Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “supercomputer”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,657 records · Page 92

Extreme-Scale Bayesian Inference for Uncertainty Quantification of Complex Simulations

Uncertainty quantification (UQ)—that is, quantifying uncertainties in complex mathematical models and their large-scale computational implementations—is widely viewed as one of the outstanding challenges facing the field of CS&E over the coming decade. The EUREKA project set to address the most difficult class of UQ problems: those for which both the underlying PDE model as well as the uncertain parameters are of extreme scale. In the project we worked on these extreme-scale challenges in the following four areas: 1. Scalable parallel algorithms for sampling and characterizing the posterior distribution that exploit the structure of the underlying PDEs and parameter-to-observable map. These include structure-exploiting versions of the randomized maximum likelihood method, which aims to overcome the intractability of employing conventional MCMC methods for solving extreme-scale Bayesian inversion problems by appealing to and adapting ideas from large-scale PDE-constrained optimization, which have been very successful at exploring high-dimensional spaces. 2. Scalable parallel algorithms for construction of prior and likelihood functions based on learning methods and non-parametric density estimation. Constructing problem-specific priors remains a critical challenge in Bayesian inference, and more so in high dimensions. Another challenge is construction of likelihood functions that capture unmodeled couplings between observations and parameters. We will create parallel algorithms for non-parametric density estimation using high dimensional N-body methods and combine them with supervised learning techniques for the construction of priors and likelihood functions. 3. Bayesian inadequacy models, which augment physics models with stochastic models that represent their imperfections. The success of the Bayesian inference framework depends on the ability to represent the uncertainty due to imperfections of the mathematical model of the phenomena of interest. This is a central challenge in UQ, especially for large-scale models. We propose to develop the mathematical tools to address these challenges in the context of extreme-scale problems. 4. Parallel scalable algorithms for Bayesian optimal experimental design (OED). Bayesian inversion yields quantified uncertainties in the model parameters, which can be propagated forward through the model to yield uncertainty in outputs of interest. This opens the way for designing new experiments to reduce the uncertainties in the model parameters and model predictions. Such experimental design problems have been intractable for large-scale problems using conventional methods; we will create OED algorithms that exploit the structure of the PDE model and the parameter-to-output map to overcome these challenges. Parallel algorithms for these four problems were created, analyzed, prototyped, implemented, tuned, and scaled up for leading-edge supercomputers, including UT-Austin’s own 10 petaflops Stampede system, ANL’s Mira system, and ORNL’s Titan system. While our focus is on fundamental mathematical/computational methods and algorithms, we will assess our methods on model problems derived from several DOE mission applications, including multiscale mechanics and ice sheet dynamics.

97 MATHEMATICS AND COMPUTING↗

PLATO (Parallel Load Assignment Tool): A Parallel Workload Partitioner for Particle-based Methods

A key first step in many large-scale high-performance scientific computing applications is the distribution of the computational domain across all participating processors of a parallel computing platform such as a shared memory machine, cluster or a tightly-coupled supercomputer. The primary goal of such a partitioning step is to ensure that the computational work performed by each process remains load-balanced throughout the execution of the parallel application. In this project, a general-purpose parallel partitioning tool, code-named PLATO, was designed and implemented. PLATO assumes that the workload is a set of points in an n-dimensional metric space. These points are abstractions of computational units that may represent point-like computational units such as celestial objects in astrophysics, atoms in materials sciences and molecules in biology/chemistry, or may represent more abstract computational units such as grid points in finite difference methods, grid elements in finite element methods or n-dimensional points in the feature space of a host of other applications. PLATO supports several key and useful capabilities, namely: (a) multiple load partitioning strategies, (b) support for arbitrary user-defined processor topology, (c) pre-fetching data from neighboring processors based on user-defined parameters, and (d) support for arbitrary number and types of attributes associated with each point in the computational domain. PLATO is implemented in the C programming language using Message Passing Interface (MPI) for inter-processor communications and its parallel performance tested on up to 48 processors of a shared memory machine. This report includes a detailed performance study of PLATO using parallel speedup and iso-efficiency as the two main metrics of parallel performance. In addition, a user manual and DOXYGEN generated code documentation have been included for completeness.

