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 502 for “"Speedups"”.

  1. Topological Speedups

    … preserving system. In this thesis we study speedups in the topological category. Specifically, we consider minimal homeomorphisms on Cantor spaces. Our main theorem gives conditions on when one such system is a speedup of another. Moreover, the main theorem serves as a topological analogue …

    denver Repository record for Topological Speedups (opens in a new tab)

  2. DEPENDENT ROUNDING SPEEDUPS AND APPLICATIONS

    … of dependent rounding enabled by these speedups. These applications are largely modifications to machine learning algorithms, such as SignSGD, that include dependent rounding in order to improve a rounding method or make a sampling method more consistent. We hope that dependent round- …

    maryland Repository record for DEPENDENT ROUNDING SPEEDUPS AND APPLICATIONS (opens in a new tab)

  3. Quantum Speedups: Structure, Design, and Application

    … studies the circumstances under which quantum speedups can arise from three perspectives. First, we study the structure of the problem. We characterize how a problem's symmetries decide whether it admits a superpolynomial or polynomial quantum speedup. In particular, we show that the …

    maryland Repository record for Quantum Speedups: Structure, Design, and Application (opens in a new tab)

  4. Quantum Machine Learning Without Any Quantum

    … many proposals for attaining large quantum speedups for computationally intensive tasks in machine learning and data analysis. However, it was unclear whether these speedups could be realized in end-to-end applications, as there had been no rigorous way to analyze such speedups. We remedy …

    washington Repository record for Quantum Machine Learning Without Any Quantum (opens in a new tab)

  5. A Sampling-Based Framework for Parallel Mining Frequent Patterns

    … that our parallel algorithms have achieved good speedups on various datasets and the speedups are scalable up to 64 processors on our 64-processor system.

    uiuc Repository record for A Sampling-Based Framework for Parallel Mining Frequent Patterns (opens in a new tab)

  6. Improving Memory Performance Using Intelligent Memory

    … as much as possible. We show that the resulting speedups are close and often higher than ideal speedups on a more expensive machine with two identical main processors.

    uiuc Repository record for Improving Memory Performance Using Intelligent Memory (opens in a new tab)

  7. Study of Fine-Grained, Irregular Parallel Applications on a Many-Core Processor

    … demonstrates the possibility of obtaining strong speedups for a variety of parallel applications versus the best serial and parallel implementations on commodity platforms. These results were obtained using the PRAM-inspired Explicit Multi-Threading (XMT) many-core computing platform, which is …

    maryland Repository record for Study of Fine-Grained, Irregular Parallel Applications on a Many-Core Processor (opens in a new tab)

  8. Modified Chebyshev-Picard Iteration Methods for Solution of Initial Value and Boundary Value Problems

    … better accuracy as well as orders of magnitude speedups, prior to parallel implementation. Modifying the algorithm to do double integration for second order systems, and using orthogonal polynomials to approximate position states lead to additional speedups. Finally, introducing perturbation …

    tamu Repository record for Modified Chebyshev-Picard Iteration Methods for Solution of Initial Value and Boundary Value Problems (opens in a new tab)

  9. Applications and verification of quantum computers

    … classical computers. While rigorously proving speedups over existing classical algorithms demonstrates the usefulness of quantum computers, analyzing the limits on efficient processes for computational tasks allows us to better understand the power of quantum computation. Indeed, hard problems …

    maryland Repository record for Applications and verification of quantum computers (opens in a new tab)

  10. Bendrosios atminties lygiagretaus programavimo modelių analizė ir eksperimentinis tyrimas /

    … parallel programming models. Finally, problems’ speedups were experimentally evaluated and the efficiency of models were identified for each problem. After completing these tasks, it was found that different parallel programming models have varying speedups for different types of problems. …

    vilnius Repository record for Bendrosios atminties lygiagretaus programavimo modelių analizė ir eksperimentinis tyrimas / (opens in a new tab)

