Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel Architectures”

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
All sourcesNASA NTRSDOE OSTI
NASA NTRS2000

Multidisciplinary High-Fidelity Analysis and Optimization of Aerospace Vehicles: Preliminary Results - Part 2

An objective of the High Performance Computing and Communication Program at the NASA Langley Research Center is to demonstrate multidisciplinary shape and sizing optimization of a complete aerospace vehicle configuration by using high-fidelity finite-element structural analysis and computational fluid dynamics aerodynamic analysis in a distributed, heterogeneous computing environment that includes high performance parallel computing. A software system has been designed and implemented to integrate a set of existing discipline analysis codes, some of them computationally intensive, into a distributed computational environment for the design of a high-speed civil transport configuration. The paper describes both the preliminary results from implementing and validating the multidisciplinary analysis and the results from an aerodynamic optimization. The discipline codes are integrated by using the Java programming language and a Common Object Request Broker Architecture compliant software product. A companion paper describes the formulation of the multidisciplinary analysis and optimization system.

Walsh, J. L.↗
NASA NTRS2006

SALT: The Simulator for the Analysis of LWP Timing

With the emergence of new processor architectures that are highly multithreaded, and support features such as full/empty memory semantics and split-phase memory transactions, the need for a processor simulator to handle these features becomes apparent. This paper describes such a simulator, called SALT.

simulation↗
DOE OSTI2020

Evaluation of Graph Analytics Frameworks Using the GAP Benchmark Suite

The analysis of connected data is an increasingly important application in high-performance computing. Such analyses can reveal fraudulent patterns in financial transactions, optimize telecommunications networks, predict information flow in social networks, etc. However, the landscape of graph analytics is highly diverse. Graph algorithms stress processor architectures differently, and no one graph can represent all topologies. Consequently, no single approach or framework is expected to be optimal for all graph analytics problems. To help make sense of this diverse landscape, we evaluated four approaches to graph analytics: GraphBLAS, Galois, BGL17, GraphIt; and compare them against hand-tuned implementations that take advantage of hardware features on our test platform. Graph- BLAS formulates graph analytics as sparse linear algebra. Galois provides syntactic constructs for data parallelism over irregular data structures. BGL17 is a generic C++ template library for implementing graph algorithms. GraphIt provides a domain- specific language to describe and optimize graph algorithms. We use the GAP Benchmark Suite to establish baseline performance and guide the side-by-side evaluation of each framework. GAP consists of 30 tests: six graph analytics algorithms (breadth- first search, single-source shortest path, PageRank, betweenness centrality, connected components, and triangle counting) run on five graphs, each with different topological characteristics (e.g., high diameter, skewed degree distribution, high average degree). High-performance reference implementations are included for each benchmark algorithm. Because a graph can be loaded into memory a number of ways (e.g., flat file on disk, compressed sparse format, data frames, retrieved from SQL or NoSQL databases), our evaluation focused on computational performance rather than I/O. Our results show the relative strengths of each framework.

Graph algorithms, Benchmarking, shared-memory prog↗
DOE OSTI2020

VTO FY20Q4 quarterly report

Project Objective.This project has three objectives: (1) tuning microstructures of 3D-printed SSE separators,(2) determining material and processing compatibilities with cathode printing,and (3)3D printing of sintering-free SSE separators.Project Impact.All-solid-state lithium batteries are difficult to process due to the brittleness of ceramic materials, poor solid-solid contact, and electrolyte-electrode stability issues. As a result, the energy and power density and also cycling stability are far from satisfying. This project will address fabrication difficulties by using state-of-the-art 3D-printing techniques that can introduce 3D interfaces and architectures to enhance solid-solid contact and reduce charge transfer resistance. Success will benefit the DOE by establishing the best manufacturing methods for ASSBsto achieve VTO goals on the performance of beyond Li-ion batteries. Approach.The project employs 3D-printing techniques to manufacture SSEs and related components for ASSBs. The team starts with direct ink writing (DIW) to develop ink recipes with desired rheological properties and explore post-sintering approaches to achieve high densification. In parallel with DIW3D printing, the team also explores other 3D printing options, such as projection microstereolithography (PuSL). Both sintering and sintering-free approaches can gain benefit from 3D printing and therefore will be investigated.Out-Year Goals.The team will determine particle sizes and morphologies as well as post-processing conditions that deliver good ionic conductivity and charge transfer properties of LLZTO separators. They will examine co-sintering of LLZTO/cathode and determine the effects of material, particle size, surface coating, and sintering conditions.Collaborations.Microstructures, ionic conductivities, and mechanical properties will be provided to the LLNL simulation team, led by PI B. Wood, for establishing and validating phase-field modeling methods.