97 MATHEMATICS AND COMPUTING↗

CRADA Final Report: Weld Predictor App

Welding is an important manufacturing process used in a broad range of industries and market sectors, including automotive, aerospace, heavy manufacturing, medical, and defense. During welded fabrication, high localized heat input and subsequent rapid cooling result in the creation of residual stresses and distortion. These residual stresses can significantly affect the fatigue resistance, cracking behavior, and load-carrying capacity of welded structures during service. Further, additional fitting and tacking time is often required to fit distorted subassemblies together, resulting in non-value added cost. Using trial-and-error methods to determine which welding parameters, welding sequences, and fixture designs will most effectively reduce distortion is a time-consuming and expensive process. For complex structures with many welds, this approach can take several months. For this reason, efficient and accurate methods of mitigating distortion are in-demand across all industries where welding is used. Analytical and computational methods and commercial software tools have been developed to predict welding-induced residual stresses and distortion. Welding process parameters, fixtures, and tooling can be optimized to reduce the HAZ softening and minimize weld residual stress and distortion, improving performance and reducing design, fabrication and testing costs. However, weld modeling technology tools are currently accessible only to engineers and designers with a background in finite element analysis (FEA) who work with large manufacturers, research institutes, and universities with access to high-performance computing (HPC) resources. Small and medium enterprises (SMEs) in the US do not typically have the human and computational resources needed to adopt and utilize weld modeling technology. To allow an engineer with no background in FEA and SMEs to gain access to this important design tool, EWI and the Ohio Supercomputer Center (OSC) developed the online weld application software tool “WeldPredictor” ( https://eweldpredictor.ewi.org ). About 1400 users have tested this application. This project marked the beginning of development on the next version of WeldPredictor that addresses many outstanding features of the original, including 3D models, allow more material hardening laws, model material phase transformation, and uses open source finite element solvers to quickly solve problems (as opposed to expensive commercial tools).

42 ENGINEERING↗

Exploring Flexible Communications for Streamlining DNN Ensemble Training Pipelines

Parallel training of a Deep Neural Network (DNN) ensemble on a cluster of nodes is a common practice to train multiple models in order to construct a model with a higher prediction accuracy. Existing ensemble training pipelines can perform a great deal of redundant operations, resulting in unnecessary CPU usage, or even poor pipeline performance. In order to remove these redundancies, we need pipelines with more communication flexibility than existing DNN frameworks can provide. This project investigates a series of designs to improve pipeline flexibility and adaptivity, while also increasing performance. We implement our designs using Tensorflow with Horovod, and test it using several large DNNs in a large scale GPU cluster, Titan supercomputer at Oak Ridge National Lab. Our results show that the CPU time spent during training is reduced by 2-11X. Furthermore, our implementation can achieve up to 10X speedups when CPU core limits are imposed. Our best pipeline also reduces the average power draw of the ensemble training process by 5-16% when compared to the baseline.

97 MATHEMATICS AND COMPUTING↗

Sparse Matrix-Matrix Multiplication on Multilevel Memory Architectures: Algorithms and Experiments

Architectures with multiple classes of memory media are becoming a common part of mainstream supercomputer deployments. So called multi-level memories offer differing characteristics for each memory component including variation in bandwidth, latency and capacity. This paper investigates the performance of sparse matrix multiplication kernels on two leading highperformance computing architectures — Intel's Knights Landing processor and NVIDIA's Pascal GPU. We describe a data placement method and a chunking-based algorithm for our kernels that exploits the existence of the multiple memory spaces in each hardware platform. We evaluate the performance of these methods w.r.t. standard algorithms using the auto-caching mechanisms Our results show that standard algorithms that exploit cache reuse performed as well as multi-memory-aware algorithms for architectures such as Ki\iLs where the memory subsystems have similar latencies. However, for architectures such as GPUS where memory subsystems differ significantly in both bandwidth and latency, multi-memory-aware methods are crucial for good performance. In addition, our new approaches permit the user to run problems that require larger capacities than the fastest memory of each compute node without depending on the software-managed cache mechanisms.

