Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel computations”

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 1,243 records · Page 69
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Using Computational Storage Devices: OpenMP/MPI and Charliecloud [Slides]

Originally used Spark and HadoopFS. Collected interesting results, but this method had its issues: limited application, too much overhead to gauge CSDs’ raw performance. Solution? Rewrite our benchmarks without Spark using Serial Python and Serial & Parallel C++ (Combinations of OpenMP & OpenMPI). Compared to Spark and Python, C++ implementation is a lot faster. Caveat: an expert with Spark or Python would likely be able to improve the performance of those implementations. Computational power of our CSDs seem to be much lower than the host machine. Using all 4 cores of a single CSD, the job takes ~6.8x longer than using just one core on the host machine. Host also seems to scale better with increasing file size. Resulting Question: When, if ever, would it make sense to use CSDs for compute rather than a much-faster host?

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Crosslinking and Gelation of Polymer Brushes and Free Polymer Chains in a Confined Space during Controlled Radical Polymerization-A Computer Simulation Study

The confinement effect on crosslinking and gelation during controlled/living copolymerization of a monovinyl and a divinyl monomer was studied by Monte Carlo computer simulation using the dynamic lattice liquid method. The simulated reactions took place in plane-parallel slits of various widths for various grafting densities (GDs) and various initial initiator/crosslinker ratios ([X] 0 /[Ini] 0 ). Monomers and crosslinkers were initially randomly distributed in the slit, but initiators were either anchored to one solid plane (polymer brushes) or randomly distributed (free chains). For brushes, the gel point (GP) depended on GD and [X] 0 /[Ini] 0 . The higher these parameters, the lower was the gel point. The gel point was also affected by the slit width. For free, nongrafted chains, the dependence of GP on slit width was negligible. For brushes, a nonuniform density of crosslinks was found, the highest density was close to the wall. This asymmetry was high at the gel point and decreased at higher conversions.

36 MATERIALS SCIENCE↗
DOE OSTI2019

Cold plasma finite element wave model for helicon waves

Helicon waves have been recently proposed as an off-axis current drive actuator due to their expected high current drive efficiency in the mid-radius region in high beta tokamaks. This current drive efficiency has mostly been calculated ignoring the effects of the plasma in the scrape-off-layer (SOL) in the modeling. The net core current drive efficiency will decrease if helicon power is lost to the SOL. Previous efforts to estimate the loss of helicon power in the SOL have used the hot plasma code AORSA. The large computational cost of AORSA prevents large parametric scans, so to further the understanding of helicon power loss in the SOL, a reduced finite element, full wave plasma model with effective collision frequency for collisional and Landau damping has been developed to study the helicon wave power lost to the SOL. It will be shown that the reduced finite element model (FEM) can reproduce the magnitude and trends of helicon |E| field patterns and power loss in the SOL of the hot plasma AORSA model. The reduced FEM provides significant advantages over AORSA in reducing the computational time and memory requirements, and in simulating arbitrary tokamak vessel geometry. Parametric scans of antenna parallel refractive index, antenna location, minimum SOL density, SOL density gradient, and vacuum vessel geometry will be carried out to determine the dependencies of the helicon power lost to the SOL as a function of important parameters. Subsequently, the helicon cutoff density is shown to be an important quantity in determining helicon power lost to the SOL. Furthermore, losses due to antenna loading and wave accessibility are also observed at different antenna and plasma parameters.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Core inductive electric field during sawtooth crashes on DIII-D

Sawtooth crashes on tokamak plasmas exhibit relaxation much faster than resistive time scales via a mechanism not fully understood. Using core magnetic measurements from the Radial Interferometer-Polarimeter (RIP) diagnostic on the DIII-D tokamak, Grad–Shafranov equilibria constrained by internal magnetic measurements that have high time resolution (<1μs) can be computed, allowing analysis of how equilibrium parameters such as safety factor q, current density J, and parallel electric field E ∥ , particularly on-axis, evolve. At the sawtooth crash, on-axis safety factor q 0 is observed to rise by 5% but remain below 1 throughout the cycle, and on-axis current density J 0 is observed to drop by 5%. On-axis parallel electric field E ∥ (0) is found to be balanced by ηJ 0 (resistivity times on-axis current density) except during the 200 µs crash period, where E ∥ (0) reaches 22 V m –1 , exceeding ηJ 0 by a factor of more than 2000. These first measurements in tokamak plasmas verify that generalized Ohm's law is not balanced during the crash by resistive effects alone; this is a finding expected due to the relaxation being much faster than resistive timescales. As a result, measurement of the electric field during the tokamak sawtooth serves to illuminate the physical mechanisms at work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2019

iez: Resource Contention Aware Load Balancing for Large-Scale Parallel File Systems

