Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed Memory Parallel”

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 505 records · Page 28

An Element-Based Concurrent Partitioner for Unstructured Finite Element Meshes

A concurrent partitioner for partitioning unstructured finite element meshes on distributed memory architectures is developed. The partitioner uses an element-based partitioning strategy. Its main advantage over the more conventional node-based partitioning strategy is its modular programming approach to the development of parallel applications. The partitioner first partitions element centroids using a recursive inertial bisection algorithm. Elements and nodes then migrate according to the partitioned centroids, using a data request communication template for unpredictable incoming messages. Our scalable implementation is contrasted to a non-scalable implementation which is a straightforward parallelization of a sequential partitioner.

concurrent partitioner finite element meshes distr↗

Mapping Dense LU Factorization on Multicore Supercomputer Nodes

Dense LU factorization is a prominent benchmark used to rank the performance of supercomputers. Many implementations use block-cyclic distributions of matrix blocks onto a two-dimensional process grid. The process grid dimensions drive a trade-off between communication and computation and are architecture- and implementation-sensitive. The critical panel factorization steps can be made less communication-bound by overlapping asynchronous collectives for pivoting with the computation of rank-k updates. By shifting the computation-communication trade-off, a modified block-cyclic distribution can beneficially exploit more available parallelism on the critical path, and reduce panel factorization's memory hierarchy contention on now-ubiquitous multicore architectures. During active panel factorization, rank-1 updates stream through memory with minimal reuse. In a column-major process grid, the performance of this access pattern degrades as too many streaming processors contend for access to memory. A block-cyclic mapping in the row-major order does not encounter this problem, but consequently sacrifices node and network locality in the critical pivoting steps. We introduce 'striding' to vary between the two extremes of row- and column-major process grids. The maximum available parallelism in the critical path work (active panel factorization, triangular solves, and subsequent broadcasts) is bounded by the length or width of the process grid. Increasing one dimension of the process grid decreases the number of distinct processes and nodes in the other dimension. To increase the harnessed parallelism in both dimensions, we start with a tall process grid. We then apply periodic 'rotation' to this grid to restore exploited parallelism along the row to previous levels. As a test-bed for further mapping experiments, we describe a dense LU implementation that allows a block distribution to be defined as a general function of block to processor. Other mappings can be tested wit...

Computer Science↗

Designing Scalable Distributed Memory Models: A Case Study

Supercomputers complexity continue to rapidly increase, requiring novel software solutions to aid in addressing the extreme abundance of parallelism, restrictive power constraints, and fault tolerance requirements. While industrial standards like MPI and OpenMP have undergone extensive efforts to prepare for future systems [1, 2], ne grain asynchronous runtimes have demonstrated an innate agility in extracting performance which is otherwise arduous to attain with current execution models

Landwehr, Joshua B.↗

Equation solvers for distributed-memory computers

A large number of scientific and engineering problems require the rapid solution of large systems of simultaneous equations. The performance of parallel computers in this area now dwarfs traditional vector computers by nearly an order of magnitude. This talk describes the major issues involved in parallel equation solvers with particular emphasis on the Intel Paragon, IBM SP-1 and SP-2 processors.

Storaasli, Olaf O.↗

PARVMEC: An Efficient, Scalable Implementation of the Variational Moments Equilibrium Code

The ability to sustain magnetically confined plasma in a state of stable equilibrium is crucial for optimal and cost-effective operations of fusion devices like tokamaks and stellarators. The Variational Moments Equilibrium Code (VMEC) is the de-facto serial application used by fusion scientists to compute magnetohydrodynamics (MHD) equilibria and study the physics of three dimensional plasmas in confined configurations. Modern fusion energy experiments have larger system scales with more interactive experimental workflows, both demanding faster analysis turnaround times on computational workloads that are stressing the capabilities of sequential VMEC. In this paper, we present PARVMEC, an efficient, parallel version of its sequential counterpart, capable of scaling to thousands of processors on distributed memory machines. PARVMEC is a non-linear code, with multiple numerical physics modules, each with its own computational complexity. A detailed speedup analysis supported by scaling results on 1,024 cores of a Cray XC30 supercomputer is presented. Depending on the mode of PARVMEC execution, speedup improvements of one to two orders of magnitude are reported. PARVMEC equips fusion scientists for the first time with a state-of-theart capability for rapid, high fidelity analyses of magnetically confined plasmas at unprecedented scales.

