Matching Items (60)
Filtering by
- All Subjects: Computer Science
- Creators: Doupe, Adam
- Status: Published
Description
Web applications are ubiquitous. Accessible from almost anywhere, web applications support multiple platforms and can be easily customized. Most people interact with web applications daily for social media, communication, research, purchases, etc. Node.js has gained popularity as a programming language for web applications. A server-side JavaScript implementation, Node.js, allows both the front-end and back-end to be coded in JavaScript. Node.js contains many features such as dynamic inclusion of other modules using a built-in function named require which dynamically locates and loads code.
To be effective, web applications must perform actions quickly while avoiding unexpected interruptions. However, dynamically linked libraries can cause delays and thus downtime, because dynamically linked code must load multiple files, often from disk. As loading is one of the slowest operations a computer performs, seeking from disk can have a negative impact on performance which causes the server to feel less responsive for users. Dynamically linked code can also break when the underlying library is updated. Normally, when trying to update a server, developers will use test servers. However, if the developer accidentally updates a library in a dynamically linked system, it may be incompatible with another portion of the program.
Statically linking code makes it more reliable and faster (to load) than dynamically linking code. The static linking process varies by programming language. Therefore, different static linkers need to be developed for different languages. This thesis describes the creation of a static linker, called FrozenNode, for the popular back-end web application language, Node.js. FrozenNode resolves Node.js applications into a single file that does not rely on dynamic libraries. FrozenNode was built on top of Closure Compiler to accurately process JavaScript. We found that the resolved application was faster and self-contained yielding significant advantages over the dynamically loaded application. Furthermore, both had the same output.
Vulnerabilities in web applications can be found using static analysis tools, however static analysis tools must reason about dynamically linked application. FrozenNode can be used to statically link a Node.js application before being used by a JavaScript static analysis tool.
To be effective, web applications must perform actions quickly while avoiding unexpected interruptions. However, dynamically linked libraries can cause delays and thus downtime, because dynamically linked code must load multiple files, often from disk. As loading is one of the slowest operations a computer performs, seeking from disk can have a negative impact on performance which causes the server to feel less responsive for users. Dynamically linked code can also break when the underlying library is updated. Normally, when trying to update a server, developers will use test servers. However, if the developer accidentally updates a library in a dynamically linked system, it may be incompatible with another portion of the program.
Statically linking code makes it more reliable and faster (to load) than dynamically linking code. The static linking process varies by programming language. Therefore, different static linkers need to be developed for different languages. This thesis describes the creation of a static linker, called FrozenNode, for the popular back-end web application language, Node.js. FrozenNode resolves Node.js applications into a single file that does not rely on dynamic libraries. FrozenNode was built on top of Closure Compiler to accurately process JavaScript. We found that the resolved application was faster and self-contained yielding significant advantages over the dynamically loaded application. Furthermore, both had the same output.
Vulnerabilities in web applications can be found using static analysis tools, however static analysis tools must reason about dynamically linked application. FrozenNode can be used to statically link a Node.js application before being used by a JavaScript static analysis tool.
ContributorsHutchins, James (Author) / Doupe, Adam (Thesis advisor) / Shoshitaishvili, Yan (Committee member) / Zhao, Ziming (Committee member) / Arizona State University (Publisher)
Created2018
Description
A Virtual Private Network (VPN) is the traditional approach for an end-to-end secure connection between two endpoints. Most existing VPN solutions are intended for wired networks with reliable connections. In a mobile environment, network connections are less reliable and devices experience intermittent network disconnections due to either switching from one network to another or experiencing a gap in coverage during roaming. These disruptive events affects traditional VPN performance, resulting in possible termination of applications, data loss, and reduced productivity. Mobile VPNs bridge the gap between what users and applications expect from a wired network and the realities of mobile computing.
