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 258 for “"stencil"”.

  1. Tiling optimizations for stencil computations

    … the techniques of tiling optimizations for stencil programs. Traditionally, research on tiling optimizations mainly focuses on tessellating tiling, atomic tiles and regular tile shapes. This thesis studies several novel tiling techniques which are out of the scope of traditional research. In …

    uiuc Repository record for Tiling optimizations for stencil computations (opens in a new tab)

  2. Extending and validating the stencil processing unit

    Stencils are an important class of programs that appear in the core of many scientific and general-purpose applications. These compute-intensive kernels can benefit heavily from the massive compute power of accelerators like the GPGPU. However, due to the absence of any form of on-chip …

    colostate Repository record for Extending and validating the stencil processing unit (opens in a new tab)

  3. The paper stencil method of silk screen printing

    … materials of this thesis are concerned with the stencil method of silk screen printing. They are intended for use by high school teachers. The research examines both the creative and technical aspects of printing designs and compositions on a large scale. Paper stencil variations are examined as …

    portland-state Repository record for The paper stencil method of silk screen printing (opens in a new tab)

  4. Efficient Domain Partitioning for Stencil-based Parallel Operators

    … that “close to 2-D” partitions are optimal for stencil-based codes on structured 3-D domains and that it is necessary to optimize for both minimizing cache-misses and communication. We advise that in light of the evolving hardware-software ecosystem, there is an imperative need to re-examine …

    whiterose Download PDF for Efficient Domain Partitioning for Stencil-based Parallel Operators (opens in a new tab)

  5. High efficiency metal stencil printed silicon solar cells

    … crystalline silicon solar cells by using metal stencil printing technique to replace screen printing or electroless plating techniques for implementing crystalline silicon solar cell front metallization. The developed laser-cut stainless steel stencils successfully challenge two of the cell …

    unsw Repository record for High efficiency metal stencil printed silicon solar cells (opens in a new tab)

  6. Automatic Loop Tuning and Memory Management for Stencil Computations

    … Of particular interest is its performance for stencil computations, such as those found in signal processing and computer vision tasks. A stencil is a loop in which the output value is updated at each position of an array by taking a weighted function of its neighbors. Efficiently mapping …

    south-carolina Repository record for Automatic Loop Tuning and Memory Management for Stencil Computations (opens in a new tab)

  7. Towards automatic compilation for energy efficient iterative stencil computations

    … of an important class of programs called "Stencil Computations", which occur frequently in a wide variety of scientific applications. We target the compute intensive stencil computations, and seek to automatically produce codes that minimize energy consumption. Two main energy consumption …

    colostate Repository record for Towards automatic compilation for energy efficient iterative stencil computations (opens in a new tab)

  8. Separating implementation concerns in stencil computations for semiregular grids

    In atmospheric and ocean simulation programs, stencil computations occur on semiregular grids where subdomains of the grid are regular (i.e. stored in an array), but boundaries between subdomains connect in an irregular fashion. Implementations of stencils on semiregular grids often have grid …

    colostate Repository record for Separating implementation concerns in stencil computations for semiregular grids (opens in a new tab)

  9. Tuned and asynchronous stencil kernels for CPU/GPU systems

    We describe heterogeneous multi-CPU and multi-GPU implementations of Jacobi's iterative method for the 2-D Poisson equation on a structured grid, in both single- and double-precision. Properly tuned, our best implementation achieves 98% of the empirical streaming GPU bandwidth (66% of peak) on a …

    gatech Repository record for Tuned and asynchronous stencil kernels for CPU/GPU systems (opens in a new tab)

  10. Automatic Parallelization of Tiled Stencil Loop Nests on GPUs

    … parallelizes loop nests; especially stencil kernels, into efficient GPU code by loop tiling transformations which the polyhedral model describes. To enhance parallel performance, we introduce three practically efficient techniques to process different types of loop nests. The …

    unsw Repository record for Automatic Parallelization of Tiled Stencil Loop Nests on GPUs (opens in a new tab)

  11. PIMS: A lightweight processing-in-memory accelerator for stencil computations

    Stencil computation is a classic computational kernel present in many high-performance scientific applications, like image processing and partial differential equation solvers (PDE). A stencil computation sweeps over a multi-dimensional grid and repeatedly updates values associated with points …

    ttu Repository record for PIMS: A lightweight processing-in-memory accelerator for stencil computations (opens in a new tab)

  12. Wave Equation Based Stencil Optimizations on a Multi-core CPU

    Wave propagation stencil kernels are engines of seismic imaging algo- rithms. These kernels are both compute- and memory-intensive. This work targets improving the performance of wave equation based stencil code parallelized by OpenMP on a multi-core CPU. To achieve this goal, we explored two …

    rice Repository record for Wave Equation Based Stencil Optimizations on a Multi-core CPU (opens in a new tab)

  13. GPU support for automatic generation of finite-differences Stencil Kernels

    … imposed by evolving algorithms based on stencil computations, such as Full Waveform Inversion and Reverse Time Migration. Graphical processing units (GPUs) are an attractive architectural target for stencil computations because of its high degree of data parallelism. However, the rapid …

    brazil-ufrn Repository record for GPU support for automatic generation of finite-differences Stencil Kernels (opens in a new tab)

  14. Screen and stencil print technologies for industrial N-type silicon solar cells

    To ensure that photovoltaics contributes significantly to future world energy production, the cost per watt of producing solar cells needs to be drastically reduced. The use of n-type silicon wafers in conjunction with industrial print technology has the potential to lower the cost per watt of …

    unsw Repository record for Screen and stencil print technologies for industrial N-type silicon solar cells (opens in a new tab)

  15. Polynomial time optimal algorithm for stencil row planning in e-beam lithography

    … (CP) technique has been proposed, and its stencil planning can be optimized with awareness of overlapping characters. However, the top-level 2D stencil planning problem has been proven to be an NP-hard problem. As its most essential step, the 1D row ordering is believed hard as well, and no …

    uiuc Repository record for Polynomial time optimal algorithm for stencil row planning in e-beam lithography (opens in a new tab)

  16. Enabling Computational Methods for Discretization of Partial Differential Equation Models Using Stencil Composition

    … along with their associated weights is called a "stencil". This dissertation explores a computational method using a certain FDM technique, called "stencil composition", whereby one stencil is composed with another stencil, enabling discretization of PDE-based models. Contributions towards the …

    buffalo Repository record for Enabling Computational Methods for Discretization of Partial Differential Equation Models Using Stencil Composition (opens in a new tab)

  17. Optimization of Reactive Ion Etching to Fabricate Silicon Nitride Stencil Masks in SF6 Plasma

    Stencil masks are used to print ultra-high resolution patterns using helium ion/atom beam lithography and are often manufactured from thin, free-standing silicon nitride membranes. The masks have sub-200nm openings etched through the thickness of the membrane using a reactive ion etch (RIE) process …

    houston Repository record for Optimization of Reactive Ion Etching to Fabricate Silicon Nitride Stencil Masks in SF6 Plasma (opens in a new tab)

Page 1 of 13