Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel processing”

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 613 records · Page 34

Expressing Parallelism with ROOT

The need for processing the ever-increasing amount of data generated by the LHC experiments in a more efficient way has motivated ROOT to further develop its support for parallelism. Such support is being tackled both for shared-memory and distributed-memory environments. The incarnations of the aforementioned parallelism are multi-threading, multi-processing and cluster-wide executions. In the area of multi-threading, we discuss the new implicit parallelism and related interfaces, as well as the new building blocks to safely operate with ROOT objects in a multi-threaded environment. Regarding multi-processing, we review the new MultiProc framework, comparing it with similar tools (e.g. multiprocessing module in Python). Finally, as an alternative to PROOF for cluster-wide executions, we introduce the efforts on integrating ROOT with state-of-the-art distributed data processing technologies like Spark, both in terms of programming model and runtime design (with EOS as one of the main components). For all the levels of parallelism, we discuss, based on real-life examples and measurements, how our proposals can increase the productivity of scientists.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

File I/O for MPI Applications in Redundant Execution Scenarios

As multi-petascale and exa-scale high-performance computing (HPC) systems inevitably have to deal with a number of resilience challenges, such as a significant growth in component count and smaller circuit sizes with lower circuit voltages, redundancy may offer an acceptable level of resilience that traditional fault tolerance techniques, such as checkpoint/restart, do not. Although redundancy in HPC is quite controversial due to the associated cost for redundant components, the constantly increasing number of cores-per-processor is tilting this cost calculation toward a system design where computation, such as for redundancy, is much cheaper and communication, needed for checkpoint/restart, is much more expensive. Recent research and development activities in redundancy for Message Passing Interface (MPI) applications focused on availability/reliability models and replication algorithms. This paper takes a first step toward solving an open research problem associated with running a parallel application redundantly, which is file I/O under redundancy. The approach intercepts file I/O calls made by a redundant application to employ coordination protocols that execute file I/O operations in a redundancy-oblivious fashion when accessing a node-local file system, or in a redundancy-aware fashion when accessing a shared networked file system. A proof-of concept prototype is presented and a number of coordination protocols are described and evaluated. The results show the performance impact for redundantly accessing a shared networked file system, but also demonstrate the capability to regain performance by utilizing MPI communication between replicas and parallel file I/O.

99 GENERAL AND MISCELLANEOUS↗

Oxygen transport properties estimation by classical trajectory–direct simulation Monte Carlo

Coupling direct simulation Monte Carlo (DSMC) simulations with classical trajectory calculations is a powerful tool to improve predictive capabilities of computational dilute gas dynamics. The considerable increase in computational effort outlined in early applications of the method can be compensated by running simulations on massively parallel computers. In particular, Graphics Processing Unit acceleration has been found quite effective in reducing computing time of classical trajectory (CT)-DSMC simulations. The aim of the present work is to study dilute molecular oxygen flows by modeling binary collisions, in the rigid rotor approximation, through an accurate Potential Energy Surface (PES), obtained by molecular beams scattering. The PES accuracy is assessed by calculating molecular oxygen transport properties by different equilibrium and non-equilibrium CT-DSMC based simulations that provide close values of the transport properties. Comparisons with available experimental data are presented and discussed in the temperature range 300–900 K, where vibrational degrees of freedom are expected to play a limited (but not always negligible) role.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Performance study of GPUs in real-time trigger applications for HEP experiments

Graphical Processing Units (GPUs) have evolved into highly parallel, multi-threaded, multicore powerful processors with high memory bandwidth. GPUs are used in a variety of intensive computing applications. The combination of highly parallel architecture and high memory bandwidth makes GPUs a potentially promising technology for effective real-time processing for High Energy Physics (HEP) experiments. However, not much is known of their performance in real-time applications that require low latency, such as the trigger for HEP experiments. We describe an R and D project with the goal to study the performance of GPU technology for possible low latency applications, performing basic operations as well as some more advanced HEP lower-level trigger algorithms (such as fast tracking or jet finding). We present some preliminary results on timing measurements, comparing the performance of a CPU versus a GPU with NVIDIA's CUDA general-purpose parallel computing architecture, carried out at CDF's Level-2 trigger test stand. These studies will provide performance benchmarks for future studies to investigate the potential and limitations of GPUs for real-time applications in HEP experiments.

