University of Illinois Urbana-Champaign

Hardware Acceleration of Short Read Alignment

Chen, Daniel

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/54545

Description

Title
Hardware Acceleration of Short Read Alignment
Author(s)
Chen, Daniel
Contributor(s)
Chen, Deming
Issue Date
2014-05
Keyword(s)
  • FPGA
  • GPA
  • OpenCL
  • Short Read Alignment
  • Hardware Acceleration
Abstract
Short read aligners are tools used to map a person's genome onto the human reference genome. A typical aligner may take around seven hours to map the DNA associated with one single chromosome. I propose porting an aligner to FPGA, which would offer speedup in addition to the familiar features present in the original aligner. Traditionally, aligners have relied on multi-core CPUs for alignment. However, this approach does not fully exploit the absurdly parallel nature of short read alignment. Read alignments have essentially no dependencies, which makes them suitable for parallel processing. There exist several GPU and FPGA aligners, but they do not include the full feature set of their CPU counterparts. Open Computing Language (OpenCL) is utilized for application development, which will allow for the ease of use on both GPU and FPGA. Eventually, the aligner will support the same tasks as the most feature-rich aligners of today. Speedups of 5x up to 50x are expected compared to traditional CPU aligners.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/54545

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research