Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Computer Operations and Hardware”

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 1,495 records · Page 83
All sourcesNASA NTRSDOE OSTI
NASA NTRS2003

Development of Algorithms for Control of Humidity in Plant Growth Chambers

Algorithms were developed to control humidity in plant growth chambers used for research on bioregenerative life support at Kennedy Space Center. The algorithms used the computed water vapor pressure (based on measured air temperature and relative humidity) as the process variable, with time-proportioned outputs to operate the humidifier and de-humidifier. Algorithms were based upon proportional-integral-differential (PID) and Fuzzy Logic schemes and were implemented using I/O Control software (OPTO-22) to define and download the control logic to an autonomous programmable logic controller (PLC, ultimate ethernet brain and assorted input-output modules, OPTO-22), which performed the monitoring and control logic processing, as well the physical control of the devices that effected the targeted environment in the chamber. During limited testing, the PLC's successfully implemented the intended control schemes and attained a control resolution for humidity of less than 1%. The algorithms have potential to be used not only with autonomous PLC's but could also be implemented within network-based supervisory control programs. This report documents unique control features that were implemented within the OPTO-22 framework and makes recommendations regarding future uses of the hardware and software for biological research by NASA.

Costello, Thomas A.↗
NASA NTRS2004

Four-Channel PC/104 MIL-STD-1553 Circuit Board

The mini bus interface card (miniBIC) is the first four-channel electronic circuit board that conforms to MIL-STD-1553 and to the electrical-footprint portion of PC/104. [MIL-STD-1553 is a military standard that encompasses a method of communication and electrical- interface requirements for digital electronic subsystems connected to a data bus. PC/104 is an industry standard for compact, stackable modules that are fully compatible (in architecture, hardware, and software) with personal-computer data- and power-bus circuitry.] Prior to the development of the miniBIC, only one- and two-channel PC/104 MIL-STD-1553 boards were available. To obtain four channels, it was necessary to include at least two boards in a PC/104 stack. In comparison with such a two-board stack, the miniBIC takes up less space, consumes less power, and is more reliable. In addition, the miniBIC includes 32 digital input/output channels. The miniBIC (see figure) contains four MIL-STD-1553B hybrid integrated circuits (ICs), four transformers, a field-programmable gate array (FPGA), and an Industry Standard Architecture (ISA) interface. Each hybrid IC includes a MILSTD-1553 dual transceiver, memory-management circuitry, processor interface logic circuitry, and 64Kx16 bits of shared static random access memory. The memory is used to configure message and data blocks. In addition, 23 16-bit registers are available for (1) configuring the hybrid IC for, and starting it in, various modes of operation; (2) reading the status of the functionality of the hybrid IC; and (3) resetting the hybrid IC to a known state. The miniBIC can operate as a remote terminal, bus controller, or bus monitor. The FPGA provides the chip-select and data-strobe signals needed for operation of the hybrid ICs. The FPGA also receives interruption signals and forwards them to the ISA bus. The ISA interface connects the address, data, and control interfaces of the hybrid ICs to the ISA backplane. Each channel is, in effect, a MIL-STD-1553 interface that can operate either independently of the others or else as a redundant version of one of the others. The transformer in each channel provides electrical isolation between the rest of the miniBIC circuitry and the bus to which that channel is connected.

Cox, Gary L.↗
NASA NTRS2014

Using SpF to Achieve Petascale for Legacy Pseudospectral Applications

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community. We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. Highlevel abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely inprocessor. The granularity of domain decomposition provided by SpF is only constrained by the datalocality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures. In this presentation, we will describe our experience in porting legacy pseudospectral models, MoSST and DYNAMO, to use SpF as well as present preliminary performance results provided by the improved scalability.

DYNAMO↗
DOE OSTI2015

Improving Block-level Efficiency with scsi-mq

Current generation solid-state storage devices are exposing a new bottlenecks in the SCSI and block layers of the Linux kernel, where IO throughput is limited by lock contention, inefficient interrupt handling, and poor memory locality. To address these limitations, the Linux kernel block layer underwent a major rewrite with the blk-mq project to move from a single request queue to a multi-queue model. The Linux SCSI subsystem rework to make use of this new model, known as scsi-mq, has been merged into the Linux kernel and work is underway for dm-multipath support in the upcoming Linux 4.0 kernel. These pieces were necessary to make use of the multi-queue block layer in a Lustre parallel filesystem with high availability requirements. We undertook adding support of the 3.18 kernel to Lustre with scsi-mq and dm-multipath patches to evaluate the potential of these efficiency improvements. In this paper we evaluate the block-level performance of scsi-mq with backing storage hardware representative of a HPC-targerted Lustre filesystem. Our findings show that SCSI write request latency is reduced by as much as 13.6%. Additionally, when profiling the CPU usage of our prototype Lustre filesystem, we found that CPU idle time increased by a factor of 7 with Linux 3.18 and blk-mq as compared to a standard 2.6.32 Linux kernel. Our findings demonstrate increased efficiency of the multi-queue block layer even with disk-based caching storage arrays used in existing parallel filesystems.