In this dissertation, MobiVPN, which was built by modifying the widely-used OpenVPN so that the requirements of a mobile VPN were met, was designed and developed. The aim in MobiVPN was for it to be a reliable and efficient VPN for mobile environments. In order to achieve these objectives, MobiVPN introduces the following features: 1) Fast and lightweight VPN session resumption, where MobiVPN is able decrease the time it takes to resume a VPN tunnel after a mobility event by an average of 97.19\% compared to that of OpenVPN. 2) Persistence of TCP sessions of the tunneled applications allowing them to survive VPN tunnel disruptions due to a gap in network coverage no matter how long the coverage gap is. MobiVPN also has mechanisms to suspend and resume TCP flows during and after a network disconnection with a packet buffering option to maintain the TCP sending rate. MobiVPN was able to provide fast resumption of TCP flows after reconnection with improved TCP performance when multiple disconnections occur with an average of 30.08\% increase in throughput in the experiments where buffering was used, and an average of 20.93\% of increased throughput for flows that were not buffered. 3) A fine-grained, flow-based adaptive compression which allows MobiVPN to treat each tunneled flow independently so that compression can be turned on for compressible flows, and turned off for incompressible ones. The experiments showed that the flow-based adaptive compression outperformed OpenVPN's compression options in terms of effective throughput, data reduction, and lesser compression operations.
In this dissertation, MobiVPN, which was built by modifying the widely-used OpenVPN so that the requirements of a mobile VPN were met, was designed and developed. The aim in MobiVPN was for it to be a reliable and efficient VPN for mobile environments. In order to achieve these objectives, MobiVPN introduces the following features: 1) Fast and lightweight VPN session resumption, where MobiVPN is able decrease the time it takes to resume a VPN tunnel after a mobility event by an average of 97.19\% compared to that of OpenVPN. 2) Persistence of TCP sessions of the tunneled applications allowing them to survive VPN tunnel disruptions due to a gap in network coverage no matter how long the coverage gap is. MobiVPN also has mechanisms to suspend and resume TCP flows during and after a network disconnection with a packet buffering option to maintain the TCP sending rate. MobiVPN was able to provide fast resumption of TCP flows after reconnection with improved TCP performance when multiple disconnections occur with an average of 30.08\% increase in throughput in the experiments where buffering was used, and an average of 20.93\% of increased throughput for flows that were not buffered. 3) A fine-grained, flow-based adaptive compression which allows MobiVPN to treat each tunneled flow independently so that compression can be turned on for compressible flows, and turned off for incompressible ones. The experiments showed that the flow-based adaptive compression outperformed OpenVPN's compression options in terms of effective throughput, data reduction, and lesser compression operations.
ContributorsAlshalan, Abdullah O. (Author) / Huang, Dijiang (Thesis advisor) / Ahn, Gail-Joon (Committee member) / Doupe, Adam (Committee member) / Zhang, Yanchao (Committee member) / Arizona State University (Publisher)
Created2017
Description
Data breaches have been on a rise and financial sector is among the top targeted. It can take a few months and upto a few years to identify the occurrence of a data breach. A major motivation behind data breaches is financial gain, hence most of the data ends up being on sale on the darkweb websites. It is important to identify sale of such stolen information on a timely and relevant manner. In this research, we present a system for timely identification of sale of stolen data on darkweb websites. We frame identifying sale of stolen data as a multi-label classification problem and leverage several machine learning approaches based on the thread content (textual) and social network analysis of the user communication seen on darkweb websites. The system generates alerts about trends based on popularity amongst the users of such websites. We evaluate our system using the K-fold cross validation as well as manual evaluation of blind (unseen) data. The method of combining social network and textual features outperforms baseline method i.e only using textual features, by 15 to 20 % improved precision. The alerts provide a good insight and we illustrate our findings by cases studies of the results.
