Matching Items (214)
Filtering by
- Creators: Arizona State University
Description
Due to high DRAM access latency and energy, several convolutional neural network(CNN) accelerators face performance and energy efficiency challenges, which are critical for embedded implementations. As these applications exploit larger datasets, memory accesses of these emerging applications are increasing. As a result, it is difficult to predict the combined dynamic random access memory (DRAM) workload behavior, which can sabotage memory optimizations in software. To understand the impact of external memory access on CNN accelerators which reduces the high DRAMaccess latency and energy, simulators such as RAMULATOR and VAMPIRE have been proposed in prior work. In this work, we utilize these simulators to benchmark external memory access in CNN accelerators. Experiments are performed generating trace files based on the number of parameters and data precision and also using trace file generated for CNN Accelerator Altera Arria 10 GX 1150 FPGA data to complete the end to end workflow using the mentioned simulators. Besides that, certain modifications were made in the default VAMPIRE code to implement certain functionalities such as PREA(Precharge All) and REF(Refresh). Then, precalculated energies were computed for DDR3, DDR4, and HBM based on the micron model to mention it in the dram specification file inputted to the VAMPIRE tool. An experimental study was performed and a comparison is made between DDR3, DDR4, and HBM, it was proved that DDR4 is nearly 31% more energy-efficient than DDR3 and HBMis 54% energy-efficient than DDR3. Performed modeling and experimental analysis on a large set of data and then split it into a set of data and compared the results of the small sets multiplied with the number of sets and the large data set and concluded that the results were nearly the same. Finally, a GUI is developed by wrapping both the simulators. GUI provides user-friendly access and can analyze the parameters without much prior knowledge and understanding of the working.
ContributorsPannala, Manvitha (Author) / Cao, Yu (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Seo, Jae-Sun (Committee member) / Arizona State University (Publisher)
Created2021
Description
This dissertation considers the question of how convenient access to copious networked observational data impacts our ability to learn causal knowledge. It investigates in what ways learning causality from such data is different from -- or the same as -- the traditional causal inference which often deals with small scale i.i.d. data collected from randomized controlled trials? For example, how can we exploit network information for a series of tasks in the area of learning causality? To answer this question, the dissertation is written toward developing a suite of novel causal learning algorithms that offer actionable insights for a series of causal inference tasks with networked observational data. The work aims to benefit real-world decision-making across a variety of highly influential applications. In the first part of this dissertation, it investigates the task of inferring individual-level causal effects from networked observational data. First, it presents a representation balancing-based framework for handling the influence of hidden confounders to achieve accurate estimates of causal effects. Second, it extends the framework with an adversarial learning approach to properly combine two types of existing heuristics: representation balancing and treatment prediction. The second part of the dissertation describes a framework for counterfactual evaluation of treatment assignment policies with networked observational data. A novel framework that captures patterns of hidden confounders is developed to provide more informative input for downstream counterfactual evaluation methods. The third part presents a framework for debiasing two-dimensional grid-based e-commerce search with observational search log data where there is an implicit network connecting neighboring products in a search result page. A novel inverse propensity scoring framework that models user behavior patterns for two-dimensional display in e-commerce websites is developed, which aims to optimize online performance of ranking algorithms with offline log data.
ContributorsGuo, Ruocheng (Author) / Liu, Huan (Thesis advisor) / Candan, K. Selcuk (Committee member) / Xue, Guoliang (Committee member) / Kiciman, Emre (Committee member) / Arizona State University (Publisher)
Created2021
Description
Convolutional neural networks(CNNs) achieve high accuracy on large datasets but requires significant computation and storage requirement for training/testing. While many applications demand low latency and energy-efficient processing of the images, deploying these complex algorithms on the hardware is a challenging task. This dissertation first presents a compiler-based CNN training accelerator using DDR3 and HBM2 memory. An optimized RTL library is implemented to perform training-specific tasks and an RTL compiler is developed to generate FPGA-synthesizable RTL based on user-defined constraints. High Bandwidth Memory(HBM) provides efficient off-chip communication and improves the training performance. The impact of HBM2 on CNN training workloads is analyzed and compressively compared with DDR3. For training ResNet-20/VGG-like CNNs for the CIFAR-10 dataset, the proposed CNN training accelerator on Stratix-10 GX FPGA(DDR3) demonstrates 479 GOPS performance, and on Stratix-10 MX FPGA(HBM) shows 4.5/9.7 X energy-efficiency improvement compared to Tesla V100 GPU. Next, the FPGA online learning accelerator is presented. Adopting model segmentation techniques from Progressive Segmented Training(PST), the online learning accelerator achieved a 4.2X reduction in training latency. Furthermore, this dissertation presents an 8-bit floating-point (FP8) training processor which implements (1) Highly parallel tensor cores that maintain high PE utilization, (2) Hardware-efficient channel gating for dynamic output activation sparsity (3) Dynamic weight sparsity based on group Lasso (4) Gradient skipping based on FP prediction error. The 28nm prototype chip demonstrates significant improvements in FLOPs reduction (7.3×), energy efficiency (16.4 TFLOPS/W), and overall training latency speedup (4.7×) for both supervised training and self-supervised training tasks. In addition to the training accelerators, this dissertation also presents a CNN inference accelerator on ASIC(FixyNN) and FPGA(FixyFPGA). FixyNN consists of a fixed-weight feature extractor that generates ubiquitous CNN features and a conventional programmable CNN accelerator. In the fixed-weight feature extractor, the network weights are hard-coded into hardware and used as a fixed operand for the multiplication. Experimental results demonstrate FixyNN can achieve very high energy efficiencies up to 26.6 TOPS/W, and FixyFPGA achieves $2.34\times$ higher GOPS on ImageNet classification. In summary, this dissertation comprehensively discusses novel architectures of high-performance and energy-efficient ASIC/FPGA CNN inference/training accelerators.
