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 76
Description
In a laboratory setting, the soil volume change behavior is best represented by using various testing standards on undisturbed or remolded samples. Whenever possible, it is most precise to use undisturbed samples to assess the volume change behavior but in the absence of undisturbed specimens, remodeled samples can be used. If that is the case, the soil is compacted to in-situ density and water content (or matric suction), which should best represent the expansive profile in question. It is standard practice to subject the specimen to a wetting process at a particular net normal stress. Even though currently accepted laboratory testing standard procedures provide insight on how the profile conditions changes with time, these procedures do not assess the long term effects on the soil due to climatic changes. In this experimental study, an assessment and quantification of the effect of multiple wetting/drying cycles on the volume change behavior of two different naturally occurring soils was performed. The changes in wetting and drying cycles were extreme when comparing the swings in matric suction. During the drying cycle, the expansive soil was subjected to extreme conditions, which decreased the moisture content less than the shrinkage limit. Nevertheless, both soils were remolded at five different compacted conditions and loaded to five different net normal stresses. Each sample was subjected to six wetting and drying cycles. During the assessment, it was evident from the results that the swell/collapse strain is highly non-linear at low stress levels. The strain-net normal stress relationship cannot be defined by one single function without transforming the data. Therefore, the dataset needs to be fitted to a bi-modal logarithmic function or to a logarithmic transformation of net normal stress in order to use a third order polynomial fit. It was also determined that the moisture content changes with time are best fit by non-linear functions. For the drying cycle, the radial strain was determined to have a constant rate of change with respect to the axial strain. However, for the wetting cycle, there was not enough radial strain data to develop correlations and therefore, an assumption was made based on 55 different test measurements/observations, for the wetting cycles. In general, it was observed that after each subsequent cycle, higher swelling was exhibited for lower net normal stress values; while higher collapse potential was observed for higher net normal stress values, once the net normal stress was less than/greater than a threshold net normal stress value. Furthermore, the swelling pressure underwent a reduction in all cases. Particularly, the Anthem soil exhibited a reduction in swelling pressure by at least 20 percent after the first wetting/drying cycle; while Colorado soil exhibited a reduction of 50 percent. After about the fourth cycle, the swelling pressure seemed to stabilized to an equilibrium value at which a reduction of 46 percent was observed for the Anthem soil and 68 percent reduction for the Colorado soil. The impact of the initial compacted conditions on heave characteristics was studied. Results indicated that materials compacted at higher densities exhibited greater swell potential. When comparing specimens compacted at the same density but at different moisture content (matric suction), it was observed that specimens compacted at higher suction would exhibit higher swelling potential, when subjected to the same net normal stress. The least amount of swelling strain was observed on specimens compacted at the lowest dry density and the lowest matric suction (higher water content). The results from the laboratory testing were used to develop ultimate heave profiles for both soils. This analysis showed that even though the swell pressure for each soil decreased with cycles, the amount of heave would increase or decrease depending upon the initial compaction condition. When the specimen was compacted at 110% of optimum moisture content and 90% of maximum dry density, it resulted in an ultimate heave reduction of 92 percent for Anthem and 685 percent for Colorado soil. On the other hand, when the soils were compacted at 90% optimum moisture content and 100% of the maximum dry density, Anthem specimens heave 78% more and Colorado specimens heave was reduced by 69%. Based on the results obtained, it is evident that the current methods to estimate heave and swelling pressure do not consider the effect of wetting/drying cycles; and seem to fail capturing the free swell potential of the soil. Recommendations for improvement current methods of practice are provided.