ContributorsDharaiya, Krishna Tushar (Author) / Shakarian, Paulo (Thesis advisor) / Doupe, Adam (Committee member) / Shoshitaishvili, Yan (Committee member) / Arizona State University (Publisher)
Created2018
Description
In this research, I try to solve multi-class multi-label classication problem, where
the goal is to automatically assign one or more labels(tags) to discussion topics seen
in deepweb. I observed natural hierarchy in our dataset, and I used dierent
techniques to ensure hierarchical integrity constraint on the predicted tag list. To
solve `class imbalance' and `scarcity of labeled data' problems, I developed semisupervised
model based on elastic search(ES) document relevance score. I evaluate
our models using standard K-fold cross-validation method. Ensuring hierarchical
integrity constraints improved F1 score by 11.9% over standard supervised learning,
while our ES based semi-supervised learning model out-performed other models in
terms of precision(78.4%) score while maintaining comparable recall(21%) score.
the goal is to automatically assign one or more labels(tags) to discussion topics seen
in deepweb. I observed natural hierarchy in our dataset, and I used dierent
techniques to ensure hierarchical integrity constraint on the predicted tag list. To
solve `class imbalance' and `scarcity of labeled data' problems, I developed semisupervised
model based on elastic search(ES) document relevance score. I evaluate
our models using standard K-fold cross-validation method. Ensuring hierarchical
integrity constraints improved F1 score by 11.9% over standard supervised learning,
while our ES based semi-supervised learning model out-performed other models in
terms of precision(78.4%) score while maintaining comparable recall(21%) score.
ContributorsPatil, Revanth (Author) / Shakarian, Paulo (Thesis advisor) / Doupe, Adam (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2018
Description
The telephone network is used by almost every person in the modern world. With the rise of Internet access to the PSTN, the telephone network today is rife with telephone spam and scams. Spam calls are significant annoyances for telephone users, unlike email spam, spam calls demand immediate attention. They are not only significant annoyances but also result in significant financial losses in the economy. According to complaint data from the FTC, complaints on illegal calls have made record numbers in recent years. Americans lose billions to fraud due to malicious telephone communication, despite various efforts to subdue telephone spam, scam, and robocalls.
In this dissertation, a study of what causes the users to fall victim to telephone scams is presented, and it demonstrates that impersonation is at the heart of the problem. Most solutions today primarily rely on gathering offending caller IDs, however, they do not work effectively when the caller ID has been spoofed. Due to a lack of authentication in the PSTN caller ID transmission scheme, fraudsters can manipulate the caller ID to impersonate a trusted entity and further a variety of scams. To provide a solution to this fundamental problem, a novel architecture and method to authenticate the transmission of the caller ID is proposed. The solution enables the possibility of a security indicator which can provide an early warning to help users stay vigilant against telephone impersonation scams, as well as provide a foundation for existing and future defenses to stop unwanted telephone communication based on the caller ID information.
In this dissertation, a study of what causes the users to fall victim to telephone scams is presented, and it demonstrates that impersonation is at the heart of the problem. Most solutions today primarily rely on gathering offending caller IDs, however, they do not work effectively when the caller ID has been spoofed. Due to a lack of authentication in the PSTN caller ID transmission scheme, fraudsters can manipulate the caller ID to impersonate a trusted entity and further a variety of scams. To provide a solution to this fundamental problem, a novel architecture and method to authenticate the transmission of the caller ID is proposed. The solution enables the possibility of a security indicator which can provide an early warning to help users stay vigilant against telephone impersonation scams, as well as provide a foundation for existing and future defenses to stop unwanted telephone communication based on the caller ID information.
ContributorsTu, Huahong (Author) / Doupe, Adam (Thesis advisor) / Ahn, Gail-Joon (Thesis advisor) / Huang, Dijiang (Committee member) / Zhang, Yanchao (Committee member) / Zhao, Ziming (Committee member) / Arizona State University (Publisher)
Created2017
Description
With the rise of the Internet of Things, embedded systems have become an integral part of life and can be found almost anywhere. Their prevalence and increased interconnectivity has made them a prime target for malicious attacks. Today, the vast majority of embedded devices are powered by ARM processors. To protect their processors from attacks, ARM introduced a hardware security extension known as TrustZone. It provides an isolated execution environment within the embedded device in which to deploy various memory integrity and malware detection tools.
