Figure 4
From: BarraCUDA - a fast short read sequence aligner using graphics processing units
The scalability of alignment throughputs using multiple GPUs and CPUs. This figures shows the effect on alignment throughputs (in megabases per seconds, Mbp/s) when multiple GPUs and CPUs were used to map a single-end library containing 13.6 million 96 bp reads to the D. Melanogaster genome. A computer node containing two 6-core Intel Xeon 5670 s and eight NVIDIA Tesla M2050 were used in this test. The throughputs of BWA were measured with 1, 2, 4, 6, 8, 10 and 12 threads and BarraCUDA with 1, 2, 4, 6 and 8 M2050s using default options.