Search NASA⌕ Search

SEARCH · Search NASA

Results for “accelerated computing”

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 667 records · Page 37

Risk-Averse Bi-Level Stochastic Network Interdiction Model for Cyber-Security Risk Management

Security of cyber networks is crucial; recent severe cyber-attacks have had a devastating effect on many large organizations. The attack graph, which maps the potential attack paths of a cyber network, is a popular tool for analyzing cyber system vulnerability. In this study, we propose a bi-level stochastic network interdiction model on an attack graph to enable a risk-averse, resource constrained cyber network defender to optimally deploy security countermeasures that protect against attackers with an uncertain budget. This risk- averse conditional-value-at-risk (CVaR) model minimizes a weighted sum of the expected maximum loss over all scenarios and the expected maximum loss from the most damaging attack scenarios. We develop a customized constraint and column generation algorithm to solve our model as well as several acceleration techniques to improve the computational efficiency. Numerical experiments demonstrate that the acceleration techniques enable the solution of relatively large problems within a reasonable amount of time: applying all the acceleration techniques also reduces the average computation time of the basic algorithm by 71% for 100-node graphs. Using metrics called mean-risk value of stochastic solution and value of risk-aversion, computational results suggest that our stochastic risk-averse model significantly outperforms deterministic and risk-neutral models when 1) the distribution of attacker budget is heavy-right-tailed and 2) the defender is highly risk-averse.

Bhuiyan, Tanveer H.↗

A highly parallel multigrid-like method for the solution of the Euler equations

We consider a highly parallel multigrid-like method for the solution of the two dimensional steady Euler equations. The new method, introduced as filtering multigrid, is similar to a standard multigrid scheme in that convergence on the finest grid is accelerated by iterations on coarser grids. In the filtering method, however, additional fine grid subproblems are processed concurrently with coarse grid computations to further accelerate convergence. These additional problems are obtained by splitting the residual into a smooth and an oscillatory component. The smooth component is then used to form a coarse grid problem (similar to standard multigrid) while the oscillatory component is used for a fine grid subproblem. The primary advantage in the filtering approach is that fewer iterations are required and that most of the additional work per iteration can be performed in parallel with the standard coarse grid computations. We generalize the filtering algorithm to a version suitable for nonlinear problems. We emphasize that this generalization is conceptually straight-forward and relatively easy to implement. In particular, no explicit linearization (e.g., formation of Jacobians) needs to be performed (similar to the FAS multigrid approach). We illustrate the nonlinear version by applying it to the Euler equations, and presenting numerical results. Finally, a performance evaluation is made based on execution time models and convergence information obtained from numerical experiments.

Tuminaro, Ray S.↗

A Framework for Lattice QCD Calculations on GPUs

Efficient calculation of the greatest common divisor (GCD) for big integers each whose number of bits is greater than or equal to 1024 has drawn a considerable amount of attention because it can be used to detect a weakness of the RSA security infrastructure. This paper presents a parallel binary GCD algorithm and its implementation for big integers on the Intel Xeon Phi coprocessor. This algorithm is capable of computing GCDs efficiently on many pairs of big integers in parallel by utilizing all cores on a Xeon Phi coprocessor as well as taking advantage of all vector processing units of the coprocessor to speed up critical integer operations within the algorithm. Using 240 threads on a Xeon Phi coprocessor to carry out GCD calculations for a large amount of 2048-bit integers, the implementation achieves the speedup of 30 times over a sequential binary GCD algorithm implementation on a single CPU core, and it delivers twice amount of performance in comparison to the same sequential binary GCD implementation running on 240 threads of the Xeon Phi.

Winter, F. T.↗

Optimizations of Human Restraint Systems for Short-Period Acceleration

A restraint system's main function is to restrain its occupant when his vehicle is subjected to acceleration. If the restraint system is rigid and well-fitting (to eliminate slack) then it will transmit the vehicle acceleration to its occupant without modifying it in any way. Few present-day restraint systems are stiff enough to give this one-to-one transmission characteristic, and depending upon their dynamic characteristics and the nature of the vehicle's acceleration-time history, they will either magnify or attenuate the acceleration. Obviously an optimum restraint system will give maximum attenuation of an input acceleration. In the general case of an arbitrary acceleration input, a computer must be used to determine the optimum dynamic characteristics for the restraint system. Analytical solutions can be obtained for certain simple cases, however, and these cases are considered in this paper, after the concept of dynamic models of the human body is introduced. The paper concludes with a description of an analog computer specially developed for the Air Force to handle completely general mechanical restraint optimization programs of this type, where the acceleration input may be any arbitrary function of time.