97 MATHEMATICS AND COMPUTING↗

OpenSHMEM Implementation of IOR Benchmark

The benchmarking effort within the Computational Research & Development Programs at the Oak Ridge National Laboratory (ORNL) seeks to design and enable High Performance Computing (HPC) benchmarks and test suites. The work described in this report is a part of the effort focusing on the comparison and analysis of OpenSHMEM implementations using the Interleave Or Random (IOR) software for benchmarking parallel file system using POSIX, MPIIO, or HDF5 interfaces. We describe the effort to emulate the MPIIO parallel collective capabilities in the IOR benchmark using OpenSHMEM communication. One development effort was in emulating the MPI derived datatype used in the read/write operations and in setting the file view. Another effort was in implementing an internal cache in OpenSHMEM distributed shared memory to facilitate global collective I/O operations. Experiments comparing collective I/O in MPIIO implementations with the OpenSHMEM implementations were performed on the SGI Turing Cluster and the Cray XK7 Titan supercomputer at the Oak Ridge Leadership Computing Facility (OLCF). The preliminary results suggest that on the Cray XK7 Titan, the MPIIO implementations obtained higher write performance and the OpenSHMEM version obtained slightly higher read performance. On the SGI Turing Cluster, the MPIIO implementations obtained slightly higher performance over the OpenSHMEM implementations on large files.

97 MATHEMATICS AND COMPUTING↗

The Hardware of Smaller Clusters

Chris Saunders and three technologists are in high demand from Sandia's deep learning teams, and they're kept busy by building new clusters of computer nodes for researchers who need the power of supercomputing on a smaller scale. Sandia researchers working on Laboratory Directed Research & Development (LDRD) projects, or innovative ideas for solutions on short timeframes, formulate new ideas on old themes and frequently rely on smaller cluster machines to help solve problems before introducing their code to larger HPC resources. These research teams need an agile hardware and software environment where nascent ideas can be tested and cultivated on a smaller scale. Saunders and his team at Sandia's Science and Engineering Computing Environments are successfully enabling this research by creating pipelines for emerging code—from Cloud, to containers, to virtual machines—that build the right environment quickly to help teams solve their problems in a matter of days rather than months. While the larger HPC sources are available, it's these smaller clusters that can rapidly build a foundation for teams to build on for later development on larger systems.

97 MATHEMATICS AND COMPUTING↗

A Strawman for an HPC PowerStack

The landscape of High-Performance Computing (HPC) is changing as we enter the exascale era and power and energy management are key design points for any next generation of supercomputers. Efficiently utilizing procured power and optimizing performance of scientific applications under power and energy constraints is challenging due to several reasons including dynamic phase behavior, processor manufacturing variability and increasing heterogeneity of node-level components. Extending the scope from the node- and application-level up to the system-level introduces further challenges on top of power-unaware job scheduling, which is known to be NP-hard on its own. While there exists several individual efforts across the community to research automatic techniques for managing power and energy better, the majority of these techniques have been specialized to meet the needs of a specific HPC center or specific optimization goals and provide little support to connect them to each other. Some projects, most notably the PowerAPI efforts [1], discuss interfaces that form a good starting point for full stack integration, but these interfaces still need to be hooked up to the wide range of software components offered by academic partners, developers or vendors. Furthermore, a recent survey conducted by the EE HPC WG concluded that the majority of such techniques have lacked the application-awareness required to achieve the best system performance and throughput. Other observations were that each technique tended to target management of power and energy for a different subset of the site or system hardware and that the different techniques tended to perform management at different (and often conflicting) granularities. Unfortunately, the existing techniques have not been designed to coexist simultaneously on one site and cooperate on management in an integrated manner [2]. The lack of application-awareness, lack of coordinated management across different granularities, and the lack of widely accepted interfaces and consequent limited connectivity between modules, can result in substantially underutilized Watts and FLOPS. To address these gaps, the HPC community needs a holistic stack for power and energy management and none currently exists. In our view, a holistic stack is one that is extensible enough to support the present and anticipated future needs of various different HPC centers, one that achieves best system performance and throughput through application-awareness, one that is designed to coordinate management at different granularities, and one that enables the seamless integration of software components from different developers and vendors. In this seminar, our goal is bring together experts from academia, research laboratories, and industry in order to take stock of existing approaches, design points and power management concepts and requirements at the various participant’s institutions, and to design concepts for a holistic power and energy management stack, which we refer to as the HPC PowerStack. Further, we hope to take steps toward defining the interfaces necessary for providing a complete prototype shared among many groups. The intention is to align development and research efforts across the community so that we may share development resources, avoid duplicating effort, agree on common interfaces and reap the rewards together as a community. The intended final outcome of this collaboration will be a holistic, flexible and extensible concept of a software stack ecosystem that allows us to combine product-grade open-source software components to enable runtime optimization of system power, energy, and performance.

