Scientific computing is used frequently in an increasing number of disciplines to accelerate scientific discovery. Many such computing problems involve the numerical solution of partial differential equations (PDE). In this thesis we explore and develop methodology for high-performance implementations of PDE solvers for shared-memory multiprocessor architectures. We consider three realistic PDE settings: solution of the Maxwell equations in 3D using an unstructured grid and the method of conjugate gradients, solution of the Poisson equation in 3D using a geometric multigrid method, and solution of an advection equation in 2D using structured adaptive mesh refinement. We apply software optimization techniques to increase both parallel efficiency and the degree of data locality. In our evaluation we use several different shared-memory architectures ranging from symmetric multiprocessors and distributed shared-memory architectures to chip-multiprocessors. For distributed shared-memory systems we explore methods of data distribution to increase the amount of geographical locality. We evaluate automatic and transparent page migration based on runtime sampling, user-initiated page migration using a directive with an affinity-on-next-touch semantic, and algorithmic optimizations for page-placement policies. Our results show that page migration increases the amount of geographical locality and that the parallel overhead related to page migration can be amortized over the iterations needed to reach convergence. This is especially true for the affinity-on-next-touch methodology whereby page migration can be initiated at an early stage in the algorithms. We also develop and explore methodology for other forms of data locality and conclude that the effect on performance is significant and that this effect will increase for future shared-memory architectures. Our overall conclusion is that, if the involved locality issues are addressed, the shared-memory programming model provides an efficient and productive environment for solving many important PDE problems.

No description available.

For many years, community colleges that chose to offer community college baccalaureate (CCB) programs were looked upon in a negative light (Rice, 2015). However, as the need for specialized baccalaureates within specific fields and job markets have continued to grow (McKee, 2005), CCB programs are becoming more widely accepted throughout the United States. In spite of this paradigm shift, Mississippi is one of the remaining states that have not embraced the idea of CCB programs, in spite of its statistical deficiency in regards to baccalaureate degree holding citizens (Williams, 2010). The focus of this study was to explore the perceptions of community college administrators in Mississippi with regards to the influence of CCB programs to the community college mission of institutions in their state. This study indicates that administrators in Mississippi recognize the benefits of offering CCB programs, but do not want CCB programs to take away from the well-established statewide higher education system through mission creep. Many of the strong position statements received overwhelmingly neutral responses. In contrast, Administrators who chose to give their opinion indicated that they are not familiar with how CCB programs are implemented, and do not believe that Mississippi is ready for CCB programs across the state. However, respondents felt that the community college mission is always evolving, should meet students’ needs, and varies from location to location. The findings also show that administrators are favorable to the piloting of CCB programs at a few (1-2) institutions, even though they believe the programs will take funding away from current programs and do not want community colleges evolving into 4-year institutions. The study also concludes that there is a significant difference between institution size and survey questions #18 and #20. There is also a significant difference between length of time in the community college sector and survey questions #15, #17, and #18.