Cluster Computing↗
DOE OSTI2021

Cybersecurity for Grid Connected eXtreme Fast Charging (XFC) Station (CyberX) (Final Scientific/Technical Report)

This report summarizes the activities conducted under the DOE VTO funded project DE- EE0008451, where ABB Inc. (ABB), in collaboration with Idaho National Laboratory (INL), APS Global (APS), and XOS Trucks (XOS) pursued the development of a cyber-resilient extreme fast charging (XFC) management system. This project entitled Cybersecurity for Grid Connected eXtreme Fast Charging (XFC) Station (CyberX) focuses on a resilient architecture for smart charging EV Supply Equipment (EVSE) device control and Coordinated Anomaly Detection System (CADS) features that can be added at the charging site depot level to increase cybersecurity. The project was split into two budget periods focused first on developing the threat model and resilient control concepts and second on testing, improving, and validating those developed resilient control algorithms and features with a focus on key vulnerabilities identified during the threat assessment portion of the project. During the first budget period of the CyberX project, the ABB led team focused on activities to identify, model, and quantitatively prioritize high-impact attack scenarios with potential cyber-physical effects while also modeling and developing concepts for a resilient control system that could securely address integration of DERs and other resources with EV charging. Development of the security focused XFC management system (XMS) was accomplished first by offline simulation using a developed XFC station or depot with 480V input level and simulating measurement inputs to monitoring and control systems in concept development. A representative distribution grid model was developed supporting an EV charging site model with BESS and 6 general EV charging models. These EV charging models allowed multiple configurations of charging level, multiple connected protection and measurement devices, and simulation function to show general compromise of EV, BESS, and protection features based on parallel threat analysis. During the second budget period, the EV site and supporting systems model was developed in more detail and converted from offline model to real-time to real-time with EV charging hardware in the loop (HIL). The resilient control architecture developed as concept in the first part of the project was further tested and validated for integration of local energy resources and XFC charging station site equipment while maintaining cybersecure operating principles. The proposed resilient architecture for smart charging and cybersecurity features consists of two main concepts developed and tested within the project. The first concept is an XFC management system (XMS) consisting of a hardware gateway, software platform, and Supervisory Control and Data Acquisition (SCADA) or Distribution Management System integration components. The second concept is a Coordinated Anomaly Detection System (CADS) which forms a primarily software-related subsystem of the total CyberX solution focused on monitoring system measurements, estimation of measurement states, and predicting current at the utility point of interaction based on machine learning for anomaly detection.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Dynamic Cooling on Contemporary Quantum Computers

We study the problem of dynamic cooling whereby a target qubit is cooled at the expense of heating up N − 1 further identical qubits by means of a global unitary operation. A standard back-of-the-envelope high-temperature estimate establishes that the target qubit temperature can be dynamically cooled by at most a factor of 1 / N . Here we provide the exact expression for the minimum temperature to which the target qubit can be cooled and reveal that there is a crossover from the high initial temperature regime, where the scaling is 1 / N , to a low initial temperature regime, where a much faster scaling of 1 / N occurs. This slow, 1 / N scaling, which was relevant for early high-temperature NMR quantum computers, is the reason dynamic cooling was dismissed as ineffectual around 20 years ago; the fact that current low-temperature quantum computers fall in the fast, 1 / N scaling regime, reinstates the appeal of dynamic cooling today. We further show that the associated work cost of cooling is exponentially more advantageous in the low-temperature regime. We discuss the implementation of dynamic cooling in terms of quantum circuits and examine the effects of hardware noise. We successfully demonstrate dynamic cooling in a three-qubit system on a real quantum processor. Since the circuit size grows quickly with N , scaling dynamic cooling to larger systems on noisy devices poses a challenge. We therefore propose a suboptimal cooling algorithm, whereby relinquishing a small amount of cooling capability results in a drastically reduced circuit complexity, greatly facilitating the implementation of dynamic cooling on near-future quantum computers. Published by the American Physical Society2024

