SEARCH · Search NASA

Results for “high performance parallel 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.

SourceResearch connectionFrom yearThrough year

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

At least 1,081 records · Page 60

All sources NASA NTRS DOE OSTI

DOE OSTI2020

TeraChem: A graphical processing unit-accelerated electronic structure package for large-scale ab initio molecular dynamics

TeraChem was born in 2008 with the goal of providing fast on-the-fly electronic structure calculations to facilitate ab initio molecular dynamics studies of large biochemical systems such as photoswitchable proteins and multichromophoric antenna complexes. Originally developed for videogaming applications, graphics processing units (GPUs) offered a low-cost parallel computer architecture that became more accessible for general-purpose GPU computing with the release of CUDA in 2007. The evaluation of the electron repulsion integrals (ERIs) is a major bottleneck in electronic structure codes and provides an attractive target for acceleration on GPUs. Thus, highly efficient routines for evaluation of and contractions between the ERIs and density matrices were implemented in TeraChem. Here, electronic structure methods were developed and implemented to leverage these integral contraction routines, resulting in the first quantum chemistry package designed from the ground up for GPUs. This GPU acceleration makes TeraChem capable of performing large-scale ground and excited state calculations in the gas and condensed phase. Today, TeraChem's speed forms the basis for a suite of quantum chemistry applications, including optimization and dynamics of proteins, automated and interactive chemical discovery tools, and large-scale nonadiabatic dynamics simulations.

74 ATOMIC AND MOLECULAR PHYSICS↗

DOE OSTI2023

An accurate and efficient fragmentation approach via the generalized many-body expansion for density matrices

With relevant chemical space growing larger and larger by the day, the ability to extend computational tractability over that larger space is of paramount importance in virtually all fields of science. The solution we aim to provide here for this issue is in the form of the generalized many-body expansion for building density matrices (GMBE-DM) based on the set-theoretical derivation with overlapping fragments, through which the energy can be obtained by a single Fock build. In combination with the purification scheme and the truncation at the one-body level, the DM-based GMBE(1)-DM-P approach shows both highly accurate absolute and relative energies for medium-to-large size water clusters with about an order of magnitude better than the corresponding energy-based GMBE(1) scheme. Simultaneously, GMBE(1)-DM-P is about an order of magnitude faster than the previously proposed MBE-DM scheme [F. Ballesteros and K. U. Lao, J. Chem. Theory Comput. 18, 179 (2022)] and is even faster than a supersystem calculation without significant parallelization to rescue the fragmentation method. For even more challenging systems including ion–water and ion–pair clusters, GMBE(1)-DM-P also performs about 3 and 30 times better than the energy-based GMBE(1) approach, respectively. In addition, this work provides the first overlapping fragmentation algorithm with a robust and effective binning scheme implemented internally in a popular quantum chemistry software package. Thus, GMBE(1)-DM-P opens a new door to accurately and efficiently describe noncovalent clusters using quantum mechanics.

Chemistry↗

DOE OSTI2020

A supernodal all-pairs shortest path algorithm

We show how to exploit graph sparsity in the Floyd-Warshall algorithm for the all-pairs shortest path (Apsp) problem. Floyd-Warshall is an attractive choice for Apsp on high-performing systems due to its structural similarity to solving dense linear systems and matrix multiplication. However, if sparsity of the input graph is not properly exploited, Floyd-Warshall will perform unnecessary asymptotic work and thus may not be a suitable choice for many input graphs. To overcome this limitation, the key idea in our approach is to use the known algebraic relationship between Floyd-Warshall and Gaussian elimination, and import several algorithmic techniques from sparse Cholesky factorization, namely, fill-in reducing ordering, symbolic analysis, supernodal traversal, and elimination tree parallelism. When combined, these techniques reduce computation, improve locality and enhance parallelism. We implement these ideas in an efficient shared memory parallel prototype that is orders of magnitude faster than an efficient multi-threaded baseline Floyd-Warshall that does not exploit sparsity. Our experiments suggest that the Floyd-Warshall algorithm can compete with Dijkstra's algorithm (the algorithmic core of Johnson's algorithm) for several classes sparse graphs.

