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 19 of 19 for “"Dataflow Architecture"”.

  1. Unidirectional circular dataflow architecture for real-time updates

    Unidirectional Circular Dataflow Architecture for Real-Time Updates The capability to present data in real-time is an essential feature to be considered when architecting modern web applications. Examination of the origin, progress and obstacles of web applications reveals how it influenced the …

    dcu Download PDF for Unidirectional circular dataflow architecture for real-time updates (opens in a new tab)

  2. A Dataflow Architecture for Accelerating Real-time Dynamic Graph Neural Network Workloads

    This thesis explores the design of a flexible dataflow architecture to accelerate dynamic Graph Neural Networks (GNNs) for real-time applications requiring strict low-latency processing. Focusing on GNN models based on Edge Convolution (EdgeConv), architectural enhancements are proposed to enable …

    gatech Repository record for A Dataflow Architecture for Accelerating Real-time Dynamic Graph Neural Network Workloads (opens in a new tab)

  3. Accelerating simulations with analogous hardware: a scalable dataflow architecture for high-performance molecular dynamics

    … validating a new, massively parallel hardware architecture capable of accelerating MD simulations by several orders of magnitude, with custom integrated circuit implementations projected to achieve timescales of up to 100 milliseconds per day. The proposed architecture is based on the …

    oxford Restricted access

  4. Supporting Transparent Distributed Messaging for Dataflow Applications in Power Electronics Control Systems

    … processors. The processors are designed using dataflow architecture. The protocol ensures transparent asynchronous communication between distributed processes. The protocol is designed such that an application can run without change in virtually any kind of distributed configuration, where …

    vt Repository record for Supporting Transparent Distributed Messaging for Dataflow Applications in Power Electronics Control Systems (opens in a new tab)

  5. High Performance Architecture using Speculative Threads and Dynamic Memory Management Hardware

    … have shifted from control flow Von-Neumann architecture back to dataflow architecture again in order to explore scalable architectures leading to multi-core systems with several hundreds of processing elements. In this dissertation, I address how the performance of modern processing systems …

    unt Repository record for High Performance Architecture using Speculative Threads and Dynamic Memory Management Hardware (opens in a new tab)

  6. Design and Evaluation of an Embedded Real-time Micro-kernel

    … operating system kernel specially designed for dataflow software. Dataflow is a style of software architecture that is well suited for control and "signal flow" applications. This architecture involves many small processes and lots of inter-process communication, which impose too much overhead …

    vt Repository record for Design and Evaluation of an Embedded Real-time Micro-kernel (opens in a new tab)

  7. Distributed, Modular, Open Control Architecture for Power Conversion Systems

    … proposes a distributed, modular, open control architecture for power conversion systems to reduce control design complexity, encapsulate and localize design dependencies, reduce unnecessary redesign effort and improve software quality. Dataflow style is chosen as the architectural style for the …

    vt Repository record for Distributed, Modular, Open Control Architecture for Power Conversion Systems (opens in a new tab)

  8. Evaluating the Perceived Overhead Imposed by Object-Oriented Programming in a Real-time Embedded System

    … kernel for real-time embedded systems based on dataflow architecture. Dataflow is a software architecture that is well suited to applications that involve signal flows and value transformations. Typically, these systems comprise numerous processes with heavy inter-process communications. The …

    vt Repository record for Evaluating the Perceived Overhead Imposed by Object-Oriented Programming in a Real-time Embedded System (opens in a new tab)

  9. Automatic Parallelisation of Programs onto CPU+GPU Hybrid Systems

    … re-written in order to run on a GPU architecture. This research aims to produce a system that will allow programs to be run without specifying which set of devices they can be run on. This will allow programs to be more easily moved between different configurations of processors, but …

    essex Download PDF for Automatic Parallelisation of Programs onto CPU+GPU Hybrid Systems (opens in a new tab)

