STLs for GPUs: Using High-Level Language Approaches

Abstract

Self-Test Libraries (STLs) are widely used for in-field fault detection in processor-based systems. Currently, their adoption is being extended to Graphics Processing Units (GPUs), due to their increasing usage in the safety-critical domain, and the demand for effective in-field functional safety mechanisms mandated by the functional safety standards (e.g., ISO 26262 for automotive). This work describes a method to develop suitable STLs resorting to High-Level Languages (HLLs) (e.g., CUDA) for some modules in GPUs, thus reducing the complexity of the STLs development process. We also discuss the method’s main advantages/limitations, as well as the challenges and constraints when developing HLL STLs for GPUs. Furthermore, we outline those cases demanding the usage of Low-Level Languages (LLLs) for the implementation of STLs. The evaluation and validation of the method resort to the FlexGripPlus GPU model, implementing one micro-architecture of NVIDIA. The experimental results show that HLL STLs can be effectively developed for regular modules in the GPU.