On the testing of special memories in GPGPUs

Nowadays, data-intensive processing applications, such as multimedia, high-performance computing and safety-critical ones (e.g., in automotive) employ General Purpose Graphics Processing Units (GPGPUs) due to their parallel processing capabilities and high performance. In these devices, multiple levels of memories are employed in GPGPUs to hide latency and increase the performance during the operation of a kernel. Moreover, modern GPGPU architectures implement cutting-edge semiconductor technologies, reducing their size and power consumption. However, some studies proved that these technologies are prone to faults during the operative life of a device, so compromising reliability. In this work, we developed functional test techniques based on parallel Software-Based Self-Test routines to test memory structures in the memory hierarchy of a GPGPU (FlexGripPlus) implementing the G80 architecture of Nvidia.