Search NASA⌕ Search

SEARCH · Search NASA

Results for “distributed memory”

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 1,693 records · Page 94

VOLTTRON: An Agent Execution Platform for the Electric Power System

Volttron is an agent execution platform that is engineered for use in the electric power system. Volttron provides resource guarantees for agents and the platform including memory and processor utilization; authentication and authorization services; directory services for agent and resource location; and agent mobility. Unlike most other agent platforms, Volttron does not depend on a single agent authoring language. Instead, we chose to design and implement Volttron as a platform service and framework that is decoupled from the agent execution environment. A prototype implementation of Volttron has been written in Python (using Python v2.7.2) and we have executed agents written in Python and Java and as shell scripts. The intended use of Volttron is in the power distribution system for managing distributed generation, demand-response, and plug-in electric vehicles.

Multi-Agent Systems↗

Automatic whole core depletion and criticality calculations by MCNPX 2.7.0

Different approaches to perform automatic whole core criticality and depletion calculations in a research reactor using MCNPX 2.7.0 are presented. An approximate method is to use the existing symmetries of the burned fuel material distribution in the core, i.e., the axial, radial and azimuth symmetries around the core center, in order to significantly reduce the computation time. In this case it is not necessary to give a unique material number to each burn up cell. Cells having similar burn up and power, achieved during similar irradiation history at same initial fuel composition, will experience similar composition evolution and can therefore be given the same material number. To study the impact of the number of unique burn up materials on the computation time and utilized RAM memory, several MCNPX models have been developed. The paper discusses the accuracy of the model on comparison with measurements of BR2 operation cycles in function of the number of unique burn up materials and the impact of the used Q-value (MeV/fission) of the recoverable fission energy. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

User's manual: Subsonic/supersonic advanced panel pilot code

Sufficient instructions for running the subsonic/supersonic advanced panel pilot code were developed. This software was developed as a vehicle for numerical experimentation and it should not be construed to represent a finished production program. The pilot code is based on a higher order panel method using linearly varying source and quadratically varying doublet distributions for computing both linearized supersonic and subsonic flow over arbitrary wings and bodies. This user's manual contains complete input and output descriptions. A brief description of the method is given as well as practical instructions for proper configurations modeling. Computed results are also included to demonstrate some of the capabilities of the pilot code. The computer program is written in FORTRAN IV for the SCOPE 3.4.4 operations system of the Ames CDC 7600 computer. The program uses overlay structure and thirteen disk files, and it requires approximately 132000 (Octal) central memory words.

Moran, J.↗

Applications Performance on NAS Intel Paragon XP/S - 15#

The Numerical Aerodynamic Simulation (NAS) Systems Division received an Intel Touchstone Sigma prototype model Paragon XP/S- 15 in February, 1993. The i860 XP microprocessor with an integrated floating point unit and operating in dual -instruction mode gives peak performance of 75 million floating point operations (NIFLOPS) per second for 64 bit floating point arithmetic. It is used in the Paragon XP/S-15 which has been installed at NAS, NASA Ames Research Center. The NAS Paragon has 208 nodes and its peak performance is 15.6 GFLOPS. Here, we will report on early experience using the Paragon XP/S- 15. We have tested its performance using both kernels and applications of interest to NAS. We have measured the performance of BLAS 1, 2 and 3 both assembly-coded and Fortran coded on NAS Paragon XP/S- 15. Furthermore, we have investigated the performance of a single node one-dimensional FFT, a distributed two-dimensional FFT and a distributed three-dimensional FFT Finally, we measured the performance of NAS Parallel Benchmarks (NPB) on the Paragon and compare it with the performance obtained on other highly parallel machines, such as CM-5, CRAY T3D, IBM SP I, etc. In particular, we investigated the following issues, which can strongly affect the performance of the Paragon: a. Impact of the operating system: Intel currently uses as a default an operating system OSF/1 AD from the Open Software Foundation. The paging of Open Software Foundation (OSF) server at 22 MB to make more memory available for the application degrades the performance. We found that when the limit of 26 NIB per node out of 32 MB available is reached, the application is paged out of main memory using virtual memory. When the application starts paging, the performance is considerably reduced. We found that dynamic memory allocation can help applications performance under certain circumstances. b. Impact of data cache on the i860/XP: We measured the performance of the BLAS both assembly coded and Fortran coded. We found that the measured performance of assembly-coded BLAS is much less than what memory bandwidth limitation would predict. The influence of data cache on different sizes of vectors is also investigated using one-dimensional FFTs. c. Impact of processor layout: There are several different ways processors can be laid out within the two-dimensional grid of processors on the Paragon. We have used the FFT example to investigate performance differences based on processors layout.

