It is generally desirable for high-performance computing (HPC) applications to be portable between HPC systems, for example to make use of more performant hardware, make effective use of allocations, and to co-locate compute jobs with large datasets. Unfortunately, moving scientific applications between HPC systems is challenging for various reasons, most notably that HPC systems have different HPC schedulers. We introduce PSI/J, a job management abstraction API intended to simplify the construction of software components and applications that are portable over various HPC scheduler implementations. We argue that such a system is both necessary and that no viable alternative currently exists. We analyze similar notable APIs and attempt to determine the factors that influenced their evolution and adoption by the HPC community. We base the design of PSI/J on that analysis. We describe how PSI/J has been integrated in three workflow systems and one application, and also show via experiments that PSI/J imposes minimal overhead.

The Arbitrary Lagrangian-Eulerian (ALE) method is used in a variety of engineering and scientific applications for enabling multi-physics simulations. Unfortunately, the ALE method can suffer from simulation failures that require users to adjust parameters iteratively in order to complete a simulation. In this paper, we present a supervised learning framework for predicting conditions leading to simulation failures. To our knowledge, this is the first time machine learning has been applied to ALE simulations. We propose a novel learning representation for mapping the ALE domain onto a supervised learning formulation. We analyze the predictability of these failures and evaluate our framework using well-known test problems.

Parallel machines are becoming more complex with increasing core counts and more heterogeneous architectures. However, the commonly used parallel programming models, C/C++ with MPI and/or OpenMP, make it difficult to write source code that is easily tuned for many targets. Newer language approaches attempt to ease this burden by providing optimization features such as automatic load balancing, overlap of computation and communication, message-driven execution, and implicit data layout optimizations. In this paper, we compare several implementations of LULESH, a proxy application for shock hydrodynamics, to determine strengths and weaknesses of different programming models for parallel computation. We focus on four traditional (OpenMP, MPI, MPI+OpenMP, CUDA) and four emerging (Chapel, Charm++, Liszt, Loci) programming models. In evaluating these models, we focus on programmer productivity, performance and ease of applying optimizations.

This paper examines whether lossy compression can be used effectively in physics simulations as a possible strategy to combat the expected data-movement bottleneck in future high performance computing architectures. We show that, for the codes and simulations we tested, compression levels of 3--5X can be applied without causing significant changes to important physical quantities.

Abstract The SQuad data structure represents the connectivity of a triangle mesh by its “S table” of about 2 rpt (integer references per triangle). Yet it allows for a simple implementation of expected constant‐time, random‐access operators for traversing the mesh, including in‐order traversal of the triangles incident upon a vertex. SQuad is more compact than the Corner Table (CT), which stores 6 rpt, and than the recently proposed SOT, which stores 3 rpt. However, in‐core access is generally faster in CT than in SQuad, and SQuad requires rebuilding the S table if the connectivity is altered. The storage reduction and memory coherence opportunities it offers may help to reduce the frequency of page faults and cache misses when accessing elements of a mesh that does not fit in memory. We provide the details of a simple algorithm that builds the S table and of an optimized implementation of the SQuad operators.

We present the application of hardware accelerated volume rendering algorithms to the simulation of radiographs as an aid to scientists designing experiments, validating simulation codes, and understanding experimental data. The techniques presented take advantage of 32-bit floating point texture capabilities to obtain solutions to the radiative transport equation for X-rays. The hardware accelerated solutions are accurate enough to enable scientists to explore the experimental design space with greater efficiency than the methods currently in use. An unsorted hexahedron projection algorithm is presented for curvilinear hexahedral meshes that produces simulated radiographs in the absorption-only regime. A sorted tetrahedral projection algorithm is presented that simulates radiographs of emissive materials. We apply the tetrahedral projection algorithm to the simulation of experimental diagnostics for inertial confinement fusion experiments on a laser at the University of Rochester.

We present a new wavelet compression and multiresolution modeling approach for sets of contours (level sets). In contrast to previous wavelet schemes, our algorithm creates a parametrization of a scalar field induced by its contours and compactly stores this parametrization rather than function values sampled on a regular grid. Our representation is based on hierarchical polygon meshes with subdivision connectivity whose vertices are transformed into wavelet coefficients. From this sparse set of coefficients, every set of contours can be efficiently reconstructed at multiple levels of resolution. When applying lossy compression, introducing high quantization errors, our method preserves contour topology, in contrast to compression methods applied to the corresponding field function. We provide numerical results for scalar fields defined on planar domains. Our approach generalizes to volumetric domains, time-varying contours, and level sets of vector fields.