ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Displaying 1 - 10 of 20
Filtering by
- All Subjects: Computer Engineering
Description
Stream processing has emerged as an important model of computation especially in the context of multimedia and communication sub-systems of embedded System-on-Chip (SoC) architectures. The dataflow nature of streaming applications allows them to be most naturally expressed as a set of kernels iteratively operating on continuous streams of data. The kernels are computationally intensive and are mainly characterized by real-time constraints that demand high throughput and data bandwidth with limited global data reuse. Conventional architectures fail to meet these demands due to their poorly matched execution models and the overheads associated with instruction and data movements.
This work presents StreamWorks, a multi-core embedded architecture for energy-efficient stream computing. The basic processing element in the StreamWorks architecture is the StreamEngine (SE) which is responsible for iteratively executing a stream kernel. SE introduces an instruction locking mechanism that exploits the iterative nature of the kernels and enables fine-grain instruction reuse. Each instruction in a SE is locked to a Reservation Station (RS) and revitalizes itself after execution; thus never retiring from the RS. The entire kernel is hosted in RS Banks (RSBs) close to functional units for energy-efficient instruction delivery. The dataflow semantics of stream kernels are captured by a context-aware dataflow execution mode that efficiently exploits the Instruction Level Parallelism (ILP) and Data-level parallelism (DLP) within stream kernels.
Multiple SEs are grouped together to form a StreamCluster (SC) that communicate via a local interconnect. A novel software FIFO virtualization technique with split-join functionality is proposed for efficient and scalable stream communication across SEs. The proposed communication mechanism exploits the Task-level parallelism (TLP) of the stream application. The performance and scalability of the communication mechanism is evaluated against the existing data movement schemes for scratchpad based multi-core architectures. Further, overlay schemes and architectural support are proposed that allow hosting any number of kernels on the StreamWorks architecture. The proposed oevrlay schemes for code management supports kernel(context) switching for the most common use cases and can be adapted for any multi-core architecture that use software managed local memories.
The performance and energy-efficiency of the StreamWorks architecture is evaluated for stream kernel and application benchmarks by implementing the architecture in 45nm TSMC and comparison with a low power RISC core and a contemporary accelerator.
This work presents StreamWorks, a multi-core embedded architecture for energy-efficient stream computing. The basic processing element in the StreamWorks architecture is the StreamEngine (SE) which is responsible for iteratively executing a stream kernel. SE introduces an instruction locking mechanism that exploits the iterative nature of the kernels and enables fine-grain instruction reuse. Each instruction in a SE is locked to a Reservation Station (RS) and revitalizes itself after execution; thus never retiring from the RS. The entire kernel is hosted in RS Banks (RSBs) close to functional units for energy-efficient instruction delivery. The dataflow semantics of stream kernels are captured by a context-aware dataflow execution mode that efficiently exploits the Instruction Level Parallelism (ILP) and Data-level parallelism (DLP) within stream kernels.
Multiple SEs are grouped together to form a StreamCluster (SC) that communicate via a local interconnect. A novel software FIFO virtualization technique with split-join functionality is proposed for efficient and scalable stream communication across SEs. The proposed communication mechanism exploits the Task-level parallelism (TLP) of the stream application. The performance and scalability of the communication mechanism is evaluated against the existing data movement schemes for scratchpad based multi-core architectures. Further, overlay schemes and architectural support are proposed that allow hosting any number of kernels on the StreamWorks architecture. The proposed oevrlay schemes for code management supports kernel(context) switching for the most common use cases and can be adapted for any multi-core architecture that use software managed local memories.
The performance and energy-efficiency of the StreamWorks architecture is evaluated for stream kernel and application benchmarks by implementing the architecture in 45nm TSMC and comparison with a low power RISC core and a contemporary accelerator.
