Treffer: A PRACTICAL MODEL of PARALLEL COMPUTATION.

The article focuses to develop a model of parallel computation that will serve as a basis for the design and analysis of fast, portable parallel algorithms. The Parallel Random Access Machine (PRAM) is the most popular model for representing and analyzing the complexity of parallel algorithms. PRAM consists of a collection of processors which compute synchronously in parallel and communicate with a global random access memory. The PRAM model is useful for gross classification of algorithms and problems. Several variations on the PRAM impose restrictions to make it more practical. These variations address memory contention, asynchrony, latency, bandwidth, and memory hierarchy. An important class of models at the opposite extreme are network models, in which communication is only allowed between directly connected processors. The LogP model describes an abstract machine configuration in terms of four performance parameters. LogP encourages techniques that work well in practice, such as coordinating the assignment of work with data placement, so as to reduce the amount of communication.