Soft core and hard core vector processors using vector backend

• Main Author: Soh, Jun Jie
• Other Authors: School of Computer Engineering
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: 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
• Online Access: http://hdl.handle.net/10356/59019
• Institution: Nanyang Technological University

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.