High Performance Biological Pairwise Sequence Alignment: FPGA versus GPU versus Cell BE versus GPP

<table class="table-group" id="tab10"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td align="left"> Platform</td><td align="center">Performance (MCUPS) per watt</td><td align="center">Normalized performance per watt</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td align="left">FPGA</td><td align="center">508</td><td align="center">584</td></tr><tr><td align="left">GPU</td><td align="center">22</td><td align="center">25</td></tr><tr><td align="left">Cell BE</td><td align="center">27</td><td align="center">31</td></tr><tr><td align="left">GPP</td><td align="center">0.87</td><td align="center">1</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Performance per watt figures of the Smith-Waterman algorithm implementation on all four technologies.

International Journal of Reconfigurable Computing

tab10

Table 10

Table 10: High Performance Biological Pairwise Sequence Alignment: FPGA versus GPU versus Cell BE versus GPP 