Parallel I/O performance is crucial to sustaining scientific applications on large-scale High-Performance Computing (HPC) systems. However, I/O load imbalance in the underlying distributed and shared storage systems can significantly reduce overall application performance. There are two conflicting challenges to mitigate this load imbalance: (i) optimizing systemwide data placement to maximize the bandwidth advantages of distributed storage servers, i.e., allocating I/O resources efficiently across applications and job runs; and (ii) optimizing client-centric data movement to minimize I/O load request latency between clients and servers, i.e., allocating I/O resources efficiently in service to a single application and job run. Moreover, existing approaches that require application changes limit wide-spread adoption in commercial or proprietary deployments. We propose iez, an “end-to-end control plane” where clients transparently and adaptively write to a set of selected I/O servers to achieve balanced data placement. Our control plane leverages realtime load information for distributed storage server global data placement while our design model leverages trace-based optimization techniques to minimize I/O load request latency between clients and servers. We evaluate our proposed system on an experimental cluster for two common use cases: synthetic I/O benchmark IOR for large sequential writes and a scientific application I/O kernel, HACC-I/O. Results show read and write performance improvements of up to 34% and 32%, respectively, compared to the state of the art.

Wadhwa, Bharti↗
DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (distributed parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

graph algorithms, high performance comptuing↗
DOE OSTI2021

MemXCT: Design, Optimization, Scaling, and Reproducibility of X-Ray Tomography Imaging

Here, this work extends our previous research entitled "MemXCT: Memory-centric X-ray CT Reconstruction with Massive Parallelization" that was originally published at SC19 conference (Hidayetoglu et al., 2019) with reproducibility of the computational imaging performance. X-ray computed tomography (XCT) is regularly used at synchrotron light sources to study the internal morphology of materials at high resolution. However, experimental constraints, such as radiation sensitivity, can result in noisy or undersampled measurements. Further, depending on the resolution, sample size and data acquisition rates, the resulting noisy dataset can be in the order of terabytes. Advanced iterative reconstruction techniques can produce high-quality images from noisy measurements, but their computational requirements have made their use an exception rather than the rule. We propose a novel memory-centric approach that avoids redundant computations at the expense of additional memory complexity. We develop a memory-centric iterative reconstruction system, MemXCT, that uses an optimized SpMV implementation with two-level pseudo-Hilbert ordering and multi-stage input buffering. We evaluate MemXCT on various supercomputer architectures involving KNL and GPU. MemXCT can reconstruct a large (11Kx11K) mouse brain tomogram in 10 seconds using 4096 KNL nodes (256K cores). The results presented in our original article at the SC19 were based on large-scale supercomputing resources. The MemXCT application was selected for the Student Cluster Competition (SCC) Reproducibility Challenge and evaluated on a variety of cloud computing resources by universities around the world in the SC20 conference. We summarize the results of the top-ranked SCC Reproducibility Challenge teams and identify the most pertinent measures for ensuring the reproducibility of our experiments in this article.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Scalable Multiphysics Block Preconditioning for Low Mach Number Compressible Resistive MHD with Application to Magnetic Confinement Fusion

This study investigates multiphysics block preconditioners that are critical in devising scalable Newton–Krylov iterative solvers for longer time-scale fully implicit fluid plasma models. The specific model of interest is the visco-resistive, low Mach number, compressible magnetohydrodynamics (MHD) model. This model describes the dynamics of conducting fluids in the presence of electromagnetic fields and can be used to study aspects of astrophysical phenomena, important science and technology applications, and basic plasma physics. The specific application of interest that motivates this study is the macroscopic simulation of longer time-scale stability and disruptions of magnetic confinement fusion devices, specifically the ITER Tokamak. The computational solution of the governing balance equations for mass, momentum, heat transfer, and magnetic induction for resistive MHD systems can be extremely challenging. These difficulties arise from both the strong nonlinear, nonsymmetric coupling of fluid and electromagnetic phenomena as well as the significant range of time and length scales that the interactions of these physical mechanisms produce. To handle the range of time and spatial scales of interest, a fully implicit unstructured variational multiscale finite element formulation is employed. For the scalable solution of the Newton linearized systems, fully coupled block preconditioners are designed to leverage algebraic multigrid subsolves. In conclusion, results are presented for the strong and weak scaling of the method as well as the robustness of these techniques for a large range of Lundquist numbers.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