Saini, Subhash↗

2-D seismic wave propagation using the distributional finite-difference method: further developments and potential for global seismology

SUMMARY We present a time-domain distributional finite-difference scheme based on the Lebedev staggered grid for the numerical simulation of wave propagation in acoustic and elastic media. The central aspect of the proposed method is the representation of the stresses and displacements with different sets of B-splines functions organized according to the staggered grid. The distributional finite-difference approach allows domain-decomposition, heterogeneity of the medium, curvilinear mesh, anisotropy, non-conformal interfaces, discontinuous grid and fluid–solid interfaces. Numerical examples show that the proposed scheme is suitable to model wave propagation through the Earth, where sharp interfaces separate large, relatively homogeneous layers. A few domains or elements are sufficient to represent the Earth’s internal structure without relying on advanced meshing techniques. We compare seismograms obtained with the proposed scheme and the spectral element method, and we show that our approach offers superior accuracy, reduced memory usage, and comparable efficiency.

Geochemistry & Geophysics↗

Distributed microprocessors in a tactical universal modem

The distributed microprocessor system associated with a wideband signal conversion unit (WBSCU) is described. Multiple embedded 8086 and 2901 microprocessors, supported by dedicated hardware modules, perform the required real time operations for both transmit and receive functions. Commands from a host computer determine the configuration of the WBSCU via the IEEE 488 bus. Each of the four WBSCU channels is assigned to process a specified IF waveform; each channel configures its own resources and, in some cases, borrows resources from other channels. The processed waveform data is communicated from individual channels to redundant global memories. Data flow between the user community and global memories occurs via redundant 1553 buses through intelligent Bus Interface Units. Each WBSCU channel contains one 2901 bit slice machine and one 8086 microprocessor. The 2901 provides high speed processing capability for the most time critical operations. The 8086 is used for lower speed processing tasks where its high level language capability can be better exploited. Each 8086 has a global bus for wideband interprocessor communication, and a local bus for 8086/2901, master/slave communication. Software architecture consists of a control and communications structure governing mode dependent signal processing tasks.

Gray, D. M.↗

A numerical treatment of geodynamic viscous flow problems involving the advection of material interfaces

Effective numerical treatment of multicomponent viscous flow problems involving the advection of sharp interfaces between materials of differing physical properties requires correction techniques to prevent spurious diffusion and dispersion. We develop a particular algorithm, based on modern shock-capture techniques, employing a two-step nonlinear method. The first step involves the global application of a high-order upwind scheme to a hyperbolic advection equation used to model the distribution of distinct material components in a flow field. The second step is corrective and involves the application of a global filter designed to remove dispersion errors that result from the advection of discontinuities (e.g., material interfaces) by high-order, minimally dissipative schemes. The filter introduces no additional diffusion error. Nonuniform viscosity across a material interface is allowed for by the implementation of a compositionally weighted-inverse interface viscosity scheme. The combined method approaches the optimal accuracy of modern shock-capture techniques with a minimal increase in computational time and memory. A key advantage of this method is its simplicity to incorporate into preexisting codes be they finite difference, element, or volume of two or three dimensions.

Lenardic, A.↗

Design of the Wind Tunnel Model Communication Controller Board

The NASA Langley Research Center's Wind Tunnel Reinvestment project plans to shrink the existing data acquisition electronics to fit inside a wind tunnel model. Space limitations within a model necessitate a distributed system of Application Specific Integrated Circuits (ASICs) rather than a centralized system based on PC boards. This thesis will focus on the design of the prototype of the communication Controller board. A portion of the communication Controller board is to be used as the basis of an ASIC design. The communication Controller board will communicate between the internal model modules and the external data acquisition computer. This board is based around an Field Programmable Gate Array (FPGA), to allow for reconfigurability. In addition to the FPGA, this board contains buffer Random Access Memory (RAM), configuration memory (EEPROM), drivers for the communications ports, and passive components.

