Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural NetworksACM Computing Surveys, 2024
- High-Level Synthesis Hardware Design for FPGA-Based Accelerators: Models, Methodologies, and FrameworksIEEE Access, 2022
- A Survey of Quantization Methods for Efficient Neural Network Inference2022
- How Reduced Data Precision and Degree of Parallelism Impact the Reliability of Convolutional Neural Networks on FPGAsIEEE Transactions on Nuclear Science, 2021
- Understanding the Impact of Quantization, Accuracy, and Radiation on the Reliability of Convolutional Neural Networks on FPGAsIEEE Transactions on Nuclear Science, 2020
- Impact of Tensor Cores and Mixed Precision on the Reliability of Matrix Multiplication in GPUsIEEE Transactions on Nuclear Science, 2020
- CNN-Grinder: From Algorithmic to High-Level Synthesis descriptions of CNNs for Low-end-low-cost FPGA SoCsMicroprocessors and Microsystems, 2020
- [DL] A Survey of FPGA-based Neural Network Inference AcceleratorsACM Transactions on Reconfigurable Technology and Systems, 2019
- OpenCL: A Parallel Programming Standard for Heterogeneous Computing SystemsComputing in Science & Engineering, 2010
- Essentials of Electronic Testing for Digital, Memory and Mixed-Signal VLSI Circuits2002