36 MATERIALS SCIENCE↗
DOE OSTI2019

Parallel storage system with burst buffer appliance for storage of partitioned key-value store across a plurality of storage tiers

Parallel storage systems are provided with a burst buffer appliance for storage of a partitioned key-value store across a plurality of storage tiers. The burst buffer appliance is configured to store key-value data on first and second storage tiers comprising respective disjoint subsets of storage. One or more servers in the partitioned key-value store provide (i) an interface between one or more local key-value stores and one or more additional storage architectures, and/or (ii) a key value interface that provides access to at least one hardware key-value store. The local key-values are optionally sorted both locally by the local store and globally by the overall MDHIM framework. The local and global sorting can be leveraged to provide batch input/output (IO) operations that aggregate multiple requests into batch operations on one or more sorted ranges.

Bent, John M.↗
DOE OSTI2022

Advanced architectures for high-performance quantum networking

As practical quantum networks prepare to serve an ever-expanding number of nodes, there has grown a need for advanced auxiliary classical systems that support the quantum protocols and maintain compatibility with the existing fiber-optic infrastructure. We propose and demonstrate a quantum local area network design that addresses current deployment limitations in timing and security in a scalable fashion using commercial off-the-shelf components. First, we employ White Rabbit switches to synchronize three remote nodes with ultra-low timing jitter, significantly increasing the fidelities of the distributed entangled states over previous work with Global Positioning System clocks. Second, using a parallel quantum key distribution channel, we secure the classical communications needed for instrument control and data management. Therefore, the conventional network that manages our entanglement network is secured using keys generated via an underlying quantum key distribution layer, preserving the integrity of the supporting systems and the relevant data in a future-proof fashion.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

PASTA: A Parallel Sparse Tensor Algorithm Benchmark Suite

Tensor methods have gained increasingly attention from various applications, including machine learning, quantum chemistry, healthcare analytics, social network analysis, data mining, and signal processing, to name a few. Sparse tensors and their algorithms become critical to further improve the performance of these methods and enhance the interpretability of their output. This work presents a sparse tensor algorithm benchmark suite (PASTA) for single- and multi-core CPUs. To the best of our knowledge, this is the first benchmark suite for sparse tensor world. PASTA targets on: 1) helping application users to evaluate different computer systems using its representative computational workloads; 2) providing insights to better utilize existed computer architecture and systems and inspiration for the future design. This benchmark suite will be publicly released.

HPC, sparse tensor, benchmark↗
DOE OSTI2019

On the memory attribution problem: A solution and case study using MPI

As parallel applications running on large–scale computing systems become increasingly memory constrained, the ability to attribute memory usage to the various components of the application is becoming increasingly important. We present the design and implementation of memnesia, a novel memory usage profiler for parallel and distributed message–passing applications. Our approach captures both application– and message–passing library–specific memory usage statistics from unmodified binaries dynamically linked to a message–passing communication library. Using microbenchmarks and proxy applications, we evaluated our profiler across three Message Passing Interface (MPI) implementations and two hardware platforms. Furthermore, the results show that our approach and the corresponding implementation can accurately quantify memory resource usage as a function of time, scale, communication workload, and software or hardware system architecture, clearly distinguishing between application and MPI library memory usage at a per–process level. With this new capability, we show that job size, communication workload, and hardware/software architecture influence peak runtime memory usage. In practice, this tool provides a potentially valuable source of information for application developers seeking to measure and optimize memory usage.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Scalable Deep Learning-Based Microarchitecture Simulation on GPUs

Cycle-accurate microarchitecture simulators are essential tools for designers to architect, estimate, optimize, and manufacture new processors that meet specific design expectations. However, conventional simulators based on discrete-event methods often require an exceedingly long time-to-solution for the simulation of applications and architectures at full complexity and scale. Given the excitement around wielding the machine learning (ML) hammer to tackle various architecture problems, there have been attempts to employ ML to perform architecture simulations, such as Ithemal and SimNet. However, the direct application of existing ML approaches to architecture simulation may be even slower due to overwhelming memory traffic and stringent sequential computation logic. This work proposes the first graphics processing unit (GPU)-based microarchitecture simulator that fully unleashes the potential of GPUs to accelerate state-of-the-art ML-based simulators. First, considering the application traces are loaded from central processing unit (CPU) to GPU for simulation, we introduce various designs to reduce the data movement cost between CPUs and GPUs. Second, we propose a parallel simulation paradigm that partitions the application trace into sub-traces to simulate them in parallel with rigorous error analysis and effective error correction mechanisms. Combined, this scalable GPU-based simulator outperforms by orders of magnitude the traditional CPU-based simulators and the state-of-the-art ML-based simulators, i.e., SimNet and Ithemal.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Frontier (HPE Cray EX) Exascale Supercomputer at the Oak Ridge Leadership Computing Facility

