SEARCH · Engineering Papers

Results for “computer architecture”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 199 records · Page 11

All sources NASA NTRS DOE OSTI

DOE OSTI2021

xSDK: Building an ecosystem of highly efficient math libraries for exascale

Current efforts to build increasingly powerful computer architectures are opening up new avenues for more complex and higher fidelity simulations coupled with data analytics and learning, leading to new scientific insights and deeper understanding. At one extreme, exascale computers will be much faster than previous computer generations (performing 10 18 operations per second—that is, 1,000 times faster than petascale). To achieve these performance improvements, computer architectures are becoming increasingly complex, with deep memory hierarchies, very high node and core counts, and heterogeneous features such as graphics processing units (GPUs). Such architectural changes impact the full breadth of computing scales, as heterogeneity pervades even current-generation laptops, workstations, and moderate-sized clusters. While emerging advanced architectures provide unprecedented opportunities, they also present significant challenges for developers of scientific applications, such as multiphysics and multiscale codes, who must adapt their software to handle disruptive changes in architectures and new programming models that have not yet stabilized. Developers must consider increasing concurrency while reducing communication and synchronization, and other complexities such as the potential for using mixed precision to leverage the compute power available in low-precision tensor cores. On one hand, developers must implement new scientific capabilities, which in turn increase code complexity. On the other hand, the codes must be ported to new architectures, requiring the inclusion of new programming models and the restructuring of code to achieve good performance. Addressing these issues is beyond the capability of any single person or team—leading to the need for collaboration among many teams, who encapsulate their expertise in reusable software and work together to create sustainable software ecosystems.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1999

Shared Memory Parallelization of an Implicit ADI-type CFD Code

A parallelization study designed for ADI-type algorithms is presented using the OpenMP specification for shared-memory multiprocessor programming. Details of optimizations specifically addressed to cache-based computer architectures are described and performance measurements for the single and multiprocessor implementation are summarized. The paper demonstrates that optimization of memory access on a cache-based computer architecture controls the performance of the computational algorithm. A hybrid MPI/OpenMP approach is proposed for clusters of shared memory machines to further enhance the parallel performance. The method is applied to develop a new LES/DNS code, named LESTool. A preliminary DNS calculation of a fully developed channel flow at a Reynolds number of 180, Re(sub tau) = 180, has shown good agreement with existing data.

Hauser, Th.↗

DOE OSTI2013

A massively parallel method of characteristic neutral particle transport code for GPUs

Over the past 20 years, parallel computing has enabled computers to grow ever larger and more powerful while scientific applications have advanced in sophistication and resolution. This trend is being challenged, however, as the power consumption for conventional parallel computing architectures has risen to unsustainable levels and memory limitations have come to dominate compute performance. Heterogeneous computing platforms, such as Graphics Processing Units (GPUs), are an increasingly popular paradigm for solving these issues. This paper explores the applicability of GPUs for deterministic neutron transport. A 2D method of characteristics (MOC) code - OpenMOC - has been developed with solvers for both shared memory multi-core platforms as well as GPUs. The multi-threading and memory locality methodologies for the GPU solver are presented. Performance results for the 2D C5G7 benchmark demonstrate 25-35 x speedup for MOC on the GPU. The lessons learned from this case study will provide the basis for further exploration of MOC on GPUs as well as design decisions for hardware vendors exploring technologies for the next generation of machines for scientific computing. (authors)

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2016

Hybrid massively parallel fast sweeping method for static Hamilton–Jacobi equations

The fast sweeping method is a popular algorithm for solving a variety of static Hamilton–Jacobi equations. Fast sweeping algorithms for parallel computing have been developed, but are severely limited. In this work, we present a multilevel, hybrid parallel algorithm that combines the desirable traits of two distinct parallel methods. The fine and coarse grained components of the algorithm take advantage of heterogeneous computer architecture common in high performance computing facilities. We present the algorithm and demonstrate its effectiveness on a set of example problems including optimal control, dynamic games, and seismic wave propagation. We give results for convergence, parallel scaling, and show state-of-the-art speedup values for the fast sweeping method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2015

High performance techniques for micro channel plate computations in photo multipliers

