Skip to main content
Fig. 7 | BMC Bioinformatics

Fig. 7

From: K-mer clustering algorithm using a MapReduce framework: application to the parallelization of the Inchworm module of Trinity

Fig. 7

(a) High-water mark for memory usage in GB over all compute nodes, (b) runtime in minutes, and (c) cumulative I/O in TB. Results are given for the mouse, sugarbeet and wheat datasets described in Table 1, and using the computing resources listed. All jobs with MapReduce-Inchworm used a 4GB pagesize parameter. Bars marked original represent runs of the original Inchworm, MR-64 represents runs of MapReduce-Inchworm using 64 compute nodes, MR-128 represents runs using 128 compute nodes, and MR-192 represents runs using 192 compute nodes

Back to article page