Thesis (Ph. D.)--University of Washington, 2001. / Vita. Includes bibliographical references (p. 132-136).

Proefschrift Universiteit van Amsterdam. / Met bibliogr., lit. opg. - Met samenvatting in het Nederlands.

Proefschrift Universiteit van Amsterdam. / Met lit. opg. - Met samenvatting in het Nederlands.

Proefschrift Amsterdam, Universiteit van Amsterdam. / Met lit. opg. - Met samenvatting in het Nederlands.

Thesis (Ph.D.)--University of Toledo, 2005. / Typescript. "A dissertation [submitted] as partial fulfillment of the requirements of the Doctor of Philosophy degree in Physics." Bibliography: leaves 328-333.

The use of asymmetric multi-core processors with on-chip computational accelerators is becoming common in a variety of environments ranging from scientific computing to enterprise applications. The focus of current research has been on making efficient use of individual systems, and porting applications to asymmetric processors. The use of these asymmetric processors, like the Cell processor, in a cluster setting is the inspiration for the Cell Connector framework presented in this thesis. Cell Connector adopts a streaming approach for providing data to compute nodes with high computing potential but limited memory resources. Instead of dividing very large data sets once among computation resources, Cell Connector slices, distributes, and collects work units off of a master data held by a single large memory machine. Using this methodology, Cell Connector is able to maximize the use of limited resources and produces results that are up to 63.3\% better compared to standard non-streaming approaches. / Master of Science

The p̄/p ratio published by AMS-02 shows an excess of p̄ at rigidities above 60 GV , which can potentially be from WIMP annihilation. To that end, one has to decouple the contribution of secondary p̄ coming from standard p + He/H → p̄ + X process. However models computing the latter component are affected by astrophysical and nuclear uncertainties. To reduce the former, the 10 Be/ 9 Be ratio is calculated by analysing 10 years of AMS-02 Be data. A set of selection criteria is developed to extract a pure sample of Be, and a fit model is constructed to extract the counts of the Be isotopes viz. 7 Be, 9 Be, and 10 Be. Additionally, the detector acceptance is computed using the AMS-MC datasets for Be, and the RTI information from the AMS-02 data is employed to calculate the exposure time. Using these components, the detector level fluxes are calculated for each of the isotopes which is then unfolded using a Bayesian iterative unfolding procedure to extract the particle level fluxes. These fluxes are then utilised to compute the ratios, 10 Be/ 9 Be and 7 Be/Total Be. The former is compared with various theoretical models for computation of galactic halo sizes from the 10 Be/ 9 Be ratio; which suggests that the AMS-02 results severely challenges our understanding of halo sizes. Furthermore, for the measurement of the p̄ production cross-section, p beam at various energies from the CERN Super Proton Synchrotron are directed at a liquid He target within the COMPASS++/AMBER experimental hall. For this purpose, the COMPASS-RICH detector is used for p̄ identification. As such, a Monte-Carlo simulation of the detector is developed in Geant4, and a reconstruction algorithm is written. This work is presented as an appendix to the thesis.

Proefschrift Amsterdam GU. / Met samenvatting in het Engels.

No description available.

<p>The special architecture of the Cell BE processor has made scientists revisit the problem of sorting. This paper implements and tests a variant of merge sort where a number of 2-to-1 mergers are connected in a pipelined tree. For large trees there are many more such mergers than processors which means they must be mapped to the processors in some way. Optimized mappings are tested and results show that changing the model used when optimizing might be beneficiary. It is also shown that the small size of the local storages on the co-processors is not limiting the performance.</p>