Quantum molecular dynamics on parallel GPUs: w13_qmdgpu [Slides]
A new algorithm for performing linear scaling quantum-based molecular dynamics simulations on multi-core machines parallel has been developed.
97 MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “parallel algorithms”
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.
Parallel-vector unsymmetric Eigen-Solver on high performance computers
The popular QR algorithm for solving all eigenvalues of an unsymmetric matrix is reviewed. Among the basic components in the QR algorithm, it was concluded from this study, that the reduction of an unsymmetric matrix to a Hessenberg form (before applying the QR algorithm itself) can be done effectively by exploiting the vector speed and multiple processors offered by modern high-performance computers. Numerical examples of several test cases have indicated that the proposed parallel-vector algorithm for converting a given unsymmetric matrix to a Hessenberg form offers computational advantages over the existing algorithm. The time saving obtained by the proposed methods is increased as the problem size increased.
Nguyen, Duc T.↗
EXAGRAPH: Graph and combinatorial methods for enabling exascale applications
Combinatorial algorithms in general and graph algorithms in particular play a critical enabling role in numerous scientific applications. However, the irregular memory access nature of these algorithms makes them one of the hardest algorithmic kernels to implement on parallel systems. With tens of billions of hardware threads and deep memory hierarchies, the exascale computing systems in particular pose extreme challenges in scaling graph algorithms. The codesign center on combinatorial algorithms, ExaGraph, was established to design and develop methods and techniques for efficient implementation of key combinatorial (graph) algorithms chosen from a diverse set of exascale applications. Algebraic and combinatorial methods have a complementary role in the advancement of computational science and engineering, including playing an enabling role on each other. In this paper, we survey the algorithmic and software development activities performed under the auspices of ExaGraph from both a combinatorial and an algebraic perspective. In particular, we detail our recent efforts in porting the algorithms to manycore accelerator (GPU) architectures. We also provide a brief survey of the applications that have benefited from the scalable implementations of different combinatorial algorithms to enable scientific discovery at scale. We believe that several applications will benefit from the algorithmic and software tools developed by the ExaGraph team.
97 MATHEMATICS AND COMPUTING↗
Speed challenge: a case for hardware implementation in soft-computing
For over a decade, JPL has been actively involved in soft computing research on theory, architecture, applications, and electronics hardware. The driving force in all our research activities, in addition to the potential enabling technology promise, has been creation of a niche that imparts orders of magnitude speed advantage by implementation in parallel processing hardware with algorithms made especially suitable for hardware implementation. We review our work on neural networks, fuzzy logic, and evolvable hardware with selected application examples requiring real time response capabilities.
neural networks fuzzy logic evolvable hardware sof↗
Extracting SIMD Parallelism from Recursive Task-Parallel Programs
The pursuit of computational efficiency has led to the proliferation of throughput-oriented hardware, from GPUs to increasingly wide vector units on commodity processors and accelerators. This hardware is designed to efficiently execute data-parallel computations in a vectorized manner. However, many algorithms are more naturally expressed as divide-and-conquer, recursive, task-parallel computations. In the absence of data parallelism, it seems that such algorithms are not well suited to throughput-oriented architectures. This paper presents a set of novel code transformations that expose the data parallelism latent in recursive, task- parallel programs. These transformations facilitate straightforward vectorization of task-parallel programs on commodity hardware. We also present scheduling policies that maintain high utilization of vector resources while limiting space usage. Across several task-parallel benchmarks, we demonstrate both efficient vector resource utilization and substantial speedup on chips using Intel’s SSE4.2 vector units, as well as accelerators using Intel’s AVX512 units. We then show through rigorous sampling that, in practice, our vectorization techniques are effective for a much larger class of programs.