  11. Performance of multicomputers using high-speed communication links

    … algorithms, some of which show almost linear speedups. For fine-grained algorithms, the high overhead in message passing proves to be a serious bottleneck, resulting in less than linear speedups.

    rice Repository record for Performance of multicomputers using high-speed communication links (opens in a new tab)

  12. Paralelização da reconstrução de geometrias moleculares

    … results were encouraging, gains were obtained (speedups) in the vast majority of the tests performed, in some of these reached speedups above 12, which demonstrates the effectiveness of the approaches employed.

    brazil-uerj Repository record for Paralelização da reconstrução de geometrias moleculares (opens in a new tab)

  13. Multi-tree Monte Carlo methods for fast, scalable machine learning

    … kernel conditional density estimation, showing speedups as high as 10⁵ on up to 1 million points. 2. Fast training for general kernel estimators (kernel density estimation, kernel regression, etc.), showing speedups as high as 10⁶ on tens of millions of points. 3. Fast singular value …

    gatech Repository record for Multi-tree Monte Carlo methods for fast, scalable machine learning (opens in a new tab)

  14. Harnessing the power of graphics processing units to accelerate computational chemistry

    … ERI and ERI derivative computation yielded speedups of 10~100 times relative to traditional CPU execution. An accuracy analysis using double-precision calculations demonstrates the accuracy is satisfactory for most applications. Besides ab inito quantum chemistry methods, GPU programming can …

    msu Repository record for Harnessing the power of graphics processing units to accelerate computational chemistry (opens in a new tab)

  15. Parallel Algorithms for VHDL Simulation

    … This technique gives us acceptable speedups, if the partitioning and placement of partitions on processors is done carefully. Partitioning and placement issues are examined thoroughly in this thesis.

    uiuc Repository record for Parallel Algorithms for VHDL Simulation (opens in a new tab)

  16. Architectures specific compilation for efficient execution of esterel

    … reduction in generated code size while gaining speedups compared to the pure software approach. Another aspect of compilation of Esterel that has been relatively unexplored is the implementation of its concurrency with true parallelism on multi-core architectures. There have been minimal …

    auckland-ms Repository record for Architectures specific compilation for efficient execution of esterel (opens in a new tab)

  17. Accelerating the Smith–Waterman Algorithm with the Actor Model

    … tasks, achieving near-linear scalability, with speedups of up to 28× on 40 cores for the BRCA1 dataset, outperforming OpenMP (15.14×) and MPI (14×). OpenMP proved most efficient for intra-alignment tasks, completing sequence alignment in 4.91 seconds for sequences of 51,000 and 53,000 …

    sask Repository record for Accelerating the Smith–Waterman Algorithm with the Actor Model (opens in a new tab)

  18. An Incompressible Navier-Stokes Equations Solver on the GPU Using CUDA

    … CPU implementations. For the iterative solvers, speedups of between six and thirteen were achieved against the MKL CPU library, and the implemented methods beats existing open source GPU implementations of equivalent methods. For the full Navier-Stokes solver, speedups of up to a factor twelve …

    chalmers Repository record for An Incompressible Navier-Stokes Equations Solver on the GPU Using CUDA (opens in a new tab)

  19. Multi-harmonic Modeling of Low-power PWM DC-DC Converter

    … harmonics, providing additional simulation speedups. For a number of converter designs, the proposed model obtains up to 10x runtime speedups over transistor-level transient simulation with a maximum output voltage error less than 4%.

    tamu Repository record for Multi-harmonic Modeling of Low-power PWM DC-DC Converter (opens in a new tab)

  20. Bandwidth Aggregation Across Multiple Smartphone Devices

    … of each other. Deployed on up to three devices, speedups of up to 1.82x were achieved for downloading a single, 10mb file. Webpage loading saw speedups of up to 1.55x.

    calpoly Repository record for Bandwidth Aggregation Across Multiple Smartphone Devices (opens in a new tab)

Page 1 of 26