libROM

libROM is a collection of C++ classes that compute reduced order models and hyperreduced order models for systems of ordinary differential equations. libROM includes parallel, adaptive methods for proper orthogonal decomposition, and parallel, non-adaptive methods for hyperreduction using the discrete empirical interpolation method.

Choi, Youngsoo↗
DOE OSTI2018

High Brightness Superconducting RF Gun Cavity

The Phase I goals were to numerically optimize a TM020/TM010 SRF gun with a demountable back wall, using SLAC’s state-of-the-art massive parallel ACE3P suite of 3D Finite Element Analysis codes available at the National Energy Research Scientific Computing Center (NERSC) , which includes: a) TM020 cell shape, including impact of RF focusing on beam dynamics; b) optimum number of TM010-cells to achieve low emittances; c) multipacting simulations back wall opening; d) dark current investigations; e) studies on LOM and HOM damping with waveguides/port on TM020-cells using wakefield solver can be conducted as well but are not required stringently; f) conceptual design of a power input coupler; g) multiphysics simulations to optimize the gun thermal management and cooling requirements for a superconducting joint; h) multivariate beam dynamical optimization in conjunction with the gun optimization; and i) finalize an engineering design for vertical high power tests at JLab.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Rapid QSTS Simulations for High-Resolution Comprehensive Assessment of Distributed PV

The rapid increase in penetration of distributed energy resources on the electric power distribution system has created a need for more comprehensive interconnection modeling and impact analysis. Unlike conventional scenario-based studies, quasi-static time-series (QSTS) simulations can realistically model time-dependent voltage controllers and the diversity of potential impacts that can occur at different times of year. However, to accurately model a distribution system with all its controllable devices, a yearlong simulation at 1-second resolution is often required, which could take conventional computers a computational time of 10 to 120 hours when an actual unbalanced distribution feeder is modeled. This computational burden is a clear limitation to the adoption of QSTS simulations in interconnection studies and for determining optimal control solutions for utility operations. The solutions we developed include accurate and computationally efficient QSTS methods that could be implemented in existing open-source and commercial software used by utilities and the development of methods to create high-resolution proxy data sets. This project demonstrated multiple pathways for speeding up the QSTS computation using new and innovative methods for advanced time-series analysis, faster power flow solvers, parallel processing of power flow solutions and circuit reduction. The target performance level for this project was achieved with year-long high-resolution time series solutions run in less than 5 minutes within an acceptable error.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Distributed Multi-GPU Community Detection on Exascale Computing Platforms

Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (Distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.

Sattar, Naw Safrin↗
DOE OSTI2020

Optimizing High Performance Markov Clustering for Pre-Exascale Architectures

HipMCL is a high-performance distributed memory implementation of the popular Markov Cluster Algorithm (MCL) and can cluster large-scale networks within hours using a few thousand CPU-equipped nodes. It relies on sparse matrix computations and heavily makes use of the sparse matrix-sparse matrix multiplication kernel (SpGEMM). The existing parallel algorithms in HipMCL are not scalable to Exascale architectures, both due to their communication costs dominating the runtime at large concurrencies and also due to their inability to take advantage of accelerators that are increasingly popular. In this work, we systematically remove scalability and performance bottlenecks of HipMCL. We enable GPUs by performing the expensive expansion phase of the MCL algorithm on GPU. Additionally, we propose a CPU-GPU joint distributed SpGEMM algorithm called pipelined Sparse SUMMA and integrate a probabilistic memory requirement estimator that is fast and accurate. Furthermore, we develop a new merging algorithm for the incremental processing of partial results produced by the GPUs, which improves the overlap efficiency and the peak memory usage. We also integrate a recent and faster algorithm for performing SpGEMM on CPUs. We validate our new algorithms and optimizations with extensive evaluations. With the enabling of the GPUs and integration of new algorithms, HipMCL is up to 12.4x faster, being able to cluster a network with 70 million proteins and 68 billion connections just under 15 minutes using 1024 nodes of ORNL's Summit supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Scalable implementation of polynomial filtering for density functional theory calculation in PARSEC

