Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 28 for “"DNN Accelerators"”.

  1. Temperature-aware 3D-integrated systolic array DNN accelerators

    Deep neural networks (DNNs) are extensively used for inference in a wide range of emerging mobile and edge application domains, including autonomous vehicles, drones, augmented and virtual reality (AR/VR), etc. Due to the increasing popularity of these applications, there has been an increasing …

    bu Repository record for Temperature-aware 3D-integrated systolic array DNN accelerators (opens in a new tab)

  2. Optimized Floating-Point Arithmetic for Efficient Operations in DNN Accelerators

    … resource efficiency in deep neural network (DNN) training accelerators through novel approaches to optimising floating-point (FP) arithmetic. While previous work has largely addressed the efficiency of inference, this thesis targets the underexplored domain of training, aiming to reduce …

    unsw Repository record for Optimized Floating-Point Arithmetic for Efficient Operations in DNN Accelerators (opens in a new tab)

  3. Investigating Opportunities and Challenges in Modeling and Designing Scale-Out DNN Accelerators

    … for the design of convolutional neural network accelerators is presented and described in detail named SCALE-Sim (Systolic CNN Accelerator Simulator). The simulator is available as an open-sourced repository and has 2 primary use-cases in which computer architects can extract significant …

    gatech Repository record for Investigating Opportunities and Challenges in Modeling and Designing Scale-Out DNN Accelerators (opens in a new tab)

  4. Hybrid Accelerator to Overcome Imperfections of Mixed-signal DNN Accelerators using Algorithm-Hardware Co-Design

    … is to increase the robustness of mixed-signal accelerators with an energy-efficient mechanism. In recent years, PIM-based mixed-signal accelerators have been proposed as energy- and area-efficient solutions with ultra-high throughput to accelerate DNN computations. However, PIM designs are …

    gatech Repository record for Hybrid Accelerator to Overcome Imperfections of Mixed-signal DNN Accelerators using Algorithm-Hardware Co-Design (opens in a new tab)

  5. A Cross-Layer Framework for Design Space Exploration and Variation Analysis of Compute-in-Memory DNN Accelerators using Non-Volatile Ferroelectric Capacitors

    Using non-volatile “capacitive” crossbar arrays for compute-in-memory (CIM) offers higher energy and area efficiency compared to “resistive” crossbar arrays. However, the impact of device-to-device (D2D) variation and temporal noise on the system-level performance has not been explored yet. In this …

    gatech Repository record for A Cross-Layer Framework for Design Space Exploration and Variation Analysis of Compute-in-Memory DNN Accelerators using Non-Volatile Ferroelectric Capacitors (opens in a new tab)

  6. Data- and communication-centric approaches to model and design flexible deep neural network accelerators

    Deep neural network (DNN) accelerators, which are specialized hardware for DNN inferences, enabled energy-efficient and low-latency DNN inferences. To maximize the efficiency (energy efficiency, latency, and throughput) of DNN accelerators, DNN accelerator designers optimize DNN accelerator and …

    gatech Repository record for Data- and communication-centric approaches to model and design flexible deep neural network accelerators (opens in a new tab)

  7. Algorithm-Hardware Co-Design Towards Efficient and Robust Edge Vision Applications

    The recent breakthroughs of deep neural networks (DNNs) and the advent of billions of Internet of Things (IoT) devices have excited an explosive demand for intelligent IoT devices equipped with domain-specific DNN accelerators. However, the deployment of DNN accelerator enabled intelligent …

    rice Repository record for Algorithm-Hardware Co-Design Towards Efficient and Robust Edge Vision Applications (opens in a new tab)

  8. Hardware-software co-design of FPGA-based neural network accelerators for edge inference

    The demand for efficient Deep Neural Network (DNN) accelerators has increased due to the growing popularity of DNNs in various applications, including image classification, speech recognition, and natural language processing. However, designing flexible, reconfigurable, and efficient DNN …

    glasgow Repository record for Hardware-software co-design of FPGA-based neural network accelerators for edge inference (opens in a new tab) Download PDF for Hardware-software co-design of FPGA-based neural network accelerators for edge inference (opens in a new tab)

  9. Automated Deep Learning Algorithm and Accelerator Co-search for Both Boosted Hardware Efficiency and Task Accuracy

    Powerful yet complex deep neural networks (DNNs) have fueled a booming demand for efficient DNN solutions to bring DNN-powered intelligence into numerous applications. Jointly optimizing the networks and their accelerators are promising in providing optimal performance. However, the great potential …

    rice Repository record for Automated Deep Learning Algorithm and Accelerator Co-search for Both Boosted Hardware Efficiency and Task Accuracy (opens in a new tab)

