Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “hardware accelerators”

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 757 records · Page 42
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Performance of the LLRF System for the Fermilab PIP-II Injector Test

PIP-II IT is a test facility for the PIP-II project where the injector, warm front-end, and the first two superconducting cryomodules are being tested. The 8-cavity half-wave-resonator (HWR) cryomodule operating at 162.5 MHz is followed by the 8-cavity single-spoke resonator(SSR1) cryomodule operating at 325 MHz. The LLRF systems for both cryomodules are based on a common SOC FPGA-based hardware platform. The resonance control systems for the two cryomodules are quite different, the first being a pneumatic system based on helium pressure and the latter a piezo/stepper motor type control. The data acquisition and control system can support both CW and Pulsed mode operations. Beam loading compensation is available which can be used for both manual/automatic control in the LLRF system. The user interfaces include EPICS, Labview, and ACNET. Testing of the RF system has progressed to the point of being ready for a 2 mA beam to be accelerated to 25 MeV. The design and performance of the field control and resonance control system operation with beam are presented in this paper.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Hls4ml Synthesis Testing

HLS4ml (high level synthesis for machine learning) Is a Python package used to translate commonly used open-source machine learning models into HLS. This is useful in machine learning applications on FPGAs. Machine learning algorithms are only as fast as the hardware that they are used on, and some applications require high speed without sacrificing accuracy. In these situations, an FPGA is a good choice since it is faster than a CPU or a GPU, but programming an FPGA is difficult. This is where HLS4ml can be used to simplify the process, as a well-known learning model can be converted to HLS and more easily deployed onto an FPGA. There are many use cases for a machine learning algorithm running on an FPGA. For example, detectors in a particle accelerator cannot keep every event that they detect, and so a computer must decide which events to keep and which to discard. Using an FPGA with a machine learning algorithm would be a good way to keep as many events as possible.

Swanson, Caiden↗
NASA NTRS1993

Capabilities and constraints of NASA's ground-based reduced gravity facilities

The ground-based reduced gravity facilities of NASA have been utilized to support numerous investigations addressing various processes and phenomina in several disciplines for the past 30 years. These facilities, which include drop towers, drop tubes, aircraft, and sounding rockets are able to provide a low gravity environment (gravitational levels that range from 10(exp -2)g to 10(exp -6)g) by creating a free fall or semi-free fall condition where the force of gravity on an experiment is offset by its linear acceleration during the 'fall' (drop or parabola). The low gravity condition obtained on the ground is the same as that of an orbiting spacecraft which is in a state of perpetual free fall. The gravitational levels and associated duration times associated with the full spectrum of reduced gravity facilities including spaced-based facilities are summarized. Even though ground-based facilities offer a relatively short experiment time, this available test time has been found to be sufficient to advance the scientific understanding of many phenomena and to provide meaningful hardware tests during the flight experiment development process. Also, since experiments can be quickly repeated in these facilities, multistep phenomena that have longer characteristic times associated with them can sometimes be examined in a step-by-step process. There is a large body of literature which has reported the study results achieved through using reduced-gravity data obtained from the facilities.

Lekan, Jack↗
DOE OSTI2024

hls4ml

hls4ml (high level synthesis for machine learning) Is a Python package used to translate commonly used open-source machine learning models into HLS. This is useful in machine learning applications on FPGAs. Machine learning algorithms are only as fast as the hardware that they are used on, and some applications require high speed without sacrificing accuracy. In these situations, an FPGA is a good choice since it is faster than a CPU or a GPU, but programming an FPGA is difficult. This is where hls4ml can be used to simplify the process, as a well-known learning model can be converted to HLS and more easily deployed onto an FPGA. There are many use cases for a machine learning algorithm running on an FPGA. For example, detectors in a particle accelerator cannot keep every event that they detect, and so a computer must decide which events to keep and which to discard. Using an FPGA with a machine learning algorithm would be a good way to keep as many events as possible.

Swanson, Caiden↗
DOE OSTI2025

Fast jet tagging with MLP-Mixers on FPGAs

We explore the innovative use of MLP-Mixer models for real-time jet tagging and establish their feasibility on resource-constrained hardware like FPGAs. MLP-Mixers excel in processing sequences of jet constituents, achieving state-of-the-art performance on datasets mimicking Large Hadron Collider conditions. By using advanced optimization techniques such as High-Granularity Quantization and Distributed Arithmetic, we achieve unprecedented efficiency. These models match or surpass the accuracy of previous architectures, reduce hardware resource usage by up to 97%, double the throughput, and half the latency. Additionally, non-permutation-invariant architectures enable smart feature prioritization and efficient FPGA deployment, setting a new benchmark for machine learning in real-time data processing at particle colliders.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Randomized Algorithms for Scientific Computing (RASC)

