Matching Items (9)
Filtering by
- All Subjects: Computer Engineering
- Genre: Doctoral Dissertation
- Creators: Wu, Carole-Jean
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
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
Advances in semiconductor technology have brought computer-based systems intovirtually all aspects of human life. This unprecedented integration of semiconductor based systems in our lives has significantly increased the domain and the number
of safety-critical applications – application with unacceptable consequences of failure. Software-level error resilience schemes are attractive because they can provide commercial-off-the-shelf microprocessors with adaptive and scalable reliability.
Among all software-level error resilience solutions, in-application instruction replication based approaches have been widely used and are deemed to be the most effective. However, existing instruction-based replication schemes only protect some part of computations i.e. arithmetic and logical instructions and leave the rest as unprotected. To improve the efficacy of instruction-level redundancy-based approaches, we developed several error detection and error correction schemes. nZDC (near Zero silent
Data Corruption) is an instruction duplication scheme which protects the execution of whole application. Rather than detecting errors on register operands of memory and control flow operations, nZDC checks the results of such operations. nZDC en
sures the correct execution of memory write instruction by reloading stored value and checking it against redundantly computed value. nZDC also introduces a novel control flow checking mechanism which replicates compare and branch instructions and
detects both wrong direction branches as well as unwanted jumps. Fault injection experiments show that nZDC can improve the error coverage of the state-of-the-art schemes by more than 10x, without incurring any more performance penalty. Further
more, we introduced two error recovery solutions. InCheck is our backward recovery solution which makes light-weighted error-free checkpoints at the basic block granularity. In the case of error, InCheck reverts the program execution to the beginning of last executed basic block and resumes the execution by the aid of preserved in formation. NEMESIS is our forward recovery scheme which runs three versions of computation and detects errors by checking the results of all memory write and branch
operations. In the case of a mismatch, NEMESIS diagnosis routine decides if the error is recoverable. If yes, NEMESIS recovery routine reverts the effect of error from the program state and resumes program normal execution from the error detection
point.
of safety-critical applications – application with unacceptable consequences of failure. Software-level error resilience schemes are attractive because they can provide commercial-off-the-shelf microprocessors with adaptive and scalable reliability.
Among all software-level error resilience solutions, in-application instruction replication based approaches have been widely used and are deemed to be the most effective. However, existing instruction-based replication schemes only protect some part of computations i.e. arithmetic and logical instructions and leave the rest as unprotected. To improve the efficacy of instruction-level redundancy-based approaches, we developed several error detection and error correction schemes. nZDC (near Zero silent
Data Corruption) is an instruction duplication scheme which protects the execution of whole application. Rather than detecting errors on register operands of memory and control flow operations, nZDC checks the results of such operations. nZDC en
sures the correct execution of memory write instruction by reloading stored value and checking it against redundantly computed value. nZDC also introduces a novel control flow checking mechanism which replicates compare and branch instructions and
detects both wrong direction branches as well as unwanted jumps. Fault injection experiments show that nZDC can improve the error coverage of the state-of-the-art schemes by more than 10x, without incurring any more performance penalty. Further
more, we introduced two error recovery solutions. InCheck is our backward recovery solution which makes light-weighted error-free checkpoints at the basic block granularity. In the case of error, InCheck reverts the program execution to the beginning of last executed basic block and resumes the execution by the aid of preserved in formation. NEMESIS is our forward recovery scheme which runs three versions of computation and detects errors by checking the results of all memory write and branch
operations. In the case of a mismatch, NEMESIS diagnosis routine decides if the error is recoverable. If yes, NEMESIS recovery routine reverts the effect of error from the program state and resumes program normal execution from the error detection
point.
