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 469 records · Page 26
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↗
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↗
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↗
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↗
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↗
DOE OSTI2025

IOTA Pre-Bake Test Development

The IOTA (Integrable Optics Test Accelerator) Bakeout project is intended to improve the quality of the vacuum within the IOTA ring. Impurities consisting of hydrogen and oxygen that build within the beampipe are reduced through applying heat to the beampipe’s exterior. Two versions of the Bakeout project exist, one as a smaller scale test setup, and one five times larger located within the IOTA ring. During my internship, I worked together with a team to bring this project from an effectively dormant state to ready for testing, working together to create full documentation of the PLC (Programmable Logic Controller) programs, making multiple new hardware configurations of this test possible, as well as an additional safety system.

Seagrave, Kayla [DuPage Coll.; Fermilab]↗
DOE OSTI2023

BUILD: Binary Understanding and Integration Logic for Dependencies (Final Report)

Increasingly diverse mission needs, the emergence of AI and cloud, and increasing hardware diversity are driving HPC software to be more complex. Modern codes are built from hundreds of small, complex components, and much of the software development process involves integrating these components rather than developing new components from scratch. The goal of the BUILD project was to ease the task of software integration for developers across LLNL’s programs. The project focused on (1) modeling software compatibility, (2) modeling ABI compatibility with binary analysis, (3) developing solver techniques to reason about compatibility, and (4) developing AI/ML models to fill gaps in our understanding of software compatibility. The project has developed several key technologies that help developers—by accelerating development workflows, removing the need for rebuilds, and enabling faster, automatic, and less error-prone code sharing. These technologies are used in LLNL codes and will be ready for the new El Capitan Exascale system in Livermore Computing. Many of these technologies have been hardened and integrated with LLNL’s Spack package manager, and they are already in use by production code teams. Results of BUILD have laid the groundwork for future advances in software integration—the ML and binary modification techniques developed in this project still need to be operationalized but have great potential to further speed up software integration.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

The future of self-driving laboratories: from human in the loop interactive AI to gamification

Recent developments in artificial intelligence (AI) and machine learning (ML), implemented through self-driving laboratories (SDLs), are rapidly creating unprecedented opportunities for the accelerated discovery and optimization of materials. This paper provides a joint analysis of SDLs from both academic and industry perspectives, highlighting the importance of integrating human intelligence in these systems. It discusses the necessity of careful planning in SDL design across physical, data, and workflow dimensions, including instrumental setup, experimental workflow, data management, and human–SDL interaction. The significance of integrating human input within SDLs, especially as the focus shifts from individual tools and tasks to the creation and management of complex workflows, is emphasized. The paper stresses on the crucial role of reward function design in developing forward-looking workflows and examines the interplay between hardware evolution, ML application across chemical processes, and the influence of reward systems in research. Ultimately, the article advocates for a future where SDLs blend human intuition in hypothesis formulation with AI's precision, speed, and data-handling capabilities.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Ultrafast High-Voltage Kicker System for Ion-Clearing Gaps

Ionization scattering of electron beams with residual gas molecules causes ion trapping in electron rings, both in a collider and electron cooling system. These trapped ions may cause emittance growth, tune shift, halo formation, and coherent coupled bunch instabilities. In order to clear the ions and prevent them from accumulating turn after turn, the gaps in a temporal structure of the beam are typically used. Typically, the gap in the bunch train has a length of a few percent of the ring circumference. In those regions, the extraction electrodes with high pulsed voltages are introduced. In this paper, we present the design consideration and initial test results of the high-voltage pulsed kicker hardware that includes vacuum device and pulsed voltage driver, capable of achieving over 3 kV of deflecting voltage amplitude, rise and fall times of less than 10 ns, 100 ns flat-top duration at 1.4 MHz repetition rate.

43 PARTICLE ACCELERATORS↗
DOE OSTI2020

The Accelerator Neutrino Neutron InteractionExperiment: Design, Construction and Preparationfor First Physics

This thesis covers work performed for the Accelerator Neutrino Neutron Interaction Experiment (ANNIE) between 2015 and 2020. ANNIE is a beamline neutrino experiment located at the Fermi National Accelerator Laboratory in Chicago. Its primary physics goals are the measurement of neutrino interaction cross-sections on oxygen, and a measurement of the multiplicity of final state neutrons from these interactions, both as functions of final state kinematics. In order to achieve these goals ANNIE will be pioneering the use of Large Area Picosecond Photodetectors and the use of gadolinium doping to enhance neutron visibility in a water Cherenkov detector. Over the time period of this thesis the ANNIE detector was constructed, an initial 'Phase I' background run was completed, the detector was decommissioned and then substantially upgraded in preparation for the main 'Phase II' physics run. At the time of writing ANNIE is being re-commissioned, with Phase II data taking anticipated to begin in 2021. During this time I spent 21/2 years on-site contributing to almost all aspects of hardware work, while performing software development for the simulation and analysis frameworks. As my first software task I developed Monte Carlo simulations of the detector response, based on the WCSim framework. While thismore » framework provided a starting point for the tank simulation significant modifications were required to implement the complete ANNIE detector system. This included a rewrite of the geometry, along with modifications to the photosensor definitions, hit collections, digitization, triggering, input and output interfaces, etc. To take advantage of improved modelling of neutrons in Geant4.10 the physics lists were also reimplemented in the new version format. As part of this work I determined performance metrics based on the output files, calculating kinematic acceptance, detector efficiency and expected event rates. My contributions on reconstruction focused primarily on the MRD, for which I implemented two track reconstruction algorithms, specialised for high and low energy muons. The high energy algorithm achieves >90% efficiency for tracks with at least 8 hits, and is robust against dead paddles and unrelated hits. The low energy algorithm performs a search in combination with tank information to provide sensitivity down to a single MRD hit. Early data handling work for the Phase I background run included writing the code for handling TDC hits and performing studies on neutron detection without the requirement of multi-hit coincidence. As the collaboration moved to a new framework for the Phase II analysis I performed a substantial amount of work to develop the codebase, implementing tools to perform tasks such as file IO, data parsing, waveform processing, event building, timestamp alignment, time clustering, hit residual calculation, event visualisation etc. I helped develop the python API for integrating multi-language tools, and ported the framework into a Singularity container to provide a self-contained environment that…« less

43 PARTICLE ACCELERATORS↗