1. [Publications](/publications) 2. SASSIFI: An Architecture-level Fault Injection Tool for GPU Application Resilience Evaluation # SASSIFI: An Architecture-level Fault Injection Tool for GPU Application Resilience Evaluation ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image") As GPUs become more pervasive in both scalable high-performance computing systems and safety-critical embedded systems, evaluating and analyzing their resilience to soft errors caused by high-energy particle strikes will grow increasingly important. GPU designers must develop tools and techniques to understand the effect of these soft errors on applications. In this project we developed an error injection-based methodology and tool called SASSIFI to study the soft error resilience of massively parallel applications running on NVIDIA GPUs. Our approach uses a low-level assembly-language instrumentation tool called SASSI to profile and inject errors. SASSI provides efficiency by allowing instrumentation code to execute entirely on the GPU and provides the ability to inject into different architecture-visible state. For example, SASSIFI can inject errors in general-purpose registers, GPU memory, condition code registers, and predicate registers. SASSIFI can also inject errors into addresses and register indices. SASSIFI is publicly available on GitHub at . ## Authors [Siva Hari](/person/siva-hari) Timothy Tsai (NVIDIA) [Mark Stephenson](/person/mark-stephenson) [Steve Keckler](/person/stephen-keckler) [Joel Emer](/person/joel-emer) ## Publication Date Tuesday, April 25, 2017 ## Published in [International Symposium on Performance Analysis of Systems and Software (ISPASS)](https://ieeexplore.ieee.org/document/7975296) ## Research Area [Computer Architecture](/research-area/computer-architecture) [High Performance Computing](/research-area/high-performance-computing) [Resilience and Safety](/research-area/resilience) ## External Links [IEEE Digital Library](https://ieeexplore.ieee.org/document/7975296) ## Uploaded Files [Published manuscript](https://d1qx31qr3h6wln.cloudfront.net/publications/ISPASS_2017_SASSIFI.pdf "Open file in new window")1.94 MB ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .