Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/76778
Title: Meltdown and Spectre vulnerabilities, and performance issues of related patches
Authors: Agius, Kevin (2020)
Keywords: Computer architecture
Computer input-output equipment
Microprocessors
Issue Date: 2020
Citation: Agius, K. (2020). Meltdown and Spectre vulnerabilities, and performance issues of related patches (Bachelor's dissertation).
Abstract: Meltdown and Spectre attacks are hardware vulnerabilities at a CPU’s microarchitectural level, in which the attacker can manipulate various performance enhancement techniques that operate, to extract sensitive data from within the cache memory. The vulnerabilities make directly use of speculative execution, branch prediction and out-of-order execution (Lipp et al, 2018) and (Kocher et al, 2019), in which the attacker injects malicious code in order to obtain data from within the CPU’s cache memory. Software patches with regards to various operating systems and system kernel have been developed and distributed in order to mitigate the attack’s severity. In this study, we used the benchmarking tool 7-Bench, which makes direct use of the operations that the patches target, mainly including branch prediction and out-oforder execution, which are the main microarchitecture functions that have been implemented in modern day CPUs and manipulated through Spectre and Meltdown. The benchmarking tool was implemented on a wide variety of modern generation processors and system frameworks in order to analyse the impact that such patches have caused across various platforms. The benchmarking tool was executed on the systems during various scenarios, these being: benchmarks with all the patches enabled and disabled, and for each patch individually. The results obtained from these benchmarks were then compared to the other results obtained from the system in order to analyse the performance differences that they have caused. Furthermore, these results were statistically analysed in order to test the hypothesis set for this study.
Description: B.Sc. IT (Hons)(Melit.)
URI: https://www.um.edu.mt/library/oar/handle/123456789/76778
Appears in Collections:Dissertations - FacICT - 2020
Dissertations - FacICTCIS - 2020

Files in This Item:
File Description SizeFormat 
20BITSD001.pdf
  Restricted Access
3.91 MBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.