SCREMS: Scientific Computing Environments for Mathematical Sciences

宾夕法尼亚州立大学数学系的一组研究人员将购买对称多处理器（SMP）集群和可视化服务器。新设备将用于支持各种正在进行的数学研究项目，包括数论、偏微分方程的数值解、氢燃料电池的数学建模和数值模拟、流体动力学和材料科学的建模、生物科学的数学建模和数值模拟、新的尖端数值技术和并行算法的分析和实施。这些项目中的大多数模型和应用都是由偏微分方程或常微分方程系统描述的，它们的数值解依赖于需要高内存容量和高内存带宽的密集计算。所购买的共享内存计算机将很好地满足这些要求，并将大大提高提案人的研究能力。受益于新设备的研究项目范围从非常基础的数学研究（如数论）到非常实际的应用（如氢燃料电池的数学建模和数值模拟），这些项目具有至关重要的国家利益（安全和环境）。申请者在系内和整个大学就各种研究课题进行交流和合作。这种合作为培养研究生、博士后和初级教员提供了良好的环境。拟议的设备还将帮助现有的，并为与其他科学和工程研究人员的新联合项目提供坚实的计算基础

A group of researchers in the Department of Mathematics at Penn Statewill purchase a symmetrical multiprocessor (SMP) cluster, and avisualization server. The new equipment will be used to supportvarious ongoing mathematical research projects including numbertheory, numerical solution of partial differential equations,mathematical modeling and numerical simulations for hydrogen fuelcells, modeling in fluid dynamics and material sciences, mathematicalmodeling and numerical simulations in biological sciences, analysisand implementation of new cutting-edge numerical techniques andparallel algorithms. Most of the models and applications from theseprojects are described by systems of partial or ordinary differentialequations and their numerical solutions rely on intensive computationsthat require high memory capacity and high memory bandwidth. Theshared memory computer to be purchased will serve well for theserequirements and will significantly enhance the proposers' researchcapabilities.The research projects that benefit from the new equipment range fromthe very basic mathematical research such as number theory to verypractical applications such as mathematical modeling and numericalsimulations of hydrogen fuel cells that have vital national interests(for security and environment). The proposers communicate andcollaborate on a various research subjects within the department aswell as across the university. Such collaborations provide astimulating environment for the training of graduate students,postdoctoral fellows, as well as junior faculty members. The proposedequipment will also aid existing, and provide solid computational basefor new joint projects with researchers from other sciences andengineering