Matching Items (18)
Filtering by
- All Subjects: Computer Science
- All Subjects: Neural Networks
- Resource Type: Text
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
Semiconductor scaling technology has led to a sharp growth in transistor counts. This has resulted in an exponential increase on both power dissipation and heat flux (or power density) in modern microprocessors. These microprocessors are integrated as the major components in many modern embedded devices, which offer richer features and attain higher performance than ever before. Therefore, power and thermal management have become the significant design considerations for modern embedded devices. Dynamic voltage/frequency scaling (DVFS) and dynamic power management (DPM) are two well-known hardware capabilities offered by modern embedded processors. However, the power or thermal aware performance optimization is not fully explored for the mainstream embedded processors with discrete DVFS and DPM capabilities. Many key problems have not been answered yet. What is the maximum performance that an embedded processor can achieve under power or thermal constraint for a periodic application? Does there exist an efficient algorithm for the power or thermal management problems with guaranteed quality bound? These questions are hard to be answered because the discrete settings of DVFS and DPM enhance the complexity of many power and thermal management problems, which are generally NP-hard. The dissertation presents a comprehensive study on these NP-hard power and thermal management problems for embedded processors with discrete DVFS and DPM capabilities. In the domain of power management, the dissertation addresses the power minimization problem for real-time schedules, the energy-constrained make-span minimization problem on homogeneous and heterogeneous chip multiprocessors (CMP) architectures, and the battery aware energy management problem with nonlinear battery discharging model. In the domain of thermal management, the work addresses several thermal-constrained performance maximization problems for periodic embedded applications. All the addressed problems are proved to be NP-hard or strongly NP-hard in the study. Then the work focuses on the design of the off-line optimal or polynomial time approximation algorithms as solutions in the problem design space. Several addressed NP-hard problems are tackled by dynamic programming with optimal solutions and pseudo-polynomial run time complexity. Because the optimal algorithms are not efficient in worst case, the fully polynomial time approximation algorithms are provided as more efficient solutions. Some efficient heuristic algorithms are also presented as solutions to several addressed problems. The comprehensive study answers the key questions in order to fully explore the power and thermal management potentials on embedded processors with discrete DVFS and DPM capabilities. The provided solutions enable the theoretical analysis of the maximum performance for periodic embedded applications under power or thermal constraints.
ContributorsZhang, Sushu (Author) / Chatha, Karam S (Thesis advisor) / Cao, Yu (Committee member) / Konjevod, Goran (Committee member) / Vrudhula, Sarma (Committee member) / Xue, Guoliang (Committee member) / Arizona State University (Publisher)
Created2012
Description
The use of energy-harvesting in a wireless sensor network (WSN) is essential for situations where it is either difficult or not cost effective to access the network's nodes to replace the batteries. In this paper, the problems involved in controlling an active sensor network that is powered both by batteries and solar energy are investigated. The objective is to develop control strategies to maximize the quality of coverage (QoC), which is defined as the minimum number of targets that must be covered and reported over a 24 hour period. Assuming a time varying solar profile, the problem is to optimally control the sensing range of each sensor so as to maximize the QoC while maintaining connectivity throughout the network. Implicit in the solution is the dynamic allocation of solar energy during the day to sensing and to recharging the battery so that a minimum coverage is guaranteed even during the night, when only the batteries can supply energy to the sensors. This problem turns out to be a non-linear optimal control problem of high complexity. Based on novel and useful observations, a method is presented to solve it as a series of quasiconvex (unimodal) optimization problems which not only ensures a maximum QoC, but also maintains connectivity throughout the network. The runtime of the proposed solution is 60X less than a naive but optimal method which is based on dynamic programming, while the peak error of the solution is less than 8%. Unlike the dynamic programming method, the proposed method is scalable to large networks consisting of hundreds of sensors and targets. The solution method enables a designer to explore the optimal configuration of network design. This paper offers many insights in the design of energy-harvesting networks, which result in minimum network setup cost through determination of optimal configuration of number of sensors, sensing beam width, and the sampling time.
