Performance Evaluation of FPGA-Based Biological Applications

Conference · Mon Jan 01 04:00:00 EST 2007

OSTI ID:931803

Storaasli, Olaf O ^[1]; Yu, Weikuan ^[1]; Strenski, Dave ^[2]; Maltby, Jim ^[3]

---

1. ORNL
2. Cray, Inc.
3. Mitrionics

On the forefront of recent HPC innovations are Field Programmable Gate Arrays (FPGA), which promise to accelerate calculations by one or more orders of magnitude. The performance of two Cray XD1 systems with Virtex-II Pro 50 and Virtex-4 LX160 FPGAs, were evaluated using a computational biological human genome comparisons program. This paper describes scalable, parallel, FPGA-accelerated results for the FASTA application ssearch34, using the Smith-Waterman algorithm for DNA, RNA and protein sequencing contained in the OpenFPGA benchmark suite. Results indicate typical Cray XD1 FPGA speedups of 50x (Virtex-II Pro 50) and 100x (Virtex-4 LX160) compared to a 2.2 GHz Opteron. Similar speedups are expected for the DRC RPU110-L200 modules (Virtex-4 LX200), which fit in an Opteron socket, and selected by Cray for its XT Supercomputers. The FPGA programming challenges, human genome benchmarking, and data verification of results, are discussed.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Center for Computational Sciences
• Sponsoring Organization: ORNL LDRD Director's R&D
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 931803
• Country of Publication: United States
• Language: English

Related Subjects

Cray
DNA
FASTA
FPGA
OpenFPGA
RNA
Smith-Waterman
Virtex
XD1
reconfigurable