ContributorsRosenbalm, Daniel Curtis (Author) / Zapata, Claudia E (Thesis advisor) / Houston, Sandra L. (Committee member) / Kavazanjian, Edward (Committee member) / Witczak, Mathew W (Committee member) / Arizona State University (Publisher)
Created2013
Description
In recent years we have witnessed a shift towards multi-processor system-on-chips (MPSoCs) to address the demands of embedded devices (such as cell phones, GPS devices, luxury car features, etc.). Highly optimized MPSoCs are well-suited to tackle the complex application demands desired by the end user customer. These MPSoCs incorporate a constellation of heterogeneous processing elements (PEs) (general purpose PEs and application-specific integrated circuits (ASICS)). A typical MPSoC will be composed of a application processor, such as an ARM Coretex-A9 with cache coherent memory hierarchy, and several application sub-systems. Each of these sub-systems are composed of highly optimized instruction processors, graphics/DSP processors, and custom hardware accelerators. Typically, these sub-systems utilize scratchpad memories (SPM) rather than support cache coherency. The overall architecture is an integration of the various sub-systems through a high bandwidth system-level interconnect (such as a Network-on-Chip (NoC)). The shift to MPSoCs has been fueled by three major factors: demand for high performance, the use of component libraries, and short design turn around time. As customers continue to desire more and more complex applications on their embedded devices the performance demand for these devices continues to increase. Designers have turned to using MPSoCs to address this demand. By using pre-made IP libraries designers can quickly piece together a MPSoC that will meet the application demands of the end user with minimal time spent designing new hardware. Additionally, the use of MPSoCs allows designers to generate new devices very quickly and thus reducing the time to market. In this work, a complete MPSoC synthesis design flow is presented. We first present a technique \cite{leary1_intro} to address the synthesis of the interconnect architecture (particularly Network-on-Chip (NoC)). We then address the synthesis of the memory architecture of a MPSoC sub-system \cite{leary2_intro}. Lastly, we present a co-synthesis technique to generate the functional and memory architectures simultaneously. The validity and quality of each synthesis technique is demonstrated through extensive experimentation.
ContributorsLeary, Glenn (Author) / Chatha, Karamvir S (Thesis advisor) / Vrudhula, Sarma (Committee member) / Shrivastava, Aviral (Committee member) / Beraha, Rudy (Committee member) / Arizona State University (Publisher)
Created2013
Description
Unsaturated soil mechanics is becoming a part of geotechnical engineering practice, particularly in applications to moisture sensitive soils such as expansive and collapsible soils and in geoenvironmental applications. The soil water characteristic curve, which describes the amount of water in a soil versus soil suction, is perhaps the most important soil property function for application of unsaturated soil mechanics. The soil water characteristic curve has been used extensively for estimating unsaturated soil properties, and a number of fitting equations for development of soil water characteristic curves from laboratory data have been proposed by researchers. Although not always mentioned, the underlying assumption of soil water characteristic curve fitting equations is that the soil is sufficiently stiff so that there is no change in total volume of the soil while measuring the soil water characteristic curve in the laboratory, and researchers rarely take volume change of soils into account when generating or using the soil water characteristic curve. Further, there has been little attention to the applied net normal stress during laboratory soil water characteristic curve measurement, and often zero to only token net normal stress is applied. The applied net normal stress also affects the volume change of the specimen during soil suction change. When a soil changes volume in response to suction change, failure to consider the volume change of the soil leads to errors in the estimated air-entry value and the slope of the soil water characteristic curve between the air-entry value and the residual moisture state. Inaccuracies in the soil water characteristic curve may lead to inaccuracies in estimated soil property functions such as unsaturated hydraulic conductivity. A number of researchers have recently recognized the importance of considering soil volume change in soil water characteristic curves. The study of correct methods of soil water characteristic curve measurement and determination considering soil volume change, and impacts on the unsaturated hydraulic conductivity function was of the primary focus of this study. Emphasis was placed upon study of the effect of volume change consideration on soil water characteristic curves, for expansive clays and other high volume change soils. The research involved extensive literature review and laboratory soil water characteristic curve testing on expansive soils. The effect of the initial state of the specimen (i.e. slurry versus compacted) on soil water characteristic curves, with regard to volume change effects, and effect of net normal stress on volume change for determination of these curves, was studied for expansive clays. Hysteresis effects were included in laboratory measurements of soil water characteristic curves as both wetting and drying paths were used. Impacts of soil water characteristic curve volume change considerations on fluid flow computations and associated suction-change induced soil deformations were studied through numerical simulations. The study includes both coupled and uncoupled flow and stress-deformation analyses, demonstrating that the impact of volume change consideration on the soil water characteristic curve and the estimated unsaturated hydraulic conductivity function can be quite substantial for high volume change soils.