ContributorsGaudette, Benjamin (Author) / Vrudhula, Sarma (Thesis advisor) / Shrivastava, Aviral (Committee member) / Sen, Arunabha (Committee member) / Arizona State University (Publisher)
Created2012
Description
Thanks to continuous technology scaling, intelligent, fast and smaller digital systems are now available at affordable costs. As a result, digital systems have found use in a wide range of application areas that were not even imagined before, including medical (e.g., MRI, remote or post-operative monitoring devices, etc.), automotive (e.g., adaptive cruise control, anti-lock brakes, etc.), security systems (e.g., residential security gateways, surveillance devices, etc.), and in- and out-of-body sensing (e.g., capsule swallowed by patients measuring digestive system pH, heart monitors, etc.). Such computing systems, which are completely embedded within the application, are called embedded systems, as opposed to general purpose computing systems. In the design of such embedded systems, power consumption and reliability are indispensable system requirements. In battery operated portable devices, the battery is the single largest factor contributing to device cost, weight, recharging time, frequency and ultimately its usability. For example, in the Apple iPhone 4 smart-phone, the battery is $40\%$ of the device weight, occupies $36\%$ of its volume and allows only $7$ hours (over 3G) of talk time. As embedded systems find use in a range of sensitive applications, from bio-medical applications to safety and security systems, the reliability of the computations performed becomes a crucial factor. At our current technology-node, portable embedded systems are prone to expect failures due to soft errors at the rate of once-per-year; but with aggressive technology scaling, the rate is predicted to increase exponentially to once-per-hour. Over the years, researchers have been successful in developing techniques, implemented at different layers of the design-spectrum, to improve system power efficiency and reliability. Among the layers of design abstraction, I observe that the interface between the compiler and processor micro-architecture possesses a unique potential for efficient design optimizations. A compiler designer is able to observe and analyze the application software at a finer granularity; while the processor architect analyzes the system output (power, performance, etc.) for each executed instruction. At the compiler micro-architecture interface, if the system knowledge at the two design layers can be integrated, design optimizations at the two layers can be modified to efficiently utilize available resources and thereby achieve appreciable system-level benefits. To this effect, the thesis statement is that, ``by merging system design information at the compiler and micro-architecture design layers, smart compilers can be developed, that achieve reliable and power-efficient embedded computing through: i) Pure compiler techniques, ii) Hybrid compiler micro-architecture techniques, and iii) Compiler-aware architectures''. In this dissertation demonstrates, through contributions in each of the three compiler-based techniques, the effectiveness of smart compilers in achieving power-efficiency and reliability in embedded systems.
ContributorsJeyapaul, Reiley (Author) / Shrivastava, Aviral (Thesis advisor) / Vrudhula, Sarma (Committee member) / Clark, Lawrence (Committee member) / Colbourn, Charles (Committee member) / Arizona State University (Publisher)
Created2012
Description
Threshold logic has been studied by at least two independent group of researchers. One group of researchers studied threshold logic with the intention of building threshold logic circuits. The earliest research to this end was done in the 1960's. The major work at that time focused on studying mathematical properties of threshold logic as no efficient circuit implementations of threshold logic were available. Recently many post-CMOS (Complimentary Metal Oxide Semiconductor) technologies that implement threshold logic have been proposed along with efficient CMOS implementations. This has renewed the effort to develop efficient threshold logic design automation techniques. This work contributes to this ongoing effort. Another group studying threshold logic did so, because the building block of neural networks - the Perceptron, is identical to the threshold element implementing a threshold function. Neural networks are used for various purposes as data classifiers. This work contributes tangentially to this field by proposing new methods and techniques to study and analyze functions implemented by a Perceptron After completion of the Human Genome Project, it has become evident that most biological phenomenon is not caused by the action of single genes, but due to the complex interaction involving a system of genes. In recent times, the `systems approach' for the study of gene systems is gaining popularity. Many different theories from mathematics and computer science has been used for this purpose. Among the systems approaches, the Boolean logic gene model has emerged as the current most popular discrete gene model. This work proposes a new gene model based on threshold logic functions (which are a subset of Boolean logic functions). The biological relevance and utility of this model is argued illustrated by using it to model different in-vivo as well as in-silico gene systems.
