An Empirical Study of the Impact of Single and Multiple Bit-Flip Errors in Programs
Journal article, 2020

Recent studies have shown that technology and voltage scaling are expected to increase the likelihood that particle-induced soft errors manifest as multiple-bit errors. This raises concerns about the validity of using single bit-flips in fault injection experiments aiming to assess the program-level impact of soft errors. The goal of this paper is to investigate whether multiple-bit errors could cause a higher percentage of silent data corruptions (SDCs) compared to single-bit errors. Based on 2700 fault injection campaigns with 15 benchmark programs, featuring a total of 27 million experiments, our results show that single-bit errors in most cases either yield a higher percentage of SDCs compared to multiple-bit errors or yield SDC results that are very close to the ones obtained for the multiple-bit errors. Further, we find that only around 2% of the multiple-bit campaigns resulted in an SDC percentage that was more than 5 percentage points higher than that obtained for the corresponding single-bit campaigns. For most of these campaigns, the highest percentage of SDCs was obtained by flipping at most 3 bits. Based on our results, we also propose four techniques for error space pruning to avoid injection of multiple-bit errors that are either unlikely or infeasible to cause SDCs.

error space pruning

Fault injection

single/multiple bit-flip errors

transient hardware faults

error space clustering

Author

Behrooz Sangchoolie

RISE Research Institutes of Sweden

Karthik Pattabiraman

University of British Columbia (UBC)

Johan Karlsson

Chalmers, Computer Science and Engineering (Chalmers), Computer Engineering (Chalmers), Real-time and Computer Graphics Systems

IEEE Transactions on Dependable and Secure Computing

1545-5971 (ISSN)

Vol. In Press

Subject Categories

Telecommunications

Medical Equipment Engineering

Signal Processing

DOI

10.1109/TDSC.2020.3043023

More information

Latest update

6/29/2021