Assessing the potential of hybrid hpc systems for scientific applications: a case study

We have conducted a detailed study to understand the po-tential of hybrid CPU/FPGA High-Performance Computers for improving the performance of data-intensive, scientific applications. In particular, we have focused on an application in proteomics (Polygraph), which is representative of many types of computational analysis applications in the lifesciences: it focuses on extracting useful information from a large body of experimentally collected data (identifying ob-served peptide spectra collected from a mass spectrometer against a well-known protein database). Our preliminary analysis of Polygraph found that morethan half (51%) of the computation time was spent in three routines. We have implemented an FPGA version of themost computationally-intensive routine (20% of the time)on a Cray XD-1 system, and measured the overall speed up achieved in comparison to an optimized software version ofthe routine running on the Cray XD-1's native Opteron processors. We have achieved computational speedups of up to9.16. When we include data movement costs, the overall speedup is reduced to 1.78. We discuss the design and implementation strategies thatled to these results, as well as advantages and limitations we found on the Cray XD-1 platform. We also addressthe advantages and limitations of current development environments, as well as discuss relevant issues we found in our experience as hybrid CPU/FPGA programming model "users".