Wilson, William C.↗

Satellite Image Mosaic Engine

A computer program automatically builds large, full-resolution mosaics of multispectral images of Earth landmasses from images acquired by Landsat 7, complete with matching of colors and blending between adjacent scenes. While the code has been used extensively for Landsat, it could also be used for other data sources. A single mosaic of as many as 8,000 scenes, represented by more than 5 terabytes of data and the largest set produced in this work, demonstrated what the code could do to provide global coverage. The program first statistically analyzes input images to determine areas of coverage and data-value distributions. It then transforms the input images from their original universal transverse Mercator coordinates to other geographical coordinates, with scaling. It applies a first-order polynomial brightness correction to each band in each scene. It uses a data-mask image for selecting data and blending of input scenes. Under control by a user, the program can be made to operate on small parts of the output image space, with check-point and restart capabilities. The program runs on SGI IRIX computers. It is capable of parallel processing using shared-memory code, large memories, and tens of central processing units. It can retrieve input data and store output data at locations remote from the processors on which it is executed.

Plesea, Lucian↗

Photographic memory: The storage and retrieval of data

The concept of density encoding digital data in a mass-storage computer peripheral is proposed. This concept requires that digital data be encoded as distinguishable density levels (DDLS) of the film to be used as the storage medium. These DDL's are then recorded on the film in relatively large pixels. Retrieval of the data would be accomplished by scanning the photographic record using a relatively small aperture. Multiplexing of the pixels is used to store data of a range greater than the number of DDL's supportable by the film in question. Although a cartographic application is used as an example for the photographic storage of data, any digital data can be stored in a like manner. When the data is inherently spatially-distributed, the aptness of the proposed scheme is even more evident. In such a case, human-readability is an advantage which can be added to those mentioned earlier: speed of acquisition, ease of implementation, and cost effectiveness.

Horton, J.↗

Quasiprobabilistic Readout Correction of Midcircuit Measurements for Adaptive Feedback via Measurement Randomized Compiling

Quantum measurements are a fundamental component of quantum computing. However, on present-day quantum computers, measurements can be more error prone than quantum gates and are susceptible to nonunital errors as well as nonlocal correlations due to measurement crosstalk. While readout errors can be mitigated in postprocessing, this is inefficient in the number of qubits due to a combinatorially large number of possible states that need to be characterized. In this work, we show that measurement errors can be tailored into a simple stochastic error model using randomized compiling, enabling the efficient mitigation of readout errors via quasiprobability distributions reconstructed from the measurement of a single preparation state in an exponentially large confusion matrix. We demonstrate the scalability and power of this approach by correcting readout errors without matrix inversion on a large number of different preparation states applied to a register of eight superconducting transmon qubits. Moreover, we show that this method can be extended to midcircuit measurements used for active feedback via quasiprobabilistic error cancellation, and we demonstrate the correction of measurement errors on an ancilla qubit used to detect and actively correct bit-flip errors on an entangled memory qubit. Our approach enables the correction of readout errors on large numbers of qubits and offers a strategy for correcting readout errors in adaptive circuits in which the results of midcircuit measurements are used to perform conditional operations on nonlocal qubits in real time.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Multiplicative Shot-Noise: A New Route to Stability of Plastic Networks

Fluctuations of synaptic weights, among many other physical, biological, and ecological quantities, are driven by coincident events of two “parent” processes. Here we propose a multiplicative shot-noise model that can capture the behaviors of a broad range of such natural phenomena, and analytically derive an approximation that accurately predicts its statistics. We apply our results to study the effects of a multiplicative synaptic plasticity rule that was recently extracted from measurements in physiological conditions. Using mean-field theory analysis and network simulations, we investigate how this rule shapes the connectivity and dynamics of recurrent spiking neural networks. The multiplicative plasticity rule is shown to support efficient learning of input stimuli, and it gives a stable, unimodal synaptic-weight distribution with a large fraction of strong synapses. The strong synapses remain stable over long times but do not “run away.” Our results suggest that the multiplicative shot-noise offers a new route to understand the tradeoff between flexibility and stability in neural circuits and other dynamic networks.