Payne, P. R.↗

Explicit TE/TM scheme for particle beam simulations

In this paper we propose an explicit two-level conservative scheme based on a TE/TM like splitting of the field components in time. Its dispersion properties are adjusted to accelerator problems. It is simpler and faster than the implicit version [I. Zagorodnov, T. Weiland, TE/TM scheme for computation of electromagnetic fields in accelerators, J. Comput. Phys. 207 (2005) 69]. It does not have dispersion in the longitudinal direction and the dispersion properties in the transverse plane are improved. The explicit character of the new scheme allows a uniformly stable conformal method without iterations and the scheme can be parallelized easily. It assures energy and charge conservation. A version of this explicit scheme for rotationally symmetric structures is free from the progressive time step reducing for higher order azimuthal modes as it takes place for Yee's explicit method used in the most popular electrodynamics codes.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

On-Chip Laser-Power Delivery System for Dielectric Laser Accelerators

We propose an on-chip optical-power delivery system for dielectric laser accelerators based on a fractal “tree-network” dielectric waveguide geometry. Here, this system replaces experimentally demanding free-space manipulations of the driving laser beam with chip-integrated techniques based on precise nanofabrication, enabling access to orders-of-magnitude increases in the interaction length and total energy gain for these miniature accelerators. Based on computational modeling, in the relativistic regime, our laser delivery system is estimated to provide 21 keV of energy gain over an acceleration length of 192 μm with a single laser input, corresponding to a 108-MV/m acceleration gradient. The system may achieve 1 MeV of energy gain over a distance of less than 1 cm by sequentially illuminating 49 identical structures. These findings are verified by detailed numerical simulation and modeling of the subcomponents, and we provide a discussion of the main constraints, challenges, and relevant parameters with regard to on-chip laser coupling for dielectric laser accelerators.

43 PARTICLE ACCELERATORS↗

Modeling and Simulation of High Dimensional Stochastic Multiscale PDE Systems at the Exascale

The thrust of the proposal was to exploit modern data-mining tools in a way that will create a systematic, computer-assisted approach to the representation of random media -- and also to the representation of the solutions of an array of important physicochemical processes that take place in/on such media. A parsimonious representation/parametrization of the random media links directly (via uncertainty quantification tools) to good sampling of the distribution of random media realizations. It also links directly to modern multiscale computational algorithms (like the equation-free approach that has been developed in our group) and plays a crucial role in accelerating the scientific computation of solutions of nonlinear PDE models (deterministic or stochastic) in such media – both solutions in particular realizations of the random media, and estimation of the statistics of the solutions over multiple realizations (e.g. expectations).

97 MATHEMATICS AND COMPUTING↗

"Forward" Projects Boost U.S. Leadership in Advanced Computing and Artificial Intelligence

High-performance computing (HPC) has been an indispensable research tool for accessing physical realms difficult, or impossible, achieve with experiment alone. For several decades, the Department of Energy’s (DOE’s) Office of Science has deployed sophisticated HPC systems for solving the nation’s most pressing grand challenge problems in energy, climate change, and human health. In addition, DOE’s National Nuclear Security Administration (NNSA) has adeptly applied HPC in support of key national security objectives, such as nuclear science and stockpile modernization and stewardship. Over time, HPC systems have become increasingly more complex and capable, and as each new machine has come online, scientists and engineers have taken advantage of vast increases in compute power to accelerate scientific discoveries and engineering innovation.

42 ENGINEERING↗

An Initial Multi-Domain Modeling of an Actively Cooled Structure

A methodology for the simulation of turbine cooling flows is being developed. The methodology seeks to combine numerical techniques that optimize both accuracy and computational efficiency. Key components of the methodology include the use of multiblock grid systems for modeling complex geometries, and multigrid convergence acceleration for enhancing computational efficiency in highly resolved fluid flow simulations. The use of the methodology has been demonstrated in several turbo machinery flow and heat transfer studies. Ongoing and future work involves implementing additional turbulence models, improving computational efficiency, adding AMR.