Monte Carlo - MC methods, requiring heavy computations of large data volume, can be used to predict the amplitude distribution and variance of outputted electron charge in Micro Channel Plates - MCPs, which are fed with primary emitted electrons in their inputs. The concept of parallel and serial combination of separate stages of such stochastic processes, which can be applied in MCP systems and simulated using MC computations, has recently proposed and shown interesting theorems and results. Separating the electron multiplication procedures, occurring in the channels of MCP systems, into sub-procedures, which are similar in nature and occur either in parallel or in consecutive manners, is equivalent to splitting the relevant stochastic system calculations into smaller ones, which can be performed concurrently and/or sequentially. In this way, calculations similar in nature, can be executed only once, thus, eliminating a great percentage of heavy computations. However, when designing and implementing the calculation inferences of the derived theorems using High Performance Computation - HPC techniques, the overall computation cost can further and significantly be reduced. In this paper, the hardware mappings of the relevant theorem inferences onto parallel computing architectures, resulting in circuits of computing blocks for calculation purposes of MCP system stochastic processes, are investigated. Each of the designed and implemented computing circuits corresponds to a theorem inference or to a combination of inferences. The parallelism of the proposed circuits consists of both the concurrent functioning of all the system blocks and of the simultaneous operation of each block, which is processing pieces of data, for many parts of the whole circuit in which it belongs. All the circuits are designed and tested using Altera Quartus II environment and can be implemented as chips, which can be incorporated in computing devices to assist Monte Carlo computations for the estimation of different MCP electron multiplication system performances.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

NASA NTRSDate not supplied

Impacts of Hybrid Parallelism and Vectorization on the Performance of Newton-Krylov Methods in Computational Aerodynamics

Finding the numerical solution of moderate and high-fidelity aerodynamics problems on modern computer architectures involves, 1) decomposing the domain into smaller regions of nearly equal size, and 2) allocating computational resources for calculations on each domain and communication between domains. Modern computer clusters are composed from hierarchies of processing, memory, and communication resources with varying capabilities and latencies.This paper focuses on the combination of domain decomposition provided by ParMETIS [1]and Newton-Krylov Methods [2–5] for the solution of Computational Aerodynamics problems of interest to NASA. Herein, trade-offs encountered when mapping aerodynamics problems to modern computer architectures are explored through examples and discussions of trade-offs in parallelism from MPI [6], Open MP [7], and vectorization as partition sizes and computational resources are varied. An example of the impact that domain decomposition and MPI+OpenMPresource allocation can have on an adjoint calculation is presented in this abstract. The full paper will include more detailed examples, discussions of difficulties and potential methods to overcome them, and topics identified for future study.

Computational Aerodynamics, Hybrid Parallelism, Ve↗

NASA NTRSDate not supplied

Assessment of Edge-Based Viscous Method for Corner-Flow Solutions on Graphics Processing Units

A highly efficient, edge-based viscous (EBV) discretization method has been recently implemented in a practical, unstructured-grid, node-centered, finite-volume flow solver and evaluated for Reynolds-averaged Navier-Stokes (RANS) formulations. In comparison to a well-established cell-based viscous (CBV) method, the EBV method has demonstrated multifold acceleration of all viscous-kernel computations on general unstructured mixed-element grids. The viscous kernels include evaluation of viscous fluxes, diffusion terms in turbulence models, and the corresponding Jacobian terms. In this paper, an EBV implementation of a nonlinear extension of the Spalart-Allmaras turbulence model, SA-neg-QCR2000, is presented and verified. The SA-neg-QCR2000 model is used for simulating turbulent corner flows. Previously reported EBV computations have been conducted on traditional computing architectures based on central processing units (CPU). This paper assesses benefits of the EBV method on modern high-performance computing architectures based on graphics processing units (GPU). The GPU implementations of the CBV and EBV methods are verified by comparing solutions and iterative convergence with those observed in CPU computations on the same grids. A comprehensive assessment of the EBV speedup on CPU and GPU architectures is presented for established benchmark corner flows, namely, a supersonic flow through a long square duct and a subsonic flow around a NASA juncture flow model.

