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 17 of 17 for “"Near-Memory Computing"”.

  1. Near-Memory Computing Architectures for Scalable Edge AI Applications

    … and machine learning (ML) are rapidly permeating nearly every aspect of modern life, frompersonal devices and autonomous systems to industrial automation and environmental monitoring. The growing demandfor intelligence at the network edge is reshaping how computing hardware is conceived and built. …

    lund Repository record for Near-Memory Computing Architectures for Scalable Edge AI Applications (opens in a new tab) Download PDF for Near-Memory Computing Architectures for Scalable Edge AI Applications (opens in a new tab)

  2. 3D Integration Technology and Near-Memory Computing for Edge AI

    … resource-constrained edge devices with reduced memory and energy deployment. In this thesis, solutions for improving edge AI implementations are evaluated considering two approaches: technology integration and hardware architecture design.Higher performance through increased technology …

    lund Repository record for 3D Integration Technology and Near-Memory Computing for Edge AI (opens in a new tab) Download PDF for 3D Integration Technology and Near-Memory Computing for Edge AI (opens in a new tab)

  3. Architectures and Frameworks for Near-Memory Computing using 3D-Stacked Memories

    … exposed significant limitations in traditional computing architectures, notably the widening gap between processor speeds and memory access latency, referred to as the memory wall, and the constraints imposed by bandwidth limitations, known as the bandwidth wall. Despite advancements following …

    qucosa-diss

  4. Efficient In- and Near- Memory Computing System With Hardware and Software Co-Design

    … daily, requiring processing and analysis by computing systems. However, modern computing systems suffer from power-hungry data transfer and processing due to the separate design of storage and processing units. This separation leads to a significant gap between supply and demand when …

    jhu Repository record for Efficient In- and Near- Memory Computing System With Hardware and Software Co-Design (opens in a new tab)

  5. MEMORY-CENTRIC ARCHITECTURES FOR AI INFERENCE ACCELERATION VIA HARDWARE–SOFTWARE CO-DESIGN

    … rapidly growing demand for energy-efficient computing, while conventional von Neumann systems are increasingly limited by data movement across the memory wall. This thesis advances memory-centric AI inference through cross-layer hardware-software co-design spanning analog and digital …

    nus Repository record for MEMORY-CENTRIC ARCHITECTURES FOR AI INFERENCE ACCELERATION VIA HARDWARE–SOFTWARE CO-DESIGN (opens in a new tab) Download file for MEMORY-CENTRIC ARCHITECTURES FOR AI INFERENCE ACCELERATION VIA HARDWARE–SOFTWARE CO-DESIGN (opens in a new tab)

  6. TASNIC : a flexible TCP offload with programmable SmartNICs

    … parallelization of the TCP data-path, and near-memory computing for high performance, while remaining flexible via a modular design. We compare TASNIC to Linux, the TAS TCP accelerator, and the Chelsio Terminator TOE. We find that Memcached scales up to 38% better on TASNIC versus TAS, …

    texas Repository record for TASNIC : a flexible TCP offload with programmable SmartNICs (opens in a new tab)

  7. Ferroelectric and Monolithic 3D (M3D) Memory Technologies for High-Performance, Energy-Efficient Computing

    Present-day hardware with limited on-chip memory capacity falls short of meeting the speed and energy-efficiency requirement for data-intensive applications such as Artificial Intelligence due to the need for expensive data transfer between processor and off-chip memory. The objective of this …

    gatech Repository record for Ferroelectric and Monolithic 3D (M3D) Memory Technologies for High-Performance, Energy-Efficient Computing (opens in a new tab)

  8. A Programmable Look-up Table-based Processing in Memory Architecture for Massively Parallel, Energy-Efficient Processing of Data-intensive Applications within DRAM

    As modern computing workloads become increasingly data-intensive, the limitations of traditional digital computing hardware, especially in terms of communication bandwidth between memory and processors, are becoming more apparent. Surprisingly, the performance and energy efficiency of the …

    rit Repository record for A Programmable Look-up Table-based Processing in Memory Architecture for Massively Parallel, Energy-Efficient Processing of Data-intensive Applications within DRAM (opens in a new tab)

  9. Near Memory Accelerators for Approximate Nearest Neighbor Search

    Approximate Nearest Neighbor (ANN) search has become a critical component in modern retrieval systems, supporting applications such as recommendation engines, semantic search, and large language models. Despite the effectiveness of embedding-based methods, performing ANN search over billion-scale, …

    mtu Repository record for Near Memory Accelerators for Approximate Nearest Neighbor Search (opens in a new tab)

  10. Reconfigurable and heterogeneous architectures for efficient computing

    … in performance or power for general-purpose computing. Thus, there is an increase in the adoption of specialized hardware, tuned to the requirements of the application or domain. These accelerators promise high performance and energy efficiency. However, with the increasing complexity and …

    uiuc Repository record for Reconfigurable and heterogeneous architectures for efficient computing (opens in a new tab)

  11. Efficient and Reliable In-Memory Computing Systems Using Emerging Technologies: From Device to Algorithm

    Big data applications are memory-intensive, and the cost of bringing data from the memory to the processor involves large overheads in energy and processing time. This has driven the push towards specialized accelerator units that can perform computations close to where the data is stored. Two …

    umn Repository record for Efficient and Reliable In-Memory Computing Systems Using Emerging Technologies: From Device to Algorithm (opens in a new tab)

  12. Design and Evaluation of a Memory-Centric Binary Hyperdimensional Computing Architecture with 1T3R Memristor-Based Nonvolatile Storage

    Hyperdimensional computing (HDC) represents information with high-dimensional distributed hypervectors and performs classification using simple binary operations such as binding, bundling, and associative search. While these operations are hardware-friendly, the large hypervector dimension creates …

    vt Repository record for Design and Evaluation of a Memory-Centric Binary Hyperdimensional Computing Architecture with 1T3R Memristor-Based Nonvolatile Storage (opens in a new tab)

  13. Optimization Techniques for Machine Learning Inference and Near Memory Image Processing in Hardware for Highly Constrained IoT Edge Nodes

    … has highlighted the limitations of conventional computing architectures. This research focuses on addressing the demand for fast, optimized, and energy-efficient machine learning inference engines as well as image processing in IoT edge applications. In this work, we address three challenging …

    usf Repository record for Optimization Techniques for Machine Learning Inference and Near Memory Image Processing in Hardware for Highly Constrained IoT Edge Nodes (opens in a new tab)

  14. High Performance Compute Accelerators for Radio Frequency Signal Processing Applications

    … RF beamforming. This is achieved by combining In-memory/Near-memory architectures with high throughput digital compute engine design. We begin by demonstrating a Near-Memory digital compute accelerator for real-time emulation of RF interactions. This architecture allows for the simulation of …

    gatech Repository record for High Performance Compute Accelerators for Radio Frequency Signal Processing Applications (opens in a new tab)