97 MATHEMATICS AND COMPUTING↗

Stochastic Simulation of Complex Fluid Flows (Progress Report for period 07/01/2016 - 06/30/2018)

At a microscopic scale, fluids are composed of molecules whose positions and velocities are random. This gives rise to thermal fluctuations that span the whole range of scales from the microscopic through the mesoscopic, and even the macroscopic. The inclusion of thermal fluctuations is crucial in multi-scale models, which are an important theme in the research program of the DOE Office of Science, and in particular the ASCR Applied Mathematics program's priority focus area on modeling of complex systems involving processes that span vastly different time and/or length scales. In this five-year Early Career project, the PI Aleksandar Donev and collaborators developed computational algorithms for modeling complex fluid mixtures at small scales using a formulation based on fluctuating hydrodynamics. Novel computational methods were developed to model complex fluids with increasing physical complexity, starting from binary miscible and immiscible mixtures, going through multispecies non-reactive and reactive mixtures, and culminating with reactive electrolytes mixtures of neutral molecules and ions. In close collaboration with the group of John Bell at Lawrence Berkeley National Laboratory, the methods were implemented in a scalable computational framework suitable for modern parallel supercomputers, and made publicly available on github. A number of physical examples in which giant nonequilibrium fluctuations are improtant were studied, with a special focus on instabilities at a liquid-liquid interface driven by gravity, diffusion, reactions, and/or electric fields. The methods and codes developed in this project are expected to enable other novel applications in the DOE Basic Energy Sciences program, and engineering sciences more broadly.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Final Technical Report for Grant No. DE-FC02-01ER54648, SciDAC Center for Simulation of Wave-Plasma Interactions

Harnessing the energy that is released in fusion reactions would provide a safe and abundant source of power to meet the growing energy needs of the world population. The next step toward the development of fusion as a practical energy source is the construction of ITER, a device capable of producing and controlling the high performance plasma required for self-sustaining fusion reactions, or “burning” plasma. The input power required to drive the ITER plasma into the burning regime will be supplied primarily with a combination of external power from radio frequency waves in the ion cyclotron range of frequencies and energetic ions from neutral beam injection sources, in addition to internally-generated Ohmic heating from the induced plasma current that also serves to create the magnetic equilibrium for the discharge. Since the success of the ITER project depends critically on the ability to create and maintain burning plasma conditions, it is absolutely necessary to have physics-based models that can accurately simulate the RF processes that affect the dynamical evolution of the ITER discharge. The Center for Simulation of Wave-Plasma Interactions (CSWPI) is a multi-institutional collaboration that has conducted ongoing research aimed at developing: (1) Coupled core-to-edge simulations that will lead to an increased understanding of parasitic losses of the applied RF power in the boundary plasma between the RF antenna and the core plasma; (2) Development of models for core interactions of RF waves with energetic electrons and ions (including fusion alpha particles and fast neutral beam ions) that include a more accurate representation of the particle dynamics in the combined equilibrium and wave fields; and (3) Development of improved algorithms that will take advantage of massively parallel computing platforms at the petascale level and beyond to achieve the needed physics, resolution, and/or statistics to address these issues. This research reported in this final technical report is focused on further verification and validation of simulation models for interactions of RF waves with energetic particles in the core with a long term goal of assessing their readiness for inclusion in integrated modeling frameworks and utilizing the world’s largest supercomputers to quantitatively predict the detailed electric field structure in the vicinity of the launching structures.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Sierra Advances Resolution of Hayward Fault Earthquake Simulations

