The Cost of A BSP Algorithm
The cost of a superstep is determined as the sum of three terms; the cost of the longest running local computation, the cost of global communication between the processors, and the cost of the barrier synchronisation at the end of the superstep. The cost of one superstep for processors:
where is the cost for the local computation in process, and is the number of messages sent or received by process . Note that homogeneous processors are assumed here. It is more common for the expression to be written as where and are maxima. The cost of the algorithm then, is the sum of the costs of each superstep.
where is the number of supersteps.
, and are usually modelled as functions, that vary with problem size. These three characteristics of a BSP algorithm are usually described in terms of asymptotic notation, e.g. .
Read more about this topic: Bulk Synchronous Parallel
Famous quotes containing the word cost:
“I favor the policy of economy, not because I wish to save money, but because I wish to save people. The men and women of this country who toil are the ones who bear the cost of the Government. Every dollar that we carelessly waste means that their life will be so much the more meager. Every dollar that we prudently save means that their life will be so much the more abundant. Economy is idealism in its most practical terms.”
—Calvin Coolidge (1872–1933)