43 PARTICLE ACCELERATORS↗

Parallel Simulation of Quantum Networks with Distributed Quantum State Management

Quantum network simulators offer the opportunity to cost-efficiently investigate potential avenues for building networks that scale with the number of users, communication distance, and application demands by simulating alternative hardware designs and control protocols. Several quantum network simulators have been recently developed with these goals in mind. As the size of the simulated networks increases, however, sequential execution becomes time-consuming. Parallel execution presents a suitable method for scalable simulations of large-scale quantum networks, but the unique attributes of quantum information create unexpected challenges. In this work, we identify requirements for parallel simulation of quantum networks and develop the first parallel discrete-event quantum network simulator by modifying the existing serial simulator SeQUeNCe. Our contributions include the design and development of a quantum state manager (QSM) that maintains shared quantum information distributed across multiple processes. We also optimize our parallel code by minimizing the overhead of the QSM and decreasing the amount of synchronization needed among processes. Using these techniques, we observe a speedup of 2 to 25 times when simulating a 1,024-node linear network topology using 2 to 128 processes. We also observe an efficiency greater than 0.5 for up to 32 processes in a linear network topology of the same size and with the same workload. We repeat this evaluation with a randomized workload on a caveman network. We also introduce several methods for partitioning networks by mapping them to different parallel simulation processes. We have released the parallel SeQUeNCe simulator as an open source tool alongside the existing sequential version.

97 MATHEMATICS AND COMPUTING↗

Petascale turbulence simulation using a highly parallel fast multipole method on GPUs

This paper reports large-scale direct numerical simulations of homogeneous-isotropic fluid turbulence, achieving sustained performance of 1.08 petaflop/s on gpu hardware using single precision. The simulations use a vortex particle method to solve the Navier–Stokes equations, with a highly parallel fast multipole method (fmm) as numerical engine, and match the current record in mesh size for this application, a cube of computational points solved with a spectral method. The standard numerical approach used in this field is the pseudo-spectral method, relying on the fft algorithm as the numerical engine. The particle-based simulations presented in this paper quantitatively match the kinetic energy spectrum obtained with a pseudo-spectral method, using a trusted code. In terms of parallel performance, weak scaling results show the fmm-based vortex method achieving 74% parallel efficiency on 4096 processes (one gpu per mpi process, 3 gpus per node of the tsubame-2.0 system). The fft-based spectral method is able to achieve just 14% parallel efficiency on the same number of mpi processes (using only cpu cores), due to the all-to-all communication pattern of the fft algorithm. The calculation time for one time step was 108 s for the vortex method and 154 s for the spectral method, under these conditions. Computing with 69 billion particles, this work exceeds by an order of magnitude the largest vortex-method calculations to date.

Computer Science↗

An Accelerated Clip Algorithm for Unstructured Meshes: A Batch-Driven Approach

The clip technique is a popular method for visualizing complex structures and phenomena within 3D unstructured meshes. Meshes can be clipped by specifying a scalar isovalue to produce an output unstructured mesh with its external surface as the isovalue. Similar to isocontouring, the clipping process relies on scalar data associated with the mesh points, including scalar data generated by implicit functions such as planes, boxes, and spheres, which facilitates the visualization of results interior to the grid. In this paper, we introduce a novel batch-driven parallel algorithm based on a sequential clip algorithm designed for high-quality results in partial volume extraction. Our algorithm comprises five passes, each progressively processing data to generate the resulting clipped unstructured mesh. The novelty lies in the use of fixed-size batches of points and cells, which enable rapid workload trimming and parallel processing, leading to a significantly improved memory footprint and run-time performance compared to the original version. On a 32-core CPU, the proposed batch-driven parallel algorithm demonstrates a run-time speed-up of up to 32.6x and a memory footprint reduction of up to 4.37x compared to the existing sequential algorithm. The software is currently available under an open-source license in the VTK visualization system.

Tsalikis, Spiros↗

Geometric GNNs for charged particle tracking at GlueX

Nuclear physics experiments are aimed at uncovering the fundamental building blocks of matter. The experiments involve high-energy collisions that produce complex events with many particle trajectories. Tracking charged particles resulting from collisions in the presence of a strong magnetic field is critical to enable the reconstruction of particle trajectories and precise determination of interactions. It is traditionally achieved through combinatorial approaches that scale worse than linearly as the number of hits grows. Since particle hit data naturally form a point cloud and can be structured as graphs, graph neural networks (GNNs) emerge as an intuitive and effective choice for this task. In this study, we evaluate the GNN model for track finding on the data from the GlueX experiment at Jefferson Lab. We use simulation data to train the model and test on both simulation and real GlueX measurements. We demonstrate that GNN-based track finding outperforms the currently used traditional method at GlueX in terms of segment-based efficiency at a fixed purity while providing faster inferences. We show that the GNN model can achieve significant speedup by processing multiple events in batches, which exploits the parallel computation capability of graphical processing units (GPUs). Finally, we compare the GNN implementation on GPU and field-programmable gate array and describe the trade-off.

batched GNN pipeline↗

Parallel FFT-based Poisson Solver for Isolated Three-dimensional Systems

We describe an implementation to solve Poisson's equation for an isolated system on a unigrid mesh using FFTs. The method solves the equation globally on mesh blocks distributed across multiple processes on a distributed-memory parallel computer. Test results to demonstrate the convergence and scaling properties of the implementation are presented. The solver is offered to interested users as the library PSPFFT.