ContributorsKolala Venkataramaniah, Shreyas (Author) / Seo, Jae-Sun (Thesis advisor) / Cao, Yu (Committee member) / Chakrabarti, Chaitali (Committee member) / Fan, Deliang (Committee member) / Arizona State University (Publisher)
Created2022
Description
This dissertation constructs a new computational processing framework to robustly and precisely quantify retinotopic maps based on their angle distortion properties. More generally, this framework solves the problem of how to robustly and precisely quantify (angle) distortions of noisy or incomplete (boundary enclosed) 2-dimensional surface to surface mappings. This framework builds upon the Beltrami Coefficient (BC) description of quasiconformal mappings that directly quantifies local mapping (circles to ellipses) distortions between diffeomorphisms of boundary enclosed plane domains homeomorphic to the unit disk. A new map called the Beltrami Coefficient Map (BCM) was constructed to describe distortions in retinotopic maps. The BCM can be used to fully reconstruct the original target surface (retinal visual field) of retinotopic maps. This dissertation also compared retinotopic maps in the visual processing cascade, which is a series of connected retinotopic maps responsible for visual data processing of physical images captured by the eyes. By comparing the BCM results from a large Human Connectome project (HCP) retinotopic dataset (N=181), a new computational quasiconformal mapping description of the transformed retinal image as it passes through the cascade is proposed, which is not present in any current literature. The description applied on HCP data provided direct visible and quantifiable geometric properties of the cascade in a way that has not been observed before. Because retinotopic maps are generated from in vivo noisy functional magnetic resonance imaging (fMRI), quantifying them comes with a certain degree of uncertainty. To quantify the uncertainties in the quantification results, it is necessary to generate statistical models of retinotopic maps from their BCMs and raw fMRI signals. Considering that estimating retinotopic maps from real noisy fMRI time series data using the population receptive field (pRF) model is a time consuming process, a convolutional neural network (CNN) was constructed and trained to predict pRF model parameters from real noisy fMRI data
ContributorsTa, Duyan Nguyen (Author) / Wang, Yalin (Thesis advisor) / Lu, Zhong-Lin (Committee member) / Hansford, Dianne (Committee member) / Liu, Huan (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2022
Description
Object tracking refers to the problem of estimating a moving object's time-varying parameters that are indirectly observed in measurements at each time step. Increased noise and clutter in the measurements reduce estimation accuracy as they increase the uncertainty of tracking in the field of view. Whereas tracking is performed using a Bayesian filter, a Bayesian smoother can be utilized to refine parameter state estimations that occurred before the current time. In practice, smoothing can be widely used to improve state estimation or correct data association errors, and it can lead to significantly better estimation performance as it reduces the impact of noise and clutter. In this work, a single object tracking method is proposed based on integrating Kalman filtering and smoothing with thresholding to remove unreliable measurements. As the new method is effective when the noise and clutter in the measurements are high, the main goal is to find these measurements using a moving average filter and a thresholding method to improve estimation. Thus, the proposed method is designed to reduce estimation errors that result from measurements corrupted with high noise and clutter. Simulations are provided to demonstrate the improved performance of the new method when compared to smoothing without thresholding. The root-mean-square error in estimating the object state parameters is shown to be especially reduced under high noise conditions.
