Hello, A yearly allocation for the LCRC cluster has been requested with the following updated information: Submitter/PI: Paul Fischer Project Name: Nek5000 Division: MCS Project title: Scalable CFD Algorithms Associated funding: Applied Math Research Program, Nuclear Energy Advanced Modeling and Simulation Other Systems: ALCF Intrepid (BG/P), 128-core Linux cluster, Cosmea Science: Our mission is to develop and deploy scalable algorithms for simulation-based science applications that rely on numerical solution of partial differential equations. Our primary vehicle for algorithm development is the fluid/thermal simulation code, Nek5000, and its off-shoots, NekCEM (for computational electromagnetics) and NekLBM (for lattice Boltzmann methods). There are approximately 30 research groups worldwide currently using Nek5000. We use Nek5000---and the science applications brought to us through our user community---as vehicles for the development and test of new numerical algorithms that include stabilized high-order methods, scalable linear solvers, advanced timestepping methods, and so forth. We emphasize that these algorithms cannot be developed in isolation from applications, as many of the relevant issues do not arise at small scale or in simple model problems devoid of complex physics and/or geometry. Thus, to address algorithmic issues at the forefront of science-based simulation we require a code that is capable of solving problems _at_scale_ and that is sufficiently flexible to allow adaptation to new physics. Project description: Nek5000 is a petascale fluid/thermal simulation code used for a host of applications including reactor thermal hydraulics, combustion, MHD, oceanography, spatiotemporal chaos, and vascular flow modeling. Nek5000 is a grid-based PDE (partial differential equation) solver in three space dimensions and time. The code has long been at the forefront of high-order methods and scalable algorithms. It was one of the first comprehensive software tools developed for distributed memory parallel platforms. It pioneered the development of high-order discretizations that, because of their ability to accurately capture interacations over a broad range of scales, are now deemed an essential ingredient of petascale simulation science and that are being adapted across virtually all disciplines (e.g., fusion, aeronautics, biofluids and geophysics). We have demonstrated > 80% parallel efficiency on BG/P (strong scaling) out to P=131,072 processors, using only 7300 points/processor at the largest scale. Nek5000 was recognized with a Gordon Bell award in 1999 for scalability and algorithmic quality. Some of the science applications we anticipate addressing in the coming year are: boundary-layer MHD, non-hydrostatic modeling of ocean currents, and film cooling for gas turbine blades. This latter problem is likely to require 50-100K core-hours. Most of the simulations, however, will be performed by the Texas A&M group leading the project with their own compute resources. This is our standard model -- get the problem running, and then turn it over to the research group in charge. In the past, this model has led to very successful collaborations in oceanography ( > 12 publications), spatiotemporal chaos ( > 12 publications), and MHD ( 4 publications and two INCITE awards). We note that we have access to a dedicated 128-core linux cluster (under a nuclear engineering project) and to resource on BG/P through INCITE and discretionay allocations. This request is to address mid-range capabilities -- particularly for those applications that would not fit on the 128-core cluster. Project URL: http://www.mcs.anl.gov/~fischer/sem1b Current FY Hours Used: undetermined amount New FY Requested allocation: 350000 Justification: Thank You, The LCRC Accounts System