Frontier is the HPE Cray EX exascale supercomputer deployed and operated by the Oak Ridge Leadership Computing Facility (OLCF) at Oak Ridge National Laboratory (ORNL). Frontier is designed for large-scale modeling, simulation, and AI workloads and is built from HPE Cray EX system architecture with AMD CPUs and AMD Instinct GPU accelerators connected by the HPE Slingshot interconnect. System composition (representative production configuration): Frontier is composed of approximately 74 cabinets with 128 compute nodes per cabinet (~9,400 compute nodes total). Each compute node contains one 64-core AMD EPYC CPU and four AMD Instinct MI250X GPUs. Nodes are connected using HPE Slingshot (Slingshot-200 class) networking with multiple NIC ports per node providing high injection bandwidth. Frontier is connected to the Orion parallel file system (multi-tier Lustre) providing a large, center-wide high-performance storage namespace. Operational context: Frontier entered public prominence as the first system to reach No. 1 on the TOP500 list in May 2022 (HPL benchmark), establishing the first widely recognized exascale-era performance milestone. The system supports DOE Office of Science mission workloads and enables leadership-class computational science and AI for open science users.

AMD EPYC↗
NASA NTRS2003

Touch modulates gravity sensing to regulate the growth of primary roots of Arabidopsis thaliana

Plants must sense and respond to diverse stimuli to optimize the architecture of their root system for water and nutrient scavenging and anchorage. We have therefore analyzed how information from two of these stimuli, touch and gravity, are integrated to direct root growth. In Arabidopsis thaliana, touch stimulation provided by a glass barrier placed across the direction of growth caused the root to form a step-like growth habit with bends forming in the central and later the distal elongation zones. This response led to the main root axis growing parallel to, but not touching the obstacle, whilst the root cap maintained contact with the barrier. Removal of the graviperceptive columella cells of the root cap using laser ablation reduced the bending response of the distal elongation zone. Similarly, although the roots of the gravisensing impaired pgm1-1 mutant grew along the barrier at the same average angle as wild-type, this angle became more variable with time. These observations imply a constant gravitropic re-setting of the root tip response to touch stimulation from the barrier. In wild-type plants, transient touch stimulation of root cap cells, but not other regions of the root, inhibited both subsequent gravitropic growth and amyloplast sedimentation in the columella. Taken together, these results suggest that the cells of the root cap sense touch stimuli and their subsequent signaling acts on the columella cells to modulate their graviresponse. This interaction of touch and gravity signaling would then direct root growth to avoid obstacles in the soil while generally maintaining downward growth.

NASA Discipline Plant Biology↗
NASA NTRS2017

Reconfigurable Model Execution in the OpenMDAO Framework

NASA's OpenMDAO framework facilitates constructing complex models and computing their derivatives for multidisciplinary design optimization. Decomposing a model into components that follow a prescribed interface enables OpenMDAO to assemble multidisciplinary derivatives from the component derivatives using what amounts to the adjoint method, direct method, chain rule, global sensitivity equations, or any combination thereof, using the MAUD architecture. OpenMDAO also handles the distribution of processors among the disciplines by hierarchically grouping the components, and it automates the data transfer between components that are on different processors. These features have made OpenMDAO useful for applications in aircraft design, satellite design, wind turbine design, and aircraft engine design, among others. This paper presents new algorithms for OpenMDAO that enable reconfigurable model execution. This concept refers to dynamically changing, during execution, one or more of: the variable sizes, solution algorithm, parallel load balancing, or set of variables-i.e., adding and removing components, perhaps to switch to a higher-fidelity sub-model. Any component can reconfigure at any point, even when running in parallel with other components, and the reconfiguration algorithm presented here performs the synchronized updates to all other components that are affected. A reconfigurable software framework for multidisciplinary design optimization enables new adaptive solvers, adaptive parallelization, and new applications such as gradient-based optimization with overset flow solvers and adaptive mesh refinement. Benchmarking results demonstrate the time savings for reconfiguration compared to setting up the model again from scratch, which can be significant in large-scale problems. Additionally, the new reconfigurability feature is applied to a mission profile optimization problem for commercial aircraft where both the parametrization of the mission profile and the time discretization are adaptively refined, resulting in computational savings of roughly 10% and the elimination of oscillations in the optimized altitude profile.