ContributorsSeo, Yongho (Author) / Papandreaou-Suppappola, Antonia (Thesis advisor) / Bliss, Daniel W (Committee member) / Chakrabarti, Chaitali (Committee member) / Moraffah, Bahman (Committee member) / Arizona State University (Publisher)
Created2022
Description
It is not merely an aggregation of static entities that a video clip carries, but alsoa variety of interactions and relations among these entities. Challenges still remain
for a video captioning system to generate natural language descriptions focusing on
the prominent interest and aligning with the latent aspects beyond observations. This
work presents a Commonsense knowledge Anchored Video cAptioNing (dubbed as
CAVAN) approach. CAVAN exploits inferential commonsense knowledge to assist the
training of video captioning model with a novel paradigm for sentence-level semantic
alignment. Specifically, commonsense knowledge is queried to complement per training
caption by querying a generic knowledge atlas ATOMIC, and form the commonsense-
caption entailment corpus. A BERT based language entailment model trained from
this corpus then serves as a commonsense discriminator for the training of video
captioning model, and penalizes the model from generating semantically misaligned
captions. With extensive empirical evaluations on MSR-VTT, V2C and VATEX
datasets, CAVAN consistently improves the quality of generations and shows higher
keyword hit rate. Experimental results with ablations validate the effectiveness of
CAVAN and reveals that the use of commonsense knowledge contributes to the video
caption generation.
ContributorsShao, Huiliang (Author) / Yang, Yezhou (Thesis advisor) / Jayasuriya, Suren (Committee member) / Xiao, Chaowei (Committee member) / Arizona State University (Publisher)
Created2022
Description
With the breakdown of Dennard scaling, computer architects can no longer rely on integrated circuit energy efficiency to scale with transistor density, and must under-clock or power-gate parts of their designs in order to fit within given power budgets. Hardware accelerators may improve energy efficiency of some compute-intensive tasks, but as more tasks are accelerated, the general-purpose portions of workloads account for a larger share of execution time while also leaving less instruction, data, or task-level parallelism to exploit. Adaptive computing systems have potential to address these challenges by modifying their behavior at runtime. Adaptation requires runtime decision-making, which can be performed both in hardware and software. While software-based decision-making is more flexible and can execute higher complexity operations compared to hardware, it also incurs a significant latency and power overhead. Hardware designs are more limited in the space of decisions they can make, but have direct access to their own internal microarchitectural states and can make faster decisions, allowing for better-informed adaptation and extracting previously unobtainable performance and security benefits. In this dissertation I study (i) the viability and trade-offs of general-purpose adaptive systems, (ii) the difficulty and complexity of making adaptation decisions, and (iii) how time spent in the observation-analysis-adaptation cycle affects adaptation benefits. I introduce techniques for (a) modeling and understanding high performance computing systems and microarchitecture, (b) enabling hardware learning and decision-making through low-latency networks, and (c) on securing hardware designs using runtime decision-making. I propose an always-awake and active learning `hardware nervous system' pervasive throughout the chip that can reason about the individual hardware module performance, energy usage, and security. I present the design and implementation of (1) a reference architecture and (2) a microarchitecture-aware static binary instrumentation tool. Finally, I provide results showing (1) that runtime adaptation is a necessary to continue improving performance on general-purpose tasks, (2) that significant performance loss and performance variation happens under the ISA-level, and is unobservable without hardware support, and (3) that hardware must possess decision-making and ‘self-awareness’ capabilities at the microarchitecture level in order to efficiently use its own faculties.
ContributorsIsakov, Mihailo (Author) / Kinsy, Michel (Thesis advisor) / Shrivastava, Aviral (Committee member) / Rudd, Kevin (Committee member) / Gadepally, Vijay (Committee member) / Arizona State University (Publisher)
Created2022
Description
Arc Routing Problems (ARPs) are a type of routing problem that finds routes of minimum total cost covering the edges or arcs in a graph representing street or road networks. They find application in many essential services such as residential waste collection, winter gritting, and others. Being NP-hard, solutions are usually found using heuristic methods. This dissertation contributes to heuristics for ARP, with a focus on the Capacitated Arc Routing Problem (CARP) with additional constraints. In operations such as residential waste collection, vehicle breakdown disruptions occur frequently. A new variant Capacitated Arc Re-routing Problem for Vehicle Break-down (CARP-VB) is introduced to address the need to re-route using only remaining vehicles to avoid missing services. A new heuristic Probe is developed to solve CARP-VB. Experiments on benchmark instances show that Probe is better in reducing the makespan and hence effective in reducing delays and avoiding missing services.
In addition to total cost, operators are also interested in solutions that are attractive, that is, routes that are contiguous, compact, and non-overlapping to manage the work. Operators may not adopt a solution that is not attractive even if it is optimum. They are also interested in solutions that are balanced in workload to meet equity requirements. A new multi-objective memetic algorithm, MA-ABC is developed, that optimizes three objectives: Attractiveness, makespan, and total cost. On testing with benchmark instances, MA-ABC was found to be effective in providing attractive and balanced route solutions without affecting the total cost.
