We discuss collisions that are of interest to multiprocessor verification. Collisions occur when different processes access a shared resource. We investigate how the results of such collisions can be presented in test programs and suggest implementations for automatically generating such tests and predicting the results of collision scenarios. Most of the ideas presented are the result of years of experience with two multi-processor test generators from IBM (Genie and Genesys-Pro) which are also briefly presented.
Because of their complexity, modern microprocessors need new tools that generate tests for micro-architectural events. Piparazzi is a test generator, developed at IBM, that generates (architectural) test programs for microarchitectural events. Piparazzi uses a declarative model of the micro-architecture and the user's definition of the required event to create an instance of a Constraint Satisfaction Problem (CSP). It then uses a dedicated CSP solver to generate a test program that covers the specific event. We show how Piparazzi yields significant improvements in covering micro-architectural events, by describing its technology and by exhibiting experimental results. Piparazzi has already been successful in finding both functional and performance bugs that could only be discovered using an exact micro-architectural model of the processor.
The continuing trend toward increased parallelism in processor design can be seen in both the growing number of processor cores per system and in on-core hardware mechanisms that assist parallelism, such as multithreading and cache hierarchies. This complexity exacerbates the problem of ensuring the functional correctness of such hardware systems. The growing importance of post-silicon validation is leading to an emerging type of parallel application, namely, the hardware exerciser. We describe a method for exercising parallel hardware by generating pseudorandom concurrent test programs. The test generation is carried out on the tested parallel platform and thus the generator itself is also a concurrent program. We describe the challenges associated with this technology and the approach used by the Threadmill hardware exerciser, a tool developed for the post-silicon validation of the IBM POWER7 processor.