Myrimatch is a tool that identifies proteins by comparing the mass spectrometry data for each constituent peptide against a known database of proteins. The application was developed by Dr. Tabb at Vanderbilt University, and is both multi-threaded and can be clustered efficiently across multiple systems. The data set for the benchmark is a set of experimental spectra data collected from baker’s yeast and compared against a FASTA database from yeastgenome.org. Thanks go to Scott Wasson of Tech Report for sharing this benchmark with us.
Previous results have shown that the performance for Myrimatch typically peaks at 4 threads, stays roughly constant at 6 threads and decreases at 8 threads due to contention and resource starvation. Consequently, we will only test one to four threads.
Figure 7 – Myrimatch Performance
We measured a modest performance benefit from the additional bandwidth available to Harpertown, about 4.2% on a clock for clock basis versus Clovertown. This is less than expected, again due to the difference in frequency for the two parts. Adjusting for that difference, and we would estimate that Harpertown would probably show about a 20% IPC advantage over a 3GHz Clovertown.