Petaflops Opportunities for the NASA Fundamental Aeronautics Program (Invited)

Abstract

The premise of this paper is the observation that the engineering community in general, and the NASA aeronautics program in particular, have not been active participants in the renewed interest in high performance computing at the national level. Advocacy for high performance computing has increasingly been taken up by the science community with the argument that computational methods are becoming a third pillar of scientific discovery alongside theory and experiment. Computational engineering, on the other hand, has continually been relegated to a set of mature software tools which run on commodity hardware, with the notion that engineering problems are not complex enough to warrant the deployment of state-of-the-art hardware on such a vast scale. We argue that engineering practices can benefit equally from an aggressive program in high performance computational methods, and that these problems are at least as important as science problems, particularly with regards to any national competitiveness agenda. Because NASA aeronautics has historically been a principal driver of computational engineering research and development, the current situation represents an opportunity for the NASA aeronautics program to resume its role as a leading advocate for high performance computational engineering at the national level. We outline a sample set of Grand Challenge problems which are used to illustrate the potential benefits a reinvigorated program could produce, and use these examples to identify critical barriers to progress and required areas of investment. We conclude by noting that other communities have spent significant efforts in formulating the case for increased investment in high performance computing activities, and that a similar roadmap will be required for the engineering community.

Enabling the environmentally clean air transportation of the future: a vision of computational fluid dynamics in 2030

“…(ii) Physical modelling Advances in the physical modelling of turbulence for separated flows, transition and combustion are critically needed to achieve the desired state of CFD in 2030 [8,[12][13][14][15][16][17]. For the advancement of turbulent flow simulation, three separate tracks for research are proposed: RANS-based turbulence treatments; hybrid RANS/LES approaches where the entire boundary layer is resolved with RANS-based models, and the outer flow is resolved with LES models; and LES, including both wall-modelled (WMLES) and wall-resolved (WRLES).…”

A Higher-Order Unstructured Finite Volume Solver for Three-Dimensional Compressible Flows

“…An hp-adaptive method increases the local order of accuracy p and decreases the mesh size h at only certain regions of the domain. In the context of design and optimization, thousands of simulations might be required for optimizing a subject geometry [42]. Thus, even a small runtime improvement for a single simulation can result in a considerable reduction of the overall resource consumption.…”

Modeling Full-Envelope Aerodynamics of Small UAVs in Realtime

“…8 One might envision using a brute force CFD analyses to generate lookup table data for a full vehicle, but the computational resources needed to cover a typical flight envelope in a reasonable period of time exceed current-day capabilities. [9][10][11] Although modeling agile static and dynamic flight presents a plethora of challenges for CFD techniques, some new approaches might make it more feasible to consider in the future. 12 Aircraft system identification methods, 13,14 as with all of the aforementioned techniques, could be used to provide insight in special cases, but general application of the system ID methods to full-envelope aerodynamics modeling would be daunting, and it has not been proposed.…”