Physics↗
DOE OSTI2026

ObstacleSense: Low-Power Neuromorphic Vision for Corridor Obstacle Awareness in Low-Level ADAS

The automotive industry’s pursuit of Level 5 autonomy is constrained by substantial perception-compute power requirements, often reaching 1, 000 + watts in full autonomy stacks. Reducing this energy burden requires rethinking perception not only at the high-end autonomy level, but also at the foundational Advanced Driver Assistance Systems (ADAS) level where low-power, safety-critical sensing can have broad impact. Neuromorphic vision provides a promising starting point: HD Dynamic Vision Sensors (DVS) can operate below 100 mW at the sensor level by reporting only asynchronous brightness changes. However, low-power sensing alone is insufficient if downstream perception reintroduces dense, energy-intensive computation. In particular, many event-driven object-detection pipelines still rely on CNN backbones, while purely spiking alternatives often trade away accuracy or ignore deployment constraints. We introduce ObstacleSense, a highly compact, CNN-free hybrid ANN–SNN framework for Level 0–1 forward-corridor obstacle awareness. Instead of performing full-scene object detection with a convolutional feature backbone, ObstacleSense targets the safety-critical question of whether the ego corridor is occupied and how far the nearest obstacle is. The architecture combines polarity-conditioned event encoding, lightweight temporal spiking dynamics, axial spatial mixing, and coarse-to-fine range estimation within a regular fixed-grid compute pattern. This design avoids the dense CNN backbone commonly used in event-based detection while maintaining a small state footprint suitable for eventual small-FPGA deployment. Before hardware mapping, we evaluate the software implementation using a model-side power proxy derived from MACs, weight and activation traffic, and spiking state updates under shared FP16 assumptions. On simulated CARLA event corpora, the deployment-oriented model achieves 0.9464 objectness F1, 0.9978 grid-level mAP, and 0.8987 m distance Mean Absolute Error at an estimated 1.92 mW proxy cost, while maintaining performance on unseen generalization test sequences.

Johnson-Scott, Zac [ORNL]↗
DOE OSTI2024

Formally Verified ZTA Requirements for OT/ICS Environments with Isabelle/HOL

The clean energy transformation includes the integration of distributed energy resources with the power grid, which has led to a substantial increase in the complexity of power grids infrastructure and the underlying operational technology environment. Power grids infrastructure represents an operational technology environment that has become a system of systems, integrating heterogeneous devices which are both software-and hardware-intensive; as a result, there are increasing demands to exploit advances in the commodity of software-hardware infrastructures to improve energy systems requirements such as cybersecurity and resilience. In such a setting, system requirements at different levels mix, which leads to vulnerabilities and undesirable outcomes. The use of formal methods to characterize and prove system requirements removes ambiguity, increases automation, and provides high levels of assurance and reliability. In this paper, we contribute a methodology and a framework for the system-level verification of zero trust architecture requirements in operational technology environments. We define a formal specification for the core functionalities of operational technology environments, the corresponding invariants, and security proofs. Of particular note is our modular approach for the formal verification of asynchronous interactions in operational technology environments. The formal specification and the proofs have been mechanized using the interactive theorem proving environment Isabelle/HOL.

formal methods↗
DOE OSTI2014

An Advanced Network and distributed Storage Laboratory (ANDSL) for Data Intensive Science (Final Report)

The original intent of this project was to build and operate an Advanced Network and Distributed Storage Laboratory (ANDSL) for Data Intensive Science that will prepare the Open Science Grid (OSG) community for a new generation of wide area communication capabilities operating at a 100Gb rate. The plan was to engage a team of four dedicated scientists that will design, develop and operate a state of the art laboratory that will be fully integrated into the organizational and operational infrastructure of the OSG. The ANDSL was planned to include host-based hardware and software required to profile, emulate and study real-life distributed storage workloads at rates of 100 Gbps. The laboratory was designed to utilize the Department Of Energy’s Advanced Network Initiative (ANI) 100GbTestbed as connections to the fabric become available so that OSG stakeholders can use it to profile real-life data intensive science applications as well as experiment with advanced storage and data management technologies. The goal of the original program of work was to close the adoption gap, decreasing the time between availability of production 100Gbps links and the end-to-end use of such a network to enable scientific discovery.

