Type

Text

Type

Thesis

Advisor

Salman, Emre. | Milder, Peter

Date

2014-12-01

Keywords

asic, checksum, fpga, hardware, implementation, parallel | Electrical engineering

Department

Department of Electrical Engineering.

Language

en_US

Source

This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree.

Identifier

http://hdl.handle.net/11401/77480

Publisher

The Graduate School, Stony Brook University: Stony Brook, NY.

Format

application/pdf

Abstract

Checksums are utilized in many contexts such as communications, storage and reliable processing. The balance between checksum strength, implementation cost and obtained throughput often pose a challenge for present day system designers. In this research we propose two new methods for implementing the Fletcher Checksum (FC) in a parallelized context. We determined an extended parallel definition from the original FC and applied it to two different hardware implementation approaches. We then created a generator that would automatically output parameterized designs. We controlled the input word length, number of parallel inputs and architecture of the designs, and we then synthesized these designs for FPGA and ASIC. Our results show that parallelization of FC is feasible and the system throughput is proportional to the cost defined by resources used, area and power consumption. In our results, we demonstrate designs with throughput up to 375 Gbits/sec in ASIC and up to 110 Gbits/sec in FPGA, depending on the specific parameters. | 36 pages

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.