On the Measurement of Safe Fault Failure Rates in High-Performance Compute Processors
- 1 November 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Abstract
Accurate determination of the safe-fault failure rate of complex digital designs is an exascale problem. We present a novel measurement methodology and results which could have a profound impact on the performance and availability for GPUs in safety critical systems. We extend our analysis with a methodology for in-the-field verification.Keywords
This publication has 12 references indexed in Scilit:
- Quantifying the Accuracy of High-Level Fault Injection Techniques for Hardware Faults2014
- Timing vulnerability factors of sequential elements in modern microprocessors2013
- Eliminating microarchitectural dependency from Architectural Vulnerability2009
- BlueGene/L Failure Analysis and Prediction Models2006
- Computing Architectural Vulnerability Factors for Address-Based Structures2005
- SoftArch: an architecture-level tool for modeling and analyzing soft errors2005
- Techniques to reduce the soft error rate of a high-performance microprocessor2004
- Characterizing the effects of transient faults on a high-performance processor pipeline2004
- A systematic methodology to compute the architectural vulnerability factors for a high-performance microprocessor2003
- A Proof for the Queuing Formula: L = λWOperations Research, 1961