ContributorsPanda, Amrit (Author) / Chatha, Karam S. (Thesis advisor) / Wu, Carole-Jean (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2014
Description
A benchmark suite that is representative of the programs a processor typically executes is necessary to understand a processor's performance or energy consumption characteristics. The first contribution of this work addresses this need for mobile platforms with MobileBench, a selection of representative smartphone applications. In smartphones, like any other portable computing systems, energy is a limited resource. Based on the energy characterization of a commercial widely-used smartphone, application cores are found to consume a significant part of the total energy consumption of the device. With this insight, the subsequent part of this thesis focuses on the portion of energy that is spent to move data from the memory system to the application core's internal registers. The primary motivation for this work comes from the relatively higher power consumption associated with a data movement instruction compared to that of an arithmetic instruction. The data movement energy cost is worsened esp. in a System on Chip (SoC) because the amount of data received and exchanged in a SoC based smartphone increases at an explosive rate. A detailed investigation is performed to quantify the impact of data movement
on the overall energy consumption of a smartphone device. To aid this study, microbenchmarks that generate desired data movement patterns between different levels of the memory hierarchy are designed. Energy costs of data movement are then computed by measuring the instantaneous power consumption of the device when the micro benchmarks are executed. This work makes an extensive use of hardware performance counters to validate the memory access behavior of microbenchmarks and to characterize the energy consumed in moving data. Finally, the calculated energy costs of data movement are used to characterize the portion of energy that MobileBench applications spend in moving data. The results of this study show that a significant 35% of the total device energy is spent in data movement alone. Energy is an increasingly important criteria in the context of designing architectures for future smartphones and this thesis offers insights into data movement energy consumption.
on the overall energy consumption of a smartphone device. To aid this study, microbenchmarks that generate desired data movement patterns between different levels of the memory hierarchy are designed. Energy costs of data movement are then computed by measuring the instantaneous power consumption of the device when the micro benchmarks are executed. This work makes an extensive use of hardware performance counters to validate the memory access behavior of microbenchmarks and to characterize the energy consumed in moving data. Finally, the calculated energy costs of data movement are used to characterize the portion of energy that MobileBench applications spend in moving data. The results of this study show that a significant 35% of the total device energy is spent in data movement alone. Energy is an increasingly important criteria in the context of designing architectures for future smartphones and this thesis offers insights into data movement energy consumption.
ContributorsPandiyan, Dhinakaran (Author) / Wu, Carole-Jean (Thesis advisor) / Shrivastava, Aviral (Committee member) / Lee, Yann-Hang (Committee member) / Arizona State University (Publisher)
Created2014
Description
Android has been the dominant platform in which most of the mobile development is being done. By the end of the second quarter of 2014, 84.7 percent of the entire world mobile phones market share had been captured by Android. The Android library internally uses the modified Linux kernel as the part of its stack. The I/O scheduler, is a part of the Linux kernel, responsible for scheduling data requests to the internal and the external memory devices that are attached to the mobile systems.
The usage of solid state drives in the Android tablet has also seen a rise owing to its speed of operation and mechanical stability. The I/O schedulers that exist in the present Linux kernel are not better suited for handling solid state drives in particular to exploit the inherent parallelism offered by the solid state drives. The Android provides information to the Linux kernel about the processes running in the foreground and background. Based on this information the kernel decides the process scheduling and the memory management, but no such information exists for the I/O scheduling. Research shows that the resource management could be done better if the operating system is aware of the characteristics of the requester. Thus, there is a need for a better I/O scheduler that could schedule I/O operations based on the application and also exploit the parallelism in the solid state drives. The scheduler proposed through this research does that. It contains two algorithms working in unison one focusing on the solid state drives and the other on the application awareness.
The Android application context aware scheduler has the features of increasing the responsiveness of the time sensitive applications and also increases the throughput by parallel scheduling of request in the solid state drive. The suggested scheduler is tested using standard benchmarks and real-time scenarios, the results convey that our scheduler outperforms the existing default completely fair queuing scheduler of the Android.