Recursive Programs, task parallelism, vectorizatio↗
Efficient Execution of Recursive Programs on Commodity Vector Hardware
The pursuit of computational efficiency has led to the proliferation of throughput-oriented hardware, from GPUs to increasingly-wide vector units on commodity processors and accelerators. This hardware is designed to efficiently execute data-parallel computations in a vectorized manner. However, many algorithms are more naturally expressed as divide-and-conquer, recursive, task-parallel computations; in the absence of data parallelism, it seems that such algorithms are not well-suited to throughput-oriented architectures. This paper presents a set of novel code transformations that expose the data-parallelism latent in recursive, task-parallel programs. These transformations facilitate straightforward vectorization of task-parallel programs on commodity hardware. We also present scheduling policies that maintain high utilization of vector resources while limiting space usage. Across several task-parallel benchmarks, we demonstrate both efficient vector resource utilization and substantial speedup on chips using Intel's SSE4.2 vector units as well as accelerators using Intel's AVX512 units.
resursion↗
A non-destructive method for crack quantification in photovoltaic backsheets under accelerated and real-world exposures
The long-term durability of photovoltaic modules is paramount for the continued growth of the industry. Polymer backsheets are of particular concern since they provide electrical insulation and an environmental barrier. In this paper, 23 freestanding, multilayer backsheets with nine unique material combinations underwent four different weathering exposures under accelerated and real-world conditions. Besides changes in color and gloss, the induced degradation included parallel or mudflat cracks on 11 backsheets, sometimes in combination with delamination or blistering. Similar degradation has been observed in previous studies and is concerning since cracks compromise the mechanical integrity and electrical safety of backsheets. Quantitative parameters are desirable to reliably classify categories of cracks and supply unbiased features for statistical analysis in predictive lifetime models. We developed an analysis technique that utilizes surface profilometry data to quantify the depth, width, area, spacing, and number of cracks. Parameters are automatically extracted from the raw data by an algorithm running on a high performance distributed computing cluster. Our algorithm excelled at characterizing parallel cracks with minimal de-adhesion, and only an estimated 4% of crack detections were false positives. The addition of humidity and temperature variation formed up to three times as many cracks on a photodose basis compared to dry, constant temperature exposures. Cracks in real-world and accelerated exposures propagated to similar depths with equivalent photodoses; however, the number of cracks formed in accelerated exposures was far greater on a photodose basis. Of samples that cracked, the best performing backsheet configuration was polyvinyl fluoride/poly (ethylene-terephthalate)/polyethylene (PVF/PET/PE) while the least durable was PET/PET/ethylene-vinyl acetate. Finally, none of the six PVF/PET/PVF backsheets cracked in any of the exposures.
14 SOLAR ENERGY↗
GronOR: Massively Parallel and GPU-Accelerated Non-Orthogonal Configuration Interaction for Large Molecular Systems
GronOR is a program package for non-orthogonal configuration interaction calculations for an electronic wave function built in terms of anti-symmetrized products of multi-configuration molecular fragment wave functions. The two-electron integrals that have to be processed may be expressed in terms of atomic orbitals or in terms of an orbital basis determined from the molecular orbitals of the fragments. The code has been specifically designed for execution on distributed memory massively parallel and Graphics Processing Unit (GPU)-accelerated computer architectures, using an MPI+OpenACC/OpenMP programming approach. The task-based execution model used in the implementation allows for linear scaling with the number of nodes on the largest pre-exascale architectures available, provides hardware fault resiliency, and enables effective execution on systems with distinct central processing unit-only and GPU-accelerated partitions. The code interfaces with existing multi-configuration electronic structure codes that provide optimized molecular fragment orbitals, configuration interaction coefficients, and the required integrals. Algorithm and implementation details, parallel and accelerated performance benchmarks, and an analysis of the sensitivity of the accuracy of results and computational performance to thresholds used in the calculations are presented.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Planar Collisionless Shock Simulations with the Semi-implicit Particle-in-cell Model FLEKS
This study investigates the applicability of the semi-implicit particle-in-cell code FLexible Exascale Kinetic Simulator (FLEKS) to heliospheric shock simulations. We examine one- and two-dimensional local planar shock simulations, initialized using MHD states with upstream conditions representative of plasmas in the hypersonic, β ∼ 1 regime, for both quasi-perpendicular and quasi-parallel configurations. The refined algorithm in FLEKS proves robust, enabling accurate shock simulations with a grid resolution on the order of the electron inertial length d e . Our simulations successfully capture key shock features, including shock structures (foot, ramp, overshoot, and undershoot), upstream and downstream waves (fast magnetosonic, whistler, Alfvén ion-cyclotron, and mirror modes), and non-Maxwellian particle distributions. Crucially, we find that at least two spatial dimensions are critical for accurately reproducing downstream-wave physics in quasi-perpendicular shocks and capturing the complex dynamics of quasi-parallel shocks, including surface rippling, shocklets, short, large-amplitude magnetic structures, magnetic reconnection, and jets. Furthermore, our parameter studies demonstrate the impact of mass ratio and grid resolution on shock physics. This work provides valuable guidance for selecting appropriate physical and numerical parameters for shock simulations using a semi-implicit PIC method, paving the way for incorporating kinetic shock processes into large-scale collisionless plasma simulations with the MHD-AEPIC model.