Seal, Sudip K↗

Livermore Big Artificial Neural Network Toolkit

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

Essen, BrianVan↗

HydraGNN v3.0

New or improved capabilities included in v3.0 release are as follows: 1. Enhancement in message passing layers through generalization of the class inheritance to enable the inclusion of a broader set of message passing policies Inclusion of equivariant message passing layers from the original implementations of: SchNet (https://pubs.aip.org/aip/jcp/article/148/24/241722/962591/SchNet-A-deep-learning-architecture-for-molecules); DimeNet++ (https://arxiv.org/abs/2011.14115); EGNN models (https://arxiv.org/pdf/2102.09844.pdf) 2. Restructuring of class inheritance for data management 3. Support of DDStore https://github.com/ORNL/DDStore capabilities for improved distributed data parallelism on large volumes of data that cannot fit on intra-node memory capacities 4. Large-scale system support for OLCF-Crusher and OLCF-Frontier

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗

Livermore Big Artificial Neural Network Toolkit

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

Essen, Brian Van↗

Parallel Programming Models and Systems for High Performance Computing. In: Emerging Research in Cloud Distributed Computing Systems

A parallel programming model is an abstraction of a parallel system that allows expression of both algorithms and shared data structures. To accommodate the diversity in parallel system architectures and user requirements, there are a variety of programming models including the models providing a shared memory view or a distributed memory view of the system. The programming models are implemented as libraries, language extensions, or compiler directives. This chapter provides a discussion on programming models and its implementations aimed at application developers, system software researchers, and hardware architects. The first part provides an overview of the programming models. The second part is an in-depth discussion on high-performance networking interface to implement the programming model. The last part of the chapter discusses implementation of a programming model with a case study. Each part of the chapter concludes with a discussion on current research trends and its impact on future architectures.

Venkata, Manjunath Gorentia↗

OpenMP and MPI implementations of an elasto-viscoplastic fast Fourier transform-based micromechanical solver for fast crystal plasticity modeling

Here, we explore several parallel implementations of an elasto-viscoplastic fast Fourier transform (EVPFFT) model using Message Passing Interface (MPI), OpenMP, and a hybrid of MPI and OpenMP to efficiently predict micromechanical response of polycrystals. Performance studies using EVPFFT are performed based on domain decomposition over voxels of a periodic cell, which is a representative volume element (RVE) of polycrystalline copper. We begin by parallelizing the computationally intensive Newton–Raphson (NR) single crystal solver within EVPFFT. Next, we compare the performance of the serial and parallel FFTW (Fastest Fourier Transform in the West) using OpenMP (OpenMP-FFTW) and MPI (MPI-FFTW) with the original Numerical Recipes-based FOURN routine within EVPFFT. In the parallel environment, we find that the FFT calculations are best performed using the MPI version of FFTW. Finally, the remainder of the code, except read/write subroutines, is parallelized. Significant speedups of the original EVPFFT model are achieved using MPI on shared memory multicore workstations. Furthermore, results achieved on a distributed memory Cray supercomputer show promising strong and weak scalability and in some cases even super scalability for the single crystal NR solver in EVPFFT. MPI-FFTW also scales perfectly for microstructure RVEs larger than 64 3 FFT voxels. For example, the MPI-EVPFFT parallel version of the code accelerates the simulations for approximately two orders of magnitude using 64 cores over the old serial code for an RVE size of 128 3 . Finally, the parallel EVPFFT code developed in this work can run massive voxel-based microstructural RVEs taking the advantages of thousands of logical cores provided by more advanced clusters.

42 ENGINEERING↗

A Distributed-Memory Package for Dense Hierarchically Semi-Separable Matrix Computations Using Randomization

In this paper, we present a distributed-memory library for computations with dense structured matrices. A matrix is considered structured if its off-diagonal blocks can be approximated by a rank-deficient matrix with low numerical rank. Here, we use Hierarchically Semi-Separable (HSS) representations. Such matrices appear in many applications, for example, finite-element methods, boundary element methods, and so on. Exploiting this structure allows for fast solution of linear systems and/or fast computation of matrix-vector products, which are the two main building blocks of matrix computations. The compression algorithm that we use, that computes the HSS form of an input dense matrix, relies on randomized sampling with a novel adaptive sampling mechanism. We discuss the parallelization of this algorithm and also present the parallelization of structured matrix-vector product, structured factorization, and solution routines. The efficiency of the approach is demonstrated on large problems from different academic and industrial applications, on up to 8,000 cores. Finally, this work is part of a more global effort, the STRUctured Matrices PACKage (STRUMPACK) software package for computations with sparse and dense structured matrices. Hence, although useful on their own right, the routines also represent a step in the direction of a distributed-memory sparse solver.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Cross-scale efficient tensor contractions for coupled cluster computations through multiple programming model backends