The usage of solid state drives in the Android tablet has also seen a rise owing to its speed of operation and mechanical stability. The I/O schedulers that exist in the present Linux kernel are not better suited for handling solid state drives in particular to exploit the inherent parallelism offered by the solid state drives. The Android provides information to the Linux kernel about the processes running in the foreground and background. Based on this information the kernel decides the process scheduling and the memory management, but no such information exists for the I/O scheduling. Research shows that the resource management could be done better if the operating system is aware of the characteristics of the requester. Thus, there is a need for a better I/O scheduler that could schedule I/O operations based on the application and also exploit the parallelism in the solid state drives. The scheduler proposed through this research does that. It contains two algorithms working in unison one focusing on the solid state drives and the other on the application awareness.
The Android application context aware scheduler has the features of increasing the responsiveness of the time sensitive applications and also increases the throughput by parallel scheduling of request in the solid state drive. The suggested scheduler is tested using standard benchmarks and real-time scenarios, the results convey that our scheduler outperforms the existing default completely fair queuing scheduler of the Android.
ContributorsSivasankaran, Jeevan Prasath (Author) / Lee, Yann Hang (Thesis advisor) / Wu, Carole-Jean (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2014
Description
Ever reducing time to market, along with short product lifetimes, has created a need to shorten the microprocessor design time. Verification of the design and its analysis are two major components of this design cycle. Design validation techniques can be broadly classified into two major categories: simulation based approaches and formal techniques. Simulation based microprocessor validation involves running millions of cycles using random or pseudo random tests and allows verification of the register transfer level (RTL) model against an architectural model, i.e., that the processor executes instructions as required. The validation effort involves model checking to a high level description or simulation of the design against the RTL implementation. Formal techniques exhaustively analyze parts of the design but, do not verify RTL against the architecture specification. The focus of this work is to implement a fully automated validation environment for a MIPS based radiation hardened microprocessor using simulation based approaches. The basic framework uses the classical validation approach in which the design to be validated is described in a Hardware Definition Language (HDL) such as VHDL or Verilog. To implement a simulation based approach a number of random or pseudo random tests are generated. The output of the HDL based design is compared against the one obtained from a "perfect" model implementing similar functionality, a mismatch in the results would thus indicate a bug in the HDL based design. Effort is made to design the environment in such a manner that it can support validation during different stages of the design cycle. The validation environment includes appropriate changes so as to support architecture changes which are introduced because of radiation hardening. The manner in which the validation environment is build is highly dependent on the specifications of the perfect model used for comparisons. This work implements the validation environment for two MIPS simulators as the reference model. Two bugs have been discovered in the RTL model, using simulation based approaches through the validation environment.
ContributorsSharma, Abhishek (Author) / Clark, Lawrence (Thesis advisor) / Holbert, Keith E. (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2011
Description
Cyber-Physical Systems (CPS) are being used in many safety-critical applications. Due to the important role in virtually every aspect of human life, it is crucial to make sure that a CPS works properly before its deployment. However, formal verification of CPS is a computationally hard problem. Therefore, lightweight verification methods such as testing and monitoring of the CPS are considered in the industry. The formal representation of the CPS requirements is a challenging task. In addition, checking the system outputs with respect to requirements is a computationally complex problem. In this dissertation, these problems for the verification of CPS are addressed. The first method provides a formal requirement analysis framework which can find logical issues in the requirements and help engineers to correct the requirements. Also, a method is provided to detect tests which vacuously satisfy the requirement because of the requirement structure. This method is used to improve the test generation framework for CPS. Finally, two runtime verification algorithms are developed for off-line/on-line monitoring with respect to real-time requirements. These monitoring algorithms are computationally efficient, and they can be used in practical applications for monitoring CPS with low runtime overhead.
ContributorsDokhanchi, Adel (Author) / Fainekos, Georgios (Thesis advisor) / Lee, Yann-Hang (Committee member) / Sarjoughian, Hessam S. (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2017
Description
General-purpose processors propel the advances and innovations that are the subject of humanity’s many endeavors. Catering to this demand, chip-multiprocessors (CMPs) and general-purpose graphics processing units (GPGPUs) have seen many high-performance innovations in their architectures. With these advances, the memory subsystem has become the performance- and energy-limiting aspect of CMPs and GPGPUs alike. This dissertation identifies and mitigates the key performance and energy-efficiency bottlenecks in the memory subsystem of general-purpose processors via novel, practical, microarchitecture and system-architecture solutions.