Even though Secure World can monitor the Normal World, attackers can attempt to bypass the security measures to retain control of a compromised system. CacheKit is a new type of rootkit that exploits such a vulnerability in the ARM architecture to hide in Normal World cache from memory introspection tools running in Secure World by exploiting cache locking mechanisms. If left unchecked, ARM processors that provide hardware assisted cache locking for performance and time-critical applications in real-time and embedded systems would be completely vulnerable to this undetectable and untraceable attack. Therefore, a new approach is needed to ensure the correct use of such mechanisms and prevent malicious code from being hidden in the cache.
CacheLight is a lightweight approach that leverages the TrustZone and Virtualization extensions of the ARM architecture to allow the system to continue to securely provide these hardware facilities to users while preventing attackers from exploiting them. CacheLight restricts the ability to lock the cache to the Secure World of the processor such that the Normal World can still request certain memory to be locked into the cache by the secure operating system (OS) through a Secure Monitor Call (SMC). This grants the secure OS the power to verify and validate the information that will be locked in the requested cache way thereby ensuring that any data that remains in the cache will not be inconsistent with what exists in main memory for inspection. Malicious attempts to hide data can be prevented and recovered for analysis while legitimate requests can still generate valid entries in the cache.
Even though Secure World can monitor the Normal World, attackers can attempt to bypass the security measures to retain control of a compromised system. CacheKit is a new type of rootkit that exploits such a vulnerability in the ARM architecture to hide in Normal World cache from memory introspection tools running in Secure World by exploiting cache locking mechanisms. If left unchecked, ARM processors that provide hardware assisted cache locking for performance and time-critical applications in real-time and embedded systems would be completely vulnerable to this undetectable and untraceable attack. Therefore, a new approach is needed to ensure the correct use of such mechanisms and prevent malicious code from being hidden in the cache.
CacheLight is a lightweight approach that leverages the TrustZone and Virtualization extensions of the ARM architecture to allow the system to continue to securely provide these hardware facilities to users while preventing attackers from exploiting them. CacheLight restricts the ability to lock the cache to the Secure World of the processor such that the Normal World can still request certain memory to be locked into the cache by the secure operating system (OS) through a Secure Monitor Call (SMC). This grants the secure OS the power to verify and validate the information that will be locked in the requested cache way thereby ensuring that any data that remains in the cache will not be inconsistent with what exists in main memory for inspection. Malicious attempts to hide data can be prevented and recovered for analysis while legitimate requests can still generate valid entries in the cache.
ContributorsGutierrez, Mauricio (Author) / Zhao, Ziming (Thesis advisor) / Doupe, Adam (Committee member) / Shoshitaishvili, Yan (Committee member) / Arizona State University (Publisher)
Created2018
Description
Compartmentalizing access to content, be it websites accessed in a browser or documents and applications accessed outside the browser, is an established method for protecting information integrity [12, 19, 21, 60]. Compartmentalization solutions change the user experience, introduce performance overhead and provide varying degrees of security. Striking a balance between usability and security is not an easy task. If the usability aspects are neglected or sacrificed in favor of more security, the resulting solution would have a hard time being adopted by end-users. The usability is affected by factors including (1) the generality of the solution in supporting various applications, (2) the type of changes required, (3) the performance overhead introduced by the solution, and (4) how much the user experience is preserved. The security is affected by factors including (1) the attack surface of the compartmentalization mechanism, and (2) the security decisions offloaded to the user. This dissertation evaluates existing solutions based on the above factors and presents two novel compartmentalization solutions that are arguably more practical than their existing counterparts.
The first solution, called FlexICon, is an attractive alternative in the design space of compartmentalization solutions on the desktop. FlexICon allows for the creation of a large number of containers with small memory footprint and low disk overhead. This is achieved by using lightweight virtualization based on Linux namespaces. FlexICon uses two mechanisms to reduce user mistakes: 1) a trusted file dialog for selecting files for opening and launching it in the appropriate containers, and 2) a secure URL redirection mechanism that detects the user’s intent and opens the URL in the proper container. FlexICon also provides a language to specify the access constraints that should be enforced by various containers.