Sao, Piyush↗

NASA NTRS1988

Implementing direct, spatially isolated problems on transputer networks

Parametric studies were performed on transputer networks of up to 40 processors to determine how to implement and maximize the performance of the solution of problems where no processor-to-processor data transfer is required for the problem solution (spatially isolated). Two types of problems are investigated a computationally intensive problem where the solution required the transmission of 160 bytes of data through the parallel network, and a communication intensive example that required the transmission of 3 Mbytes of data through the network. This data consists of solutions being sent back to the host processor and not intermediate results for another processor to work on. Studies were performed on both integer and floating-point transputers. The latter features an on-chip floating-point math unit and offers approximately an order of magnitude performance increase over the integer transputer on real valued computations. The results indicate that a minimum amount of work is required on each node per communication to achieve high network speedups (efficiencies). The floating-point processor requires approximately an order of magnitude more work per communication than the integer processor because of the floating-point unit's increased computing capacity.

Ellis, Graham K.↗

NASA NTRS2001

A Parallel Cartesian Approach for External Aerodynamics of Vehicles with Complex Geometry

This workshop paper presents the current status in the development of a new approach for the solution of the Euler equations on Cartesian meshes with embedded boundaries in three dimensions on distributed and shared memory architectures. The approach uses adaptively refined Cartesian hexahedra to fill the computational domain. Where these cells intersect the geometry, they are cut by the boundary into arbitrarily shaped polyhedra which receive special treatment by the solver. The presentation documents a newly developed multilevel upwind solver based on a flexible domain-decomposition strategy. One novel aspect of the work is its use of space-filling curves (SFC) for memory efficient on-the-fly parallelization, dynamic re-partitioning and automatic coarse mesh generation. Within each subdomain the approach employs a variety reordering techniques so that relevant data are on the same page in memory permitting high-performance on cache-based processors. Details of the on-the-fly SFC based partitioning are presented as are construction rules for the automatic coarse mesh generation. After describing the approach, the paper uses model problems and 3- D configurations to both verify and validate the solver. The model problems demonstrate that second-order accuracy is maintained despite the presence of the irregular cut-cells in the mesh. In addition, it examines both parallel efficiency and convergence behavior. These investigations demonstrate a parallel speed-up in excess of 28 on 32 processors of an SGI Origin 2000 system and confirm that mesh partitioning has no effect on convergence behavior.

Aftosmis, M. J.↗

NASA NTRS2012

Flying Schedule-Matching Descents to Explore Flight Crews' Perceptions of Their Load and Task Feasibility

Multiple studies have investigated the development and use of ground-based (controller) tools to manage and schedule traffic in future terminal airspace. No studies have investigated the impacts that such tools (and concepts) could have on the flight-deck. To begin to redress the balance, an exploratory study investigated the procedures and actions of ten Boeing-747-400 crews as they flew eight continuous descent approaches in the Los Angeles terminal airspace, with the descents being controlled using speed alone. Although the study was exploratory in nature, four variables were manipulated: speed changes, route constraints, clearance phraseology, and winds. Despite flying the same scenarios with the same events and timing, there was at least a 50 second difference in the time it took crews to fly the approaches. This variation is the product of a number of factors but highlights potential difficulties for scheduling tools that would have to accommodate this amount of natural variation in descent times. The primary focus of this paper is the potential impact of ground scheduling tools on the flight crews performance and procedures. Crews reported "moderate to low" workload, on average; however, short periods of intense and high workload were observed. The non-flying pilot often reported a higher level of workload than the flying-pilot, which may be due to their increased interaction with the Flight Management Computer, when using the aircraft automation to assist with managing the descent clearances. It is concluded that ground-side tools and automation may have a larger impact on the current-day flight-deck than was assumed and that studies investigating this impact should continue in parallel with controller support tool development.

Martin, Lynne Hazel↗

DOE OSTI2019

Vectorization of Random Number Generation and Reproducibility of Concurrent Particle Transport Simulation

Efficient random number generation with high quality statistical properties and exact reproducibility of Monte Carlo simulations are important requirements in many areas of computational science. VecRNG is a package providing pseudo-random number generation (pRNG) in the context of a new library VecMath. This library bundles up several general-purpose mathematical utilities, data structures, and algorithms having both SIMD and SIMT (GPUs) support based on VecCore.~Several state-of-the-art RNG algorithms are implemented as kernels supporting parallel generation of random numbers in scalar, vector, and Cuda workflows. In this report, we will present design considerations, implementation details, and computing performance of parallel pRNG engines on both CPU and GPU. Reproducibility of propagating multiple particles in parallel for HEP event simulation is demonstrated, using GeantV-based examples, for both sequential and fine-grain track-level concurrent simulation wor kflows. Strategies for efficient uses of vectorized pRNG and non-overlapping streams of random number sequences in concurrent computing environments is discussed as well.

