Concurrent programs are difficult to write, reason about, re-use, and maintain. In particular, for system-level ions that use a shared memory abstraction for thread or process syn...
The predominant thread-based approach to concurrent programming is bug-prone, difficult to reason about, and does not scale well to large numbers of processors. Sieves provide a s...
Using multi-GPU systems, including GPU clusters, is gaining popularity in scientific computing. However, when using multiple GPUs concurrently, the conventional data parallel GPU...
Abstract. Measurement and modelling of distributions of data communication times is commonly done for telecommunication networks, but this has not previously been done for message ...