Download PDFOpen PDF in browserImproving GPU Register File Reliability With a Comprehensive ISA ExtensionEasyChair Preprint no. 46362 pages•Date: November 23, 2020AbstractThis work proposes a comprehensive ISA extension to improve GPU reliability to transient effects. Three additional instructions are proposed, implemented, and combined with software-based datapath duplication. Modified program codes are compared to state-of-the-art software-based fault tolerance techniques in terms of execution time, the circuit area is evaluated against the original GPU architecture, and a fault injection campaign is performed to assess reliability. Results show that the proposed ISA extension improves the performance of software-based approaches while maintaining fault detection capabilities at negligible costs in the circuit area. This work can help engineers in designing more efficient and resilient GPU architectures. Keyphrases: fault tolerance, GPU, hardening techniques, ISA extension
|