The second solution called Auto-FBI, deals with web-based attacks by creating multiple instances of the browser and providing mechanisms for switching between the browser instances. The prototype implementation for Firefox and Chrome uses system call interposition to control the browser’s network access. Auto-FBI can be ported to other platforms easily due to simple design and the ubiquity of system call interposition methods on all major desktop platforms.
The first solution, called FlexICon, is an attractive alternative in the design space of compartmentalization solutions on the desktop. FlexICon allows for the creation of a large number of containers with small memory footprint and low disk overhead. This is achieved by using lightweight virtualization based on Linux namespaces. FlexICon uses two mechanisms to reduce user mistakes: 1) a trusted file dialog for selecting files for opening and launching it in the appropriate containers, and 2) a secure URL redirection mechanism that detects the user’s intent and opens the URL in the proper container. FlexICon also provides a language to specify the access constraints that should be enforced by various containers.
The second solution called Auto-FBI, deals with web-based attacks by creating multiple instances of the browser and providing mechanisms for switching between the browser instances. The prototype implementation for Firefox and Chrome uses system call interposition to control the browser’s network access. Auto-FBI can be ported to other platforms easily due to simple design and the ubiquity of system call interposition methods on all major desktop platforms.
ContributorsZohrevandi, Mohsen (Author) / Bazzi, Rida A (Thesis advisor) / Ahn, Gail-Joon (Committee member) / Doupe, Adam (Committee member) / Zhao, Ming (Committee member) / Arizona State University (Publisher)
Created2018
Description
Network Management is a critical process for an enterprise to configure and monitor the network devices using cost effective methods. It is imperative for it to be robust and free from adversarial or accidental security flaws. With the advent of cloud computing and increasing demands for centralized network control, conventional management protocols like Simple Network Management Protocol (SNMP) appear inadequate and newer techniques like Network Management Datastore Architecture (NMDA) design and Network Configuration (NETCONF) have been invented. However, unlike SNMP which underwent improvements concentrating on security, the new data management and storage techniques have not been scrutinized for the inherent security flaws.
In this thesis, I identify several vulnerabilities in the widely used critical infrastructures which leverage the NMDA design. Software Defined Networking (SDN), a proponent of NMDA, heavily relies on its datastores to program and manage the network. I base my research on the security challenges put forth by the existing datastore’s design as implemented by the SDN controllers. The vulnerabilities identified in this work have a direct impact on the controllers like OpenDayLight, Open Network Operating System and their proprietary implementations (by CISCO, Ericsson, RedHat, Brocade, Juniper, etc). Using the threat detection methodology, I demonstrate how the NMDA-based implementations are vulnerable to attacks which compromise availability, integrity, and confidentiality of the network. I finally propose defense measures to address the security threats in the existing design and discuss the challenges faced while employing these countermeasures.
In this thesis, I identify several vulnerabilities in the widely used critical infrastructures which leverage the NMDA design. Software Defined Networking (SDN), a proponent of NMDA, heavily relies on its datastores to program and manage the network. I base my research on the security challenges put forth by the existing datastore’s design as implemented by the SDN controllers. The vulnerabilities identified in this work have a direct impact on the controllers like OpenDayLight, Open Network Operating System and their proprietary implementations (by CISCO, Ericsson, RedHat, Brocade, Juniper, etc). Using the threat detection methodology, I demonstrate how the NMDA-based implementations are vulnerable to attacks which compromise availability, integrity, and confidentiality of the network. I finally propose defense measures to address the security threats in the existing design and discuss the challenges faced while employing these countermeasures.