ContributorsDidehban, Moslem (Author) / Shrivastava, Aviral (Thesis advisor) / Wu, Carole-Jean (Committee member) / Clark, Lawrence (Committee member) / Mahlke, Scott (Committee member) / Arizona State University (Publisher)
Created2018
Description
Cyber-physical systems and hard real-time systems have strict timing constraints that specify deadlines until which tasks must finish their execution. Missing a deadline can cause unexpected outcome or endanger human lives in safety-critical applications, such as automotive or aeronautical systems. It is, therefore, of utmost importance to obtain and optimize a safe upper bound of each task’s execution time or the worst-case execution time (WCET), to guarantee the absence of any missed deadline. Unfortunately, conventional microarchitectural components, such as caches and branch predictors, are only optimized for average-case performance and often make WCET analysis complicated and pessimistic. Caches especially have a large impact on the worst-case performance due to expensive off- chip memory accesses involved in cache miss handling. In this regard, software-controlled scratchpad memories (SPMs) have become a promising alternative to caches. An SPM is a raw SRAM, controlled only by executing data movement instructions explicitly at runtime, and such explicit control facilitates static analyses to obtain safe and tight upper bounds of WCETs. SPM management techniques, used in compilers targeting an SPM-based processor, determine how to use a given SPM space by deciding where to insert data movement instructions and what operations to perform at those program locations. This dissertation presents several management techniques for program code and stack data, which aim to optimize the WCETs of a given program. The proposed code management techniques include optimal allocation algorithms and a polynomial-time heuristic for allocating functions to the SPM space, with or without the use of abstraction of SPM regions, and a heuristic for splitting functions into smaller partitions. The proposed stack data management technique, on the other hand, finds an optimal set of program locations to evict and restore stack frames to avoid stack overflows, when the call stack resides in a size-limited SPM. In the evaluation, the WCETs of various benchmarks including real-world automotive applications are statically calculated for SPMs and caches in several different memory configurations.
ContributorsKim, Yooseong (Author) / Shrivastava, Aviral (Thesis advisor) / Broman, David (Committee member) / Fainekos, Georgios (Committee member) / Wu, Carole-Jean (Committee member) / Arizona State University (Publisher)
Created2017
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
Description
Deep neural network-based methods have been proved to achieve outstanding performance on object detection and classification tasks. Deep neural networks follow the ``deeper model with deeper confidence'' belief to gain a higher recognition accuracy. However, reducing these networks' computational costs remains a challenge, which impedes their deployment on embedded devices. For instance, the intersection management of Connected Autonomous Vehicles (CAVs) requires running computationally intensive object recognition algorithms on low-power traffic cameras. This dissertation aims to study the effect of a dynamic hardware and software approach to address this issue. Characteristics of real-world applications can facilitate this dynamic adjustment and reduce the computation. Specifically, this dissertation starts with a dynamic hardware approach that adjusts itself based on the toughness of input and extracts deeper features if needed. Next, an adaptive learning mechanism has been studied that use extracted feature from previous inputs to improve system performance. Finally, a system (ARGOS) was proposed and evaluated that can be run on embedded systems while maintaining the desired accuracy. This system adopts shallow features at inference time, but it can switch to deep features if the system desires a higher accuracy. To improve the performance, ARGOS distills the temporal knowledge from deep features to the shallow system. Moreover, ARGOS reduces the computation furthermore by focusing on regions of interest. The response time and mean average precision are adopted for the performance evaluation to evaluate the proposed ARGOS system.
ContributorsFarhadi, Mohammad (Author) / Yang, Yezhou (Thesis advisor) / Vrudhula, Sarma (Committee member) / Wu, Carole-Jean (Committee member) / Ren, Yi (Committee member) / Arizona State University (Publisher)
Created2022
Description
User satisfaction is pivotal to the success of mobile applications. At the same time, it is imperative to maximize the energy efficiency of the mobile device to ensure optimal usage of the limited energy source available to mobile devices while maintaining the necessary levels of user satisfaction. However, this is complicated due to user interactions, numerous shared resources, and network conditions that produce substantial uncertainty to the mobile device's performance and power characteristics. In this dissertation, a new approach is presented to characterize and control mobile devices that accurately models these uncertainties. The proposed modeling framework is a completely data-driven approach to predicting power and performance. The approach makes no assumptions on the distributions of the underlying sources of uncertainty and is capable of predicting power and performance with over 93% accuracy.
Using this data-driven prediction framework, a closed-loop solution to the DEM problem is derived to maximize the energy efficiency of the mobile device subject to various thermal, reliability and deadline constraints. The design of the controller imposes minimal operational overhead and is able to tune the performance and power prediction models to changing system conditions. The proposed controller is implemented on a real mobile platform, the Google Pixel smartphone, and demonstrates a 19% improvement in energy efficiency over the standard frequency governor implemented on all Android devices.
