Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel processors”

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 1,585 records · Page 88

Parallel integer sorting with medium and fine-scale parallelism

Two new parallel integer sorting algorithms, queue-sort and barrel-sort, are presented and analyzed in detail. These algorithms do not have optimal parallel complexity, yet they show very good performance in practice. Queue-sort designed for fine-scale parallel architectures which allow the queueing of multiple messages to the same destination. Barrel-sort is designed for medium-scale parallel architectures with a high message passing overhead. The performance results from the implementation of queue-sort on a Connection Machine CM-2 and barrel-sort on a 128 processor iPSC/860 are given. The two implementations are found to be comparable in performance but not as good as a fully vectorized bucket sort on the Cray YMP.

Dagum, Leonardo↗

Implementation of Adaptive Digital Controllers on Programmable Logic Devices

Much has been made of the capabilities of FPGA's (Field Programmable Gate Arrays) in the hardware implementation of fast digital signal processing. Such capability also makes an FPGA a suitable platform for the digital implementation of closed loop controllers. Other researchers have implemented a variety of closed-loop digital controllers on FPGA's. Some of these controllers include the widely used proportional-integral-derivative (PID) controller, state space controllers, neural network and fuzzy logic based controllers. There are myriad advantages to utilizing an FPGA for discrete-time control functions which include the capability for reconfiguration when SRAM-based FPGA's are employed, fast parallel implementation of multiple control loops and implementations that can meet space level radiation tolerance requirements in a compact form-factor. Generally, a software implementation on a DSP (Digital Signal Processor) or microcontroller is used to implement digital controllers. At Marshall Space Flight Center, the Control Electronics Group has been studying adaptive discrete-time control of motor driven actuator systems using digital signal processor (DSP) devices. While small form factor, commercial DSP devices are now available with event capture, data conversion, pulse width modulated (PWM) outputs and communication peripherals, these devices are not currently available in designs and packages which meet space level radiation requirements. In general, very few DSP devices are produced that are designed to meet any level of radiation tolerance or hardness. The goal of this effort is to create a fully digital, flight ready controller design that utilizes an FPGA for implementation of signal conditioning for control feedback signals, generation of commands to the controlled system, and hardware insertion of adaptive control algorithm approaches. An alternative is required for compact implementation of such functionality to withstand the harsh environment encountered on spacecraft. Radiation tolerant FPGA's are a feasible option for reaching this goal.

Gwaltney, David A.↗

GPU-Accelerated Text Mining

Accelerating hardware devices represent a novel promise for improving the performance for many problem domains but it is not clear for which domains what accelerators are suitable. While there is no room in general-purpose processor design to significantly increase the processor frequency, developers are instead resorting to multi-core chips duplicating conventional computing capabilities on a single die. Yet, accelerators offer more radical designs with a much higher level of parallelism and novel programming environments. This present work assesses the viability of text mining on CUDA. Text mining is one of the key concepts that has become prominent as an effective means to index the Internet, but its applications range beyond this scope and extend to providing document similarity metrics, the subject of this work. We have developed and optimized text search algorithms for GPUs to exploit their potential for massive data processing. We discuss the algorithmic challenges of parallelization for text search problems on GPUs and demonstrate the potential of these devices in experiments by reporting significant speedups. Our study may be one of the first to assess more complex text search problems for suitability for GPU devices, and it may also be one of the first to exploit and report on atomic instruction usage that have recently become available in NVIDIA devices.

43 PARTICLE ACCELERATORS↗

Pamgen, a library for parallel generation of simple finite element meshes.

Generating finite-element meshes is a serious bottleneck for large parallel simulations. When mesh generation is limited to serial machines and element counts approach a billion, this bottleneck becomes a roadblock. Pamgen is a parallel mesh generation library that allows on-the-fly scalable generation of hexahedral and quadrilateral finite element meshes for several simple geometries. It has been used to generate more that 1.1 billion elements on 17,576 processors. Pamgen generates an unstructured finite element mesh on each processor at the start of a simulation. The mesh is specified by commands passed to the library as a 'C'-programming language string. The resulting mesh geometry, topology, and communication information can then be queried through an API. pamgen allows specification of boundary condition application regions using sidesets (element faces) and nodesets (collections of nodes). It supports several simple geometry types. It has multiple alternatives for mesh grading. It has several alternatives for the initial domain decomposition. Pamgen makes it easy to change details of the finite element mesh and is very useful for performance studies and scoping calculations.