59 BASIC BIOLOGICAL SCIENCES↗

PUF-Based Two-Factor Authentication Protocol for Securing the Power Grid Against Insider Threat

Recent advances in smart grid technologies have enabled additional distributed control paradigms that allow more efficient and reliable operation. However, this creates new security concerns for the grid, such as attackers using spoofed grid control devices to generate false measurements. This paper introduces a two-factor authentication protocol leveraging standard public-key cryptography as one authentication factor and a hardware-based fingerprint, known as a Physical Unclonable Function, as a second authentication factor. This protocol incurs a small overhead and prevents cyber-attacks even when an adversary is able to compromise the cryptographic keys stored in the non-volatile memory of an intelligent control device.

42 ENGINEERING↗

WfBench: Automated Generation of Scientific Workflow Benchmarks

The prevalence of scientific workflows with high computational demands calls for their execution on various distributed computing platforms, including large-scale leadership-class high-performance computing (HPC) clusters. To handle the deployment, monitoring, and optimization of workflow executions, many workflow systems have been developed over the past decade. There is a need for workflow benchmarks that can be used to evaluate the performance of workflow systems on current and future software stacks and hardware platforms.We present a generator of realistic workflow benchmark specifications that can be translated into benchmark code to be executed with current workflow systems. Our approach generates workflow tasks with arbitrary performance characteristics (CPU, memory, and I/O usage) and with realistic task dependency structures based on those seen in production workflows. We present experimental results that show that our approach generates benchmarks that are representative of production workflows, and conduct a case study to demonstrate the use and usefulness of our generated benchmarks to evaluate the performance of workflow systems under different configuration scenarios.

Coleman, Taina↗

The ETROC2 as the Final Version for CMS Endcap Timing Layer (ETL) Upgrade

The ETROC (Endcap Timing Readout Chip) is being developed for the LGAD-based CMS Endcap Timing Layer (ETL) at HL-LHC. The ETL on each side of the interaction region will be instrumented with a two-disk system of MIP-sensitive LGAD (Low Gain Avalanche Diodes) silicon devices, read out by ETROCs for precision timing measurement with down to ~30 ps timing resolution per track. The ETROC is designed to handle a 16 x 16 pixel cell matrix, with each pixel being 1.3 mm x 1.3 mm to match the LGAD sensor pixel size. The front-end design for preamplifier and discriminator has been specifically optimized for the reduced LGAD signals, with enough flexibilities to meet the ETL specific needs for time resolution, power budget and radiation profile. The ETROC chip is implemented in a commercial 65nm CMOS process. Each channel consists of a preamplifier, a discriminator, a TDC used for TOA (Time Of Arrival) and TOT (Time Over Threshold) measurements, and a memory for data storage and readout. An in-pixel auto threshold calibration is included, along with a self-testing pattern generator. The TOT is used for time-walk correction of the TOA measurement. The detailed hit information (TOA and TOT) from each cell will be read out from a local circular buffer after each Level-1 Accept (about 1 MHz). In addition, a charge injection circuit is implemented to allow for testing and calibration. For more detailed monitoring of the signal pulses, waveform sampling circuits are included for one pixel. The clock distribution is based on a 16x16 H-tree design with a shielding structure to alleviate potential interference. The global peripheral circuits include a PLL, a phase shifter, an I2C slave controller, a fast control block, a global readout, and a data driver along with an efuse and temperature sensor. The ETROC builds event data frames for each L1A selected event and is also capable of providing L1 trigger information for user-defined delayed hits. The main design challenge is how to extract precision timing information from the small LGAD signals in the presence of high irradiation fluence, while keeping the power consumption and digital activity low. The ETL design goal for the time resolution of 50 ps per hit is required to achieve a 35 ps arrival time measurement for a MIP particle, which has its track registered in two ETL disk layers. The LGAD contribution is known to be about 30 ps, this means that the jitter from the ETROC has to be kept below 40 ps. The ETROC2 is the first full size full functionality prototype design fully compatible with the final chip specifications for CMS ETL and now becomes the final version. The ETROC2 chips have been extensively tested. We will present here new testing results including the bump bonding yield improvement study, the time walk correction (TWC) generality study with one pixel TWC applying to all pixels, the final SEU testing using both heavy ion and proton beam, more beam test studies including different sensors, and readiness for the ETROC2 production for CMS ETL upgrade.

