Please use this identifier to cite or link to this item:
Title: Soft core and hard core vector processors using vector backend
Authors: Soh, Jun Jie
Keywords: DRNTU::Engineering::Computer science and engineering::Computer systems organization::Processor architectures
DRNTU::Engineering::Computer science and engineering::Hardware::Performance and reliability
DRNTU::Engineering::Computer science and engineering::Theory of computation::Analysis of algorithms and problem complexity
DRNTU::Engineering::Computer science and engineering::Computer systems organization::Performance of systems
Issue Date: 2014
Abstract: As the size and complexity of today’s most modern computer processors increase,designing these processors may not necessary increase the speed of the processor.However, these processors can be designed by using soft core processors which is customizable and hard core processors which are fixed and cannot be modified.For this project, we will look at two soft and hard core processors which can be designed usign vector architecture; VectorBlox MXP processor and NEON processor. Both processors will be benchmarked using the Zedboard by using a set of benchmark metrics and compared to determine which processor is faster under certain conditions. In order to implement vector backend suitable to be used on these processors for benchmarking, SCORE compiler is used to achieve this task.The project objectives is to design these processors using the SCORE Compiler and analyze both processors within one year based on the resources given and the reading list.
Schools: School of Computer Engineering 
Research Centres: Centre for High Performance Embedded Systems 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
425.94 kBAdobe PDFView/Open

Page view(s)

Updated on Sep 25, 2023

Download(s) 50

Updated on Sep 25, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.