97 MATHEMATICS AND COMPUTING↗

Implementation of an ADI method on parallel computers

In this paper the implementation of an ADI method for solving the diffusion equation on three parallel/vector computers is discussed. The computers were chosen so as to encompass a variety of architectures. They are the MPP, an SIMD machine with 16-Kbit serial processors; Flex/32, an MIMD machine with 20 processors; and Cray/2, an MIMD machine with four vector processors. The Gaussian elimination algorithm is used to solve a set of tridiagonal systems on the Flex/32 and Cray/2 while the cyclic elimination algorithm is used to solve these systems on the MPP. The implementation of the method is discussed in relation to these architectures and measures of the performance on each machine are given. Simple performance models are used to describe the performance. These models highlight the bottlenecks and limiting factors for this algorithm on these architectures. Finally conclusions are presented.

Fatoohi, Raad A.↗

Parallel transport sweeps on two-dimensional cartesian and hexagonal grids

This paper aims to provide a proof of concept for parallel transport sweeps on two-dimensional hexagonal grids for the discrete ordinates transport equation. While the method is an extension of the popular and well-established Koch-Baker-Alcoulffe (KBA) algorithm, there are significant differences between the cartesian and hexagonal grid and thereafter sweep. The most important is the three-way connectivity of hexagons within the grid which creates greater dependencies between the elements. The KBA method in structured orthogonal grids was first implemented in the DRAGON5 code and the method is first described here. The differences in implementation for the hexagonal grid are also described. Benchmark results are also presented, showing roughly 10 times speedup in computational times with roughly 100 processors, in both cases. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Overview of the NCC

A multi-disciplinary design/analysis tool for combustion systems is critical for optimizing the low-emission, high-performance combustor design process. Based on discussions between then NASA Lewis Research Center and the jet engine companies, an industry-government team was formed in early 1995 to develop the National Combustion Code (NCC), which is an integrated system of computer codes for the design and analysis of combustion systems. NCC has advanced features that address the need to meet designer's requirements such as "assured accuracy", "fast turnaround", and "acceptable cost". The NCC development team is comprised of Allison Engine Company (Allison), CFD Research Corporation (CFDRC), GE Aircraft Engines (GEAE), NASA Glenn Research Center (LeRC), and Pratt & Whitney (P&W). The "unstructured mesh" capability and "parallel computing" are fundamental features of NCC from its inception. The NCC system is composed of a set of "elements" which includes grid generator, main flow solver, turbulence module, turbulence and chemistry interaction module, chemistry module, spray module, radiation heat transfer module, data visualization module, and a post-processor for evaluating engine performance parameters. Each element may have contributions from several team members. Such a multi-source multi-element system needs to be integrated in a way that facilitates inter-module data communication, flexibility in module selection, and ease of integration. The development of the NCC beta version was essentially completed in June 1998. Technical details of the NCC elements are given in the Reference List. Elements such as the baseline flow solver, turbulence module, and the chemistry module, have been extensively validated; and their parallel performance on large-scale parallel systems has been evaluated and optimized. However the scalar PDF module and the Spray module, as well as their coupling with the baseline flow solver, were developed in a small-scale distributed computing environment. As a result, the validation of the NCC beta version as a whole was quite limited. Current effort has been focused on the validation of the integrated code and the evaluation/optimization of its overall performance on large-scale parallel systems.

