GPUs (Graphics Processing Units) have gained wide adoption as accelerators for general purpose computing. They are widely used in error-sensitive applications, i.e. General Purpose GPU (GPGPU) applications However, the reliability implications of using GPUs are unclear. This paper presents a fault injection study to investigate the end-to-end reliability characteristics of GPGPU applications. The investigation showed that 8% to 40% of the faults result in Silent Data Corruption (SDC). To reduce the percentage of SDCs, we propose heuristics to selectively protect specific elements of the application and design error detectors based on heuristics. We evaluate the efficacy of the detectors in reducing SDCs and measure performance overheads of the detectors. Our results show that the heuristics are able to reduce the SDC causing faults by 60% on average, while incurring reasonable performance overheads (35% to 95%).
email: email@example.comPhone: 604-827-4245 (please email first)
Address: Rm. 4048, Fred Kaiser Building, 2332 Main Mall, Vancouver, BC V6T1Z4.
- Out of Control: Stealthy Attacks on Robotic Vehicles Protected by Control-Based Techniques
- A Tale of Two Injectors: End-to-End Comparison of IR-level and Assembly-Level Fault Injection
- BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems
- OneOS: IoT Platform based on Posix and Actors
- BonVoision: Leveraging Spatial Data Smoothness for Recovery from Memory Soft Errors
- Design-Level and Code-Level Security Analysis of IoT Devices
- Failure Prediction in the Internet of Things due to Memory Exhaustion
- CORGIDS: A Correlation-based Generic Intrusion Detection System
- TensorFI: A Configurable Fault Injector for TensorFlow Applications
- DynPolAC: Dynamic Policy-based Access Control for IoT Systems