Liu, Tiehui [Fermilab] (ORCID:0009000765225605)↗

CORE-BFS: Communication-Optimized REctangular-partitioned BFS Achieving 160.845 TeraTEPS on Frontier Supercomputer

Distributed Breadth-First Search (BFS) is fundamental to many large-scale graph applications, but its performance on parallel systems is often limited by high communication overhead. This paper presents CORE-BFS, an extremely scalable GPU-based BFS implementation that introduces a unique rectangular 2D partitioning-based design for Frontier supercomputer. To further improve performance, we propose four key optimizations: (1) Rectangular 2D-partition specific data formats that use two compressed row and one compressed column status array bitmaps combined with a Double Compressed Sparse Row (DCSR) format per partition, reducing memory footprint and inter-rank traffic; (2) Adaptive frontier & communication strategy that unifies top-down and bottom-up traversal on the rectangular layout, uses lazy synchronization in top-down levels, and switches variants based on frontier size to minimize communication overhead; (3) Frontier-split degree-aware update that maps frontier vertices to thread-centric, wavefront-centric, and block-centric kernels based on their degree to improve GPU utilization and memory coalescing; (4) Row-reduction pipeline that overlaps bottom-up adjacency list processing with row-wise bitmap reduction to hide inter-rank latency. Together, these techniques increase parallelism while reducing memory and communication overhead. On the Graph500 benchmark, CORE - BFS scales up to 9,248 Frontier nodes with scale-42 graphs and reaches 160.845 TTEPS, delivering a 5.42 × speedup over our previous Frontier implementation.

Yang, Haoshen [Rutgers University]↗

Publication of science data on CD-ROM: A guide and example

CD-ROM (Compact Disk-Read Only Memory) is becoming the standard media not only in audio recording, but also in the publication of data and information accessible on many computer platforms. Little has been written about the complicated process involved in creating easy-to-use, high quality, and useful CD-ROM's containing scientific data. This document is a manual designed to aid those who are responsible for the publication of scientific data on CD-ROM. All aspects and steps of the procedure are covered, from feasibility assessment through disk design, data preparation, disc mastering, and CD-ROM distribution. General advice and actual examples are based on lessons learned from the publication of scientific data for an interdisciplinary field experiment. Appendices include actual files from a CD-ROM, a purchase request for CD-ROM mastering services, and the disk art for the first disk published for the project.

Angelici, Gary↗

Achieving High Performance With TCP Over 40 GbE on NUMA Architectures for CMS Data Acquisition

TCP and the socket abstraction have barely changed over the last two decades, but at the network layer there has been a giant leap from a few megabits to 100 gigabits in bandwidth. At the same time, CPU architectures have evolved into the multicore era and applications are expected to make full use of all available resources. Applications in the data acquisition domain based on the standard socket library running in a Non-Uniform Memory Access (NUMA) architecture are unable to reach full efficiency and scalability without the software being adequately aware about the IRQ (Interrupt Request), CPU and memory affinities. During the first long shutdown of LHC, the CMS DAQ system is going to be upgraded for operation from 2015 onwards and a new software component has been designed and developed in the CMS online framework for transferring data with sockets. This software attempts to wrap the low-level socket library to ease higher-level programming with an API based on an asynchronous event driven model similar to the DAT uDAPL API. It is an event-based application with NUMA optimizations, that allows for a high throughput of data across a large distributed system. This paper describes the architecture, the technologies involved and the performance measurements of the software in the context of the CMS distributed event building.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