99 GENERAL AND MISCELLANEOUS↗

Parallel Block Structured Adaptive Mesh Refinement on Graphics Processing Units

Block-structured adaptive mesh refinement is a technique that can be used when solving partial differential equations to reduce the number of zones necessary to achieve the required accuracy in areas of interest. These areas (shock fronts, material interfaces, etc.) are recursively covered with finer mesh patches that are grouped into a hierarchy of refinement levels. Despite the potential for large savings in computational requirements and memory usage without a corresponding reduction in accuracy, AMR adds overhead in managing the mesh hierarchy, adding complex communication and data movement requirements to a simulation. In this paper, we describe the design and implementation of a native GPU-based AMR library, including: the classes used to manage data on a mesh patch, the routines used for transferring data between GPUs on different nodes, and the data-parallel operators developed to coarsen and refine mesh data. We validate the performance and accuracy of our implementation using three test problems and two architectures: an eight-node cluster, and over four thousand nodes of Oak Ridge National Laboratory’s Titan supercomputer. Our GPU-based AMR hydrodynamics code performs up to 4.87× faster than the CPU-based implementation, and has been scaled to over four thousand GPUs using a combination of MPI and CUDA.

97 MATHEMATICS AND COMPUTING↗

Graphics processing unit accelerated three-dimensional model for the simulation of pulsed low-temperature plasmas

A 3-dimensional particle-in-cell/Monte Carlo collision simulation that is fully implemented on a graphics processing unit (GPU) is described and used to determine low-temperature plasma characteristics at high reduced electric field, E/n, in nitrogen gas. Details of implementation on the GPU using the NVIDIA Compute Unified Device Architecture framework are discussed with respect to efficient code execution. The software is capable of tracking around 10 × 10{sup 6} particles with dynamic weighting and a total mesh size larger than 10{sup 8} cells. Verification of the simulation is performed by comparing the electron energy distribution function and plasma transport parameters to known Boltzmann Equation (BE) solvers. Under the assumption of a uniform electric field and neglecting the build-up of positive ion space charge, the simulation agrees well with the BE solvers. The model is utilized to calculate plasma characteristics of a pulsed, parallel plate discharge. A photoionization model provides the simulation with additional electrons after the initial seeded electron density has drifted towards the anode. Comparison of the performance benefits between the GPU-implementation versus a CPU-implementation is considered, and a speed-up factor of 13 for a 3D relaxation Poisson solver is obtained. Furthermore, a factor 60 speed-up is realized for parallelization of the electron processes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Parallel point defect identification in molecular dynamics simulations without post-processing: A compute and dump style for LAMMPS

Two classes for the molecular dynamics program LAMMPS – one compute style and one dump style – are presented that are designed to identify, count, and output point defects in cascade damage and related molecular dynamics simulations. The calculations are done in parallel across multiple MPI processes, and can be done at the same time as the original simulation. This drastically reduces storage requirements by eliminating the need to post-process every atom in the system. Non-cubic lattices, free surfaces, and large voids can be eliminated from the output by suitable choices of the reference lattice. The classes are derived from LAMMPS’s Dump and Compute classes, and pose no additional overhead to LAMMPS if they are not used.

42 ENGINEERING↗

Computational Complexity of Neuromorphic Algorithms

Neuromorphic computing has several characteristics that make it an extremely compelling computing paradigm for post Moore computation. Some of these characteristics include intrinsic parallelism, inherent scalability, collocated processing and memory, and event-driven computation. While these characteristics impart energy efficiency to neuromorphic systems, they do come with their own set of challenges. One of the biggest challenges in neuromorphic computing is to establish the theoretical underpinnings of the computational complexity of neuromorphic algorithms. In this paper, we take the first steps towards defining the space and time complexity of neuromorphic algorithms. Specifically, we describe a model of neuromorphic computation and state the assumptions that govern the computational complexity of neuromorphic algorithms. Next, we present a theoretical framework to define the computational complexity of a neuromorphic algorithm. We explicitly define what space and time complexities mean in the context of neuromorphic algorithms based on our model of neuromorphic computation. Finally, we leverage our approach and define the computational complexities of six neuromorphic algorithms: constant function, successor function, predecessor function, projection function, neuromorphic sorting algorithm and neighborhood subgraph extraction algorithm.