ContributorsLinge Gowda, Tejaswi (Author) / Vrudhula, Sarma (Thesis advisor) / Shrivastava, Aviral (Committee member) / Chatha, Karamvir (Committee member) / Kim, Seungchan (Committee member) / Arizona State University (Publisher)
Created2012
Description
In recent years, we have observed the prevalence of stream applications in many embedded domains. Stream programs distinguish themselves from traditional sequential programming languages through well defined independent actors, explicit data communication, and stable code/data access patterns. In order to achieve high performance and low power, scratch pad memory (SPM) has been introduced in today's embedded multicore processors. Current design frameworks for developing stream applications on SPM enhanced embedded architectures typically do not include a compiler that can perform automatic partitioning, mapping and scheduling under limited on-chip SPM capacities and memory access delays. Consequently, many designs are implemented manually, which leads to lengthy tasks and inferior designs. In this work, optimization techniques that automatically compile stream programs onto embedded multi-core architectures are proposed. As an initial case study, we implemented an automatic target recognition (ATR) algorithm on the IBM Cell Broadband Engine (BE). Then integer linear programming (ILP) and heuristic approaches were proposed to schedule stream programs on a single core embedded processor that has an SPM with code overlay. Later, ILP and heuristic approaches for Compiling Stream programs on SPM enhanced Multicore Processors (CSMP) were studied. The proposed CSMP ILP and heuristic approaches do not optimize for cycles in stream applications. Further, the number of software pipeline stages in the implementation is dependent on actor to processing engine (PE) mapping and is uncontrollable. We next presented a Retiming technique for Throughput optimization on Embedded Multi-core processors (RTEM). RTEM approach inherently handles cycles and can accept an upper bound on the number of software pipeline stages to be generated. We further enhanced RTEM by incorporating unrolling (URSTEM) that preserves all the beneficial properties of RTEM heuristic and also scales with the number of PEs through unrolling.
ContributorsChe, Weijia (Author) / Chatha, Karam Singh (Thesis advisor) / Vrudhula, Sarma (Committee member) / Chakrabarti, Chaitali (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2012
Description
The quality and quantity of talented members of the US STEM workforce has
been a subject of great interest to policy and decision makers for the past 40 years.
Recent research indicates that while there exist specific shortages in specific disciplines
and areas of expertise in the private sector and the federal government, there is no
noticeable shortage in any STEM academic discipline, but rather a surplus of PhDs
vying for increasingly scarce tenure track positions. Despite the seeming availability
of industry and private sector jobs, recent PhDs still struggle to find employment in
those areas. I argue that the decades old narrative suggesting a shortage of STEM
PhDs in the US poses a threat to the value of the natural science PhD, and that
this narrative contributes significantly to why so many PhDs struggle to find career
employment in their fields. This study aims to address the following question: what is
the value of a STEM PhD outside academia? I begin with a critical review of existing
literature, and then analyze programmatic documents for STEM PhD programs at
ASU, interviews with industry employers, and an examination the public face of value
for these degrees. I then uncover the nature of the value alignment, value disconnect,
and value erosion in the ecosystem which produces and then employs STEM PhDs,
concluding with specific areas which merit special consideration in an effort to increase
the value of these degrees for all stakeholders involved.
been a subject of great interest to policy and decision makers for the past 40 years.
Recent research indicates that while there exist specific shortages in specific disciplines
and areas of expertise in the private sector and the federal government, there is no
noticeable shortage in any STEM academic discipline, but rather a surplus of PhDs
vying for increasingly scarce tenure track positions. Despite the seeming availability
of industry and private sector jobs, recent PhDs still struggle to find employment in
those areas. I argue that the decades old narrative suggesting a shortage of STEM
PhDs in the US poses a threat to the value of the natural science PhD, and that
this narrative contributes significantly to why so many PhDs struggle to find career
employment in their fields. This study aims to address the following question: what is
the value of a STEM PhD outside academia? I begin with a critical review of existing
literature, and then analyze programmatic documents for STEM PhD programs at
ASU, interviews with industry employers, and an examination the public face of value
for these degrees. I then uncover the nature of the value alignment, value disconnect,
and value erosion in the ecosystem which produces and then employs STEM PhDs,
concluding with specific areas which merit special consideration in an effort to increase
the value of these degrees for all stakeholders involved.
ContributorsGarbee, Elizabeth (Author) / Maynard, Andrew D. (Thesis advisor) / Wetmore, Jameson (Committee member) / Anderson, Derrick (Committee member) / Arizona State University (Publisher)
Created2018
Description
Deep learning (DL) has proved itself be one of the most important developements till date with far reaching impacts in numerous fields like robotics, computer vision, surveillance, speech processing, machine translation, finance, etc. They are now widely used for countless applications because of their ability to generalize real world data, robustness to noise in previously unseen data and high inference accuracy. With the ability to learn useful features from raw sensor data, deep learning algorithms have out-performed tradinal AI algorithms and pushed the boundaries of what can be achieved with AI. In this work, we demonstrate the power of deep learning by developing a neural network to automatically detect cough instances from audio recorded in un-constrained environments. For this, 24 hours long recordings from 9 dierent patients is collected and carefully labeled by medical personel. A pre-processing algorithm is proposed to convert event based cough dataset to a more informative dataset with start and end of coughs and also introduce data augmentation for regularizing the training procedure. The proposed neural network achieves 92.3% leave-one-out accuracy on data captured in real world.