100Gb networks↗
NASA NTRS2007

Wireless Acoustic Measurement System

A prototype wireless acoustic measurement system (WAMS) is one of two main subsystems of the Acoustic Prediction/ Measurement Tool, which comprises software, acoustic instrumentation, and electronic hardware combined to afford integrated capabilities for predicting and measuring noise emitted by rocket and jet engines. The other main subsystem is described in the article on page 8. The WAMS includes analog acoustic measurement instrumentation and analog and digital electronic circuitry combined with computer wireless local-area networking to enable (1) measurement of sound-pressure levels at multiple locations in the sound field of an engine under test and (2) recording and processing of the measurement data. At each field location, the measurements are taken by a portable unit, denoted a field station. There are ten field stations, each of which can take two channels of measurements. Each field station is equipped with two instrumentation microphones, a micro- ATX computer, a wireless network adapter, an environmental enclosure, a directional radio antenna, and a battery power supply. The environmental enclosure shields the computer from weather and from extreme acoustically induced vibrations. The power supply is based on a marine-service lead-acid storage battery that has enough capacity to support operation for as long as 10 hours. A desktop computer serves as a control server for the WAMS. The server is connected to a wireless router for communication with the field stations via a wireless local-area network that complies with wireless-network standard 802.11b of the Institute of Electrical and Electronics Engineers. The router and the wireless network adapters are controlled by use of Linux-compatible driver software. The server runs custom Linux software for synchronizing the recording of measurement data in the field stations. The software includes a module that provides an intuitive graphical user interface through which an operator at the control server can control the operations of the field stations for calibration and for recording of measurement data. A test engineer positions and activates the WAMS. The WAMS automatically establishes the wireless network. Next, the engineer performs pretest calibrations. Then the engineer executes the test and measurement procedures. After the test, the raw measurement files are copied and transferred, through the wireless network, to a hard disk in the control server. Subsequently, the data are processed into 1.3-octave spectrograms.

Anderson, Paul D.↗
DOE OSTI2017

Random access quantum information processors using multimode circuit quantum electrodynamics

Qubit connectivity is an important property of a quantum processor, with an ideal processor having random access—the ability of arbitrary qubit pairs to interact directly. This a challenge with superconducting circuits, as state-of-the-art architectures rely on only nearest-neighbor coupling. Here, we implement a random access superconducting quantum information processor, demonstrating universal operations on a nine-qubit memory, with a Josephson junction transmon circuit serving as the central processor. The quantum memory uses the eigenmodes of a linear array of coupled superconducting resonators. We selectively stimulate vacuum Rabi oscillations between the transmon and individual eigenmodes through parametric flux modulation of the transmon frequency. Utilizing these oscillations, we perform a universal set of quantum gates on 38 arbitrary pairs of modes and prepare multimode entangled states, all using only two control lines. We thus achieve hardware-efficient random access multi-qubit control in an architecture compatible with long-lived microwave cavity-based quantum memories.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2010

Demonstration of an Aerocapture GN and C System Through Hardware-in-the-Loop Simulations

Aerocapture is an orbit insertion maneuver in which a spacecraft flies through a planetary atmosphere one time using drag force to decelerate and effect a hyperbolic to elliptical orbit change. Aerocapture employs a feedback Guidance, Navigation, and Control (GN&C) system to deliver the spacecraft into a precise postatmospheric orbit despite the uncertainties inherent in planetary atmosphere knowledge, entry targeting and aerodynamic predictions. Only small amounts of propellant are required for attitude control and orbit adjustments, thereby providing mass savings of hundreds to thousands of kilograms over conventional all-propulsive techniques. The Analytic Predictor Corrector (APC) guidance algorithm has been developed to steer the vehicle through the aerocapture maneuver using bank angle control. Through funding provided by NASA's In-Space Propulsion Technology Program, the operation of an aerocapture GN&C system has been demonstrated in high-fidelity simulations that include real-time hardware in the loop, thus increasing the Technology Readiness Level (TRL) of aerocapture GN&C. First, a non-real-time (NRT), 6-DOF trajectory simulation was developed for the aerocapture trajectory. The simulation included vehicle dynamics, gravity model, atmosphere model, aerodynamics model, inertial measurement unit (IMU) model, attitude control thruster torque models, and GN&C algorithms (including the APC aerocapture guidance). The simulation used the vehicle and mission parameters from the ST-9 mission. A 2000 case Monte Carlo simulation was performed and results show an aerocapture success rate of greater than 99.7%, greater than 95% of total delta-V required for orbit insertion is provided by aerodynamic drag, and post-aerocapture orbit plane wedge angle error is less than 0.5 deg (3-sigma). Then a real-time (RT), 6-DOF simulation for the aerocapture trajectory was developed which demonstrated the guidance software executing on a flight-like computer, interfacing with a simulated IMU and simulated thrusters, with vehicle dynamics provided by an external simulator. Five cases from the NRT simulations were run in the RT simulation environment. The results compare well to those of the NRT simulation thus verifying the RT simulation configuration. The results of the above described simulations show the aerocapture maneuver using the APC algorithm can be accomplished reliably and the algorithm is now at TRL-6. Flight validation is the next step for aerocapture technology development.

