned to an SM) correctly, we show that we can still make use of these SMs to improve system throughput by generating and supplying high-level hints to other functional SMs. By making the faulty SMs supply hints to functional SMs, we have been able to achieve an average speed-up of about 16 % over the baseline case (wherein the faulty SMs are turned off). The proposed technique requires minimal hardware overhead and is highly scalable.

Original languageEnglish (US)
Title of host publication2011 IEEE 29th International Conference on Computer Design, ICCD 2011
Pages346-351
Number of pages6
DOIs
StatePublished - 2011
Event29th IEEE International Conference on Computer Design 2011, ICCD 2011 - Amherst, MA, United States
Duration: Nov 9 2011Nov 12 2011

Publication series

NameProceedings - IEEE International Conference on Computer Design: VLSI in Computers and Processors
ISSN (Print)1063-6404

Other

Other29th IEEE International Conference on Computer Design 2011, ICCD 2011
CountryUnited States
CityAmherst, MA
Period11/9/1111/12/11

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Improving GPU robustness by making use of faulty parts'. Together they form a unique fingerprint.

Cite this