Jun, S. Y.↗

DOE OSTI2018

3-D Semantic Information Inference from Airborne Video. Final Report

We developed a full 3D modeling pipeline focusing on an important application scenario: city-scale 3D reconstruction from aerial imagery. We propose an approach to solve camera pose estimation and dense reconstruction from Wide Area Aerial Surveillance (WAAS) videos captured by an airborne platform. Our approach solves them in an online fashion: it incrementally updates a sparse 3D map and estimates the camera pose as each new frame arrives; depth maps of selected key frames are computed using a variational method and integrated to produce a full 3D model via volumetric reconstruction. In practice, aerial imagery is usually captured using a multicamera system. We propose an approach for camera pose estimation of multi-camera aerial imagery which is parallelized on multiple GPUs for efficiency. The approach is also extended for progressive 3D model acquisition with a hand-held camera. We also developed an offline approach since online approach is not a necessity and accuracy has higher priority over efficiency in many scenarios. We presented MeshRecon, a mesh-based offline system composed of three modules: a dense point cloud is generated using multi-resolution plane sweep method; an initial mesh model is extracted from the point cloud via global optimization considering visibility information of all images; the mesh model is then iteratively refined to capture structural details by optimizing the photometric consistency and spatial regularization. The major processes are parallelized on GPU for efficiency. For the aerial imagery case, we evaluate our system on several real-world multicamera aerial imagery datasets, each covering an urban scenario of several square kilometers. Quantitative result shows that the reconstructed geometric 3D model is highly accurate with error smaller than 1 meter over the entire city. Besides aerial imagery, we also evaluate its performance on general geometric 3D model acquisition of real-world objects. Result shows that the system is robust and flexible for various types of objects at different scales in both indoor and outdoor environments. Based on city 3D models reconstructed at different times, we present a system for city-scale geometry change detection by performing comparisons at the 3D geometry level. Our system is able to detect geometry changes at different scales, ranging from a building cluster to small-scale vegetation changes, with high accuracy.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1982

A scheme for handling arrays in data-flow systems

An examination of the effects of atomicity (higher resolution) on the performance of array processors (data-flow computers) is presented. Data-flow principles are reviewed, noting the reliance on parallel processing using functional languages to specify sequencing of the operations. Techniques are described for eliminating the necessity of copying whole arrays between processing steps, thereby reducing the number of store cycles. The method involves setting whole columns to specific values rather than individual elements. The individual column values can be processed in parallel, i.e., a locally optimized condition exists. A drawback of the system is the need for more low level arguments, to identify the appropriate processing sequences, and high system complexity.

Gaudiot, J.-L.↗

NASA NTRS1992

The design and implementation of a parallel unstructured Euler solver using software primitives

This paper is concerned with the implementation of a 3D unstructured-grid Euler-solver on massively parallel distributed-memory computer architectures. The goal is to minimize solution time by achieving high computational rates with a numerically efficient algorithm. An unstructured multigrid algorithm with an edge-based data-structure has been adopted, and a number of optimizations have been devised and implemented in order to accelerate the parallel computational rates. The implementation is carried out by creating a set of software tools, which ease the implementation of computational problems on parallel architecture machines by relieving the user of the low-level machine specific issues. The quantitative effect of the various optimizations are demonstrated, and we show that the combined effect of these optimizations leads to roughly a factor of three performance improvement. The overall solution efficiency is compared with that obtained on the CRAY-YMP vector supercomputer.