Liu, Nan-Suey↗

Symplectic multi-particle tracking on GPUs

A symplectic multi-particle tracking model is implemented on the Graphic Processing Units (GPUs) using the Compute Unified Device Architecture (CUDA) language. The symplectic tracking model can preserve phase space structure and reduce non-physical effects in long term simulation, which is important for beam property evaluation in particle accelerators. Though this model is computationally expensive, it is very suitable for parallelization and can be accelerated significantly by using GPUs. In this paper, we optimized the implementation of the symplectic tracking model on both single GPU and multiple GPUs. Using a single GPU processor, the code achieves a factor of 2-10 speedup for a range of problem sizes compared with the time on a single state-of-the-art Central Processing Unit (CPU) node with similar power consumption and semiconductor technology. It also shows good scalability on a multi-GPU cluster at Oak Ridge Leadership Computing Facility. In an application to beam dynamics simulation, the GPU implementation helps save more than a factor of two total computing time in comparison to the CPU implementation.

43 PARTICLE ACCELERATORS↗

Hard scaling challenges for ab initio molecular dynamics capabilities in NWChem: Using 100,000 CPUs per second

An overview of the parallel algorithms for ab initio molecular dynamics (AIMD) used in the NWChem program package is presented, including recent developments for computing exact exchange. These algorithms make use of a two-dimensional processor geometry proposed by Gygi et al for use in AIMD algorithms. Using this strategy, a highly scalable algorithm for exact exchange has been developed and incorporated it into AIMD. This new algorithm for exact exchange employs an incomplete butterfly to overcome the bottleneck associated with exact exchange term, and it makes judicious use of data replication. Initial testing has shown that this algorithm can scale to over 20,000 CPUs even for modest size simulation.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

CMS multicore scheduling strategy

In the next years, processor architectures based on much larger numbers of cores will be most likely the model to continue 'Moore's Law' style throughput gains. This not only results in many more jobs in parallel running the LHC Run 1 era monolithic applications, but also the memory requirements of these processes push the workernode architectures to the limit. One solution is parallelizing the application itself, through forking and memory sharing or through threaded frameworks. CMS is following all of these approaches and has a comprehensive strategy to schedule multicore jobs on the GRID based on the glideinWMS submission infrastructure. The main component of the scheduling strategy, a pilot-based model with dynamic partitioning of resources that allows the transition to multicore or whole-node scheduling without disallowing the use of single-core jobs, is described. This contribution also presents the experiences made with the proposed multicore scheduling schema and gives an outlook of further developments working towards the restart of the LHC in 2015.

Perez-Calero Yzquierdo, Antonio↗

TGE: Machine Learning Based Task Graph Embedding for Large-Scale Topology Mapping

Task mapping is an important problem in parallel and distributed computing. The goal in task mapping is to find an optimal layout of the processes of an application (or a task) onto a given network topology. We target this problem in the context of staging applications. A staging application consists of two or more parallel applications (also referred to as staging tasks) which run concurrently and exchange data over the course of computation. Task mapping becomes a more challenging problem in staging applications, because not only data is exchanged between the staging tasks, but also the processes of a staging task may exchange data with each other. We propose a novel method, called Task Graph Embedding (TGE), that harnesses the observable graph structures of parallel applications and network topologies. TGE employs a machine learning based algorithm to find the best representation of a graph, called an embedding, onto a space in which the task-to-processor mapping problem can be solved. We evaluate and demonstrate the effectiveness of TGE experimentally with the communication patterns extracted from runs of XGC, a large-scale fusion simulation code, on Titan.

Choi, Jong Youl↗

A high-performance parallel algorithm for nonnegative matrix factorization

Non-negative matrix factorization (NMF) is the problem of determining two non-negative low rank factors W and H, for the given input matrix A, such that A ≈ WH. NMF is a useful tool for many applications in different domains such as topic modeling in text mining, background separation in video analysis, and community detection in social networks. Despite its popularity in the data mining community, there is a lack of efficient distributed algorithms to solve the problem for big data sets. We propose a high-performance distributed-memory parallel algorithm that computes the factorization by iteratively solving alternating non-negative least squares (NLS) subproblems for W and H. It maintains the data and factor matrices in memory (distributed across processors), uses MPI for interprocessor communication, and, in the dense case, provably minimizes communication costs (under mild assumptions). As opposed to previous implementations, our algorithm is also flexible: (1) it performs well for both dense and sparse matrices, and (2) it allows the user to choose any one of the multiple algorithms for solving the updates to low rank factors W and H within the alternating iterations. We demonstrate the scalability of our algorithm and compare it with baseline implementations, showing significant performance improvements.