Hwang, John T.↗
DOE OSTI2022

m-CUBES An efficient and portable implementation of multi-dimensional integration for gpus

The task of multi-dimensional numerical integration is frequently encountered in physics and other scientific fields, e.g., in modeling the effects of systematic uncertainties in physical systems and in Bayesian parameter estimation. Multi-dimensional integration is often time-prohibitive on CPUs. Efficient implementation on many-core architectures is challenging as the workload across the integration space cannot be predicted a priori. We propose m-Cubes, a novel implementation of the well-known Vegas algorithm for execution on GPUs. Vegas transforms integration variables followed by calculation of a Monte Carlo integral estimate using adaptive partitioning of the resulting space. m-Cubes improves performance on GPUs by maintaining relatively uniform workload across the processors. As a result, our optimized Cuda implementation for Nvidia GPUs outperforms parallelization approaches proposed in past literature. We further demonstrate the efficiency of m-Cubes by evaluating a six-dimensional integral from a cosmology application, achieving significant speedup and greater precision than the CUBA library's CPU implementation of VEGAS. We also evaluate m-Cubes on a standard integrand test suite. m-Cubes outperforms the serial implementations of the Cuba and GSL libraries by orders of magnitude speedup while maintaining comparable accuracy. Our approach yields a speedup of at least 10 when compared against publicly available Monte Carlo based GPU implementations. In summary, m-Cubes can solve integrals that are prohibitively expensive using standard libraries and custom implementations. A modern C++ interface header-only implementation makes m-Cubes portable, allowing its utilization in complicated pipelines with easy to define stateful integrals. Compatibility with non-Nvidia GPUs is achieved with our initial implementation of m-Cubes using the Kokkos framework.

Sakiotis, Ioannis↗
NASA NTRS1985

Performance evaluation of a simulated data-flow computer with low-resolution actors

Basic problems related to the exploitation of parallelism in a program include sequencing of the instructions and communication of the data. It is pointed out that the data-flow approach offers an elegant solution to the sequencing problem, since all data dependencies are automatically handled and only instructions with ready input sets are activated. It is shown that a change in the level of subcomputations (actors) affects communications costs. The concept of variable resolution is discussed, and the testbed environment is examined. Attention is given to the architecture of the processing elements, the communication network, and the simulators. A description of the analytical model is also provided. Simulation and results are discussed, taking into account test programs and allocation, the variation of the number of processing elements, the variation of the resolution in directed acyclic graphs, performance in processing loops, and array handling.

Gaudiot, J. L.↗
NASA NTRS1988

Problems in characterizing barrier performance

The barrier is a synchronization construct which is useful in separating a parallel program into parallel sections which are executed in sequence. The completion of a barrier requires cooperation among all executing processes. This requirement not only introduces the wait for the slowest process delay which is inherent in the definition of the synchronization, but also has implications for the efficient implementation and measurement of barrier performance in different systems. Types of barrier implementation and their relationship to different multiprocessor environments are described. Then the problem of measuring the performance of barrier implementations on specific machine architecture is discussed. The fact that the barrier synchronization requires the cooperation of all processes makes the problem of performance measurement similarly global. Making non-intrusive measurements of sufficient accuracy can be tricky on systems offering only rudimentary measurement tools.