plasma astrophysics↗
Assignment Of Finite Elements To Parallel Processors
Elements assigned approximately optimally to subdomains. Mapping algorithm based on simulated-annealing concept used to minimize approximate time required to perform finite-element computation on hypercube computer or other network of parallel data processors. Mapping algorithm needed when shape of domain complicated or otherwise not obvious what allocation of elements to subdomains minimizes cost of computation.
Salama, Moktar A.↗
Block-Iterative Methods for 3D Constant-Coefficient Stencils on GPUs and Multicore CPUs
Block iterative methods are extremely important as smoothers for multigrid methods, as preconditioners for Krylov methods, and as solvers for diagonally dominant linear systems. Developing robust and efficient smoother algorithms suitable for current and evolving GPU and multicore CPU systems is a significant challenge. We address this issue in the case of constant-coefficient stencils arising in the solution of elliptic partial differential equations on structured 3D uniform and adaptively refined block structured grids. Robust, highly parallel implementations of block Jacobi and chaotic block Gauss-Seidel algorithms with exact inversion of the blocks are developed using different parallelization techniques. Experimental results for NVIDIA Fermi/Kepler GPUs and AMD multicore systems are presented.
97 MATHEMATICS AND COMPUTING↗
On the parallel efficiency of the Frederickson-McBryan multigrid
To take full advantage of the parallelism in a standard multigrid algorithm requires as many processors as points. However, since coarse grids contain fewer points, most processors are idle during the coarse grid iterations. Frederickson and McBryan claim that retaining all points on all grid levels (using all processors) can lead to a superconvergent algorithm. The purpose of this work is to show that the parellel superconvergent multigrid (PSMG) algorithm of Frederickson and McBryan, though it achieves perfect processor utilization, is no more efficient than a parallel implementation of standard multigrid methods. PSMG is simply a new and perhaps simpler way of achieving the same results.
Decker, Naomi H.↗
Parallel Implementation of the Recursive Approximation of an Unsupervised Hierarchical Segmentation Algorithm
The hierarchical image segmentation algorithm (referred to as HSEG) is a hybrid of hierarchical step-wise optimization (HSWO) and constrained spectral clustering that produces a hierarchical set of image segmentations. HSWO is an iterative approach to region grooving segmentation in which the optimal image segmentation is found at N(sub R) regions, given a segmentation at N(sub R+1) regions. HSEG's addition of constrained spectral clustering makes it a computationally intensive algorithm, for all but, the smallest of images. To counteract this, a computationally efficient recursive approximation of HSEG (called RHSEG) has been devised. Further improvements in processing speed are obtained through a parallel implementation of RHSEG. This chapter describes this parallel implementation and demonstrates its computational efficiency on a Landsat Thematic Mapper test scene.
Tilton, James C.↗
Parallel simulated annealing with embedded machine learning and multifidelity models for reactor core design
This paper presents extensions to a penalty-free, parallel simulated annealing (SA) algorithm for multi-constrained combinatorial optimization with the aim of embedding multi-fidelity physics models into the annealing procedure. The method uses a low-fidelity, quickly executing model for rapid design space exploration and a high-fidelity model for detailed constraint resolution and on-the-fly bias correction. Machine learning models updated within the annealing procedure were used to bridge the gap between the multi-fidelity models, which led to accurate rapid exploration and efficient detailed constraint resolution. A software implementation of the new multi-fidelity optimization methods, called ML-PSA, was demonstrated on a continuous multi-fidelity optimization problem and a constrained combinatorial PWR lattice design problem. These problems demonstrate some of the features, parallel performance characteristics, and extensible nature of the multi-fidelity SA methods. This paper shows that the developed software and procedure are a general optimization tool that can be applied to a wide variety of scientific and engineering design optimization applications. (authors)
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
Dynamic programming on a shared-memory multiprocessor
Three new algorithms for solving dynamic programming problems on a shared-memory parallel computer are described. All three algorithms attempt to balance work load, while keeping synchronization cost low. In particular, for a multiprocessor having p processors, an analysis of the best algorithm shows that the arithmetic cost is O(n-cubed/6p) and that the synchronization cost is O(absolute value of log sub C n) if p much less than n, where C = (2p-1)/(2p + 1) and n is the size of the problem. The low synchronization cost is important for machines where synchronization is expensive. Analysis and experiments show that the best algorithm is effective in balancing the work load and producing high efficiency.
