Date of Graduation

1-2018

Document Type

Thesis

Degree Name

Master of Science in Computer Engineering (MSCmpE)

Degree Level

Graduate

Department

Computer Science & Computer Engineering

Advisor

James Parkerson

Committee Member

Gordon Beavers

Second Committee Member

Jia Di

Keywords

FPGA, Performance, Reconfigurable Computing

Abstract

One important aspect of many commercial computer systems is their performance; therefore, system designers seek to improve the performance next-generation systems with respect to previous generations. This could mean improved computational performance, reduced power consumption leading to better battery life in mobile devices, smaller form factors, or improvements in many areas. In terms of increased system speed and computation performance, processor manufacturers have been able to increase the clock frequency of processors up to a point, but now it is more common to seek performance gains through increased parallelism (such as a processor having more processor cores on a single chip or an increased number of physical processors in the system) rather than increased processor frequency.

This paper proposes an additional strategy for increasing system performance by allowing application developers to design custom circuitry for either their whole application or at least some portions of it that are on the critical path or that are computationally expensive. This will improve application performance by avoiding executing application instructions on a general-purpose CPU and instead executing on a specialized circuit designed to perform the desired algorithm, offloading tasks from the CPU (thereby reducing the overall system load) and enabling true parallelism for applications that can take advantage of a more parallel architecture.

For this paper, an Altera Cyclone II FPGA is used, but in practice, a higher performance and higher density FPGA should be used.

Share

COinS