In this work, we present an efficient implementation of polynomial filtering methods in PARSEC, a real-space pseudopotential based Kohn–Sham density functional theory solver. The implementation described here improves upon a Chebyshev-filtered subspace iteration algorithm used in the previous version of PARSEC. We present a hybrid polynomial filtering scheme that combines Chebyshev-filtered subspace iteration and a spectrum slicing method that partitions the spectrum into several spectral slices and uses bandpass-filtered subspace iteration to compute approximate eigenpairs within each interior slice simultaneously. We describe a procedure to partition a spectrum and construct polynomial filters. We also discuss a number of practical issues such as the use of appropriate data layouts for carrying out the computation on a two-dimensional process grid and how to achieve good load balance by allocating an appropriate number of process groups to each spectral slice. Numerical examples are presented to demonstrate the effectiveness of the hybrid polynomial filtering method as well as the superior parallel scalability of spectrum slicing in comparison to that of Chebyshev-filtered subspace iteration.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Production Application Performance Data Streaming for System Monitoring

In this article, we present an approach to streaming collection of application performance data. Practical application performance tuning and troubleshooting in production high-performance computing (HPC) environments requires an understanding of how applications interact with the platform, including (but not limited to) parallel programming libraries such as Message Passing Interface (MPI). Several profiling and tracing tools exist that collect heavy runtime data traces either in memory (released only at application exit) or on a file system (imposing an I/O load that may interfere with the performance being measured). Although these approaches are beneficial in development stages and post-run analysis, a systemwide and low-overhead method is required to monitor deployed applications continuously. This method must be able to collect information at both the application and system levels to yield a complete performance picture. In our approach, an application profiler collects application event counters. A sampler uses an efficient inter-process communication method to periodically extract the application counters and stream them into an infrastructure for performance data collection. We implement a tool-set based on our approach and integrate it with the Lightweight Distributed Metric Service (LDMS) system, a monitoring system used on large-scale computational platforms. LDMS provides the infrastructure to create and gather streams of performance data in a low overhead manner. We demonstrate our approach using applications implemented with MPI, as it is one of the most common standards for the development of large-scale scientific applications. We utilize our tool-set to study the impact of our approach on an open source HPC application, Nalu. Our tool-set enables us to efficiently identify patterns in the behavior of the application without source-level knowledge. We leverage LDMS to collect system-level performance data and explore the correlation between the system and application events. Finally, we demonstrate how our tool-set can help detect anomalies with a low latency. We run tests on two different architectures: a system enabled with Intel Xeon Phi and another system equipped with Intel Xeon processor. Our overhead study shows our method imposes at most 0.5% CPU usage overhead on the application in realistic deployment scenarios.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A step towards the final frontier: Lessons learned from acceptance testing of the first HPE/Cray EX 3000 system at ORNL

Summary In this article, we summarize the deployment of the Air Force Weather (AFW) HPC11 system at Oak Ridge National Laboratory (ORNL) including the process followed to successfully complete acceptance testing of the system. HPC11 is the first HPE/Cray EX 3000 system that has been successfully released to its user community in a federal facility. HPC11 consists of two identical 800‐node supercomputers, Fawbush and Miller, with access to two independent and identical lustre parallel file systems. HPC11 is equipped with Slingshot 10 interconnect technology and relies on the HPE Performance Cluster Manager software for system configuration. ORNL has a clearly defined acceptance testing process used to ensure that every new system deployed can provide the necessary capabilities to support user workloads. We worked closely with HPE and AFW to develop a set of tests that used the United Kingdom's Meteorological Office's Unified Model and 4‐dimensional variational data assimilation. We also included benchmarks and applications from the Oak Ridge Leadership Computing Facility portfolio to fully exercise the HPE/Cray programming environment and evaluate the functionality and performance of the system. Acceptance testing of HPC11 required parallel execution of each element on Fawbush and Miller. In addition, careful coordination was needed to ensure successful acceptance of the newly deployed lustre file systems alongside the compute resources. In this work, we present test results from specific system components and provide an overview of the issues identified, challenges encountered, and the lessons learned along the way.

Melesse Vergara, Verónica G.↗