Addressing the important Last Level Cache (LLC) management problem in CMPs, I observe that LLC management decisions made in isolation, as in prior proposals, often lead to sub-optimal system performance. I demonstrate that in order to maximize system performance, it is essential to manage the LLCs while being cognizant of its interaction with the system main memory. I propose ReMAP, which reduces the net memory access cost by evicting cache lines that either have no reuse, or have low memory access cost. ReMAP improves the performance of the CMP system by as much as 13%, and by an average of 6.5%.
Rather than the LLC, the L1 data cache has a pronounced impact on GPGPU performance by acting as the bandwidth filter for the rest of the memory subsystem. Prior work has shown that the severely constrained data cache capacity in GPGPUs leads to sub-optimal performance. In this thesis, I propose two novel techniques that address the GPGPU data cache capacity problem. I propose ID-Cache that performs effective cache bypassing and cache line size selection to improve cache capacity utilization. Next, I propose LATTE-CC that considers the GPU’s latency tolerance feature and adaptively compresses the data stored in the data cache, thereby increasing its effective capacity. ID-Cache and LATTE-CC are shown to achieve 71% and 19.2% speedup, respectively, over a wide variety of GPGPU applications.
Complementing the aforementioned microarchitecture techniques, I identify the need for system architecture innovations to sustain performance scalability of GPG- PUs in the face of slowing Moore’s Law. I propose a novel GPU architecture called the Multi-Chip-Module GPU (MCM-GPU) that integrates multiple GPU modules to form a single logical GPU. With intelligent memory subsystem optimizations tailored for MCM-GPUs, it can achieve within 7% of the performance of a similar but hypothetical monolithic die GPU. Taking a step further, I present an in-depth study of the energy-efficiency characteristics of future MCM-GPUs. I demonstrate that the inherent non-uniform memory access side-effects form the key energy-efficiency bottleneck in the future.
In summary, this thesis offers key insights into the performance and energy-efficiency bottlenecks in CMPs and GPGPUs, which can guide future architects towards developing high-performance and energy-efficient general-purpose processors.
Addressing the important Last Level Cache (LLC) management problem in CMPs, I observe that LLC management decisions made in isolation, as in prior proposals, often lead to sub-optimal system performance. I demonstrate that in order to maximize system performance, it is essential to manage the LLCs while being cognizant of its interaction with the system main memory. I propose ReMAP, which reduces the net memory access cost by evicting cache lines that either have no reuse, or have low memory access cost. ReMAP improves the performance of the CMP system by as much as 13%, and by an average of 6.5%.
Rather than the LLC, the L1 data cache has a pronounced impact on GPGPU performance by acting as the bandwidth filter for the rest of the memory subsystem. Prior work has shown that the severely constrained data cache capacity in GPGPUs leads to sub-optimal performance. In this thesis, I propose two novel techniques that address the GPGPU data cache capacity problem. I propose ID-Cache that performs effective cache bypassing and cache line size selection to improve cache capacity utilization. Next, I propose LATTE-CC that considers the GPU’s latency tolerance feature and adaptively compresses the data stored in the data cache, thereby increasing its effective capacity. ID-Cache and LATTE-CC are shown to achieve 71% and 19.2% speedup, respectively, over a wide variety of GPGPU applications.
Complementing the aforementioned microarchitecture techniques, I identify the need for system architecture innovations to sustain performance scalability of GPG- PUs in the face of slowing Moore’s Law. I propose a novel GPU architecture called the Multi-Chip-Module GPU (MCM-GPU) that integrates multiple GPU modules to form a single logical GPU. With intelligent memory subsystem optimizations tailored for MCM-GPUs, it can achieve within 7% of the performance of a similar but hypothetical monolithic die GPU. Taking a step further, I present an in-depth study of the energy-efficiency characteristics of future MCM-GPUs. I demonstrate that the inherent non-uniform memory access side-effects form the key energy-efficiency bottleneck in the future.
In summary, this thesis offers key insights into the performance and energy-efficiency bottlenecks in CMPs and GPGPUs, which can guide future architects towards developing high-performance and energy-efficient general-purpose processors.