Edmonds, Phil↗
Ab Initio Computation of Rotationally-Averaged Pump–Probe X-ray and Electron Diffraction Signals
We develop a new algorithm for the computation of the rotationally averaged elastic molecular diffraction signal for the cases of perpendicular or parallel pump–probe geometries. The algorithm first collocates the charge density from an arbitrary ab initio wave function onto a Becke quadrature grid [A. Becke, J. Chem. Phys. 1988, 88, 2457], providing a high-fidelity multiresolution representation of the charge density. A double sum is then performed over the Becke grid points, and the interaction between points computed using the scattering kernels of Williamson and Zewail [J. C. Williamson and A. H. Zewail, J. Phys. Chem. 1994, 98, 2766]. These kernels analytically average over the molecular orientations with the cos 2 γ selection factor appropriate for one-photon dipole absorption in a perpendicular pump–probe geometry. We demonstrate that the method is converged with small grids containing <500 points/atom. We implement the algorithm on a GPU for increased efficiency and emonstrate the algorithm for molecules with up to a few dozen atoms. We explore the accuracy of the independent atom model (IAM) by comparison with our new and more accurate method. We also investigate the possibility of detecting signatures of electronic transitions in polyatomic pump–probe diffraction experiments.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Application of data flow concepts to a multigrid solver for the Euler equations
In this study a multigrid solver for Euler equations (FLO52R) was examined to determine its performance potential on a hypothetical computer using a data flow architecture. The proposed computer would require massive parallelism to realize its design performance. On the other hand this parallelism would be more easily realized than with a conventional vector processor such as the Cray-1S. Several changes to the proposed design substantially alleviated most of the remaining bottlenecks to parallel processing. Other changes allowed clearer definition of memory access and disk I/O. Finally, a portion of the algorithm was rewritten to improve parallel performance. With these changes, performance levels approaching that of a Cray-1S may be possible for a computer costing far less. Estimates are given for overall speed, memory, and network bandwidth, and for instruction memory requirements.
Merriam, M. L.↗
An Efficient and Accurate Algorithm for Computing Grid-Averaged Solar Fluxes for Horizontally Inhomogeneous Clouds
A computationally efficient method is presented to account for the horizontal cloud inhomogeneity by using a radiatively equivalent plane parallel homogeneous (PPH) cloud. The algorithm can accurately match the calculations of the reference (rPPH) independent column approximation (ICA) results, but use only the same computational time required for a single plane parallel computation. The effective optical depth of this synthetic sPPH cloud is derived by exactly matching the direct transmission to that of the inhomogeneous ICA cloud. The ffective9 scattering asymmetry factor is found from a pre-calculated albedo inverse look-up-table that is allowed to vary over the range from -1.0 to 1.0. In the special cases of conservative scattering and total absorption, the synthetic method is exactly equivalent to the ICA, with only a small bias (about 0.2% in flux) relative to ICA due to imperfect interpolation in using the look-up tables. In principle, the ICA albedo can be approximated accurately regardless of cloud inhomogeneity. For a more complete comparison, the broadband shortwave albedo and transmission calculated from the synthetic sPPH cloud and averaged over all incident directions, have the RMS biases of 0.26% and 0.76%, respectively, for inhomogeneous clouds over a wide variation of particle size. The advantages of the synthetic PPH method are that (1) it is not required that all the cloud subcolumns have uniform microphysical characteristic, (2) it is applicable to any 1D radiative transfer scheme, and (3) it can handle arbitrary cloud optical depth distributions and an arbitrary number of cloud subcolumns with uniform computational efficiency.
cloud inhomogeneity↗