Masciarelli, James↗
DOE OSTI2017

Creation of System Validation Platform

The objective of this CRADA between Sandia National Laboratories (SNL) and SunSpec Alliance (SunSpec) was to create a software test platform called the System Validation Platform (SVP) that performs end-to-end certification testing of photovoltaic (PV) inverters, energy storage systems, and other distributed energy resources (DERs). The SVP automates interactions of test equipment (PV and grid simulators), data acquisition systems, and interoperable DERs to certify the devices for advanced grid-support functions and interoperability. To assist electricity grid, operators maintain voltage and frequency, new interconnection requirements in the U.S. and Europe require DERs to have grid-support functions with adjustable settings. Automating the certification process for DER devices impacts the bottom line of NRTLs because they do not need to rely on test engineers running days (or weeks) of experiments to validate the performance of the equipment. These savings can then be passed down to the DER vendors so the certification process becomes less expensive and lowers the barrier to market for PV inverters, charge controllers, and other grid-interconnected equipment. This technology can also be used as a research platform for SNL, other national labs, and universities that would like to run hardware tests with power electronics equipment.

14 SOLAR ENERGY↗
DOE OSTI2019

Informative Path Planning for Mapping Radiation

This project involves making measurements of contaminated areas using portable radiation detectors and small robots. Tasks involve operating detectors and small robots, combining data acquisition for the two systems, and automating the systems. The end result is a radiation map of contamination areas. Localization of radioactive sources and mapping of contamination distribution is essential when responding to emergencies, or when dealing with cleanup efforts. Radiation maps are used for situational awareness and for establishing a safe perimeter. However, it may be hazardous or impossible for humans to safely enter the site and survey the area. Informative Path Planning (IPP) is used to design a path for a robotic sensor platform to gather the most information about the radiation distribution while operating under the set of constraints given by the dynamics of the robot and other requirements such as minimizing the overall mission time. The key challenge for IPP is the tight coupling in multiple layers of decisions: Selection of locations to visit; Allocation of sensors to those locations; Processing of information gathered. Given a robot equipped with a basic gamma detector and Lidar sensor, how can we efficiently explore an unknown environment in such a way that we can satisfy the robot's constraints while simultaneously maximizing the accuracy of the map and minimizing the total runtime? This work presents a systematic procedure for IPP and environmental mapping that: Selects the best locations at which to sample; Finds the best path for robots; Estimates the measurement value at unknown locations using a Gaussian Process regression framework. Given a set of points where radiation measurements were taken, we are utilizing a Gaussian Process Regression with a Matern kernel to reconstruct the shape of the underlying ground truth. Mapping is done via the Robot Operating System's OpenSlam Gmapping package, which creates a 2D occupancy grid map. Simulated trials were run with a radiation source placed at random locations, and allowing the robot to select and move towards 20 samples at separate locations, as well as sampling along the path while moving. The simulated sensor model assumed an efficiency of 0.3, collection time of 1 second. Various weighting schemes were tested and compared. Quantitative evaluations often favored exploitation-heavy weighting schemes where μ was emphasized, with the Root Mean Squared Error (RMSE) quickly tending towards 2, whereas qualitative comparisons would favor exploration-biased schemes with greater weight on σ. The difference comes from operators often favoring knowing the general location of a source, rather than the exact properties of a source. Weighting of the path-length π often reduced the quality of the regression as less exploration occurred, however this may be deemed a worthwhile trade-off under certain circumstances, such as with sensitive robots. Successfully developed a methodology for informative path-planning for a robot to efficiently gather information and create a map of radiation. In the future, we would like to focus on: Hardware trials with integration of the robot platform and the IPP software; More refined sensor and environmental modeling; Multiple robot platforms.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Entity—Hardware-agnostic Particle-in-cell Code for Plasma Astrophysics. I. Curvilinear Special Relativistic Module

