This article presents a general algorithm for transforming sequential imperative programs into parallel data-flow programs. Our algorithm operates on a program dependence graph i...
Graphics processing units (GPUs) are powerful devices capable of rapid parallel computation. GPU programming, however, can be quite difficult, limiting its use to experienced prog...
Workload, platform, and available resources constitute a parallel program’s execution environment. Most parallelization efforts statically target an anticipated range of environ...
Arun Raman, Ayal Zaks, Jae W. Lee, David I. August
Existing dynamic race detectors suffer from at least one of the following three limitations: (i) space overhead per memory location grows linearly with the number of parallel thre...