VLIW machines possibly provide the most direct way to exploit instruction level parallelism; however, they cannot be used to emulate current general-purpose instruction set archit...
Parallel processing networks, even full crossbars, that only implement point-to-point and multicast message passing are inefficient for collective communications because multiple ...
paper we describe d/streams, a language-independent abstraction with a small set of simple primitives for buffered I/O on distributed data-structures. We describe the interface an...
Big data is the tar sands of the data world: vast reserves of raw gritty data whose valuable information content can only be extracted at great cost. MapReduce is a popular parall...
We propose a formalisation of the notion of transaction, using a variant of CCS, RCCS, that distinguishes reversible and irreversible actions, and incorporates a distributed backtr...