ContributorsDixit, Vaibhav Hemant (Author) / Ahn, Gail-Joon (Thesis advisor) / Doupe, Adam (Thesis advisor) / Shoshitaishvili, Yan (Committee member) / Zhao, Ziming (Committee member) / Arizona State University (Publisher)
Created2018
Description
Cyber-systems and networks are the target of different types of cyber-threats and attacks, which are becoming more common, sophisticated, and damaging. Those attacks can vary in the way they are performed. However, there are similar strategies
and tactics often used because they are time-proven to be effective. The motivations behind cyber-attacks play an important role in designating how attackers plan and proceed to achieve their goals. Generally, there are three categories of motivation
are: political, economical, and socio-cultural motivations. These indicate that to defend against possible attacks in an enterprise environment, it is necessary to consider what makes such an enterprise environment a target. That said, we can understand
what threats to consider and how to deploy the right defense system. In other words, detecting an attack depends on the defenders having a clear understanding of why they become targets and what possible attacks they should expect. For instance,
attackers may preform Denial of Service (DoS), or even worse Distributed Denial of Service (DDoS), with intention to cause damage to targeted organizations and prevent legitimate users from accessing their services. However, in some cases, attackers are very skilled and try to hide in a system undetected for a long period of time with the incentive to steal and collect data rather than causing damages.
Nowadays, not only the variety of attack types and the way they are launched are important. However, advancement in technology is another factor to consider. Over the last decades, we have experienced various new technologies. Obviously, in the beginning, new technologies will have their own limitations before they stand out. There are a number of related technical areas whose understanding is still less than satisfactory, and in which long-term research is needed. On the other hand, these new technologies can boost the advancement of deploying security solutions and countermeasures when they are carefully adapted. That said, Software Defined Networking i(SDN), its related security threats and solutions, and its adaption in enterprise environments bring us new chances to enhance our security solutions. To reach the optimal level of deploying SDN technology in enterprise environments, it is important to consider re-evaluating current deployed security solutions in traditional networks before deploying them to SDN-based infrastructures. Although DDoS attacks are a bit sinister, there are other types of cyber-threats that are very harmful, sophisticated, and intelligent. Thus, current security defense solutions to detect DDoS cannot detect them. These kinds of attacks are complex, persistent, and stealthy, also referred to Advanced Persistent Threats (APTs) which often leverage the bot control and remotely access valuable information. APT uses multiple stages to break into a network. APT is a sort of unseen, continuous and long-term penetrative network and attackers can bypass the existing security detection systems. It can modify and steal the sensitive data as well as specifically cause physical damage the target system. In this dissertation, two cyber-attack motivations are considered: sabotage, where the motive is the destruction; and information theft, where attackers aim to acquire invaluable information (customer info, business information, etc). I deal with two types of attacks (DDoS attacks and APT attacks) where DDoS attacks are classified under sabotage motivation category, and the APT attacks are classified under information theft motivation category. To detect and mitigate each of these attacks, I utilize the ease of programmability in SDN and its great platform for implementation, dynamic topology changes, decentralized network management, and ease of deploying security countermeasures.
and tactics often used because they are time-proven to be effective. The motivations behind cyber-attacks play an important role in designating how attackers plan and proceed to achieve their goals. Generally, there are three categories of motivation
are: political, economical, and socio-cultural motivations. These indicate that to defend against possible attacks in an enterprise environment, it is necessary to consider what makes such an enterprise environment a target. That said, we can understand
what threats to consider and how to deploy the right defense system. In other words, detecting an attack depends on the defenders having a clear understanding of why they become targets and what possible attacks they should expect. For instance,
attackers may preform Denial of Service (DoS), or even worse Distributed Denial of Service (DDoS), with intention to cause damage to targeted organizations and prevent legitimate users from accessing their services. However, in some cases, attackers are very skilled and try to hide in a system undetected for a long period of time with the incentive to steal and collect data rather than causing damages.
