Concurrency bugs are among the most difficult to test and diagnose of all software bugs. The multicore technology trend worsens this problem. Most previous concurrency bug detection work focuses on one bug subclass, data races, and neglects many other important ones such as atomicity violations, which will soon become increasingly important due to the emerging trend of transactional memory models. This paper proposes an innovative, comprehensive, invariantbased approach called AVIO to detect atomicity violations. Our idea is based on a novel observation called access interleaving invariant, which is a good indication of programmers' assumptions about the atomicity of certain code regions. By automatically extracting such invariants and detecting violations of these invariants at run time, AVIO can detect a variety of atomicity violations. Based on this idea, we have designed and built two implementations of AVIO and evaluated the trade-offs between them. The first implementation, AVIO-S, is purely in software, while the second, AVIO-H, requires some simple extensions to the cache coherence hardware. AVIO-S is cheaper and more accurate but incurs much higher overhead and thus more run-time perturbation than AVIO-H. Therefore, AVIO-S is more suitable for in-house bug detection and postmortem bug diagnosis, while AVIO-H can be used for bug detection during production runs. We evaluate both implementations of AVIO using large realworld server applications (Apache and MySQL) with six representative real atomicity violation bugs, and SPLASH-2 benchmarks. Our results show that AVIO detects more tested atomicity violations of various types and has 25 times fewer false positives than previous solutions on average.

The first step towards the design of video processors and video systems is to achieve an accurate understanding of the major video applications, including not only the fundamentals of the many video compression standards, but also the workload characteristics of those applications. Introduced in 1997, the MediaBench benchmark suite provided the first set of full application-level benchmarks for studying video processing characteristics, and has consequently enabled significant research in computer architecture and compiler research for multimedia systems. To expedite the next generation of systems research, the MediaBench Consortium is developing the MediaBench II benchmark suite, incorporating benchmarks from the latest multimedia technologies, and providing both a single composite benchmark suite as well as separate benchmark suites for each area of multimedia. In the area of video, MediaBench II Video includes both the popular mainstream video compression standards, such as Motion-JPEG, H.263, and MPEG-2, and the more recent next-generation standards, including MPEG-4, Motion-JPEG2000, and H.264. This paper introduces MediaBench II Video and provides a comprehensive workload evaluation of its major processing characteristics.

Current data intensive scalable computing (DISC) systems, although scalable, achieve embarrassingly low rates of processing per node. We feel that current DISC systems have repeated a mistake of old high-performance systems: focusing on scalability without considering efficiency. This poor efficiency comes with issues in reliability, energy, and cost. As the gap between theoretical performance and what is actually achieved has become glaringly large, we feel there is a pressing need to rethink the design of future data intensive computing and carefully consider the direction of future research.

We thank the members and companies of the PDL Consortium (including EMC, Hewlett-Packard, Hitachi, IBM, Intel, Microsoft, Network Appliance, Oracle, Panasas, Seagate, Sun, and Veritas) for their interest, insights, feedback, and support. We thank IBM and Intel for hardware grants supporting our research efforts.