Timings for associative operations on the MASC model
Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001
The MASC (Multiple Associative Computing) model is a generalized associative-style computational model that naturally supports massive data-parallelism and also control-parallelism. A wide range of applications has been developed on this model. Recent research has compared its power to the power of other popular parallel models such as the PRAM and MMB models using simulations. However, the simulation of MMB has identified some important issues regarding the cost of certain basic MASC
... asic MASC operations required for associative computing such as broadcasts, reductions, and associative searches. This paper investigates these issues and gives background information and an analysis of timings for these operations, based on implementation techniques and comparison fairness with respect to other models. It aims to provide justification and clarify arguments on the timings for these constant-time or nearly constant-time basic MASC operations. 0-7695-0990-8/01/$10.00 (C) 2001 IEEE The MASC model The MASC model consists of an array of processing elements (PEs) and an array of instruction stream processors (ISs). Each PE, paired with its local memory, is called a cell. There are three real or virtual networks to connect cells and ISs, namely, a cell network used for communication among cells, an instruction stream broadcast/reduction network used for communication between ISs and their cells, and an IS network used for communication among ISs (Figure 1 ).