CFD↗

NASA NTRSDate not supplied

Assessment of Edge-Based Viscous Method for Corner-Flow Solutions on Graphics Processing Units

CFD↗

NASA NTRS1985

VLSI architectures for computing multiplications and inverses in GF(2m)

Finite field arithmetic logic is central in the implementation of Reed-Solomon coders and in some cryptographic algorithms. There is a need for good multiplication and inversion algorithms that are easily realized on VLSI chips. Massey and Omura recently developed a new multiplication algorithm for Galois fields based on a normal basis representation. A pipeline structure is developed to realize the Massey-Omura multiplier in the finite field GF(2m). With the simple squaring property of the normal-basis representation used together with this multiplier, a pipeline architecture is also developed for computing inverse elements in GF(2m). The designs developed for the Massey-Omura multiplier and the computation of inverse elements are regular, simple, expandable and, therefore, naturally suitable for VLSI implementation.

Wang, C. C.↗

NASA NTRS1983

VLSI architectures for computing multiplications and inverses in GF(2-m)

Wang, C. C.↗

NASA NTRS1981

HiMAT onboard flight computer system architecture and qualification

Two highly maneuverable aircraft technology (HiMAT) remotely piloted research vehicles (RPRV's) are being flight tested at NASA Dryden Flight Research Center, Edwards, California, to demonstrate and evaluate a number of technological advances applicable to future fighter aircraft. Closed-loop primary flight control is performed from a ground-based cockpit utilizing a digital computer and up/down telemetry links. A backup flight control system for emergency operation resides in one of two onboard computers. Other functions of the onboard computer system are uplink processing, downlink processing, engine control, failure detection, and redundancy management. This paper describes the architecture, functions, and flight qualification of the HiMAT onboard flight computer systems.

Myers, A. F.↗

NASA NTRS1996

The NIST Real-Time Control System (RCS): A Reference Model Architecture for Computational Intelligence

The Real-time Control System (RCS) developed at NIST and elsewhere over the past two decades defines a reference model architecture for design and analysis of complex intelligent control systems. The RCS architecture consists of a hierarchically layered set of functional processing modules connected by a network of communication pathways. The primary distinguishing feature of the layers is the bandwidth of the control loops. The characteristic bandwidth of each level is determined by the spatial and temporal integration window of filters, the temporal frequency of signals and events, the spatial frequency of patterns, and the planning horizon and granularity of the planners that operate at each level. At each level, tasks are decomposed into sequential subtasks, to be performed by cooperating sets of subordinate agents. At each level, signals from sensors are filtered and correlated with spatial and temporal features that are relevant to the control function being implemented at that level.

Albus, James S.↗

DOE OSTI2019

Hierarchical power distribution in large scale computing systems

Techniques for managing power distribution amongst processors in a massively parallel computer architecture are disclosed. The techniques utilize a hierarchy that organizes the various processors of the massively parallel computer architecture. The hierarchy groups numbers of the processors at the lowest level. When processors complete tasks, the power assigned to those processors is distributed to other processors in the same group so that the performance of those processors can be increased. Hierarchical organization simplifies the calculations required for determining how and when to distribute power, because when tasks are complete and power is available for distribution, a relatively small number of processors are available for consideration to receive that power. The number of processors that are grouped together can be adjusted in real time based on performance factors to improve the trade-off between calculation speed and power distribution efficacy.

42 ENGINEERING↗

DOE OSTI2019

VEXS, An Open Platform for the Study of Continuous-Energy Cross-Section Lookup Algorithms on GPU’s

A significant bottleneck in continuous-energy neutron transport simulations is the cross-section lookup problem, especially in the case of those occurring in depleted fuel regions. Several algorithms have been developed over the years to solve this problem on more traditional CPU-based platforms, however new computational architectures such as GPUs may not benefit as significantly from these algorithms. As there is increasing interest in using these new computational architectures as a core part of large simulations, the relative efficacy of these algorithms compared to one another is an interesting area of research. Additionally, implementations of these algorithms are sometimes inaccessible to interested scientists outside of the nuclear engineering field given the export-controlled nature of the codes they are implemented in. In this paper, we describe our work to extend an existing open-source platform for cross-section lookup simulation, XSBench, to GPUs. We also describe our adaptation of the original codebase to handle more realistic datasets, and our efforts to accommodate different in-memory data layouts in order to more closely approximate those implementations used in production codes. Finally, we compare our results with those obtained from Shift, a GPU-enabled Monte Carlo transport solver developed for large neutron transport simulations.