Jordan, Harry F.↗
NASA NTRS2010

Modeling of Failure for Analysis of Triaxial Braided Carbon Fiber Composites

In the development of advanced aircraft-engine fan cases and containment systems, composite materials are beginning to be used due to their low weight and high strength. The design of these structures must include the capability of withstanding impact loads from a released fan blade. Relatively complex triaxially braided fiber architectures have been found to yield the best performance for the fan cases. To properly work with and design these structures, robust analytical tools are required that can be used in the design process. A new analytical approach models triaxially braided carbon fiber composite materials within the environment of a transient dynamic finite-element code, specifically the commercially available transient dynamic finite-element code LS-DYNA. The geometry of the braided composites is approximated by a series of parallel laminated composites. The composite is modeled by using shell finite elements. The material property data are computed by examining test data from static tests on braided composites, where optical strain measurement techniques are used to examine the local strain variations within the material. These local strain data from the braided composite tests are used along with a judicious application of composite micromechanics- based methods to compute the stiffness properties of an equivalent unidirectional laminated composite required for the shell elements. The local strain data from the braided composite tests are also applied to back out strength and failure properties of the equivalent unidirectional composite. The properties utilized are geared towards the application of a continuum damage mechanics-based composite constitutive model available within LS-DYNA. The developed model can be applied to conduct impact simulations of structures composed of triaxially braided composites. The advantage of this technology is that it facilitates the analysis of the deformation and damage response of a triaxially braided polymer matrix composite within the environment of a transient dynamic finite-element code such as LS-DYNA in a manner which accounts for the local physical mechanisms but is still computationally efficient. This methodology is tightly coupled to experimental tests on the braided composite, which ensures that the material properties have physical significance. Aerospace or automotive companies interested in using triaxially braided composites in their structures, particularly for impact or crash applications, would find the technology useful. By the development of improved design tools, the amount of very expensive impact testing that will need to be performed can be significantly reduced.

Goldberg, Robert K.↗
NASA NTRS2012

Variable Vector Countermeasure Suit (V2Suit) for Space Habitation and Exploration

The "Variable Vector Countermeasure Suit (V2Suit) for Space Habitation and Exploration" is a visionary system concept that will revolutionize space missions by providing a platform for integrating sensors and actuators with daily astronaut intravehicular activities to improve human health and performance. The V2Suit uses control moment gyroscopes (CMGs) within a miniaturized module placed on body segments to provide a "viscous resistance" during movements and a countermeasure to the sensorimotor and musculoskeletal adaptation performance decrements that manifest themselves while living and working in microgravity and during gravitational transitions during long-duration spaceflight, including post-flight recovery and rehabilitation. Through an integrated design, system initialization, and control systems approach the V2Suit is capable of generating this "viscous resistance" along an arbitrarily specified direction of "down." When movements are made, for example, parallel to that "down" direction a resistance is applied, and when the movement is perpendicular to that direction no resistance is applied. The V2Suit proposes to be a countermeasure to this spaceflight-related adaptation and de-conditioning and the unique sensorimotor characteristics associated with living and working in 0-G, which are critical for future long-duration space missions.This NIAC Phase I project focused on detailing several aspects of the V2Suit concept, including human-system integration, system architecture, computer aided design (CAD) modeling, and closed-loop simulation and analysis. In addition, early-stage breadboard prototyping of several aspects of the V2Suit system modules enabled characterization of expected performance and identified areas for further research and development to enable operational implementation of the V2Suit. In particular, potential challenges with integration of commercial-off-the-shelf components were identified. The key enabler for operational use and adoption of the V2Suit is a low-profile body worn form factor that does not interfere with normal, everyday movements and interfaces adequately with the body as to provide the generated gyroscopic torque for the perceptions of movement with a "viscous resistance." These aspects were investigated through mockups using a life-size mannequin, and through body attachment mechanisms on the breadboard prototype. Through the evaluation and investigation of commercially-available components, as well as an identification of desirable form factors, CAD models of the V2Suit modules were developed. These models included all of the required elements and spin motors, flywheel masses, gimbal motors, slip rings, inertial measurement units, motor controllers, and the required mounting brackets/hardware and cabling. The configuration and orientation of the control moment gyroscopes (CMGs) was specified according to results from the modeling, simulation and analysis. Two revisions of the CAD model were investigated through closed-loop simulation of the CMGs, and their ability to generate a resultant reaction force during movement and null undesirable torques due to changes in the direction of the angular momentum vector as a result of the normal body movements.

space missions↗
NASA NTRS1989

Algorithmic considerations of integrated design for CSI on a hypercube architecture

An approach is presented to the integrated design problem for actively controlled large, flexible mechanical systems for which Control Structure Interaction (CSI) problems are of concern. The two coupled design problems were identified as the optimal Structural Design problem the optimal Controller Design problem. These two problems can be addressed within a decision making loop that would consider each separately, and then sequentially analyze the effects of one on the other. Embedded in such a loop would be the simulation and coordination tasks as part of the decision tools required in a total (software) package. All of the above are compute-intensive tasks. In any such task, possible decompositions and gains due to the inherent parallelism have to be exploited. The problems under consideration, as applied to large flexible mechanical structures, are particularly suited to be mapped onto multicomputer systems in a hypercube topology.

Oezguener, UE.↗