Deep neural networks are composed of multiple layers that are compute/memory intensive. This makes it difficult to execute these algorithms real-time with low power consumption using existing general purpose computers. In this work, we propose hardware accelerators for a traditional AI algorithm based on random forest trees and two representative deep convolutional neural networks (AlexNet and VGG). With the proposed acceleration techniques, ~ 30x performance improvement was achieved compared to CPU for random forest trees. For deep CNNS, we demonstrate that much higher performance can be achieved with architecture space exploration using any optimization algorithms with system level performance and area models for hardware primitives as inputs and goal of minimizing latency with given resource constraints. With this method, ~30GOPs performance was achieved for Stratix V FPGA boards.
Hardware acceleration of DL algorithms alone is not always the most ecient way and sucient to achieve desired performance. There is a huge headroom available for performance improvement provided the algorithms are designed keeping in mind the hardware limitations and bottlenecks. This work achieves hardware-software co-optimization for Non-Maximal Suppression (NMS) algorithm. Using the proposed algorithmic changes and hardware architecture
With CMOS scaling coming to an end and increasing memory bandwidth bottlenecks, CMOS based system might not scale enough to accommodate requirements of more complicated and deeper neural networks in future. In this work, we explore RRAM crossbars and arrays as compact, high performing and energy efficient alternative to CMOS accelerators for deep learning training and inference. We propose and implement RRAM periphery read and write circuits and achieved ~3000x performance improvement in online dictionary learning compared to CPU.
This work also examines the realistic RRAM devices and their non-idealities. We do an in-depth study of the effects of RRAM non-idealities on inference accuracy when a pretrained model is mapped to RRAM based accelerators. To mitigate this issue, we propose Random Sparse Adaptation (RSA), a novel scheme aimed at tuning the model to take care of the faults of the RRAM array on which it is mapped. Our proposed method can achieve inference accuracy much higher than what traditional Read-Verify-Write (R-V-W) method could achieve. RSA can also recover lost inference accuracy 100x ~ 1000x faster compared to R-V-W. Using 32-bit high precision RSA cells, we achieved ~10% higher accuracy using fautly RRAM arrays compared to what can be achieved by mapping a deep network to an 32 level RRAM array with no variations.
Deep neural networks are composed of multiple layers that are compute/memory intensive. This makes it difficult to execute these algorithms real-time with low power consumption using existing general purpose computers. In this work, we propose hardware accelerators for a traditional AI algorithm based on random forest trees and two representative deep convolutional neural networks (AlexNet and VGG). With the proposed acceleration techniques, ~ 30x performance improvement was achieved compared to CPU for random forest trees. For deep CNNS, we demonstrate that much higher performance can be achieved with architecture space exploration using any optimization algorithms with system level performance and area models for hardware primitives as inputs and goal of minimizing latency with given resource constraints. With this method, ~30GOPs performance was achieved for Stratix V FPGA boards.
Hardware acceleration of DL algorithms alone is not always the most ecient way and sucient to achieve desired performance. There is a huge headroom available for performance improvement provided the algorithms are designed keeping in mind the hardware limitations and bottlenecks. This work achieves hardware-software co-optimization for Non-Maximal Suppression (NMS) algorithm. Using the proposed algorithmic changes and hardware architecture
With CMOS scaling coming to an end and increasing memory bandwidth bottlenecks, CMOS based system might not scale enough to accommodate requirements of more complicated and deeper neural networks in future. In this work, we explore RRAM crossbars and arrays as compact, high performing and energy efficient alternative to CMOS accelerators for deep learning training and inference. We propose and implement RRAM periphery read and write circuits and achieved ~3000x performance improvement in online dictionary learning compared to CPU.
This work also examines the realistic RRAM devices and their non-idealities. We do an in-depth study of the effects of RRAM non-idealities on inference accuracy when a pretrained model is mapped to RRAM based accelerators. To mitigate this issue, we propose Random Sparse Adaptation (RSA), a novel scheme aimed at tuning the model to take care of the faults of the RRAM array on which it is mapped. Our proposed method can achieve inference accuracy much higher than what traditional Read-Verify-Write (R-V-W) method could achieve. RSA can also recover lost inference accuracy 100x ~ 1000x faster compared to R-V-W. Using 32-bit high precision RSA cells, we achieved ~10% higher accuracy using fautly RRAM arrays compared to what can be achieved by mapping a deep network to an 32 level RRAM array with no variations.