Steinthorsson, Erlendur↗

Toward a Seamless Integration of Computing, Experimental, and Observational Science Facilities: A Blueprint to Accelerate Discovery

The Department of Energy, Office of Science operates world-leading facilities for experimental, observational, and computational science. DOE supercomputing facilities will reach performance at the scale of ExaFLOPs in the coming years, enabling new vistas of scale and precision for large scale simulations and data analysis. Experimental scientific facilities are undergoing similar upgrades that will lead to higher data rates and correspondingly larger computational demands, and will increase the need for near-real-time processing and resilient support for more complex workflows. A transformation of science is underway, with workloads at supercomputing facilities increasingly driven by this explosion of data from instruments and experimental facilities, as well as the accelerating use of Artificial Intelligence (AI) as a tool for scientific discovery. A seamless integration of computing, networking, instruments, and experimental facilities is required to support these emerging workloads and open up a new frontier of U.S. leadership in scientific discovery. We propose to accomplish this by providing frictionless access to the ASCR supercomputing facilities. We describe our vision of combining the power of ASCR supercomputers and networking infrastructure into an integrated scalable fabric, available to end user scientists via interfaces that aim to automate and simplify access to high performance computing systems. This will enable unprecedented computational science capabilities for experimental and observational facilities, and will create new opportunities to combine large simulations and modeling with experimental facility data analysis. This blueprint for creating an integrated network of computational and experimental facilities will provide an enriched discovery environment and open doors for new scientific communities to access the DOE’s world-leading computing and networking capabilities.

97 MATHEMATICS AND COMPUTING↗

Efficient simulation of electron trapping in laser and plasma wakefield acceleration

The two-dimensional quasistatic simulation code WAKE [P. Mora and T. Antonsen, Phys. Plasmas 4, 217 (1997)] used to model laser pulse propagation in tenuous plasma is modified to describe the dynamics of energetic particles. In the original code, all particles were assumed to satisfy the quasistatic approximation, which assumes that the driver and its wakefields are undisturbed during the transit time of plasma electrons through the pulse. Here, WAKE is modified to include the effects of electron trapping and beam loading by introducing a population of beam electrons, which are no longer subject to the quasistatic approximation. Algorithms for populating the group of beam particles are considered and are benchmarked to the full particle-in-cell simulations and experimental results. These modifications to WAKE provide a tool for simulating GeV laser or plasma wakefield acceleration on desktop computers.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Exploiting first-class arrays in Fortran for accelerator programming

Emerging architectures for high performance computing often are well suited to a data parallel programming model. This paper presents a simple programming methodology based on existing languages and compiler tools that allows programmers to take advantage of these systems. We will work with the array features of Fortran 90 to show how this infrequently exploited, standardized language feature is easily transformed to lower level accelerator code. Our transformations are based on a mapping from Fortran 90 to C++ code with OpenCL extensions. The sheer complexity of programming for clusters of many or multi-core processors with tens of millions threads of execution make the simplicity of the data parallel model attractive. Furthermore, the increasing complexity of todays applications (especially when convolved with the increasing complexity of the hardware) and the need for portability across hardware architectures make a higher-level and simpler programming model like data parallel attractive. The goal of this work has been to exploit source-to-source transformations that allow programmers to develop and maintain programs at a high-level of abstraction, without coding to a specific hardware architecture. Furthermore these transformations allow multiple hardware architectures to be targeted without changing the high-level source. It also removes the necessity for application programmers to understand details of the accelerator architecture or to know OpenCL.

43 PARTICLE ACCELERATORS↗

SFU-Driven Transparent Approximation Acceleration on GPUs

Approximate computing, the technique that sacrifices certain amount of accuracy in exchange for substantial performance boost or power reduction, is one of the most promising solutions to enable power control and performance scaling towards exascale. Although most existing approximation designs target the emerging data-intensive applications that are comparatively more error-tolerable, there is still high demand for the acceleration of traditional scientific applications (e.g., weather and nuclear simulation), which often comprise intensive transcendental function calls and are very sensitive to accuracy loss. To address this challenge, we focus on a very important but often ignored approximation unit on GPUs.

Approximate computing↗

Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning

Abstract The current predictive modeling techniques applied to Density Functional Theory (DFT) computations have helped accelerate the process of materials discovery by providing significantly faster methods to scan materials candidates, thereby reducing the search space for future DFT computations and experiments. However, in addition to prediction error against DFT-computed properties, such predictive models also inherit the DFT-computation discrepancies against experimentally measured properties. To address this challenge, we demonstrate that using deep transfer learning, existing large DFT-computational data sets (such as the Open Quantum Materials Database (OQMD)) can be leveraged together with other smaller DFT-computed data sets as well as available experimental observations to build robust prediction models. We build a highly accurate model for predicting formation energy of materials from their compositions; using an experimental data set of $$1,643$$ 1 , 643 observations, the proposed approach yields a mean absolute error (MAE) of $$0.07$$ 0.07 eV/atom, which is significantly better than existing machine learning (ML) prediction modeling based on DFT computations and is comparable to the MAE of DFT-computation itself.

