Theses and Dissertations from UMD
Permanent URI for this communityhttp://hdl.handle.net/1903/2
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
3 results
Search Results
Item PARALLEL COMPUTING WITH P2P DESKTOP GRIDS(2015) Jackson, Gary Lee; Sussman, Alan; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Tightly-coupled parallel computing is an important tool for problem solving. Structured peer-to-peer network overlays are failure-tolerant and have a low admin- istrative burden. This work seeks to unite the two. First, I present a completely decentralized algorithm for parallel job scheduling and load balancing in distributed peer-to-peer environments. This algorithm is useful for meta-scheduling across known clusters and scheduling on desktop grids. To accomplish this, I build on previous work to route jobs to appropriate resources then use the new algorithm to start parallel jobs and balance load across the grid. I also discuss what constitutes useful clusterings for this algorithm as well as inherent scaling limitations. Ultimately, I show that my algorithm performs comparably to one using centralized load balancing with global up-to-date information. The principal contribution of this work is that the parallel job scheduling is completely decentralized, which is not featured in previous work, and enables reliable ad hoc sharing of distributed resources to run parallel computations. Second, I show how clusters of computers can be found dynamically by using an existing latency prediction technique coupled with a new refinement algorithm. Several latency prediction techniques are compared experimentally. One, based on a tree metric space embedding, is found to be superior to the others. Nevertheless, I show that it is not quite accurate enough. To solve this problem, I present a refinement algorithm for producing quality clusters while still maintaining bounds for the amount of information any given node must store about other nodes. I show that clusters derived this way have scheduler performance comparable to those chosen statically with global knowledge. Lastly, I discuss previously undiscovered under-specifications in the Content Addressable Network (CAN) structured peer to peer system. In high-churn situ- ations, the CAN allows stale information and changes to the overlay structure to create routing problems. I show solutions to these two problems, as well as discuss other issues that may also disrupt a CAN.Item Automated Floating-Point Precision Analysis(2014) Lam, Michael Oneil; Hollingsworth, Jeffrey K; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)As scientific computation continues to scale upward, correct and efficient use of floating-point arithmetic is crucially important. Users of floating-point arithmetic encounter many problems, including rounding error, cancellation, and a tradeoff between performance and accuracy. This dissertation addresses these issues by introducing techniques for automated floating-point precision analysis. The contributions include a software framework that enables floating-point program analysis at the binary level, as well as specific techniques for cancellation detection, mixed-precision configuration, and reduced-precision sensitivity analysis. This work demonstrates that automated, practical techniques can provide insights regarding floating-point behavior as well as guidance towards acceptable precision level reduction. The tools and techniques in this dissertation represent novel contributions to the fields of high performance computing and program analysis, and serve as the first major step towards the larger vision of automated floating-point precision and performance tuning.Item Development of An Empirical Approach to Building Domain-Specific Knowledge Applied to High-End Computing(2006-07-23) Hochstein, Lorin Michael; Basili, Victor R; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This dissertation presents an empirical approach for building and storing knowledge about software engineering through human-subject research. It is based on running empirical studies in stages, where previously held hypotheses are supported or refuted in different contexts, and new hypotheses are generated. The approach is both mixed-methods based and opportunistic, and focuses on identifying a diverse set of potential sources for running studies. The output produced is an experience base which contains a set of these hypotheses, the empirical evidence which generated them, and the implications for practitioners and researchers. This experience base is contained in a software system which can be navigated by stakeholders to trace the "chain of evidence" of hypotheses as they evolve over time and across studies. This approach has been applied to the domain of high-end computing, to build knowledge related to programmer productivity. The methods include controlled experiments and quasi-experiments, case studies, observational studies, interviews, surveys, and focus groups. The results of these studies have been stored in a proof-of-concept system that implements the experience base.