Das, R.↗

DOE OSTI2019

Nalu-Wind and OpenFAST: A high-fidelity modeling and simulation environment for wind energy. Milestone ECP-Q2-FY19

The goal of the ExaWind project is to enable predictive simulations of wind farms comprised of many megawatt-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 physics codes in the ExaWind project are Nalu-Wind, which is an unstructured-grid solver for the acoustically incompressible Navier-Stokes equations, and OpenFAST, which is a whole-turbine simulation code. The Nalu-Wind 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 reinitialization of matrices and recomputation of preconditioners is required at every time step. This milestone represents the culmination of several parallel development activities towards the goal of establishing a full-physics simulation capability for modeling wind turbines operating in turbulent atmospheric inflow conditions. The demonstration simulation performed in this milestone is the first step towards the "ground truth" simulation and includes the following components: neutral atmospheric boundary layer inflow conditions generated using a precursor simulation, a hybrid RANS/LES simulation of the wall-resolved turbine geometry, hybridization of the turbulence equations using a blending function approach to transition from the atmospheric scales to the blade boundary layer scales near the turbine, fluid-structure interaction (FSI) that accounts for the complete set of blade deformations (bending, twisting and pitch motion, yaw and tower displacements) by coupling to a comprehensive turbine dynamics code (OpenFAST). The use of overset mesh methodology for the simulations in this milestone presents a significant deviation from the previous efforts where a sliding mesh approach was employed to model the rotation of the turbine blades. The choice of overset meshes was motivated by the need to handle arbitrarily large deformations of the blade and to allow for blade pitching in the presence of a controller and the ease of mesh generation compared to the sliding mesh approach. FSI and the new timestep algorithm used in the simulations were developed in partnership with the A2e High-Fidelity Modeling project. The individual physics components were verified and validated (V%V) through extensive code-to-code comparisons and with experiments where possible. The detailed V&V efforts provide confidence in the final simulation where these physics models were combined together even though no detailed experimental data is available to perform validation of the final configuration. Taken together, this milestone successfully demonstrated the most advanced simulation to date that has been performed with Nalu-Wind.

17 WIND ENERGY↗

DOE OSTI2022

Estimating the randomness of quantum circuit ensembles up to 50 qubits

Random quantum circuits have been utilized in the contexts of quantum supremacy demonstrations, variational quantum algorithms for chemistry and machine learning, and blackhole information. The ability of random circuits to approximate any random unitaries has consequences on their complexity, expressibility, and trainability. To study this property of random circuits, we develop numerical protocols for estimating the frame potential, the distance between a given ensemble and the exact randomness. Our tensor-network-based algorithm has polynomial complexity for shallow circuits and is high-performing using CPU and GPU parallelism. We study 1. local and parallel random circuits to verify the linear growth in complexity as stated by the Brown–Susskind conjecture, and; 2. hardware-efficient ansätze to shed light on its expressibility and the barren plateau problem in the context of variational algorithms. Our work shows that large-scale tensor network simulations could provide important hints toward open problems in quantum information science.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

FPGAs as a Service to Accelerate Machine Learning Inference [PowerPoint]

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC, and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave b y Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

NASA NTRS2000

Performance of the OVERFLOW-MLP and LAURA-MLP CFD Codes on the NASA Ames 512 CPU Origin System

The shared memory Multi-Level Parallelism (MLP) technique, developed last year at NASA Ames has been very successful in dramatically improving the performance of important NASA CFD codes. This new and very simple parallel programming technique was first inserted into the OVERFLOW production CFD code in FY 1998. The OVERFLOW-MLP code's parallel performance scaled linearly to 256 CPUs on the NASA Ames 256 CPU Origin 2000 system (steger). Overall performance exceeded 20.1 GFLOP/s, or about 4.5x the performance of a dedicated 16 CPU C90 system. All of this was achieved without any major modification to the original vector based code. The OVERFLOW-MLP code is now in production on the inhouse Origin systems as well as being used offsite at commercial aerospace companies. Partially as a result of this work, NASA Ames has purchased a new 512 CPU Origin 2000 system to further test the limits of parallel performance for NASA codes of interest. This paper presents the performance obtained from the latest optimization efforts on this machine for the LAURA-MLP and OVERFLOW-MLP codes. The Langley Aerothermodynamics Upwind Relaxation Algorithm (LAURA) code is a key simulation tool in the development of the next generation shuttle, interplanetary reentry vehicles, and nearly all "X" plane development. This code sustains about 4-5 GFLOP/s on a dedicated 16 CPU C90. At this rate, expected workloads would require over 100 C90 CPU years of computing over the next few calendar years. It is not feasible to expect that this would be affordable or available to the user community. Dramatic performance gains on cheaper systems are needed. This code is expected to be perhaps the largest consumer of NASA Ames compute cycles per run in the coming year.The OVERFLOW CFD code is extensively used in the government and commercial aerospace communities to evaluate new aircraft designs. It is one of the largest consumers of NASA supercomputing cycles and large simulations of highly resolved full aircraft are routinely undertaken. Typical large problems might require 100s of Cray C90 CPU hours to complete. The dramatic performance gains with the 256 CPU steger system are exciting. Obtaining results in hours instead of months is revolutionizing the way in which aircraft manufacturers are looking at future aircraft simulation work. Figure 2 below is a current state of the art plot of OVERFLOW-MLP performance on the 512 CPU Lomax system. As can be seen, the chart indicates that OVERFLOW-MLP continues to scale linearly with CPU count up to 512 CPUs on a large 35 million point full aircraft RANS simulation. At this point performance is such that a fully converged simulation of 2500 time steps is completed in less than 2 hours of elapsed time. Further work over the next few weeks will improve the performance of this code even further.The LAURA code has been converted to the MLP format as well. This code is currently being optimized for the 512 CPU system. Performance statistics indicate that the goal of 100 GFLOP/s will be achieved by year's end. This amounts to 20x the 16 CPU C90 result and strongly demonstrates the viability of the new parallel systems rapidly solving very large simulations in a production environment.