ContributorsArunkumar, Akhil (Author) / Wu, Carole-Jean (Thesis advisor) / Shrivastava, Aviral (Committee member) / Lee, Yann-Hang (Committee member) / Bolotin, Evgeny (Committee member) / Arizona State University (Publisher)
Created2018
Description
The Internet of Things ecosystem has spawned a wide variety of embedded real-time systems that complicate the identification and resolution of bugs in software. The methods of concurrent checkpoint provide a means to monitor the application state with the ability to replay the execution on like hardware and software, without holding off and delaying the execution of application threads. In this thesis, it is accomplished by monitoring physical memory of the application using a soft-dirty page tracker and measuring the various types of overhead when employing concurrent checkpointing. The solution presented is an advancement of the Checkpoint and Replay In Userspace (CRIU) thereby eliminating the large stalls and parasitic operation for each successive checkpoint. Impact and performance is measured using the Parsec 3.0 Benchmark suite and 4.11.12-rt16+ Linux kernel on a MinnowBoard Turbot Quad-Core board.
ContributorsPrinke, Michael L (Author) / Lee, Yann-Hang (Thesis advisor) / Shrivastava, Aviral (Committee member) / Zhao, Ming (Committee member) / Arizona State University (Publisher)
Created2018
Description
Automated driving systems are in an intensive research and development stage, and the companies developing these systems are targeting to deploy them on public roads in a very near future. Guaranteeing safe operation of these systems is crucial as they are planned to carry passengers and share the road with other vehicles and pedestrians. Yet, there is no agreed-upon approach on how and in what detail those systems should be tested. Different organizations have different testing approaches, and one common approach is to combine simulation-based testing with real-world driving.
One of the expectations from fully-automated vehicles is never to cause an accident. However, an automated vehicle may not be able to avoid all collisions, e.g., the collisions caused by other road occupants. Hence, it is important for the system designers to understand the boundary case scenarios where an autonomous vehicle can no longer avoid a collision. Besides safety, there are other expectations from automated vehicles such as comfortable driving and minimal fuel consumption. All safety and functional expectations from an automated driving system should be captured with a set of system requirements. It is challenging to create requirements that are unambiguous and usable for the design, testing, and evaluation of automated driving systems. Another challenge is to define useful metrics for assessing the testing quality because in general, it is impossible to test every possible scenario.
The goal of this dissertation is to formalize the theory for testing automated vehicles. Various methods for automatic test generation for automated-driving systems in simulation environments are presented and compared. The contributions presented in this dissertation include (i) new metrics that can be used to discover the boundary cases between safe and unsafe driving conditions, (ii) a new approach that combines combinatorial testing and optimization-guided test generation methods, (iii) approaches that utilize global optimization methods and random exploration to generate critical vehicle and pedestrian trajectories for testing purposes, (iv) a publicly-available simulation-based automated vehicle testing framework that enables application of the existing testing approaches in the literature, including the new approaches presented in this dissertation.
One of the expectations from fully-automated vehicles is never to cause an accident. However, an automated vehicle may not be able to avoid all collisions, e.g., the collisions caused by other road occupants. Hence, it is important for the system designers to understand the boundary case scenarios where an autonomous vehicle can no longer avoid a collision. Besides safety, there are other expectations from automated vehicles such as comfortable driving and minimal fuel consumption. All safety and functional expectations from an automated driving system should be captured with a set of system requirements. It is challenging to create requirements that are unambiguous and usable for the design, testing, and evaluation of automated driving systems. Another challenge is to define useful metrics for assessing the testing quality because in general, it is impossible to test every possible scenario.
The goal of this dissertation is to formalize the theory for testing automated vehicles. Various methods for automatic test generation for automated-driving systems in simulation environments are presented and compared. The contributions presented in this dissertation include (i) new metrics that can be used to discover the boundary cases between safe and unsafe driving conditions, (ii) a new approach that combines combinatorial testing and optimization-guided test generation methods, (iii) approaches that utilize global optimization methods and random exploration to generate critical vehicle and pedestrian trajectories for testing purposes, (iv) a publicly-available simulation-based automated vehicle testing framework that enables application of the existing testing approaches in the literature, including the new approaches presented in this dissertation.