Randomized algorithms have propelled advances in artificial intelligence (AI) and represent a foundational research area in advancing AI for Science. Future advancements in DOE Office of Science priority areas such as climate science, astrophysics, fusion, advanced materials, combustion, and quantum computing all require randomized algorithms for surmounting challenges of complexity, robustness, and scalability. Advances in data collection and numerical simulation have changed the dynamics of scientific research and motivate the need for randomized algorithms. For instance, advances in imaging technologies such as X-ray ptychography, electron microscopy, electron energy loss spectroscopy, or adaptive optics lattice light-sheet microscopy collect hyperspectral imaging and scattering data in terabytes, at breakneck speed enabled by state-of-the-art detectors. The data collection is exceptionally fast compared with its analysis. Likewise, advances in high-performance architectures have made exascale computing a reality and changed the economies of scientific computing in the process. Floating-point operations that create data are essentially free in comparison with data movement. Thus far, most approaches have focused on creating faster hardware. Ironically, this faster hardware has exacerbated the problem by making data still easier to create. Under such an onslaught, scientists often resort to heuristic deterministic sampling schemes (e.g., low-precision arithmetic, sampling every nth element) and sacrifice potentially valuable accuracy. Dramatically better results can be achieved via randomized algorithms, reducing the data size as much as or more than naive deterministic subsampling can achieve, while retaining the high accuracy of computing on the full data set. By randomized algorithms we mean those algorithms that employ some form of randomness in internal algorithmic decisions to accelerate time to solution, increase scalability, or improve reliability. Examples include matrix sketching for solving large-scale least-squares problems (see Figure 1) and stochastic gradient descent for training machine learning models. We are not recommending heuristic methods but rather randomized algorithms that have certificates of correctness and probabilistic guarantees of optimality and near-optimality. Such approaches can be useful beyond acceleration, for example, in understanding how to avoid measure zero worst-case scenarios that plague methods such as QR matrix factorization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Reliable edge machine learning hardware for scientific applications

Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simulations for performance validation in experimental software frameworks, verifying those ML models are robust under extreme quantization and pruning, and enabling ultra-fine-grained model inspection for efficient fault tolerance. We discuss approaches to developing and validating reliable algorithms at the scientific edge under such strict latency, resource, power, and area requirements in extreme experimental environments. We study metrics for developing robust algorithms, present preliminary results and mitigation strategies, and conclude with an outlook of these and future directions of research towards the longer-term goal of developing autonomous scientific experimentation methods for accelerated scientific discovery.

Baldi, Tommaso↗
NASA NTRS2010

A Study of Fluid Interface Configurations in Exploration Vehicle Propellant Tanks

The equilibrium shape and location of fluid interfaces in spacecraft propellant tanks while in low-gravity is of interest to system designers, but can be challenging to predict. The propellant position can affect many aspects of the spacecraft such as the spacecraft center of mass, response to thruster firing due to sloshing, liquid acquisition, propellant mass gauging, and thermal control systems. We use Surface Evolver, a fluid interface energy minimizing algorithm, to investigate theoretical equilibrium liquid-vapor interfaces for spacecraft propellant tanks similar to those that have been considered for NASA's new class of Exploration vehicles. The choice of tank design parameters we consider are derived from the NASA Exploration Systems Architecture Study report. The local acceleration vector employed in the computations is determined by estimating low-Earth orbit (LEO) atmospheric drag effects and centrifugal forces due to a fixed spacecraft orientation with respect to the Earth or Moon, and rotisserie-type spacecraft rotation. Propellant/vapor interface positions are computed for the Earth Departure Stage and Altair lunar lander descent and ascent stage tanks for propellant loads applicable to LEO and low-lunar orbit. In some of the cases investigated the vapor ullage bubble is located at the drain end of the tank, where propellant management device hardware is often located.

Zimmerli, Gregory A.↗
DOE OSTI2022

Upgrade and Operation of the ATLAS Radiation Interlock System (ARIS)

ATLAS (the Argonne Tandem Linac Accelerator Sys-tem) is a superconducting heavy ion accelerator which can accelerate nearly all stable, and some unstable, iso-topes between hydrogen and uranium. Prompt radiation fields from gamma and or neutron are typically below 1 rem/hr at 30 cm, but are permitted up to 300 rem/hr at 30 cm. The original ATLAS Radiation Interlock System (ARIS), hereafter referred to as ARIS 1.0 was installed 30 years ago. While it has been a functional critical safe-ty system, its age has exposed the facility to high risk of temporary shutdown due to failure of obsolete compo-nents. Topics discussed will be architecture, hardware improvements, functional improvements, and operation permitting personnel access to areas with low levels of radiation.