Taft, James R.↗

NASA NTRS1985

Parallel computation with the force

A methodology, called the force, supports the construction of programs to be executed in parallel by a force of processes. The number of processes in the force is unspecified, but potentially very large. The force idea is embodied in a set of macros which produce multiproceossor FORTRAN code and has been studied on two shared memory multiprocessors of fairly different character. The method has simplified the writing of highly parallel programs within a limited class of parallel algorithms and is being extended to cover a broader class. The individual parallel constructs which comprise the force methodology are discussed. Of central concern are their semantics, implementation on different architectures and performance implications.

Jordan, H. F.↗

DOE OSTI2019

MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles

Optimal engine operation during a transient driving cycle is the key to achieving greater fuel economy, engine efficiency, and reduced emissions. In order to achieve continuously optimal engine operation, engine calibration methods use a combination of static correlations obtained from dynamometer tests for steady-state operating points and road and/or track performance data. As the parameter space of control variables, design variable constraints, and objective functions increases, the cost and duration for optimal calibration become prohibitively large. In order to reduce the number of dynamometer tests required for calibrating modern engines, a large-scale simulation-driven machine learning approach is presented in this work. A parallel, fast, robust, physics-based reduced-order engine simulator is used to obtain performance and emission characteristics of engines over a wide range of control parameters under various transient driving conditions (drive cycles). We scale the simulation up to 3,906 nodes of the Theta supercomputer at the Argonne Leadership Computing Facility to generate data required to train a machine learning model. The trained model is then used to predict various engine parameters of interest, and the results are compared with those predicted by the engine simulator. Our results show that a deepneural-network-based surrogate model achieves high accuracy: Pearson product-moment correlation values larger than 0.99 and mean absolute percentage error within 1.07% for various engine parameters such as exhaust temperature, exhaust pressure, nitric oxide, and engine torque. Once trained, the deep-neural-network-based surrogate model is fast for inference: it requires about 16 mu s for predicting the engine performance and emissions for a single design configuration compared with about 0.5 s per configuration with the engine simulator. Moreover, we demonstrate that transfer learning and retraining can be leveraged to incrementally retrain the surrogate model to cope with new configurations that fall outside the training data space.

deep learning↗

DOE OSTI2019

FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) ms with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600–700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Neuromorphic scaling advantages for energy-efficient random walk computations

Computing stands to be radically improved by neuromorphic computing (NMC) approaches inspired by the brain's incredible efficiency and capabilities. Most NMC research, which aims to replicate the brain's computational structure and architecture in man-made hardware, has focused on artificial intelligence; however, less explored is whether this brain-inspired hardware can provide value beyond cognitive tasks. We demonstrate that high-degree parallelism and configurability of spiking neuromorphic architectures makes them well-suited to implement random walks via discrete time Markov chains. Such random walks are useful in Monte Carlo methods, which represent a fundamental computational tool for solving a wide range of numerical computing tasks. Additionally, we show how the mathematical basis for a probabilistic solution involving a class of stochastic differential equations can leverage those simulations to provide solutions for a range of broadly applicable computational tasks. Despite being in an early development stage, we find that NMC platforms, at a sufficient scale, can drastically reduce the energy demands of high-performance computing platforms.

59 BASIC BIOLOGICAL SCIENCES↗