ContributorsBani Hashem, Elham (Author) / Houston, Sandra L. (Thesis advisor) / Kavazanjian, Edward (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2013
Description
This thesis presents a probabilistic evaluation of multiple laterally loaded drilled pier foundation design approaches using extensive data from a geotechnical investigation for a high voltage electric transmission line. A series of Monte Carlo simulations provide insight about the computed level of reliability considering site standard penetration test blow count value variability alone (i.e., assuming all other aspects of the design problem do not contribute error or bias). Evaluated methods include Eurocode 7 Geotechnical Design procedures, the Federal Highway Administration drilled shaft LRFD design method, the Electric Power Research Institute transmission foundation design procedure and a site specific variability based approach previously suggested by the author of this thesis and others. The analysis method is defined by three phases: a) Evaluate the spatial variability of an existing subsurface database. b) Derive theoretical foundation designs from the database in accordance with the various design methods identified. c) Conduct Monti Carlo Simulations to compute the reliability of the theoretical foundation designs. Over several decades, reliability-based foundation design (RBD) methods have been developed and implemented to varying degrees for buildings, bridges, electric systems and other structures. In recent years, an effort has been made by researchers, professional societies and other standard-developing organizations to publish design guidelines, manuals and standards concerning RBD for foundations. Most of these approaches rely on statistical methods for quantifying load and resistance probability distribution functions with defined reliability levels. However, each varies with regard to the influence of site-specific variability on resistance. An examination of the influence of site-specific variability is required to provide direction for incorporating the concept into practical RBD design methods. Recent surveys of transmission line engineers by the Electric Power Research Institute (EPRI) demonstrate RBD methods for the design of transmission line foundations have not been widely adopted. In the absence of a unifying design document with established reliability goals, transmission line foundations have historically performed very well, with relatively few failures. However, such a track record with no set reliability goals suggests, at least in some cases, a financial premium has likely been paid.
ContributorsHeim, Zackary (Author) / Houston, Sandra (Thesis advisor) / Witczak, Matthew (Committee member) / Kavazanjian, Edward (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2014
Description
Hydrocarbon spill site cleanup is challenging when contaminants are present in lower permeability layers. These are difficult to remediate and may result in long-term groundwater impacts. The research goal is to investigate strategies for long-term reduction of contaminant emissions from sources in low permeability layers through partial source treatment at higher/lower permeability interfaces. Conceptually, this provides a clean/reduced concentration zone near the interface, and consequently a reduced concentration gradient and flux from the lower permeability layer. Treatment by in-situ chemical oxidation (ISCO) was evaluated using hydrogen peroxide (H2O2) and sodium persulfate (Na2S2O8). H2O2 studies included lab and field-scale distribution studies and lab emission reduction experiments. The reaction rate of H2O2 in soils was so fast it did not travel far (<1 m) from delivery points under typical flow conditions. Oxygen gas generated and partially trapped in soil pores served as a dissolved oxygen (DO) source for >60 days in field and lab studies. During that period, the laboratory studies had reduced hydrocarbon impacts, presumably from aerobic biodegradation, which rebounded once the O2 source depleted. Therefore field monitoring should extend beyond the post-treatment elevated DO. Na2S2O8 use was studied in two-dimensional tanks (122-cm tall, 122-cm wide, and 5-cm thick) containing two contrasting permeability layers (three orders of magnitude difference). The lower permeability layer initially contained a dissolved-sorbed contaminant source throughout this layer, or a 10-cm thick non-aqueous phase liquid (NAPL)-impacted zone below the higher/lower permeability interface. The dissolved-sorbed source tank was actively treated for 14 d. Two hundred days after treatment, the emission reduction of benzene, toluene, ethylbenzene, and p-xylene (BTEX) were 95-99% and methyl tert-butyl ether (MTBE) was 63%. The LNAPL-source tank had three Na2S2O8 and two sodium hydroxide (NaOH) applications for S2O82- base activation. The resulting emission reductions for BTEX, n-propylbenzene, and 1,3,5 trymethylbenzene were 55-73%. While less effective at reducing emissions from LNAPL sources, the 14-d treatment delivered sufficient S2O82- though diffusion to remediate BTEX from the 60 cm dissolved-sorbed source. The overall S2O82- utilization in the dissolved source experiment was calculated by mass balance to be 108-125 g S2O82-/g hydrocarbon treated.