ContributorsMohanty, Abinash (Author) / Cao, Yu (Thesis advisor) / Seo, Jae-Sun (Committee member) / Vrudhula, Sarma (Committee member) / Chakrabarti, Chaitali (Committee member) / Arizona State University (Publisher)
Created2018
Description
This paper details the specification and implementation of a single-machine blockchain simulator. It also includes a brief introduction on the history & underlying concepts of blockchain, with explanations on features such as decentralization, openness, trustlessness, and consensus. The introduction features a brief overview of public interest and current implementations of blockchain before stating potential use cases for blockchain simulation software. The paper then gives a brief literature review of blockchain's role, both as a disruptive technology and a foundational technology. The literature review also addresses the potential and difficulties regarding the use of blockchain in Internet of Things (IoT) networks, and also describes the limitations of blockchain in general regarding computational intensity, storage capacity, and network architecture. Next, the paper gives the specification for a generic blockchain structure, with summaries on the behaviors and purposes of transactions, blocks, nodes, miners, public & private key cryptography, signature validation, and hashing. Finally, the author gives an overview of their specific implementation of the blockchain using C/C++ and OpenSSL. The overview includes a brief description of all the classes and data structures involved in the implementation, including their function and behavior. While the implementation meets the requirements set forward in the specification, the results are more qualitative and intuitive, as time constraints did not allow for quantitative measurements of the network simulation. The paper concludes by discussing potential applications for the simulator, and the possibility for future hardware implementations of blockchain.
ContributorsRauschenbach, Timothy Rex (Author) / Vrudhula, Sarma (Thesis director) / Nakamura, Mutsumi (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
Description
Improving energy efficiency has always been the prime objective of the custom and automated digital circuit design techniques. As a result, a multitude of methods to reduce power without sacrificing performance have been proposed. However, as the field of design automation has matured over the last few decades, there have been no new automated design techniques, that can provide considerable improvements in circuit power, leakage and area. Although emerging nano-devices are expected to replace the existing MOSFET devices, they are far from being as mature as semiconductor devices and their full potential and promises are many years away from being practical.
The research described in this dissertation consists of four main parts. First is a new circuit architecture of a differential threshold logic flipflop called PNAND. The PNAND gate is an edge-triggered multi-input sequential cell whose next state function is a threshold function of its inputs. Second a new approach, called hybridization, that replaces flipflops and parts of their logic cones with PNAND cells is described. The resulting \hybrid circuit, which consists of conventional logic cells and PNANDs, is shown to have significantly less power consumption, smaller area, less standby power and less power variation.
Third, a new architecture of a field programmable array, called field programmable threshold logic array (FPTLA), in which the standard lookup table (LUT) is replaced by a PNAND is described. The FPTLA is shown to have as much as 50% lower energy-delay product compared to conventional FPGA using well known FPGA modeling tool called VPR.
Fourth, a novel clock skewing technique that makes use of the completion detection feature of the differential mode flipflops is described. This clock skewing method improves the area and power of the ASIC circuits by increasing slack on timing paths. An additional advantage of this method is the elimination of hold time violation on given short paths.
Several circuit design methodologies such as retiming and asynchronous circuit design can use the proposed threshold logic gate effectively. Therefore, the use of threshold logic flipflops in conventional design methodologies opens new avenues of research towards more energy-efficient circuits.
The research described in this dissertation consists of four main parts. First is a new circuit architecture of a differential threshold logic flipflop called PNAND. The PNAND gate is an edge-triggered multi-input sequential cell whose next state function is a threshold function of its inputs. Second a new approach, called hybridization, that replaces flipflops and parts of their logic cones with PNAND cells is described. The resulting \hybrid circuit, which consists of conventional logic cells and PNANDs, is shown to have significantly less power consumption, smaller area, less standby power and less power variation.
Third, a new architecture of a field programmable array, called field programmable threshold logic array (FPTLA), in which the standard lookup table (LUT) is replaced by a PNAND is described. The FPTLA is shown to have as much as 50% lower energy-delay product compared to conventional FPGA using well known FPGA modeling tool called VPR.
Fourth, a novel clock skewing technique that makes use of the completion detection feature of the differential mode flipflops is described. This clock skewing method improves the area and power of the ASIC circuits by increasing slack on timing paths. An additional advantage of this method is the elimination of hold time violation on given short paths.
Several circuit design methodologies such as retiming and asynchronous circuit design can use the proposed threshold logic gate effectively. Therefore, the use of threshold logic flipflops in conventional design methodologies opens new avenues of research towards more energy-efficient circuits.
ContributorsKulkarni, Niranjan (Author) / Vrudhula, Sarma (Thesis advisor) / Colbourn, Charles (Committee member) / Seo, Jae-Sun (Committee member) / Yu, Shimeng (Committee member) / Arizona State University (Publisher)
Created2015