Blomberg, B. R.↗
DOE OSTI2020

FY20 ASC IC L2 Milestone 7180: Performance Portability of SIERRA Mechanics Applications to ATS-1 and ATS-2. Executive Summary

The overall goal of this work was to accelerate simulations supporting the nuclear deterrence (ND) mission through improved performance of key algorithms in the ASC IC Sierra multi-physics application suite. This work focused on porting and optimizing algorithms for the graphics processing units (GPU) on the second ASC advanced technology system (ATS-2), while maintaining or improving performance on commodity technology systems (CTS) and ATS-1. Furthermore, these algorithmic developments used the ASC developed Kokkos performance portability abstraction library to maintain high performance across platforms using identical code, and enable sustainable reduced-cost migration and performance optimization to emerging hardware.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2012

Development and Testing of Molecular Adsorber Coatings

The effect of on-orbit molecular contamination has the potential to degrade the performance of spaceflight hardware and diminish the lifetime of the spacecraft. For example, sensitive surfaces, such as optical surfaces, electronics, detectors, and thermal control surfaces, are vulnerable to the damaging effects of contamination from outgassed materials. The current solution to protect these surfaces is through the use of zeolite coated ceramic adsorber pucks. However, these pucks and its additional complex mounting hardware requirements result in several disadvantages, such as size, weight, and cost related concerns, that impact the spacecraft design and the integration and test schedule. As a result, a new innovative molecular adsorber coating was developed as a sprayable alternative to mitigate the risk of on-orbit molecular contamination. In this study, the formulation for molecular adsorber coatings was optimized using various binders, pigment treatment methods, binder to pigment ratios, thicknesses, and spray application techniques. The formulations that passed coating adhesion and vacuum thermal cycling tests were further tested for its adsorptive capacity. Accelerated molecular capacitance tests were performed in an innovatively designed multi-unit system containing idealized contaminant sources. This novel system significantly increased the productivity of the testing phase for the various formulations that were developed. Work performed during the development and testing phases has demonstrated successful application of molecular adsorber coatings onto metallic substrates, as well as, very promising results for the adhesion performance and the molecular capacitance of the coating. Continued testing will assist in the qualification of molecular adsorber coatings for use on future contamination sensitive spaceflight missions.

Abraham, Nithin↗
DOE OSTI2023

Modeling for the phased injector upgrade for 12 GeV CEBAF

As a follow on to the 12 GeV upgrade to the Continuous Electron Beam Accelerator Facility, the front end of the DC photo-gun-based injector has gone through a phased upgrade. The first phase focused on the beamline between the gun and the RF chopper system, and the second phase addresses the beamline after the RF chopper system including replacing the capture section and quarter cryomodule with a new booster module containing a 2-cell and 7-cell cavity string. Throughout the design process, we maintained and developed three models, one for the existing injector and one for each of the upgrade phases. With these models, we evaluated proposed hardware upgrades, evaluated and determined optimized beamline element positions, developed buncher voltage requirements, and settings for optimal injector running. In this paper, we will describe the models and results from these various studies and provide a brief summary of Phase 1 commissioning.

Kazimi, R.↗
DOE OSTI2021

Accelerating End-to-End Deep Learning for Particle Reconstruction using CMS open data

Machine learning algorithms are gaining ground in high energy physics for applications in particle and event identification, physics analysis, detector reconstruction, simulation and trigger. Currently, most data-analysis tasks at LHC experiments benefit from the use of machine learning. Incorporating these computational tools in the experimental framework presents new challenges. This paper reports on the implementation of the end-to-end deep learning with the CMS software framework and the scaling of the end-to-end deep learning with multiple GPUs. The end-to-end deep learning technique combines deep learning algorithms and low-level detector representation for particle and event identification. We demonstrate the end-to-end implementation on a top quark benchmark and perform studies with various hardware architectures including single and multiple GPUs and Google TPU.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Optimization and Portability of a Fusion OpenACC-based FORTRAN HPC Code from NVIDIA to AMD GPUs

NVIDIA has been the main provider of GPU hardware in HPC systems for over a decade. Most applications that benefit from GPUs have thus been developed and optimized for the NVIDIA software stack. Recent exascale HPC systems are, however, introducing GPUs from other vendors, e.g. with the AMD GPU-based OLCF Frontier system just becoming available. AMD GPUs cannot be directly accessed using the NVIDIA software stack, and require a porting effort by the application developers. This paper provides an overview of our experience porting and optimizing the CGYRO code, a widely-used fusion simulation tool based on FORTRAN with OpenACC-based GPU acceleration. While the porting from the NVIDIA compilers was relatively straightforward using the CRAY compilers on the AMD systems, the performance optimization required more fine-tuning. In the optimization effort, we uncovered code sections that had performed well on NVIDIA GPUs, but were unexpectedly slow on AMD GPUs. After AMD-targeted code optimizations, performance on AMD GPUs has increased to meet our expectations. Modest speed improvements were also seen on NVIDIA GPUs, which was an unexpected benefit of this exercise.