ContributorsCavanagh, Bridget (Author) / Johnson, Paul C (Thesis advisor) / Westerhoff, Paul (Committee member) / Kavazanjian, Edward (Committee member) / Bruce, Cristin (Committee member) / Arizona State University (Publisher)
Created2014
Description
In this thesis we deal with the problem of temporal logic robustness estimation. We present a dynamic programming algorithm for the robust estimation problem of Metric Temporal Logic (MTL) formulas regarding a finite trace of time stated sequence. This algorithm not only tests if the MTL specification is satisfied by the given input which is a finite system trajectory, but also quantifies to what extend does the sequence satisfies or violates the MTL specification. The implementation of the algorithm is the DP-TALIRO toolbox for MATLAB. Currently it is used as the temporal logic robust computing engine of S-TALIRO which is a tool for MATLAB searching for trajectories of minimal robustness in Simulink/ Stateflow. DP-TALIRO is expected to have near linear running time and constant memory requirement depending on the structure of the MTL formula. DP-TALIRO toolbox also integrates new features not supported in its ancestor FW-TALIRO such as parameter replacement, most related iteration and most related predicate. A derivative of DP-TALIRO which is DP-T-TALIRO is also addressed in this thesis which applies dynamic programming algorithm for time robustness computation. We test the running time of DP-TALIRO and compare it with FW-TALIRO. Finally, we present an application where DP-TALIRO is used as the robustness computation core of S-TALIRO for a parameter estimation problem.
ContributorsYang, Hengyi (Author) / Fainekos, Georgios (Thesis advisor) / Sarjoughian, Hessam S. (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2013
Description
Characterization of petroleum spill site source zones directly influences the selection of corrective action plans and frequently affects the success of remediation efforts. For example, simply knowing whether or not nonaqueous phase liquid (NAPL) is present, or if there is chemical storage in less hydraulically accessible regions, will influence corrective action planning. The overarching objective of this study was to assess if macroscopic source zone features can be inferred from dissolved concentration vs. time data. Laboratory-scale physical model studies were conducted for idealized sources; defined as Type-1) NAPL-impacted high permeability zones, Type-2) NAPL-impacted lower permeability zones, and Type-3) dissolved chemical matrix storage in lower permeability zones. Aquifer source release studies were conducted using two-dimensional stainless steel flow-through tanks outfitted with sampling ports for the monitoring of effluent concentrations and flow rates. An idealized NAPL mixture of key gasoline components was used to create the NAPL source zones, and dissolved sources were created using aqueous solutions having concentrations similar to water in equilibrium with the NAPL sources. The average linear velocity was controlled by pumping to be about 2 ft/d, and dissolved effluent concentrations were monitored daily. The Type-1 experiment resulted in a source signature similar to that expected for a relatively well-mixed NAPL source, with dissolved concentrations dependent on chemical solubility and initial mass fraction. The Type-2 and Type-3 experiments were conducted for 320 d and 190 d respectively. Unlike the Type-1 experiment, the concentration vs. time behavior was similar for all chemicals, for both source types. The magnitudes of the effluent concentrations varied between the Type-2 and Type-3 experiments, and were related to the hydrocarbon source mass. A fourth physical model experiment was performed to identify differences between ideal equilibrium behavior and the source concentration vs. time behavior observed in the tank experiments. Screening-level mathematical models predicted the general behavior observed in the experiments. The results of these studies suggest that dissolved concentration vs. time data can be used to distinguish between Type-1 sources in transmissive zones and Type-2 and Type-3 sources in lower permeability zones, provided that many years to decades of data are available. The results also suggest that concentration vs. time data alone will be insufficient to distinguish between NAPL and dissolved-phase storage sources in lower permeability regions.
