Figure 7.

Speedup on NVIDIA Tesla Fermi C2050. Speedup on the Tesla Fermi C2050 is greater than Tesla C1060 due to the presence of hierarchy of caches on the C2050 GPU. Baseline: No-approximation CPU implementation optimized by hand-tuned SSE Intrinsics and parallelized across 16 cores.

Daga and Feng BMC Bioinformatics 2012 13(Suppl 5):S4   doi:10.1186/1471-2105-13-S5-S4