Widely used data race detectors, including the state-of-the-art FastTrack algorithm, incur performance costs that are acceptable for regular in-house testing, but miss races detectable from the analyzed execution. Predictive analyses detect more data races in an analyzed execution than FastTrack detects, but at significantly higher performance cost.

Data races are a real problem for parallel software, yet hard to detect. Sound predictive analysis observes a program execution and detects data races that exist in some other, unobserved execution. However, existing predictive analyses miss races because they do not scale to full program executions or do not precisely incorporate data and control dependence. This paper introduces two novel, sound predictive approaches that incorporate data and control dependence and handle full program executions. An evaluation using real, large Java programs shows that these approaches detect more data races than the closest related approaches, thus advancing the state of the art in sound predictive race detection.

Dynamic program analysis can predict data races knowable from an observed execution, but existing predictive analyses either miss races or cannot analyze full program executions. This paper presents Vindicator, a novel, sound (no false races) predictive approach that finds more data races than existing predictive approaches. Vindicator achieves high coverage by using a new, efficient analysis that finds all possible predictable races but may detect false races. Vindicator ensures soundness using a novel algorithm that checks each potential race to determine whether it is a true predictable race. An evaluation using large Java programs shows that Vindicator finds hard-to-detect predictable races that existing sound predictive analyses miss, at a comparable performance cost.

Shared-memory parallel programs are hard to get right. A major challenge is that language and hardware memory models allow unexpected, erroneous behaviors for executions containing data races. Researchers have introduced dynamic analyses that expose weak memory model behaviors, but these approaches cannot expose behaviors due to loading a "future value" -- a value written by a program store that executes after the program load that uses the value. This paper presents prescient memory (PM), a novel dynamic analysis that exposes behaviors due to future values. PM speculatively returns a future value at a program load, and tries to validate the speculative value at a later store. To enable PM to expose behaviors due to future values in real application executions, we introduce a novel approach that increases the chances of using and successfully validating future values, by profiling and predicting future values and guiding execution. Experiments show that our approach is able to uncover a few previously unknown behaviors due to future values in benchmarked versions of real applications. Overall, PM overcomes a key limitation of existing approaches, broadening the scope of program behaviors that dynamic analyses can expose.

For this study the techniques of virtual machine migration are understood and the affects deduplication has on migration are evaluated. The benefits of using deduplication and compression on virtual machines show in the metric of space saved during migrating. Deduplication is computationally expensive so we evaluate how to group virtual machines with similar elements in order to improve migration. From this study, grouping virtual machines based on similar elements improves the overhead from deduplication and compression but estimates which virtual machines are best grouped together.