Nowadays, not only the variety of attack types and the way they are launched are important. However, advancement in technology is another factor to consider. Over the last decades, we have experienced various new technologies. Obviously, in the beginning, new technologies will have their own limitations before they stand out. There are a number of related technical areas whose understanding is still less than satisfactory, and in which long-term research is needed. On the other hand, these new technologies can boost the advancement of deploying security solutions and countermeasures when they are carefully adapted. That said, Software Defined Networking i(SDN), its related security threats and solutions, and its adaption in enterprise environments bring us new chances to enhance our security solutions. To reach the optimal level of deploying SDN technology in enterprise environments, it is important to consider re-evaluating current deployed security solutions in traditional networks before deploying them to SDN-based infrastructures. Although DDoS attacks are a bit sinister, there are other types of cyber-threats that are very harmful, sophisticated, and intelligent. Thus, current security defense solutions to detect DDoS cannot detect them. These kinds of attacks are complex, persistent, and stealthy, also referred to Advanced Persistent Threats (APTs) which often leverage the bot control and remotely access valuable information. APT uses multiple stages to break into a network. APT is a sort of unseen, continuous and long-term penetrative network and attackers can bypass the existing security detection systems. It can modify and steal the sensitive data as well as specifically cause physical damage the target system. In this dissertation, two cyber-attack motivations are considered: sabotage, where the motive is the destruction; and information theft, where attackers aim to acquire invaluable information (customer info, business information, etc). I deal with two types of attacks (DDoS attacks and APT attacks) where DDoS attacks are classified under sabotage motivation category, and the APT attacks are classified under information theft motivation category. To detect and mitigate each of these attacks, I utilize the ease of programmability in SDN and its great platform for implementation, dynamic topology changes, decentralized network management, and ease of deploying security countermeasures.
ContributorsAlshamrani, Adel (Author) / Huang, Dijiang (Thesis advisor) / Doupe, Adam (Committee member) / Ahn, Gail-Joon (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2018
Description
One of the main goals of computer architecture design is to improve performance without much increase in the power consumption. It cannot be achieved by adding increasingly complex intelligent schemes in the hardware, since they will become increasingly less power-efficient. Therefore, parallelism comes up as the solution. In fact, the irrevocable trend of computer design in near future is still to keep increasing the number of cores while reducing the operating frequency. However, it is not easy to scale number of cores. One important challenge is that existing cores consume too much power. Another challenge is that cache-based memory hierarchy poses a serious limitation due to the rapidly increasing demand of area and power for coherence maintenance.
In this dissertation, opportunities to resolve the aforementioned issues were explored in two aspects.
Firstly, the possibility of removing hardware cache altogether, and replacing it with scratchpad memory with software management was explored. Scratchpad memory consumes much less power than caches. However, as data management logic is completely shifted to Software, how to reduce software overhead is challenging. This thesis presents techniques to manage scratchpad memory judiciously by exploiting application semantics and knowledge of data access patterns, thereby enabling optimization of data movement across the memory hierarchy. Experimental results show that the optimization was able to reduce stack data management overhead by 13X, produce better code mapping in more than 80% of the case, and improve performance by 83% in heap management.
Secondly, the possibility of using software branch hinting to replace hardware branch prediction to completely eliminate power consumption on corresponding hardware components was explored. As branch predictor is removed from hardware, software logic is responsible for reducing branch penalty. Techniques to minimize the branch penalty by optimizing branch hint placement were proposed, which can reduce branch penalty by 35.4% over the state-of-the-art.
In this dissertation, opportunities to resolve the aforementioned issues were explored in two aspects.
Firstly, the possibility of removing hardware cache altogether, and replacing it with scratchpad memory with software management was explored. Scratchpad memory consumes much less power than caches. However, as data management logic is completely shifted to Software, how to reduce software overhead is challenging. This thesis presents techniques to manage scratchpad memory judiciously by exploiting application semantics and knowledge of data access patterns, thereby enabling optimization of data movement across the memory hierarchy. Experimental results show that the optimization was able to reduce stack data management overhead by 13X, produce better code mapping in more than 80% of the case, and improve performance by 83% in heap management.
Secondly, the possibility of using software branch hinting to replace hardware branch prediction to completely eliminate power consumption on corresponding hardware components was explored. As branch predictor is removed from hardware, software logic is responsible for reducing branch penalty. Techniques to minimize the branch penalty by optimizing branch hint placement were proposed, which can reduce branch penalty by 35.4% over the state-of-the-art.
ContributorsLu, Jing (Author) / Shrivastava, Aviral (Thesis advisor) / Sarjoughian, Hessam S. (Committee member) / Wu, Carole-Jean (Committee member) / Doupe, Adam (Committee member) / Arizona State University (Publisher)
Created2019