Characterizing the Impact of Soft Errors Affecting Floating-point ALUs using RTL-level Fault Injection
- BATTELLE (PACIFIC NW LAB)
- University of Texas at Austin
Strategies to detect, correct, or mitigate the impact of soft errors rely on errors-injection experiments. For efficient evaluation, such experiments typically inject errors in software by sampling errors from a candidate distribution. Most often, these strategies randomly select and flip one bit in the output of an instruction. While single-bit flips might constitute a meaningful model for errors affecting hardware, the appropriateness of this model for software-based errors has not been studied. In this paper, we study the manifestation of errors in the output registers due to errors affecting candidate instructions executed by floating point ALUs. We inject single-bit flips into the RTL descriptions of floating point ALUs and analyze the differences between anticipated and observed outputs when executing floating-point addition, subtraction, multiplication, and division. We choose the operands for these instructions randomly and from operands observed in five benchmarks. We observe a rich distribution of errors in the output and analyze their implications for software-based fault-injection campaigns.
- Research Organization:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 1617875
- Report Number(s):
- PNNL-SA-134868
- Resource Relation:
- Conference: Proceedings of the 47th International Conference on Parallel Processing, (ICPP 2018), August 13-16, 2018, Eugene, OR
- Country of Publication:
- United States
- Language:
- English
Similar Records
Quantifying the Impact of Single Bit Flips on Floating Point Arithmetic
Exploiting data representation for fault tolerance