Coupled-cluster methods provide highly accurate models of molecular structure through explicit numerical calculation of tensors representing the correlation between electrons. These calculations are dominated by a sequence of tensor contractions, motivating the development of numerical libraries for such operations. While based on matrix–matrix multiplication, these libraries are specialized to exploit symmetries in the molecular structure and in electronic interactions, and thus reduce the size of the tensor representation and the complexity of contractions. The resulting algorithms are irregular and their parallelization has been previously achieved via the use of dynamic scheduling or specialized data decompositions. We introduce our efforts to extend the Libtensor framework to work in the distributed memory environment in a scalable and energy-efficient manner. We achieve up to 240× speedup compared with the optimized shared memory implementation of Libtensor. We attain scalability to hundreds of thousands of compute cores on three distributed-memory architectures (Cray XC30 and XC40, and IBM Blue Gene/Q), and on a heterogeneous GPU-CPU system (Cray XK7). As the bottlenecks shift from being compute-bound DGEMM's to communication-bound collectives as the size of the molecular system scales, we adopt two radically different parallelization approaches for handling load-imbalance, tasking and bulk synchronous models. Nevertheless, we preserve a unified interface to both programming models to maintain the productivity of computational quantum chemists.

97 MATHEMATICS AND COMPUTING↗

PapyrusKV: a high-performance parallel key-value store for distributed NVM architectures

This paper introduces PapyrusKV, a parallel embedded key-value store (KVS) for distributed high-performance computing (HPC) architectures that offer potentially massive pools of nonvolatile memory (NVM). PapyrusKV stores keys with their values in arbitrary byte arrays across multiple NVMs in a distributed system. PapyrusKV provides standard KVS operations such as put, get, and delete. More importantly, PapyrusKV provides advanced features for HPC such as dynamic consistency control, zero-copy workflow, and asynchronous checkpoint/restart. Beyond filesystems, PapyrusKV provides HPC programmers with a high-level interface to exploit distributed NVM in the system, and it transparently organizes data to achieve high performance. Also, it allows HPC applications to specialize PapyrusKV to meet their specific requirements. We empirically evaluate PapyrusKV on three HPC systems with real NVM devices: OLCF's Summitdev, TACC's Stampede, and NERSC's Cori. Our results show that PapyrusKV can offer high performance, scalability, and portability across these various distributed NVM architectures.

97 MATHEMATICS AND COMPUTING↗

A multiarchitecture parallel-processing development environment

A description is given of the hardware and software of a multiprocessor test bed - the second generation Hypercluster system. The Hypercluster architecture consists of a standard hypercube distributed-memory topology, with multiprocessor shared-memory nodes. By using standard, off-the-shelf hardware, the system can be upgraded to use rapidly improving computer technology. The Hypercluster's multiarchitecture nature makes it suitable for researching parallel algorithms in computational field simulation applications (e.g., computational fluid dynamics). The dedicated test-bed environment of the Hypercluster and its custom-built software allows experiments with various parallel-processing concepts such as message passing algorithms, debugging tools, and computational 'steering'. Such research would be difficult, if not impossible, to achieve on shared, commercial systems.

Townsend, Scott↗

3D numerical simulation of the long range propagation of acoustical shock waves through a heterogeneous and moving medium

Many situations involve the propagation of acoustical shock waves through flows. Natural sources such as lightning, volcano explosions, or meteoroid atmospheric entries, emit loud, low frequency, and impulsive sound that is influenced by atmospheric wind and turbulence. The sonic boom produced by a supersonic aircraft and explosion noises are examples of intense anthropogenic sources in the atmosphere. The Buzz-Saw-Noise produced by turbo-engine fan blades rotating at supersonic speed also propagates in a fast flow within the engine nacelle. Simulating these situations is challenging, given the 3D nature of the problem, the long range propagation distances relative to the central wavelength, the strongly nonlinear behavior of shocks associated to a wide-band spectrum, and finally the key role of the flow motion. With this in view, the so-called FLHOWARD (acronym for FLow and Heterogeneous One-Way Approximation for Resolution of Diffraction) method is presented with three-dimensional applications. A scalar nonlinear wave equation is established in the framework of atmospheric applications, assuming weak heterogeneities and a slow wind. It takes into account diffraction, absorption and relaxation properties of the atmosphere, quadratic nonlinearities including weak shock waves, heterogeneities of the medium in sound speed and density, and presence of a flow (assuming a mean stratified wind and 3D turbulent ? flow fluctuations of smaller amplitude). This equation is solved in the framework of the one-way method. A split-step technique allows the splitting of the non-linear wave equation into simpler equations, each corresponding to a physical effect. Each sub-equation is solved using an analytical method if possible, and finite-differences otherwise. Nonlinear effects are solved in the time domain, and others in the frequency domain. Homogeneous diffraction is handled by means of the angular spectrum method. Ground is assumed perfectly flat and rigid. Due to the 3D aspect, the code was massively parallelized using the single program, multiple data paradigm with the Message Passing Interfaces (MPI) for distributed memory architectures. This allows us to handle problems in the order of a thousand billion mesh points in the four dimensions (3 dimensions of space plus time). The validity of the method has been thoroughly evaluated on many cases with known solutions: linear piston, scattering of plane wave by a heterogeneous sphere, propagation in a waveguide with a shear flow, scattering by a finite amplitude vortex and nonlinear propagation in a thermoviscous medium. This validation process allows for a detailed assessment of the advantages and limitations of the method. Finally, applications to atmospheric propagation of shock waves will be presented.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Parallel DTFE Surface Density Field Reconstruction