Using this data-driven prediction framework, a closed-loop solution to the DEM problem is derived to maximize the energy efficiency of the mobile device subject to various thermal, reliability and deadline constraints. The design of the controller imposes minimal operational overhead and is able to tune the performance and power prediction models to changing system conditions. The proposed controller is implemented on a real mobile platform, the Google Pixel smartphone, and demonstrates a 19% improvement in energy efficiency over the standard frequency governor implemented on all Android devices.
ContributorsGaudette, Benjamin David (Author) / Vrudhula, Sarma (Thesis advisor) / Wu, Carole-Jean (Thesis advisor) / Fainekos, Georgios (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2017
Description
With the rapid development of both hardware and software, mobile devices with their advantages in mobility, interactivity, and privacy have enabled various applications, including social networking, mixed reality, entertainment, authentication, and etc.In diverse forms such as smartphones, glasses, and watches, the number of mobile devices is expected to increase by 1 billion per year in the future.
These devices not only generate and exchange small data such as GPS data, but also large data including videos and point clouds.
Such massive visual data presents many challenges for processing on mobile devices.
First, continuously capturing and processing high resolution visual data is energy-intensive, which can drain the battery of a mobile device very quickly.
Second, data offloading for edge or cloud computing is helpful, but users are afraid that their privacy can be exposed to malicious developers.
Third, interactivity and user experience is degraded if mobile devices cannot process large scale visual data in real-time such as off-device high precision point clouds. To deal with these challenges, this work presents three solutions towards fine-grained control of visual data in mobile systems, revolving around two core ideas, enabling resolution-based tradeoffs and adopting split-process to protect visual data.In particular, this work introduces: (1) Banner media framework to remove resolution reconfiguration latency in the operating system for enabling seamless dynamic resolution-based tradeoffs;
(2) LesnCap split-process application development framework to protect user's visual privacy against malicious data collection in cloud-based Augmented Reality (AR) applications by isolating the visual processing in a distinct process;
(3) A novel voxel grid schema to enable adaptive sampling at the edge device that can sample point clouds flexibly for interactive 3D vision use cases across mobile devices and mobile networks. The evaluation in several mobile environments demonstrates that, by controlling visual data at a fine granularity, energy efficiency can be improved by 49% switching between resolutions, visual privacy can be protected through split-process with negligible overhead, and point clouds can be delivered at a high throughput meeting various requirements.Thus, this work can enable more continuous mobile vision applications for the future of a new reality.
ContributorsHu, Jinhan (Author) / LiKamWa, Robert (Thesis advisor) / Wu, Carole-Jean (Committee member) / Doupe, Adam (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2022
Description
Graphic Processing Units (GPUs) have become a key enabler of the big-data revolution, functioning as defacto co-processors to accelerate large-scale computation. As the GPU programming stack and tool support have matured, the technology has alsobecome accessible to programmers. However, optimizing programs to run efficiently on GPUs requires developers to have both detailed understanding of the application logic and significant knowledge of parallel programming and GPU architectures.
This dissertation proposes GEVO, a tool for automatically tuning the performance of GPU kernels in the LLVM representation to meet desired criteria. GEVO uses population-based search to find edits to programs compiled to LLVM-IR which improves performance on desired criteria and retains required functionality. The evaluation of GEVO on the Rodinia benchmark suite demonstrates many runtime optimization techniques. One of the key insights is that semantic relaxation enables GEVO to
discover these optimizations that are usually prohibited by the compiler. GEVO also explores many other optimizations, including architecture- and application-specific. A follow-up evaluation of three bioinformatics applications at their different stages of development suggests that GEVO can optimize programs as well as human experts, sometimes even into a code base that is beyond a programmer’s reach. Furthermore, to unshackle the constraint of GEVO in optimizing neural network (NN) models,
GEVO-ML is proposed by extending the representation capability of GEVO, where NN models and the training/prediction process are uniformly represented in a single intermediate language. An evaluation of GEVO-ML shows that GEVO-ML can
optimize network models similar to how human developers improve model design, for example, by changing learning rates or pruning non-essential parameters. These results showcase the potential of automated program optimization tools to both reduce
the optimization burden for researchers and provide new insights for GPU experts.
ContributorsLiou, Jhe-Yu (Author) / Forrest, Stephanie (Thesis advisor) / Wu, Carole-Jean (Thesis advisor) / Lee, Yann-Hang (Committee member) / Weimer, Westley (Committee member) / Arizona State University (Publisher)
Created2023