Search

This paper presents HyperCODA, the hypersonics extension to the flow solver CODA (CFD for ONERA, DLR and Airbus). Similar to the spacecraft extensions of TAU, HyperCODA extends CODA for applications at high Mach numbers, including non-ideal gas thermodynamics, gas mixtures, and chemistry. The paper discusses simulations demonstrating numerical convergence and stability properties, as well as a supersonic rocket retropropulsion maneuver. Cross-code comparisons are made against the established DLR TAU code.

Aeroelasticity simulations increase in importance for aircraft design, requiring an efficient coupling of computational fluid dynamics (CFD) with computational structure mechanics (CSM) solvers. This contribution investigates the scalability of a high-fidelity CFD-CSM toolchain on modern high-performance computing (HPC) architectures. It consists of DLR's TAU solver for fluid dynamics simulations [1], and FlowSimulator [2] components for the incorporation of precomputed structural normal mode data, as well as for the underlying mesh deformations. The computational performance of the entire simulation pipeline is evaluated using a single measurement suite, allowing to identify bottlenecks of individual components and differences in their scalability. Preliminary improvements are realized via hybrid parallelization. Although this study focuses on a specific toolchain, key findings about scalability issues are relevant for complex CFD-CSM or other coupled simulations in general.

High-order methods gain more and more attention in computational fluid dynamics. Among these, spectral element methods and discontinuous Galerkin methods introduce element-wise approximations by means of a polynomial basis. This leads to a small number of operators consuming a large portion of the runtime of CFD applications. The present paper addresses tensor-product bases which are among the most frequent in these applications. Various implementations are developed and performance tests conducted for the interpolation operator, the Helmholtz operator, and the fast diagonalization operator. For each, up to 50% of the peak performance is attained, beating matrix-matrix multiplication for every polynomial degree relevant for simulations. This extremely high efficiency of the method developed is then demonstrated on a combustion problem with 1.72 · 109 mesh points.

This paper investigates static load balancing models for CPU-GPU coupling from a computational fluid dynamics perspective. While able to generate a benefit, traditional load balancing models are found to be too inaccurate to predict the runtime of a preconditioned conjugate gradient solver. Hence, an expanded model is derived that accounts for the multi-step nature of the solver, i.e. several communication barriers per iteration. It is able to predict the runtime to a margin of 5%, rendering CPU-GPU coupling better predictable so that load balancing can be improved substantially.

The prospect of wildly heterogeneous computer systems has led to a renewed discussion of programming approaches in high-performance computing, of which computational fluid dynamics is a major field. The challenge consists in harvesting the performance of all available hardware components while retaining good programmability. In particular the use of graphic cards is an important trend. This is addressed in the present paper by devising a hybrid programming model to create a heterogeneous data-parallel computation with a single source code. The concept is demonstrated for a one-dimensional spectral-element discretization of a fluid dynamics problem. To exploit the additional hardware available when coupling GPGPU-accelerated processes with excess CPU cores, a straight-forward load balancing model for such heterogeneous environments is developed. The paper presents a large number of run time measurements and demonstrates that the achieved performance gains are close to optimal. This provides valuable information for the implementation of fluid dynamics codes on modern heterogeneous hardware.

International audience; Many numerical algorithms are naturally expressed as operations on tensors (i.e. multi-dimensional arrays). Hence, tensor expressions occur in a wide range of application domains , e.g. quantum chemistry and physics; big data analysis and machine learning; and computational fluid dynamics. Each domain, typically, has developed its own strategies for efficiently generating optimized code, supported by tools such as domain-specific languages, compilers, and libraries. However, strategies and tools are rarely portable between domains, and generic solutions typically act as " black boxes " that offer little control over code generation and optimization. As a consequence, there are application domains without adequate support for easily generating optimized code, e.g. computational fluid dynamics. In this paper we propose a generic and easily extensible intermediate language for expressing tensor computations and code transformations in a modular and generative fashion. Beyond being an intermediate language, our solution also offers meta-programming capabilities for experts in code optimization. While applications from the domain of computational fluid dynamics serve to illustrate our proposed solution, we believe that our general approach can help unify research in tensor optimizations and make solutions more portable between domains.

Current research in computational fluid dynamics focuses on higher-order methods. These possess a more extensive coupling between degrees of freedom, resulting in a larger runtime per degree of freedom compared to low-order methods. This work tries to tackle this issue by combining the static condensation method with tensor-product and sum factorization, leading to a well-scaling solver for the Helmholtz equation.