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 12 of 12 for “"Algorithm acceleration"”.

  1. Applications of reprogrammability in algorithm acceleration

    … deal with hardware-based reprogrammability in algorithm acceleration with a specific emphasis on the possibilities offered by modern large-scale Field Programmable Gate Arrays (FPGAs) in computationally demanding applications. The historical evolution of both the theoretical and technological …

    aalto Repository record for Applications of reprogrammability in algorithm acceleration (opens in a new tab)

  2. Domain-Specific Analog Accelerators for Artificial Intelligent Algorithms Implementation

    This thesis discusses some circuit designs for AI algorithm acceleration. Instead of using digital computing components for algorithm implementations, this thesis describes new ideas to design and implement algorithms directly at the circuit-level. The first large section is about feedforward …

    carleton Repository record for Domain-Specific Analog Accelerators for Artificial Intelligent Algorithms Implementation (opens in a new tab)

  3. Augmented Surface Integral Equation Method for Low-Frequency Electromagnetic Analysis

    … solved with appropriate preconditioning and fast algorithm acceleration. As required in many applications, a generalized impedance boundary condition (GIBC) formulation is developed to handle the skin effect rigorously and efficiently. It degenerates into traditional methods with two steps of …

    uiuc Repository record for Augmented Surface Integral Equation Method for Low-Frequency Electromagnetic Analysis (opens in a new tab)

  4. GPU ACCELERATED CLUSTER DRIVEN ANISOTROPIC DIFFUSION FOR SPECKLE REDUCTION IN ULTRASOUND IMAGES

    … model and is driven by the K-means clustering algorithm. Compared with other AD filters, such as speckle reducing anisotropic diffusion (SRAD), the proposed method has many benefits. For example, instead of manually selecting a homogeneous sample region for the computation of diffusion …

    mtu Repository record for GPU ACCELERATED CLUSTER DRIVEN ANISOTROPIC DIFFUSION FOR SPECKLE REDUCTION IN ULTRASOUND IMAGES (opens in a new tab)

  5. Design and Analysis of Hardware-Based Scheduler and Multi-Photon Quantum Cryptography Protocol

    … dissertation, a new hardware-based scheduling algorithm is proposed for multiprocessor task scheduling. The proposed algorithm has O(1) runtime complexity and can be scaled to schedule hundreds or thousands of processors. In addition, this dissertation develops analytical models for …

    houston Repository record for Design and Analysis of Hardware-Based Scheduler and Multi-Photon Quantum Cryptography Protocol (opens in a new tab)

  6. Modeling and Development of Iterative Reconstruction Algorithms in Emerging X-ray Imaging Technologies

    … advanced multi-channel (MC) image reconstruction algorithm, which reconstructs three object properties simultaneously. We developed an advanced algorithm based on the proximal point algorithm and the augmented Lagrangian method to rapidly solve the MC reconstruction problem. Thirdly, to mitigate …

    wustl Repository record for Modeling and Development of Iterative Reconstruction Algorithms in Emerging X-ray Imaging Technologies (opens in a new tab)

  7. Computational Acceleration for Next Generation Chemical Standoff Sensors Using FPGAs

    … calculation limiting real-time execution of the algorithm is the determination of the projection matrix using the algebraic reconstruction technique (ART). The computation utilizes the inherent parallel nature of ART with an implementation of the algorithm on a field programmable gate array. The …

    temple Repository record for Computational Acceleration for Next Generation Chemical Standoff Sensors Using FPGAs (opens in a new tab)

  8. Akcelerace algoritmů Lattice-Boltzmann pro modelování toku krve v mozku

    Tato práce se zabývá implementací a možnými optimalizacemi metody lattice-Boltzmann. Tato metoda umožňuje modelovat tok kapalin pomocí simulace pohybu fiktivních částic. Práce se zaměřuje na možná vylepšení existujícícho nástroje HemeLB, který se specializuje na simulaci proudění krve v mozku. V …

    brno-tech Repository record for Akcelerace algoritmů Lattice-Boltzmann pro modelování toku krve v mozku (opens in a new tab)

  9. Akcelerace šifrovacích algoritmů pomocí FPGA

    Tato práce se zabývá možností akcelerace šifrovacích algoritmů pomocí rekonfigurovatelných obvodů FPGA a zkoumáním rozdílu rychlosti implementace oproti implementaci softwarové. Práce popisuje základy šifrování a akcelerace algoritmů na FPGA. Dále se zabývá procesem návrhu, implementace, simulace a …

    brno-tech Repository record for Akcelerace šifrovacích algoritmů pomocí FPGA (opens in a new tab)

  10. Hardwarová akcelerace algoritmu pro hledání podobnosti dvou DNA řetězců

    Metody pro zarovnání různých typů bioinformatických sekvencí jsou klíčovou součástí výzkumu v této oblasti. Úlohy jsou časově velmi náročné, a proto má smysl vytvořit hardwarovou platformu pro urychlení těchto výpoětů. Cílem této práce je navržení obecné architektury založené na FPGA technologii, …

    brno-tech Repository record for Hardwarová akcelerace algoritmu pro hledání podobnosti dvou DNA řetězců (opens in a new tab)

  11. Mapping efficient convolutional neural networks to resource-limited system-on-chip field-programmable gate arrays for mobile deep learning application acceleration

    … computation requirement of the deep learning algorithms, and, at the same time, achieve low power consumption. Low parameter and high accuracy Convolutional Neural Networks (CNNs) have made a strong appearance in the deep learning research community. These efficient CNNs are the most suitable …

    greece Repository record for Mapping efficient convolutional neural networks to resource-limited system-on-chip field-programmable gate arrays for mobile deep learning application acceleration (opens in a new tab)

  12. A coprocessor design for the architectural support of non-numeric operations

    … speeds. New special purpose parallel hardware algorithms can yield complexity improvements. This dissertation presents a parallel hardware regular expression searching algorithm which requires linear time and quadratic space compared to software uniprocessor algorithms which require exponential …

    ucf Repository record for A coprocessor design for the architectural support of non-numeric operations (opens in a new tab)