  10. Supporting Distributed Fault Tolerance In A Real-Time Micro-Kernel

    … This thesis describes research to extend the Dataflow Architecture Real-time Kernel (DARK) to support distributed, fault-tolerant execution of control algorithms for power electronics control systems. An appropriate scheme for fault-tolerant scheduling of processes on distributed processing …

    vt Repository record for Supporting Distributed Fault Tolerance In A Real-Time Micro-Kernel (opens in a new tab)

  11. FPGA-Augmented Secure Crash-Consistent Non-Volatile Memory

    … prominence of CPU-FPGA heterogeneous computing architectures, ARES leverages FPGA's hardware reconfigurability to offload performance-critical and security-related functions to the programmable hardware without microprocessors' involvement. In particular, recognizing that the traditional Merkle …

    ucf Repository record for FPGA-Augmented Secure Crash-Consistent Non-Volatile Memory (opens in a new tab)

  12. Accelerating Scientific Computations on Modern Node Architectures

    … transistor density to creating parallel architectures due to the end of Moore's Law. Many-core architectures with wide or scalable SIMD vector extensions, GPUs, domain-specific hardware, and dataflow architectures, have gained traction and are now widely used to accelerate scientific …

    rice Repository record for Accelerating Scientific Computations on Modern Node Architectures (opens in a new tab)

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

    … 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 faced when designing a many-core DNN accelerator to handle the data movement …

    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)

  14. Non-Grid Opportunistic Resources for (Big Data) Volunteer Computing

    … using those opportunistic resources. The DIRAC architecture allows the use of the existing institutional grid resources. To expand the capability of existing computing powers, I have proposed to integrate opportunistic resources in the distributed computing system (DIRAC). In order, not to be …

    kent Download PDF for Non-Grid Opportunistic Resources for (Big Data) Volunteer Computing (opens in a new tab)

  15. Contributions to the joint segmentation and classification of sequences (My two cents on decoding and handwriting recognition)

    … requiring dictionary look-ups (e.g. hashing). A dataflow architecture allowing the design of flexible and diverse recognition systems from a little repertoire of components has been proposed, including a novel DAG serialization protocol. DAG generators can take over-segmentation constraints into …

    upv Repository record for Contributions to the joint segmentation and classification of sequences (My two cents on decoding and handwriting recognition) (opens in a new tab)

  16. Hardware acceleration techniques for computation and data intensive machine learning and bioinformatic applications

    … that matches the accelerator's memory architecture to its computation and memory access patterns.In the second part of the thesis, we study the effect of acceleration techniques on one of the major bottlenecks of a typical genomic pipeline, which is short read alignment. In our study we …

    greece Repository record for Hardware acceleration techniques for computation and data intensive machine learning and bioinformatic applications (opens in a new tab)

  17. An Application Framework for a Power-Aware Processor Architecture

    … Tech proposed a novel data-flow processor architecture design to bridge the gap between event-driven applications and the target architecture. The architecture, although promising in terms of performance and energy-efficiency, was explored for limited number of applications. This thesis …

    vt Repository record for An Application Framework for a Power-Aware Processor Architecture (opens in a new tab)

  18. TOWARD GENERAL-PURPOSE DYNAMIC DATAFLOW PROCESSING

    … environments. Coarse-Grained Reconfigurable Architectures (CGRAs) are often considered an efficient, programmable alternative. Unlike CPUs, CGRAs enable direct data transfer between operations through a grid network, simplifying hardware design but facing challenges finding optimal routing …

    nus Repository record for TOWARD GENERAL-PURPOSE DYNAMIC DATAFLOW PROCESSING (opens in a new tab) Download file for TOWARD GENERAL-PURPOSE DYNAMIC DATAFLOW PROCESSING (opens in a new tab)

  19. DEMAND-DRIVEN EXECUTION USING FUTURE GATED SINGLE ASSIGNMENT FORM

    … of the compiler as well as the Instruction Set Architecture (ISA) of the machine. This work develops the instruction set architecture, the programming language pragmatics, and the microarchitecture for the demand-driven execution paradigm.

    mtu Repository record for DEMAND-DRIVEN EXECUTION USING FUTURE GATED SINGLE ASSIGNMENT FORM (opens in a new tab)