  10. Impact of HKMG and FDSOI FeFET Drain Current Variation in Processing-in-Memory Architectures

    … processing-in-memory (PIM) deep neural network (DNN) accelerators. When performing repeated read operations on several devices at various read frequencies and under various biasing and programming conditions, non-Normal variation in drain current is observed. Device-circuit co-analysis is used to …

    gatech Repository record for Impact of HKMG and FDSOI FeFET Drain Current Variation in Processing-in-Memory Architectures (opens in a new tab)

  11. PLUG-AND-PLAY FOSS ML ACCELERATOR : FROM CONCEPT TO CONCEPTION

    ML accelerators are a fairly new research area and it is important that the archi- tecture community is able to iterate quickly on architectural exploration. Although there are a number of commercial Deep Neural Network(DNN) accelerators avail- able on the market and a plethora of creative ML …

    gatech Repository record for PLUG-AND-PLAY FOSS ML ACCELERATOR : FROM CONCEPT TO CONCEPTION (opens in a new tab)

  12. Hardware-Friendly Model Compression techniques for Deep Learning Accelerators

    … solutions to make energy-efficient \gls{dnn} accelerators to be deployable on edge devices through developing hardware-aware \gls{dnn} compression methods. The rising popularity of intelligent mobile devices and the computational cost of deep learning-based models call for efficient and …

    gatech Repository record for Hardware-Friendly Model Compression techniques for Deep Learning Accelerators (opens in a new tab)

  13. Efficient Modeling for DNN Hardware Resiliency Assessment

    Deep neural network (DNN) hardware accelerators are critical enablers of the current resurgence in machine learning technologies. Adopting machine learning in safety-critical systems imposes additional reliability requirements on hardware design. Addressing these requirements mandates an accurate …

    mcmaster Repository record for Efficient Modeling for DNN Hardware Resiliency Assessment (opens in a new tab)

  14. Design of Efficient DNN Accelerator Architectures

    Deep Neural Networks (DNNs) are the fundamental processing unit behind modern Artificial Intelligence (AI). Accordingly, expecting a future with smart devices that are able to monitor, decide, and take action seems reasonable. However, DNNs are computation and power-hungry, which makes deployment …

    sask Repository record for Design of Efficient DNN Accelerator Architectures (opens in a new tab)

  15. Resilient and secure deep learning-oriented microarchitectures

    Deep neural networks (DNNs) have emerged as crucial methods for solving complex problems in various domains, including computer vision, natural language processing, and recommendation systems. An ideal DNN-based system should accurately make predictions or classifications based on some input data …

    brazil-uerj Repository record for Resilient and secure deep learning-oriented microarchitectures (opens in a new tab)

  16. METHODOLOGY AND ANALYSIS FOR EFFICIENT CUSTOM ARCHITECTURE DESIGN USING MACHINE LEARNING

    … algorithms especially Deep Neural Networks (DNNs) have revolutionized the arena of computing in the last decade. DNNs along the with the computational advancements also bring an unprecedented appetite for compute and parallel processing. Computer architects have risen to challenge by creating …

    gatech Repository record for METHODOLOGY AND ANALYSIS FOR EFFICIENT CUSTOM ARCHITECTURE DESIGN USING MACHINE LEARNING (opens in a new tab)

  17. Domain-aware Genetic Algorithms for Hardware and Mapping Optimization for Efficient DNN Acceleration

    … games) has led to the rise of domain-specific accelerators for deep learning. At design-time, these accelerators carefully architect the on-chip dataflow to maximize data reuse (over space and time) and size the hardware resources (PEs and buffers) to maximize performance and energy-efficiency, …

    gatech Repository record for Domain-aware Genetic Algorithms for Hardware and Mapping Optimization for Efficient DNN Acceleration (opens in a new tab)

  18. Efficient Networks-On-Chip Communication Support Solutions for Deep Neural Network Acceleration

    The increasing popularity of deep neural network (DNN) applications demands high computing power and efficient hardware accelerator architectures. DNN accelerators use a large number of processing elements (PEs) and on-chip memory for storing weights and other parameters. A significant challenge is …

    unlv Repository record for Efficient Networks-On-Chip Communication Support Solutions for Deep Neural Network Acceleration (opens in a new tab) Download PDF for Efficient Networks-On-Chip Communication Support Solutions for Deep Neural Network Acceleration (opens in a new tab)

  19. Error Resilient and Adaptive Deep Learning Systems

    … demand for low-power, high-performance hardware accelerators in edge computing environments presents further challenges in balancing computational efficiency and energy consumption. In response to these challenges, this research proposes a signature-based predictive testing framework for …

    gatech Repository record for Error Resilient and Adaptive Deep Learning Systems (opens in a new tab)

Page 1 of 2