ContributorsTuncali, Cumhur Erkan (Author) / Fainekos, Georgios (Thesis advisor) / Ben Amor, Heni (Committee member) / Kapinski, James (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2019
Description
The availability of a wide range of general purpose as well as accelerator cores on
modern smartphones means that a significant number of applications can be executed
on a smartphone simultaneously, resulting in an ever increasing demand on the memory
subsystem. While the increased computation capability is intended for improving
user experience, memory requests from each concurrent application exhibit unique
memory access patterns as well as specific timing constraints. If not considered, this
could lead to significant memory contention and result in lowered user experience.
This work first analyzes the impact of memory degradation caused by the interference
at the memory system for a broad range of commonly-used smartphone applications.
The real system characterization results show that smartphone applications,
such as web browsing and media playback, suffer significant performance degradation.
This is caused by shared resource contention at the application processor’s last-level
cache, the communication fabric, and the main memory.
Based on the detailed characterization results, rest of this thesis focuses on the
design of an effective memory interference mitigation technique. Since web browsing,
being one of the most commonly-used smartphone applications and represents many
html-based smartphone applications, my thesis focuses on meeting the performance
requirement of a web browser on a smartphone in the presence of background processes
and co-scheduled applications. My thesis proposes a light-weight user space frequency
governor to mitigate the degradation caused by interfering applications, by predicting
the performance and power consumption of web browsing. The governor selects an
optimal energy-efficient frequency setting periodically by using the statically-trained
performance and power models with dynamically-varying architecture and system
conditions, such as the memory access intensity of background processes and/or coscheduled applications, and temperature of cores. The governor has been extensively evaluated on a Nexus 5 smartphone over a diverse range of mobile workloads. By
operating at the most energy-efficient frequency setting in the presence of interference,
energy efficiency is improved by as much as 35% and with an average of 18% compared
to the existing interactive governor, while maintaining the satisfactory performance
of web page loading under 3 seconds.
modern smartphones means that a significant number of applications can be executed
on a smartphone simultaneously, resulting in an ever increasing demand on the memory
subsystem. While the increased computation capability is intended for improving
user experience, memory requests from each concurrent application exhibit unique
memory access patterns as well as specific timing constraints. If not considered, this
could lead to significant memory contention and result in lowered user experience.
This work first analyzes the impact of memory degradation caused by the interference
at the memory system for a broad range of commonly-used smartphone applications.
The real system characterization results show that smartphone applications,
such as web browsing and media playback, suffer significant performance degradation.
This is caused by shared resource contention at the application processor’s last-level
cache, the communication fabric, and the main memory.
Based on the detailed characterization results, rest of this thesis focuses on the
design of an effective memory interference mitigation technique. Since web browsing,
being one of the most commonly-used smartphone applications and represents many
html-based smartphone applications, my thesis focuses on meeting the performance
requirement of a web browser on a smartphone in the presence of background processes
and co-scheduled applications. My thesis proposes a light-weight user space frequency
governor to mitigate the degradation caused by interfering applications, by predicting
the performance and power consumption of web browsing. The governor selects an
optimal energy-efficient frequency setting periodically by using the statically-trained
performance and power models with dynamically-varying architecture and system
conditions, such as the memory access intensity of background processes and/or coscheduled applications, and temperature of cores. The governor has been extensively evaluated on a Nexus 5 smartphone over a diverse range of mobile workloads. By
operating at the most energy-efficient frequency setting in the presence of interference,
energy efficiency is improved by as much as 35% and with an average of 18% compared
to the existing interactive governor, while maintaining the satisfactory performance
of web page loading under 3 seconds.
ContributorsShingari, Davesh (Author) / Wu, Carole-Jean (Thesis advisor) / Vrudhula, Sarma (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2016
Description
With the massive multithreading execution feature, graphics processing units (GPUs) have been widely deployed to accelerate general-purpose parallel workloads (GPGPUs). However, using GPUs to accelerate computation does not always gain good performance improvement. This is mainly due to three inefficiencies in modern GPU and system architectures.
