RunSAFER: A Novel Runtime Fault Detection Approach for Systolic Array Accelerators
Authors:
- 6 November 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 596-604
Abstract
In this study, we introduce a new runtime fault detection technique for systolic array accelerators oriented to neural network applications. The method exploits the functional path of the systolic array to compute and process checksum values during the execution of the current application instructions flow and integrates self-testing capabilities within the systolic array Instruction Set Architecture. The proposed technique does not require additional hardware self-testing modules, and the test pattern penalty is limited to 3 clock cycles independent of the size of the systolic array. Experimental analysis performed with fault injection campaigns demonstrates full fault detection capabilities of stuck-at faults with an average computing overhead 4 times lower than state-of-the-art solutions. Additionally, our approach exhibits diminished hardware overhead in contrast to conventional techniques.Keywords
This publication has 23 references indexed in Scilit:
- Implementierung einer Tensor Processing Unit mit dem Fokus auf Embedded Systems und das Internet of Things2019
- Impact of Structural Faults on Neural Network Performance2019
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- Extending checksum-based ABFT to tolerate soft errors online in iterative methods2014
- Effective emulation of permanent faults in ASICs through dynamically reconfigurable FPGAs2014
- Algorithm-based fault tolerance applied to high performance computingJournal of Parallel and Distributed Computing, 2009
- VLSI design and implementation of a self-testing systolic array chip for signal processing2003
- Algorithm-based fault location and recovery for matrix computations2002
- A self-testing and self-diagnostic systolic array cell for signal processing2002
- Efficient techniques for the analysis of algorithm-based fault tolerance (ABFT) schemesIEEE Transactions on Computers, 1996