Changes in the problem specification such as demand and topology occurs frequently in business operations. Machine learning be applied to learn the distribution behind these changes and generate solutions quickly at time of inference. Splice is a machine learning framework for CARP that generates closer to optimum solutions quickly using a graph neural network and deep Q-learning. Splice can solve several variants of node and arc routing problems using the same architecture without any modification. Splice was trained and tested using randomly generated instances. Splice generated solutions faster that are also better in comparison to popular metaheuristics.
ContributorsRamamoorthy, Muhilan (Author) / Syrotiuk, Violet R. (Thesis advisor) / Forrest, Stephanie (Committee member) / Mirchandani, Pitu (Committee member) / Sen, Arunabha (Committee member) / Arizona State University (Publisher)
Created2022
Description
The security of Internet-of-Things (IoT) is essential for its widespread adoption. The recent advancement in Artificial Intelligence (AI) brings both challenges and opportunities to IoT security. On the one hand, AI enables better security designs. On the other hand, AI-based advanced attacks are more threatening than traditional ones. This dissertation aims to study the dual effects of AI on IoT security, specifically IoT device security and IoT communication security. Particularly, this dissertation investigates three important topics: 1) security of acoustic mobile authentication, 2) Deep Learning (DL)-guided jamming attacks on cross-technology IoT networks, and 3) DL-powered scalable group-key establishment for large IoT networks. Chapter 2 presents a thorough study on the security of acoustic mobile authentication. In particular, this chapter proposes two mobile authentication schemes identifying the user's mobile device with its linear and nonlinear acoustic fingerprints, respectively. Both schemes adopt the Data Mining (DM) techniques to improve their identification accuracy. This chapter identifies a novel fingerprint-emulation attack and proposes the dynamic challenge and response method as an effective defense. A comprehensive comparison between two schemes in terms of security, usability, and deployment is presented at the end of this chapter, which suggests their respective suitable application scenarios. Chapter 3 identifies a novel DL-guided predictive jamming attack named DeepJam. DeepJam targets at cross-technology IoT networks and explores Deep Reinforcement Learning (DRL) to predict the victim's transmissions that are not subject to the Cross-Technology Interference (CTI). This chapter also proposes two effective countermeasures against DeepJam for resource capable and resource constrained IoT networks, respectively. Chapter 4 proposes a drone-aided DL-powered scalable group-key generation scheme, named DroneKey, for large-scale IoT networks. DroneKey is a physical-layer key generation scheme. In particular, DroneKey actively induces correlated changes to the wireless signals received by a group of devices and explores DL techniques to extract a common key from them. DroneKey significantly outperforms existing solutions in terms of the scalability and key-generation rate.
ContributorsHan, Dianqi (Author) / Zhang, Yanchao YZ (Thesis advisor) / Reisslein, Martin MR (Committee member) / Xue, Guoliang GX (Committee member) / Zhang, Junshan JZ (Committee member) / Arizona State University (Publisher)
Created2022
Description
Adversarial threats of deep learning are increasingly becoming a concern due to the ubiquitous deployment of deep neural networks(DNNs) in many security-sensitive domains. Among the existing threats, adversarial weight perturbation is an emerging class of threats that attempts to perturb the weight parameters of DNNs to breach security and privacy.In this thesis, the first weight perturbation attack introduced is called Bit-Flip Attack (BFA), which can maliciously flip a small number of bits within a computer’s main memory system storing the DNN weight parameter to achieve malicious objectives. Our developed algorithm can achieve three specific attack objectives: I) Un-targeted accuracy degradation attack, ii) Targeted attack, & iii) Trojan attack. Moreover, BFA utilizes the rowhammer technique to demonstrate the bit-flip attack in an actual computer prototype. While the bit-flip attack is conducted in a white-box setting, the subsequent contribution of this thesis is to develop another novel weight perturbation attack in a black-box setting. Consequently, this thesis discusses a new study of DNN model vulnerabilities in a multi-tenant Field Programmable Gate Array (FPGA) cloud under a strict black-box framework. This newly developed attack framework injects faults in the malicious tenant by duplicating specific DNN weight packages during data transmission between off-chip memory and on-chip buffer of a victim FPGA. The proposed attack is also experimentally validated in a multi-tenant cloud FPGA prototype. In the final part, the focus shifts toward deep learning model privacy, popularly known as model extraction, that can steal partial DNN weight parameters remotely with the aid of a memory side-channel attack. In addition, a novel training algorithm is designed to utilize the partially leaked DNN weight bit information, making the model extraction attack more effective. The algorithm effectively leverages the partial leaked bit information and generates a substitute prototype of the victim model with almost identical performance to the victim.
ContributorsRakin, Adnan Siraj (Author) / Fan, Deliang (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Seo, Jae-Sun (Committee member) / Cao, Yu (Committee member) / Arizona State University (Publisher)
Created2022