First, not all parallel threads have a uniform amount of workload to fully utilize GPU’s computation ability, leading to a sub-optimal performance problem, called warp criticality. To mitigate the degree of warp criticality, I propose a Criticality-Aware Warp Acceleration mechanism, called CAWA. CAWA predicts and accelerates the critical warp execution by allocating larger execution time slices and additional cache resources to the critical warp. The evaluation result shows that with CAWA, GPUs can achieve an average of 1.23x speedup.
Second, the shared cache storage in GPUs is often insufficient to accommodate demands of the large number of concurrent threads. As a result, cache thrashing is commonly experienced in GPU’s cache memories, particularly in the L1 data caches. To alleviate the cache contention and thrashing problem, I develop an instruction aware Control Loop Based Adaptive Bypassing algorithm, called Ctrl-C. Ctrl-C learns the cache reuse behavior and bypasses a portion of memory requests with the help of feedback control loops. The evaluation result shows that Ctrl-C can effectively improve cache utilization in GPUs and achieve an average of 1.42x speedup for cache sensitive GPGPU workloads.
Finally, GPU workloads and the co-located processes running on the host chip multiprocessor (CMP) in a heterogeneous system setup can contend for memory resources in multiple levels, resulting in significant performance degradation. To maximize the system throughput and balance the performance degradation of all co-located applications, I design a scalable performance degradation predictor specifically for heterogeneous systems, called HeteroPDP. HeteroPDP predicts the application execution time and schedules OpenCL workloads to run on different devices based on the optimization goal. The evaluation result shows HeteroPDP can improve the system fairness from 24% to 65% when an OpenCL application is co-located with other processes, and gain an additional 50% speedup compared with always offloading the OpenCL workload to GPUs.
In summary, this dissertation aims to provide insights for the future microarchitecture and system architecture designs by identifying, analyzing, and addressing three critical performance problems in modern GPUs.
First, not all parallel threads have a uniform amount of workload to fully utilize GPU’s computation ability, leading to a sub-optimal performance problem, called warp criticality. To mitigate the degree of warp criticality, I propose a Criticality-Aware Warp Acceleration mechanism, called CAWA. CAWA predicts and accelerates the critical warp execution by allocating larger execution time slices and additional cache resources to the critical warp. The evaluation result shows that with CAWA, GPUs can achieve an average of 1.23x speedup.
Second, the shared cache storage in GPUs is often insufficient to accommodate demands of the large number of concurrent threads. As a result, cache thrashing is commonly experienced in GPU’s cache memories, particularly in the L1 data caches. To alleviate the cache contention and thrashing problem, I develop an instruction aware Control Loop Based Adaptive Bypassing algorithm, called Ctrl-C. Ctrl-C learns the cache reuse behavior and bypasses a portion of memory requests with the help of feedback control loops. The evaluation result shows that Ctrl-C can effectively improve cache utilization in GPUs and achieve an average of 1.42x speedup for cache sensitive GPGPU workloads.
Finally, GPU workloads and the co-located processes running on the host chip multiprocessor (CMP) in a heterogeneous system setup can contend for memory resources in multiple levels, resulting in significant performance degradation. To maximize the system throughput and balance the performance degradation of all co-located applications, I design a scalable performance degradation predictor specifically for heterogeneous systems, called HeteroPDP. HeteroPDP predicts the application execution time and schedules OpenCL workloads to run on different devices based on the optimization goal. The evaluation result shows HeteroPDP can improve the system fairness from 24% to 65% when an OpenCL application is co-located with other processes, and gain an additional 50% speedup compared with always offloading the OpenCL workload to GPUs.
In summary, this dissertation aims to provide insights for the future microarchitecture and system architecture designs by identifying, analyzing, and addressing three critical performance problems in modern GPUs.
ContributorsLee, Shin-Ying (Author) / Wu, Carole-Jean (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Ren, Fengbo (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2017