The character of strong earthquake shaking within a few kilometers of a fault is highly variable and poorly constrained by relatively few empirical recordings. Supercomputers enable simulation of earthquake motions to investigate the hazard and risk to buildings and infrastructure before damaging events occur. However, they require meter scale resolution to capture fine details in high frequency waves (5 - 10 Hz) on regional scales (~ 100 km).

58 GEOSCIENCES↗

SW4 final report for iCOE

The seismic simulation code SW4 was adapted to run on modern supercomputers. SW4 solves the elastic wave equation in second order formulation. It uses a fourth order accurate finite difference method with explicit time stepping. The approximation conserves energy perfectly, and is stable under a CFL restriction on the time step.

97 MATHEMATICS AND COMPUTING↗

Deploy threading in Nalu solver stack

The goal of the ExaWind project is to enable predictive simulations of wind farms composed of many MW-scale turbines situated in complex terrain. Predictive simulations will require computational fluid dynamics (CFD) simulations for which the mesh resolves the geometry of the turbines, and captures the rotation and large deflections of blades. Whereas such simulations for a single turbine are arguably petascale class, multi-turbine wind farm simulations will require exascale-class resources. The primary code in the ExaWind project is Nalu, which is an unstructured-grid solver for the acousticallyincompressible Navier-Stokes equations, and mass continuity is maintained through pressure projection. The model consists of the mass-continuity Poisson-type equation for pressure and a momentum equation for the velocity. For such modeling approaches, simulation times are dominated by linear-system setup and solution for the continuity and momentum systems. For the ExaWind challenge problem, the moving meshes greatly affect overall solver costs as re-initialization of matrices and re-computation of preconditioners is required at every time step In this Milestone, we examine the effect of threading on the solver stack performance against flat-MPI results obtained from previous milestones using Haswell performance data full-turbine simulations. Whereas the momentum equations are solved only with the Trilinos solvers, we investigate two algebraic-multigrid preconditioners for the continuity equations: Trilinos/Muelu and HYPRE/BoomerAMG. These two packages embody smoothed-aggregation and classical Ruge-Stiiben AMG methods, respectively. In our FY18 Q2 report, we described our efforts to improve setup and solve of the continuity equations under flat-MPI parallelism. While significant improvement was demonstrated in the solve phase, setup times remained larger than expected. Starting with the optimized settings described in the Q2 report, we explore here simulation performance where OpenMP threading is employed in the solver stack. For Trilinos, threading is acheived through the Kokkos abstraction where, whereas HYPRE/BoomerAMG employs straight OpenMP. We examined results for our mid-resolution baseline turbine simulation configuration (229M DOF). Simulations on 2048 Haswell cores explored the effect of decreasing the number of MPI ranks while increasing the number of threads. Both HYPRE and Trilinos exhibited similar overal solution times, and both showed dramatic increases in simulation time in the shift from MPI ranks to OpenMP threads. This increase is attributed to the large amount of work per MPI rank starting at the single-thread configuration. Decreasing MPI ranks, while increasing threads, may be increasing simulation time due to thread synchronization and start-up overhead contributing to the latency and serial time in the model. These result showed that an MPI+OpenMP parallel decomposition will be more effective as the amount per MPI rank computation per MPI rank decreases and the communication latency increases. This idea was demonstrated in a strong scaling study of our low-resolution baseline model (29M DOF) with the Trilinos-HYPRE configuration. While MPI-only results showed scaling improvement out to about 1536 cores, engaging threading carried scaling improvements out to 4128 cores — roughly 7000 DOF per core. This is an important result as improved strong scaling is needed for simulations to be executed over sufficiently long simulated durations (i.e., for many timesteps). In addition to threading work described above, the team examined solver-performance improvements by exploring communication-overhead in the HYPRE-GMRES implementation through a communicationoptimal- GMRE algorithm (CO-GMRES), and offloading compute-intensive solver actions to GPUs. To those ends, a HYPRE mini-app was allow us to easily test different solver approaches and HYPRE parameter settings without running the entire Nalu code. With GPU acceleration on the Summitdev supercomputer, a 20x speedup was achieved for the overall preconditioner and solver execution time for the mini-app. A study on Haswell processors showed that CO-GMRES provides benefits as one increases MPI ranks.

