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 13 of 13 for “"3D memory"”.

  1. ELECTRONIC DESIGN AUTOMATION FOR HIGH-PERFORMANCE AND RELIABLE 3D MEMORY CUBES AND PROCESSORS

    … we conceive a new die stacking architecture for 3D memory cubes targeting space applications, complemented with custom radiation-hardened-by-design logic controllers. In the second theme, we explore machine learning to improve the implementation flow of a large field-programmable gate array …

    gatech Repository record for ELECTRONIC DESIGN AUTOMATION FOR HIGH-PERFORMANCE AND RELIABLE 3D MEMORY CUBES AND PROCESSORS (opens in a new tab)

  2. System Optimization for 3D-Stacking Memories

    … the channel-level parallelism present in modern 3D-memory like HMC and HBM. This can improve the performance of both domain-specific accelerators (DSAs) and universal computer systems, achieving performance improvements ranging from 2$\times$ to 8$\times$ to eightfold as opposed to systems that …

    penn Repository record for System Optimization for 3D-Stacking Memories (opens in a new tab)

  3. Built-in controller for self-test and repair of 3D integrated Nand flash memory chip, used in radiation intense space environment

    The perennial need for memory storage is further increasing with the advancements in technology. Both terrestrial and space related applications thrive on efficient ways and new technology for storing data that is incorruptible and dependable. Research is continuously carried out on making storage …

    unm Repository record for Built-in controller for self-test and repair of 3D integrated Nand flash memory chip, used in radiation intense space environment (opens in a new tab)

  4. Exploiting on-chip memory concurrency in 3d manycore architectures

    … of this thesis is to optimize the uncore of 3D many-core architectures. More specifically, we note that technology trends point to large increases in memory-level concurrency. This in turn affects the design of the multi-core interconnect and organization of the memory hierarchy. The work …

    gatech Repository record for Exploiting on-chip memory concurrency in 3d manycore architectures (opens in a new tab)

  5. Code generation and adaptive control divergence management for light weight SIMT processors

    … a resurgence in the interest in processing-in-memory (PIM) architectures. This challenge has spawned the development of a scalable, parametric data parallel architecture referred at the Heterogeneous Architecture Research Prototype (HARP) - a single instruction multiple thread (SIMT) …

    gatech Repository record for Code generation and adaptive control divergence management for light weight SIMT processors (opens in a new tab)

  6. Charge State Dynamics and Quantum Sensing with Defects in Diamond

    … charge state could serve as an ultra-dense 3D memory platform. The NV center has also been used as a nanoscale magnetometer. The high degree of spin polarization and the ease of manipulation of the NV allows us to transfer this polarization to other spins in the diamond and assists in the …

    cuny-grad Repository record for Charge State Dynamics and Quantum Sensing with Defects in Diamond (opens in a new tab)

  7. Improving Scalability of Deep Learning Accelerators Using 3D IC

    … (DL) accelerators face in both interconnect and memory system design. As DL models grow increasingly diverse in their shapes, operators, and data reuse patterns, rigid architectures such as systolic arrays struggle to maintain high utilization, leading to inefficient execution on emerging …

    gatech Repository record for Improving Scalability of Deep Learning Accelerators Using 3D IC (opens in a new tab)

  8. MEMS GHz Sonar for Through Silicon Communications and Sensing Applications

    … via (UTSV), a new type of wireless 3D interconnect that enables chip-to-chip communication in multi-chip 3D integrated circuit (3DIC) stacks. The second application is the GHz sonic memory – a delay line memory that uses the UTSV as an ultrasonic delay line and stores digital bits as …

    cornell Repository record for MEMS GHz Sonar for Through Silicon Communications and Sensing Applications (opens in a new tab)

  9. Methodologies and Architectures for AI Inference Hardware: From Foundational Networks to Large Language Models

    … include fitting model parameters within on-chip memory to improve performance, co-optimizing chip size with software mapping to reduce TCO, and effectively exploiting model sparsity to support larger models. Additionally, the thesis discusses ChronoStack, a 3D memory architecture developed as …

    washington Repository record for Methodologies and Architectures for AI Inference Hardware: From Foundational Networks to Large Language Models (opens in a new tab)

  10. Two-photon 3d Optical Data Storage Via Fluorescence Modulation Of Fluorene Dyes By Photochromic Diarylethenes

    Three-dimensional (3D) optical data storage based on two-photon processes provides highly confined excitation in a recording medium and a mechanism for writing and reading data with less cross talk between multiple memory layers, due to the quadratic dependence of two photon absorption (2PA) on the …

    ucf Repository record for Two-photon 3d Optical Data Storage Via Fluorescence Modulation Of Fluorene Dyes By Photochromic Diarylethenes (opens in a new tab)

  11. Flexible Multiple-Precision Fused Arithmetic Units for Efficient Deep Learning Computation

    … operations are both computation intensive and memory intensive. Many research works in the literature focused on improving the efficiency of deep learning operations. In this thesis, special focus is put on improving deep learning computation and several efficient arithmetic unit architectures …

    sask Repository record for Flexible Multiple-Precision Fused Arithmetic Units for Efficient Deep Learning Computation (opens in a new tab)

  12. Dataflow Processing in Memory Achieves Significant Energy Efficiency

    … difference between processor CPU cycle time and memory access time, often referred to as the memory wall, severely limits the performance of streaming applications. Some data centers have shown servers being idle three out of four clocks. High performance instruction sequenced systems are not …

    unt Repository record for Dataflow Processing in Memory Achieves Significant Energy Efficiency (opens in a new tab)