SCBI_MapReduce, a New Ruby Task-Farm Skeleton for Automated Parallelisation and Distribution in Chunks of Sequences: The Implementation of a Boosted Blast+
Figure 1
Comparison of parallelisation flowgrams for a single “job”. (a) The classic MapReduce view in which the input data of a job are split into smaller data chunks by a “mapper” process and executed by separated parallel “tasks”; once all tasks have been finished, the results are combined by a “reduce” process. (b) SCBI_MAPREDUCE task-farm flowgram, in which a job is handled by a single “manager”, which is controlling the start and end of each distributed “task” executed by every “worker”.