Kannan, Ramakrishnan↗

HPC-NMF: A High-Performance Parallel Algorithm for Nonnegative Matrix Factorization

NMF is a useful tool for many applications in different domains such as topic modeling in text mining, background separation in video analysis, and community detection in social networks. Despite its popularity in the data mining community, there is a lack of efficient distributed algorithms to solve the problem for big data sets. We propose a high-performance distributed-memory parallel algorithm that computes the factorization by iteratively solving alternating non-negative least squares (NLS) subproblems for $\WW$ and $\HH$. It maintains the data and factor matrices in memory (distributed across processors), uses MPI for interprocessor communication, and, in the dense case, provably minimizes communication costs (under mild assumptions). As opposed to previous implementation, our algorithm is also flexible: It performs well for both dense and sparse matrices, and allows the user to choose any one of the multiple algorithms for solving the updates to low rank factors $\WW$ and $\HH$ within the alternating iterations.

Kannan, Ramakrishnan↗

Efficient matrix partitioning for optical computing

Techniques for partitioning optical linear algebra problems to make them amenable to solution using optical processors programmed with simple algorithms are explored. Generalized methods for splitting a linear algebra matrix into a series of submatrices are reviewed, showing that simple forms can be pipelined smoothly and that parallel accumulation can be achieved by beam combining on detectors or by summing electronically. The techniques offer simplified bookkeeping, algorithmic independence, and high efficiency. The computational speed will depend on the number of multiplier-accumulators devoted to the task.

Caulfield, H. J.↗

Distributed computation of graphics primitives on a transputer network

A method is developed for distributing the computation of graphics primitives on a parallel processing network. Off-the-shelf transputer boards are used to perform the graphics transformations and scan-conversion tasks that would normally be assigned to a single transputer based display processor. Each node in the network performs a single graphics primitive computation. Frequently requested tasks can be duplicated on several nodes. The results indicate that the current distribution of commands on the graphics network shows a performance degradation when compared to the graphics display board alone. A change to more computation per node for every communication (perform more complex tasks on each node) may cause the desired increase in throughput.

Ellis, Graham K.↗

Graph-Based Dynamic Assignment Of Multiple Processors

Algorithm-to-architecture mapping model (ATAMM) is strategy minimizing time needed to periodically execute graphically described, data-driven application algorithm on multiple data processors. Implemented as operating system managing flow of data and dynamically assigns nodes of graph to processors. Predicts throughput versus number of processors available to execute given application algorithm. Includes rules ensuring application algorithm represented by graph executed periodically without deadlock and in shortest possible repetition time. ATAMM proves useful in maximizing effectiveness of parallel computing systems.

Hayes, Paul J.↗

Final Report, DE-FG01-06ER25718 Domain Decomposition and Parallel Computing

The goal of this project is to develop and improve domain decomposition algorithms for a variety of partial differential equations such as those of linear elasticity and electro-magnetics.These iterative methods are designed for massively parallel computing systems and allow the fast solution of the very large systems of algebraic equations that arise in large scale and complicated simulations. A special emphasis is placed on problems arising from Maxwell's equation. The approximate solvers, the preconditioners, are combined with the conjugate gradient method and must always include a solver of a coarse model in order to have a performance which is independent of the number of processors used in the computer simulation. A recent development allows for an adaptive construction of this coarse component of the preconditioner.

97 MATHEMATICS AND COMPUTING↗

A computational fluid dynamics algorithm on a massively parallel computer

The implementation and performance of a finite-difference algorithm for the compressible Navier-Stokes equations in two or three dimensions on the Connection Machine are described. This machine is a single-instruction multiple-data machine with up to 65536 physical processors. The implicit portion of the algorithm is of particular interest. Running times and megadrop rates are given for two- and three-dimensional problems. Included are comparisons with the standard codes on a Cray X-MP/48.

Jespersen, Dennis C.↗