36 MATERIALS SCIENCE↗

Union: A Unified HW-SW Co-Design Ecosystem in MLIR for Evaluating Tensor Operationson Spatial Accelerators

To meet the extreme compute demands for deep learning across commercial and scientific applications, dataflow accelerators are becoming increasingly popular. While these“domain-specific” accelerators are not fully programmable like CPUs and GPUs, they retain varying levels of flexibility with respect to data orchestration, i.e., dataflow and tiling optimizations to enhance efficiency. There are several challenges when designing new algorithms and mapping approaches to execute the algorithms for a target problem on new hardware. Previous works have addressed these challenges individually. To address this challenge as a whole, in this work, we present an HW-SW co-design ecosystem for spatial accelerators called Union within the popular MLIR compiler infrastructure. Our framework allows exploring different algorithms and their mappings on several accelerator cost models. Union also includes a plug-and-play library of accelerator cost models and mappers which can easily be extended. The algorithms and accelerator cost models are connected via a novel mapping abstraction that captures the map space of spatial accelerators which can be systematically pruned based on constraints from the hardware, workload, and mapper. We demonstrate the value of Union for the community with several case studies which examine offloading different tensor operations (CONV/GEMM/Tensor Contraction) on diverse accelerator architectures using different mapping schemes.

Jeong, Geonhwa↗

3D treatment planning systems

Three-dimensional (3D) treatment planning systems have evolved and become crucial components of modern radiation therapy. The systems are computer-aided designing or planning softwares that speed up the treatment planning processes to arrive at the best dose plans for the patients undergoing radiation therapy. Furthermore, the systems provide new technology to solve problems that would not have been considered without the use of computers such as conformal radiation therapy (CRT), intensity-modulated radiation therapy (IMRT), and volumetric modulated arc therapy (VMAT). The 3D treatment planning systems vary amongst the vendors and also the dose delivery systems they are designed to support. As such these systems have different planning tools to generate the treatment plans and convert the treatment plans into executable instructions that can be implemented by the dose delivery systems. The rapid advancements in computer technology and accelerators have facilitated constant upgrades and the introduction of different and unique dose delivery systems than the traditional C-arm type medical linear accelerators. The focus of this special issue is to gather relevant 3D treatment planning systems for the radiation oncology community to keep abreast of technology advancement by assess the planning tools available as well as those unique ''tricks or tips'' used to support the different dose delivery systems.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Bringing Federated Identity to Grid Computing

The Fermi National Accelerator Laboratory (FNAL) is facing the challenge of providing scientific data access and grid submission to scientific collaborations that span the globe but are hosted at FNAL. Users in these collaborations are currently required to register as an FNAL user and obtain FNAL credentials to access grid resources to perform their scientific computations. These requirements burden researchers with managing additional authentication credentials, and put additional load on FNAL for managing user identities. Our design integrates the existing InCommon federated identity infrastructure, CILogon Basic CA, and MyProxy with the FNAL grid submission system to provide secure access for users from diverse experiments and collab orations without requiring each user to have authentication credentials from FNAL. The design automates the handling of certificates so users do not need to manage them manually. Although the initial implementation is for FNAL's grid submission system, the design and the core of the implementation are general and could be applied to other distributed computing systems.

Teheran, Jeny↗

GPU acceleration and performance of the particle-beam-dynamics code Elegant

Elegant is an accelerator physics and particle-beam dynamics code widely used for modeling and design of a variety of high-energy particle accelerators and accelerator-based systems. We discuss a recently developed version of the code that can take advantage of CUDA-enabled graphics processing units (GPUs) to achieve significantly improved performance for a large class of simulations that are important in practice. The GPU version is largely defined by a framework that simplifies implementations of the fundamental kernel types that are used by Elegant: particle operations, reductions, particle loss, histograms, array convolutions and random number generation. Accelerated performance on the Titan Cray XK-7 supercomputer is approximately 6–10 times better with the GPU than all the CPU cores associated with the same node count. In addition to performance, the maintainability of the GPU-accelerated version of the code was considered a key design objective. Accuracy with respect to the CPU implementation is also a core consideration. Finally, four different methods are used to ensure that the accelerated code faithfully reproduces the CPU results.

43 PARTICLE ACCELERATORS↗