Sfiligoi, Igor↗
DOE OSTI2022

Co-Design of Marine Energy Converters for Autonomous Underwater Vehicle Docking and Recharging - Software and Data

Software and testing data from the OH Hinsdale Wave lab for DOE-funded project on Co-Design of Marine Energy Converters for Autonomous Underwater Vehicle Docking and Recharging. This project will perform foundational research and testing to accelerate the sector-wide development and deployment of marine energy converters to provide Power-At-Sea. Specifically, we seek to overcome known challenges and knowledge gaps for the successful co-design of coupled Wave Energy Converter (WEC)-Autonomous Underwater Vehicles (AUV) systems; systems designed and tested for WEC array system health and environmental monitoring applications. This project brings together an experienced, multi-institution, and multi-disciplinary team to focus on the co-design of marine energy (ME) technologies and AUV docking systems, including multi-body hydrodynamic modeling, active control, autonomy, and hardware interfaces necessary to enable new WEC-focused understanding, and allow for robust and ubiquitous AUV docking and recharging in real-world conditions.

16 TIDAL AND WAVE POWER↗
NASA NTRS1996

Thermal Control Subsystem Design for the Avionics of a Space Station Payload

A case study of the thermal control subsystem development for a space based payload is presented from the concept stage through preliminary design. This payload, the Space Acceleration Measurement System 2 (SAMS-2), will measure the acceleration environment at select locations within the International Space Station. Its thermal control subsystem must maintain component temperatures within an acceptable range over a 10 year life span, while restricting accessible surfaces to touch temperature limits and insuring fail safe conditions in the event of loss of cooling. In addition to these primary design objectives, system level requirements and constraints are imposed on the payload, many of which are driven by multidisciplinary issues. Blending these issues into the overall system design required concurrent design sessions with the project team, iterative conceptual design layouts, thermal analysis and modeling, and hardware testing. Multiple tradeoff studies were also performed to investigate the many options which surfaced during the development cycle.

Moran, Matthew E.↗
NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Reinforcement Learning

To continue on a sustainable and flexible path, NASA needs to address the challenge of collecting and moving large amounts of regolith at the destination. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU) processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. The goal of reinforcement learning is for an agent to learn a policy (task strategy) through interactions with an environment. When the agent performs an action, a change occurs in environment state and a numerical reward is received which informs the agent whether the action performed was good or not. Since reinforcement learning algorithms learn through trial-and-error, a simulation is a desirable first environment for development and learning. We developed two simulations, the first is a 2D excavation simulation developed to facilitate parameter selection, and a 3D simulation developed using a game physics engine, to simulate simplified soil interactions and increase the fidelity of the dynamic models of the robotic agents. The development of this 3D simulation has enabled the training of additional sensing capabilities and research both at the granular mechanics and operations levels. We experimented with various virtual sensor payloads to identify a combination that enabled efficient excavation operation and learning. Our reward function is based on how much material is excavated per step. A penalty is also received for leaving the dig site and to smooth the acceleration of the drum arms. We implemented pseudo time-of-flight sensors to report distance from each drum to ground and the height above ground which was found to be more efficient than existing solutions. Our findings suggest that reinforcement learning for autonomous operations has learned viable trenching strategies within 3000 training episodes in our simplified 2D environment and helped identify desirable sensing capabilities, arrangements, and considerations such as the positioning of time-of-flight sensors. Future work includes expanding our simulation to more complex environments and scenarios, and transfer learning from simulation to RASSOR 2.0 hardware for deployment in the Regolith Test Bin at NASA's Kennedy Space Center.

rassor↗
DOE OSTI2022

Machine learning on FPGA for event selection

Real-time data processing is a frontier field in experimental particle physics. The application of FPGAs at the trigger level is used by many current and planned experiments (CMS, LHCb, Belle2, PANDA). Usually they use conventional processing algorithms. LHCb has implemented Machine Learning (ML) elements for real-time data processing with a triggered readout system that runs most of the ML algorithms on a computer farm. The work described in this article aims to test the ML-FPGA algorithms for streaming data acquisition. Herein, there are many experiments working in this area and they have a lot in common, but there are many specific solutions for detector and accelerator parameters that are worth exploring further. This report describes the purpose of the work and progress in evaluating the ML-FPGA application.

47 OTHER INSTRUMENTATION↗