Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators

Mahdi Taheri1, Natalia cherezova2, Mohammad Saeed Ansari3, Maksim Jenihhin2, ALI Mahani4, Masoud Daneshtalab5, Jaan Raik2
1PhD researcher at Tallinn university of Technology, 2Tallinn University of Technology, 3University of Alberta, 4Shahid Bahonar University of Kerman, 5KTH Royal Institute of Technology


The stringent requirements for the Deep Neural Networks (DNNs) accelerator's reliability stand along with the need for reducing the computational burden on the hardware platforms, i.e. reducing the energy consumption and execution time as well as increasing the efficiency of DNN accelerators. Moreover, the growing demand for specialized DNN accelerators with tailored requirements, particularly for safety-critical applications, necessitates a comprehensive design space exploration to enable the development of efficient and robust accelerators that meet those requirements. Therefore, the trade-off between hardware performance, i.e. area and delay, and the reliability of the DNN accelerator implementation becomes critical and requires tools for analysis. This paper presents a comprehensive methodology for exploring and enabling a holistic assessment of the trilateral impact of quantization on model accuracy, activation fault reliability, and hardware efficiency. A fully automated framework is introduced that is capable of applying various quantization-aware techniques, fault injection, and hardware implementation, thus enabling the measurement of hardware parameters. Moreover, this paper proposes a novel lightweight protection technique integrated within the framework to ensure the dependable deployment of the final systolic-array-based FPGA implementation. The experiments on established benchmarks demonstrate the analysis flow and the profound implications of quantization on reliability, hardware performance, and network accuracy, particularly concerning the transient faults in the network's activations.