Shriver, Forrest↗

NASA NTRS1997

A Multi-Level Parallelization Concept for High-Fidelity Multi-Block Solvers

The integration of high-fidelity Computational Fluid Dynamics (CFD) analysis tools with the industrial design process benefits greatly from the robust implementations that are transportable across a wide range of computer architectures. In the present work, a hybrid domain-decomposition and parallelization concept was developed and implemented into the widely-used NASA multi-block Computational Fluid Dynamics (CFD) packages implemented in ENSAERO and OVERFLOW. The new parallel solver concept, PENS (Parallel Euler Navier-Stokes Solver), employs both fine and coarse granularity in data partitioning as well as data coalescing to obtain the desired load-balance characteristics on the available computer platforms. This multi-level parallelism implementation itself introduces no changes to the numerical results, hence the original fidelity of the packages are identically preserved. The present implementation uses the Message Passing Interface (MPI) library for interprocessor message passing and memory accessing. By choosing an appropriate combination of the available partitioning and coalescing capabilities only during the execution stage, the PENS solver becomes adaptable to different computer architectures from shared-memory to distributed-memory platforms with varying degrees of parallelism. The PENS implementation on the IBM SP2 distributed memory environment at the NASA Ames Research Center obtains 85 percent scalable parallel performance using fine-grain partitioning of single-block CFD domains using up to 128 wide computational nodes. Multi-block CFD simulations of complete aircraft simulations achieve 75 percent perfect load-balanced executions using data coalescing and the two levels of parallelism. SGI PowerChallenge, SGI Origin 2000, and a cluster of workstations are the other platforms where the robustness of the implementation is tested. The performance behavior on the other computer platforms with a variety of realistic problems will be included as this on-going study progresses.

Hatay, Ferhat F.↗

DOE OSTI2019

Graph-based modeling and simulation of complex systems

We present graph-based modeling abstractions to represent cyber-physical dependencies arising in complex systems. Specifically, we propose an algebraic graph abstraction to capture physical connectivity in complex optimization models and a computing graph abstraction to capture communication connectivity in computing architectures. The proposed abstractions are scalable and are used as the backbone of a Julia-based software package that we call Plasmo.j1. Here, we show how the algebraic graph abstraction facilitates the implementation, analysis, and decomposition of optimization problems and we show how the computing graph abstraction facilitates the implementation of optimization and control algorithms and their simulation in virtual environments that involve distributed, centralized, and hierarchical computing architectures.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1989

Parallel algorithms and architecture for computation of manipulator forward dynamics

Parallel computation of manipulator forward dynamics is investigated. Considering three classes of algorithms for the solution of the problem, that is, the O(n), the O(n exp 2), and the O(n exp 3) algorithms, parallelism in the problem is analyzed. It is shown that the problem belongs to the class of NC and that the time and processors bounds are of O(log2/2n) and O(n exp 4), respectively. However, the fastest stable parallel algorithms achieve the computation time of O(n) and can be derived by parallelization of the O(n exp 3) serial algorithms. Parallel computation of the O(n exp 3) algorithms requires the development of parallel algorithms for a set of fundamentally different problems, that is, the Newton-Euler formulation, the computation of the inertia matrix, decomposition of the symmetric, positive definite matrix, and the solution of triangular systems. Parallel algorithms for this set of problems are developed which can be efficiently implemented on a unique architecture, a triangular array of n(n+2)/2 processors with a simple nearest-neighbor interconnection. This architecture is particularly suitable for VLSI and WSI implementations. The developed parallel algorithm, compared to the best serial O(n) algorithm, achieves an asymptotic speedup of more than two orders-of-magnitude in the computation the forward dynamics.

Fijany, Amir↗

NASA NTRS1991

Digital optical computers at the optoelectronic computing systems center

The Digital Optical Computing Program within the National Science Foundation Engineering Research Center for Opto-electronic Computing Systems has as its specific goal research on optical computing architectures suitable for use at the highest possible speeds. The program can be targeted toward exploiting the time domain because other programs in the Center are pursuing research on parallel optical systems, exploiting optical interconnection and optical devices and materials. Using a general purpose computing architecture as the focus, we are developing design techniques, tools and architecture for operation at the speed of light limit. Experimental work is being done with the somewhat low speed components currently available but with architectures which will scale up in speed as faster devices are developed. The design algorithms and tools developed for a general purpose, stored program computer are being applied to other systems such as optimally controlled optical communication networks.

Jordan, Harry F.↗