Date, Prasanna↗

Reduced model simulations of the scrape-off-layer heat-flux width and comparison with experiment

Reduced model simulations of turbulence in the edge and scrape-off-layer (SOL) region of a spherical torus or tokamak plasma are employed to address the physics of the scrape-off-layer heat flux width. The simulation model is an electrostatic two-dimensional fluid turbulence model, applied in the plane perpendicular to the magnetic field at the outboard midplane of the torus. The model contains curvature-driven-interchange modes, sheath losses, and both perpendicular turbulent diffusive and convective (blob) transport. These transport processes compete with classical parallel transport to set the SOL width. Midplane SOL profiles of density, temperature and parallel heat flux are obtained from the simulation and compared with experimental results from the National Spherical Torus Experiment (NSTX) to study the scaling of the heat flux width with power and plasma current. It is concluded that midplane turbulence is the main contributor to the SOL heat flux width for the low power H-mode discharges studied, while additional physics is required to explain the plasma current scaling of the SOL heat flux width observed experimentally in higher power discharges. Intermittent separatrix spanning convective cells are found to be the main mechanism that sets the near-SOL width in the simulations. The roles of sheared flows and blob trapping vs. emission are discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Lazy Shadowing: An Adaptive, Power-Aware, Resiliency Framework for Extreme Scale Computing

The inherent instability of extreme-scale computing systems puts into question the viability of traditional fault-tolerance methods and calls for a reconsideration of the fault-tolerance and power-awareness problem, at scale. This project explores a novel paradigm, Lazy Shadowing, to achieve high resiliency in future extreme-scale systems. The basic tenet of Lazy Shadowing is the association of a shadow with each process which runs in parallel, but on a different node and at a reduced execution rate, than its associated process. The successful completion of the main process causes the immediate termination of the shadow, resulting in significant energy savings. Upon failure of the main process, however, the shadow’s execution rate is increased so that it completes by the expected completion time without significantly impacting the progress of the remaining tasks. Different approaches can be used to control execution rate, including co-locating multiple shadows on a single computing node and/or using Dynamic Voltage and Frequency Scaling.

97 MATHEMATICS AND COMPUTING↗

Multi-petascale highly efficient parallel supercomputer

A Multi-Petascale Highly Efficient Parallel Supercomputer of 100 petaflop-scale includes node architectures based upon System-On-a-Chip technology, where each processing node comprises a single Application Specific Integrated Circuit (ASIC). The ASIC nodes are interconnected by a five dimensional torus network that optimally maximize the throughput of packet communications between nodes and minimize latency. The network implements collective network and a global asynchronous network that provides global barrier and notification functions. Integrated in the node design include a list-based prefetcher. The memory system implements transaction memory, thread level speculation, and multiversioning cache that improves soft error rate at the same time and supports DMA functionality allowing for parallel processing message-passing.

97 MATHEMATICS AND COMPUTING↗

Towards Flexible Exascale Stream Processing System Simulation

Stream processing is an important emerging computational model for performing complex operations on and across multi-source, high-volume, unpredictable dataflows. We present Flow, a platform for parallel and distributed stream processing system simulation that provides a flexible modeling environment for analyzing stream processing applications. The Flow stream processing system simulator is a high-performance, scalable simulator that automatically parallelizes chunks of the model space and incurs near-zero synchronization overhead for acyclic stream application graphs. We show promising parallel and distributed event rates exceeding 149 million events per second on a cluster with 512 processor cores.

99 GENERAL AND MISCELLANEOUS↗

The High-Stakes Race in High-Performance Computing

Very fast computers are increasingly critical to maintain national security and for many areas of science and industry to model chemical processes or predict material properties. U.S. leadership in high-performance computing is now challenged by China, as each country seeks to build faster computers by increasing the number of processing units that operate in parallel. It turns out, however, that raw computing speed is not the only thing that counts. Specialized software that can make effective use of these massively parallel computers—by dividing up problems among all those processing units and reassembling the results—is equally important. And here the U.S. holds a substantial lead, thanks to decades of research supported initially by the Basic Energy Sciences (BES) office of DOE (and now by many agencies).

97 MATHEMATICS AND COMPUTING↗