ContributorsWilson, Sean Tomas (Author) / Johnson, Paul (Thesis advisor) / Kavazanjian, Edward (Committee member) / Fox, Peter (Committee member) / Arizona State University (Publisher)
Created2014
Description
Software has a great impact on the energy efficiency of any computing system--it can manage the components of a system efficiently or inefficiently. The impact of software is amplified in the context of a wearable computing system used for activity recognition. The design space this platform opens up is immense and encompasses sensors, feature calculations, activity classification algorithms, sleep schedules, and transmission protocols. Design choices in each of these areas impact energy use, overall accuracy, and usefulness of the system. This thesis explores methods software can influence the trade-off between energy consumption and system accuracy. In general the more energy a system consumes the more accurate will be. We explore how finding the transitions between human activities is able to reduce the energy consumption of such systems without reducing much accuracy. We introduce the Log-likelihood Ratio Test as a method to detect transitions, and explore how choices of sensor, feature calculations, and parameters concerning time segmentation affect the accuracy of this method. We discovered an approximate 5X increase in energy efficiency could be achieved with only a 5% decrease in accuracy. We also address how a system's sleep mode, in which the processor enters a low-power state and sensors are turned off, affects a wearable computing platform that does activity recognition. We discuss the energy trade-offs in each stage of the activity recognition process. We find that careful analysis of these parameters can result in great increases in energy efficiency if small compromises in overall accuracy can be tolerated. We call this the ``Great Compromise.'' We found a 6X increase in efficiency with a 7% decrease in accuracy. We then consider how wireless transmission of data affects the overall energy efficiency of a wearable computing platform. We find that design decisions such as feature calculations and grouping size have a great impact on the energy consumption of the system because of the amount of data that is stored and transmitted. For example, storing and transmitting vector-based features such as FFT or DCT do not compress the signal and would use more energy than storing and transmitting the raw signal. The effect of grouping size on energy consumption depends on the feature. For scalar features energy consumption is proportional in the inverse of grouping size, so it's reduced as grouping size goes up. For features that depend on the grouping size, such as FFT, energy increases with the logarithm of grouping size, so energy consumption increases slowly as grouping size increases. We find that compressing data through activity classification and transition detection significantly reduces energy consumption and that the energy consumed for the classification overhead is negligible compared to the energy savings from data compression. We provide mathematical models of energy usage and data generation, and test our ideas using a mobile computing platform, the Texas Instruments Chronos watch.
ContributorsBoyd, Jeffrey Michael (Author) / Sundaram, Hari (Thesis advisor) / Li, Baoxin (Thesis advisor) / Shrivastava, Aviral (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2014
Description
Expansive soils impose challenges on the design, maintenance and long-term stability of many engineered infrastructure. These soils are composed of different clay minerals that are susceptible to changes in moisture content. Expansive clay soils wreak havoc due to their volume change property and, in many cases, exhibit extreme swelling and shrinking potentials. Understanding what type of minerals and clays react in the presence of water would allow for a more robust design and a better way to mitigate undesirable soil volume change. The relatively quick and widely used method of X-ray Diffraction (XRD) allows identifying the type of minerals present in the soil. As part of this study, three different clays from Colorado, San Antonio Texas, and Anthem Arizona were examined using XRD techniques. Oedometer-type testing was simultaneously preformed in the laboratory to benchmark the behavior of these soils. This analysis allowed performing comparative studies to determining if the XRD technique and interpretation methods currently available could serve as quantitative tools for estimating swell potential through mineral identification. The soils were analyzed using two different software protocols after being subjected to different treatment techniques. Important observations include the formation of Ettringite and Thaumasite, the effect of mixed-layer clays in the interpretation of the data, and the soils being subject to Gypsification. The swelling data obtained from the oedometer-type laboratory testing was compared with predictive swelling functions available from literature. A correlation analysis was attempted in order to find what index properties and mineralogy parameters were most significant to the swelling behavior of the soils. The analysis demonstrated that Gypsification is as important to the swelling potential of the soil as the presence of expansive clays; and it should be considered in the design and construction of structures in expansive soils. Also, the formation of Ettringite and Thaumasite observed during the treatment process validates the evidence of Delayed Ettringite Formation (DEF) reported in the literature. When comparing the measured results with a proposed method from the University of Texas at Arlington (UTA), it was found that the results were somewhat indicative of swell potential but did not explain all causes for expansivity. Finally, it was found that single index properties are not sufficient to estimate the free swell or the swell pressure of expansive soils. In order to have a significant correlation, two or more index properties should be combined when estimating the swell potential. When properties related to the soil mineralogy were correlated with swell potential parameters, the amount of Gypsum present in the soil seems to be as significant to the swell behavior of the soil as the amount of Smectite found.
ContributorsShafer, Zachery (Author) / Zapata, Claudia (Thesis advisor) / Kavazanjian, Edward (Committee member) / Houston, Sandra (Committee member) / Arizona State University (Publisher)
Created2014
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