17 WIND ENERGY↗

Free Energy Landscapes of Membrane Transport Proteins

Molecular dynamics (MD) is now a widespread tool for investigating biochemical and biomolecular systems, its prevalence, in no small part, being due to significant advances in computational hardware over the last few decades. Even non-experts can now routinely use MD for protein and nucleic acid structure refinement, studying conformational switching events, and investigating solvation effects due to ligand/drug binding. Nonetheless, the vast majority of simulations being done today utilize only rudimentary algorithmic approaches – so-called “brute force” MD – which only permit access to a small fraction of what the approach has to offer. This is largely because the core algorithm is simple, while advanced techniques can require everything from more sophisticated models and data structures to complicated on-the-fly analysis. A core goal of this early science project is to bring one such advanced MD approach into the broader arena of high-performance computing.In particular, the powerful method of constant-pH MD has long been a relegated to experienced users and specialized model systems. In this work we develop and implement a constant-pH MD algorithm in the NAMD simulation engine making it suitable for deployment on large-scale, next-generation supercomputers as well as ambitious, cutting-edge biological applications. We report,for the first time, constant-pH simulations of a membrane transport protein and use the results to analyze its free energy landscape for ion-selectivity.

59 BASIC BIOLOGICAL SCIENCES↗

ASC news highlight for HQ, 12/11/18

LLNL’s package management tool, Spack, has reduced software build times from weeks to hours for programmatic codes, and the tool’s popularity has grown beyond the NNSA laboratories. New workflow features and ongoing community-building efforts have led ECP and many top supercomputing sites worldwide to adopt Spack as their official deployment tool. With a community of over 330 Spack contributors, the maintenance burden for over 3,000 open source packages is now shared with other centers. This reduction of general ASC software maintenance costs frees up code development resources to address unique requirements specific to the stockpile stewardship mission.

97 MATHEMATICS AND COMPUTING↗

Strong and Weak Scaling of the Sierra/SD Eigenvector Problem to a Billion Degrees of Freedom

Sierra/SD is a structural dynamics finite element software package that is known for its scalability and performance on DOE supercomputers. While there are historical documents demonstrating weak and strong scaling on DOE systems such as Redsky, no such formal studies have been done on modern architectures. This report demonstrates that Sierra/SD still scales on modern architectures. Non structured meshes in the shape of an I-Beam are solved in sizes ranging from fifty thousand degrees of freedom in serial up to one and a half billion degrees of freedom on over eighteen thousand processors using only default solver options. The report serves as a baseline for users to estimate computation cost of finite element analyses in Sierra/SD, understand how solver options relate to computational costs, and pick optimal processor counts to solve a given problem size, as well as a baseline for evaluating computational cost and scalability on next generation architectures.

42 ENGINEERING↗

High Performance Computing - Power Application Programming Interface Specification

Achieving practical exascale supercomputing will require massive increases in energy efficiency. The bulk of this improvement will likely be derived from hardware advances such as improved semiconductor device technologies and tighter integration, hopefully resulting in more energy efficient computer architectures. Still, software will have an important role to play. With every generation of new hardware, more power measurement and control capabilities are exposed. Many of these features require software involvement to maximize feature benefits. This trend will allow algorithm designers to add power and energy efficiency to their optimization criteria. Similarly, at the system level, opportunities now exist for energy-aware scheduling to meet external utility constraints such as time of day cost charging and power ramp rate limitations. Finally, future architectures might not be able to operate all components at full capability for a range of reasons including temperature considerations or power delivery limitations. Software will need to make appropriate choices about how to allocate the available power budget given many, sometimes conflicting considerations.

97 MATHEMATICS AND COMPUTING↗