Methods and systems for monitoring the subset of GPU components used by an application in safety critical environments

A non-transitory computer-readable storage medium having instructions stored thereon for execution by at least one processing unit, the instructions for implementing a method comprising:

• providing at least one test seed and at least one subsystem command to the GPU;
• monitoring one or more host computer system application commands to the GPU for a test interval;
• determining whether the host computer system application commands cause subsystems of the GPU to be active for that test interval;
• receiving at least one test result from the GPU in response to providing the at least one test seed and the at least one subsystem command to the GPU, wherein the at least one subsystem command to the GPU is directed to subsystems determined to be active;
• and
• if the at least one test result does not correspond to at least one expected result, identifying the GPU as being in an undesired state.