A compact hardware-software co-processing platform

FPGAs are powerful devices to be used in a large variety of applications such as intensive numerical processing, image and video processing due to their parallel processing ability. Therefore, more and more interest in using FPGA to be a computing accelerator device working with a general-purpose pr...

Full description

Bibliographic Details
Main Author: Shasha, Tian
Other Authors: Chen Shoushun
Format: Final Year Project (FYP)
Language:English
Published: 2015
Subjects:
Online Access:http://hdl.handle.net/10356/64466
_version_ 1811689894034014208
author Shasha, Tian
author2 Chen Shoushun
author_facet Chen Shoushun
Shasha, Tian
author_sort Shasha, Tian
collection NTU
description FPGAs are powerful devices to be used in a large variety of applications such as intensive numerical processing, image and video processing due to their parallel processing ability. Therefore, more and more interest in using FPGA to be a computing accelerator device working with a general-purpose processor. This report explores using a hardware-software co-processing approach for doing intensive data processing. The co-processing platform uses a Raspberry Pi as a PC in conjunction with an FPGA-based board and a mini LCD display interfacing to the Raspberry Pi. All the devices in this co-processing platform are credit card sized which can be installed in moving application such as unmanned aerial vehicle (UVA) to improve performance of image processing. This hardware-software co-processing platform is designed to implement a floating-point adder on the FPGA-base board and develop an interface application on the host Raspberry Pi for interconnection and communication. The single precision 32-bits floating-point adder was designed in HDL Verilog according to IEEE 754. The method to configure and interface to the hardware is using the concept of FrontPanel Endpoints provided by Opal Kelly. The hose PC-side interface application using for loading configuration files and data exchanging is developed in C++. Once the FPGA is configured, Raspberry Pi can transmit values to the hardware for data processing, which can return the result back to Raspberry Pi and displayed on the mini LCD.
first_indexed 2024-10-01T05:55:21Z
format Final Year Project (FYP)
id ntu-10356/64466
institution Nanyang Technological University
language English
last_indexed 2024-10-01T05:55:21Z
publishDate 2015
record_format dspace
spelling ntu-10356/644662023-07-07T16:11:45Z A compact hardware-software co-processing platform Shasha, Tian Chen Shoushun School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering FPGAs are powerful devices to be used in a large variety of applications such as intensive numerical processing, image and video processing due to their parallel processing ability. Therefore, more and more interest in using FPGA to be a computing accelerator device working with a general-purpose processor. This report explores using a hardware-software co-processing approach for doing intensive data processing. The co-processing platform uses a Raspberry Pi as a PC in conjunction with an FPGA-based board and a mini LCD display interfacing to the Raspberry Pi. All the devices in this co-processing platform are credit card sized which can be installed in moving application such as unmanned aerial vehicle (UVA) to improve performance of image processing. This hardware-software co-processing platform is designed to implement a floating-point adder on the FPGA-base board and develop an interface application on the host Raspberry Pi for interconnection and communication. The single precision 32-bits floating-point adder was designed in HDL Verilog according to IEEE 754. The method to configure and interface to the hardware is using the concept of FrontPanel Endpoints provided by Opal Kelly. The hose PC-side interface application using for loading configuration files and data exchanging is developed in C++. Once the FPGA is configured, Raspberry Pi can transmit values to the hardware for data processing, which can return the result back to Raspberry Pi and displayed on the mini LCD. Bachelor of Engineering 2015-05-27T02:28:33Z 2015-05-27T02:28:33Z 2015 2015 Final Year Project (FYP) http://hdl.handle.net/10356/64466 en Nanyang Technological University 53 p. application/pdf
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Shasha, Tian
A compact hardware-software co-processing platform
title A compact hardware-software co-processing platform
title_full A compact hardware-software co-processing platform
title_fullStr A compact hardware-software co-processing platform
title_full_unstemmed A compact hardware-software co-processing platform
title_short A compact hardware-software co-processing platform
title_sort compact hardware software co processing platform
topic DRNTU::Engineering::Electrical and electronic engineering
url http://hdl.handle.net/10356/64466
work_keys_str_mv AT shashatian acompacthardwaresoftwarecoprocessingplatform
AT shashatian compacthardwaresoftwarecoprocessingplatform