Figure 8
Performance comparison with the CUDA implementation on a single Nvidia GeForce 8800GTX. Performance comparison between our CBESW implementation with CUDA implementation on a single Nvidia GeForce 8800GTX, in terms of MCUPS. All queries were run against Swiss-Prot release 55.2. Seventeen query sequences with lengths of 63 to 852 amino acids were used. The scoring matrix used for the CUDA implementation was BLOSUM 50.