We improve the interpolation accuracy and efficiency of the Delaunay tessellation field estimator (DTFE) for surface density field reconstruction by proposing an algorithm that takes advantage of the adaptive triangular mesh for line-of-sight integration. The costly computation of an intermediate 3D grid is completely avoided by our method and only optimally chosen interpolation points are computed, thus, the overall computational cost is significantly reduced. The algorithm is implemented as a parallel shared-memory kernel for large-scale grid rendered field reconstructions in our distributed-memory framework designed for N-body gravitational lensing simulations in large volumes. We also introduce a load balancing scheme to optimize the efficiency of processing a large number of field reconstructions. Our results show our kernel outperforms existing software packages for volume weighted density field reconstruction, achieving ~ 10x speedup, and our load balancing algorithm gains an additional ~ 3.6x speedup at scales with ~ 16k processes.

97 MATHEMATICS AND COMPUTING↗

Communication Studies of DMP and SMP Machines

Understanding the interplay between machines and problems is key to obtaining high performance on parallel machines. This paper investigates the interplay between programming paradigms and communication capabilities of parallel machines. In particular, we explicate the communication capabilities of the IBM SP-2 distributed-memory multiprocessor and the SGI PowerCHALLENGEarray symmetric multiprocessor. Two benchmark problems of bitonic sorting and Fast Fourier Transform are selected for experiments. Communication-efficient algorithms are developed to exploit the overlapping capabilities of the machines. Programs are written in Message-Passing Interface for portability and identical codes are used for both machines. Various data sizes and message sizes are used to test the machines' communication capabilities. Experimental results indicate that the communication performance of the multiprocessors are consistent with the size of messages. The SP-2 is sensitive to message size but yields a much higher communication overlapping because of the communication co-processor. The PowerCHALLENGEarray is not highly sensitive to message size and yields a low communication overlapping. Bitonic sorting yields lower performance compared to FFT due to a smaller computation-to-communication ratio.

Sohn, Andrew↗

Streaming Matching and Edge Cover in Practice

Graph algorithms with polynomial space and time requirements often become infeasible for massive graphs with billions of edges or more. State-of-the-art approaches therefore employ approximate serial, parallel, and distributed algorithms to tackle these challenges. However, such approaches require storing the entire graph in memory and thus need access to costly computing resources such as clusters and supercomputers. In this paper, we present practical streaming approaches for solving massive graph problems using limited memory for two prototypical graph problems: maximum weighted matching and minimum weighted edge cover. For matching, we conduct a thorough computational study on two of the semi-streaming algorithms including a recent breakthrough result that achieves a $1/(2+\varepsilon)$-approximation of the weight while using $O( n \log W /\epsilon)$ memory (here $n$ is the number of vertices and $W$ is the maximum edge weight), designed by Paz and Schwartzman [SODA, 2017]. Empirically, we show that the semi-streaming algorithms produce matchings whose weight is close to the best $1/2$-approximate offline algorithm while requiring less time and an order-of-magnitude less memory. For minimum weighted edge cover, we develop three novel semi-streaming algorithms. Two of these algorithms require a single pass through the input graph, require $O(n \log n)$ memory, and provide a 2-approximation guarantee on the objective. We also leverage a relationship between approximate maximum weighted matching and approximate minimum weighted edge cover to develop a two-pass $3/2+\epsilon$-approximate algorithm with the memory requirement of Paz and Schwartzman's semi-streaming matching algorithm. These streaming approaches are compared against the state-of-the-art 3/2-approximate offline algorithm. The semi-streaming matching and the novel edge cover algorithms proposed in this paper can process graphs with several billions of edges in under 30 minutes using 6 GB of memory, which is at least an order of magnitude improvement from the offline (non-streaming) algorithms. For the largest graph, the best alternative offline parallel approximation algorithm (GPA+ROMA) could not finish in three hours even while employing hundreds of processors and 1 TB of memory. We also demonstrate an application of the semi-streaming algorithm by computing a matching using linearly bounded memory on item intersection graphs derived from three machine learning datasets, whereas the existing offline algorithms could not complete on one of these datasets since their memory requirements exceeded 1TB.

Ferdous, S M.↗