Entity is a new-generation, fully open-source particle-in-cell (PIC) code developed to overcome key limitations in astrophysical plasma modeling, particularly the extreme separation of scales and the performance challenges associated with evolving, GPU-centric computing infrastructures. It achieves hardware-agnostic performance portability across various GPU and CPU architectures using the Kokkos library. Crucially, Entity maintains a high standard for usability, clarity, and customizability, offering a robust and easy-to-use framework for developing new algorithms and grid geometries, which allows extensive control without requiring edits to the core source code. This paper details the core general-coordinate special relativistic module. Entity is the first PIC code designed to solve the Vlasov–Maxwell system in general coordinates, enabling a coordinate-agnostic framework that provides the foundational structure for straightforward extension to arbitrary coordinate geometries. The core methodology achieves numerical stability by solving particle equations of motion in the global orthonormal Cartesian basis, despite using generalized coordinates like Cartesian, axisymmetric spherical, and quasi-spherical grids. Charge conservation is ensured via a specialized current deposition technique using conformal currents. The code exhibits robust scalability and performance portability on major GPU platforms (AMD MI250X, NVIDIA A100, and Intel Max Series), with the 3D particle pusher and the current deposition operating efficiently at about 2 ns per particle per time step. Functionality is validated through a comprehensive suite of standard Cartesian plasma tests and the accurate modeling of relativistic magnetospheres in curvilinear axisymmetric geometries.

Hakobyan, Hayk [Flatiron Institute, New York, NY (↗
NASA NTRS2013

SpF: Enabling Petascale Performance for Pseudospectral Dynamo Models

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community.We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. High-level abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely in-processor. The granularity of domain-decomposition provided by SpF is only constrained by the data-locality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures.In this presentation, we will describe the basic architecture of SpF as well as preliminary performance data and experience with adapting legacy dynamo codes. We will conclude with a discussion of planned extensions to SpF that will provide pseudospectral applications with additional flexibility with regard to time integration, linear solvers, and discretization in the radial direction.

Pseudospectral (PS)↗
DOE OSTI2015

EMMA: an adaptive mesh refinement cosmological simulation code with radiative transfer

EMMA is a cosmological simulation code aimed at investigating the reionization epoch. It handles simultaneously collisionless and gas dynamics, as well as radiative transfer physics using a moment-based description with the M1 approximation. Field quantities are stored and computed on an adaptive three-dimensional mesh and the spatial resolution can be dynamically modified based on physically motivated criteria. Physical processes can be coupled at all spatial and temporal scales. We also introduce a new and optional approximation to handle radiation: the light is transported at the resolution of the non-refined grid and only once the dynamics has been fully updated, whereas thermo-chemical processes are still tracked on the refined elements. Such an approximation reduces the overheads induced by the treatment of radiation physics. A suite of standard tests are presented and passed by EMMA, providing a validation for its future use in studies of the reionization epoch. The code is parallel and is able to use graphics processing units (GPUs) to accelerate hydrodynamics and radiative transfer calculations. Depending on the optimizations and the compilers used to generate the CPU reference, global GPU acceleration factors between ×3.9 and ×16.9 can be obtained. As a result, vectorization and transfer operations currently prevent better GPU performance and we expect that future optimizations and hardware evolution will lead to greater accelerations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Fault Injection for TensorFlow Applications

As machine learning (ML) has seen increasing adoption in safety-critical domains (e.g., autonomous vehicles), the reliability of ML systems has also grown in importance. While prior studies have proposed techniques to enable efficient error-resilience (e.g., selective instruction duplication), a fundamental requirement for realizing these techniques is a detailed understanding of the application’s resilience. In this work, we present TensorFI 1 and TensorFI 2, high-level fault injection (FI) frameworks for TensorFlow-based applications. TensorFI 1 and 2 are able to inject both hardware and software faults in any general TensorFlow 1 and 2 program respectively. Both are configurable FI tools that are flexible, easy to use, and portable. They can be integrated into existing TensorFlow programs to assess their resilience for different fault types (e.g., bit-flips in particular operations or layers). We use the TensorFI 1 and TensorFI 2 to evaluate the resilience of 12 and 10 ML programs written in TensorFlow, including DNNs used in the autonomous vehicle domain. The results give us insights into why some of the models are more resilient. We also measure the performance overheads of the two injectors, and present 4 case studies, two for each tool, to demonstrate their utility.

97 MATHEMATICS AND COMPUTING↗