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.
Argonaut - A Robotic System for Cryogenic Environments
Fermilab and the HEP community invest significant resources into liquid argon detectors. The largest and most expensive of these detectors will be located in the Deep Underground Neutrino Experiment (DUNE). However, recent experiences have shown that there are limited avenues of monitoring, intervention, and interaction in the internal liquid environment. This proposal shows a technological path that could provide a valuable tool to ensure or at least improve the management of these HEP detectors. The development of a robotic system named Argonaut will demonstrate several technologies including 1) demonstration of suitable mobility of a small robotic device at liquid argon temperatures, 2) demonstration of wireless communication, 3) demonstration of improved diagnostics capabilities - such as tunable optics with motion control, 4) demonstration of interconnectivity of a robotic system with hardware residing within the detector. This initial research will be a seed for extended development in cold robotics and associated technologies. This work will allow FNAL to contribute a significant technology capability to recent efforts to cryogenic detector operations.
A Simulation and Optimization Framework for Managing Wind-Driven Loading on PV Systems
As PV modules continue to trend toward larger, thinner, and more flexible forms they grow more susceptible to damage from dynamic wind loading. As a result, understanding the impact of wind on PV systems, particularly when mounted on solar-tracking hardware, and identifying robust, stable array layouts and stow strategies is becoming increasingly important for the PV community. We are developing an open-source software package, PVade (PV aerodynamic design engineering), to simulate the cascading fluid-structure interaction that occurs within solar-tracking arrays to enable researchers to test hardware, layout, and tracker control changes, leading to enhanced stability and a reduction in wind-driven damage. We will give an overview of the PVade software and present the latest outcomes from our ongoing validation campaign in which we compare statistical structural responses with field data. From there, we will present simulated results from a larger, multi-row array and highlight the effect of varying tracker angles on stability as measured by both acceleration and deformation, focusing on the stability differences between positive and negative tilt angles.
Building an Integrated Ecosystem of Computational and Observational Facilities to Accelerate Scientific Discovery
Future scientific discoveries will rely on flexible ecosystems that incorporate modern scientific instruments, high performance computing resources, parallel distributed data storage, and performant networks across multiple, independent facilities. In addition to connecting physical resources, such an ecosystem presents many challenges in logistics and accessibility, especially in orchestrating computations and experiments that span across leadership computing systems and experimental instruments. Past efforts have typically been application-specific or limited to interfaces for computing resources. This paper proposes a general framework for integrating computation resources and instrument operations, addressing challenges in code development/execution, data staging and collection, software stack, control mechanisms, resource authorization and governance, and hardware integration. We also describe a demonstration use case wherein a Bayesian optimization algorithm running on an edge computing resource guides a scanning probe microscope to autonomously and intelligently characterize a material sample. This science edge ecosystem framework will provide a blueprint for federating multi-institutional, disparate resources and orchestrating scientific workflows across them to enable next-generation discoveries.
MRT 7365: Power flow physics and key physics phenomena
The Z accelerator at Sandia National Laboratories conducts z-pinch experiments at 26 MA in support of DOE missions in stockpile stewardship, dynamic materials, fusion, and other basic sciences. Increasing the current delivered to the z-pinch would extend our reach in each of these disciplines. To achieve increases in current and accelerator efficiency, a fraction of Z’s shots are set aside for research into transmission-line power flow. These shots, with supporting simulations and theory, are incorporated into this Advanced Diagnostics milestone report. The efficiency of Z is reduced as some portion of the total current is shunted across the transmission-line gaps prior to the load. This is referred to as “current loss”. Electrode plasmas have long been implicated in this process, so the bulk of dedicated power-flow experiments are designed to measure the plasma environment. The experimental analyses are enhanced by simulations conducted using realistic hardware and Z voltage pulses. In the same way that diagnostics are continually being improved for sensitivity and resolution, the modeling capability is continually being improved to provide faster and more realistic simulations. The specifics of the experimental hardware, diagnostics, simulations, and algorithm developments are provided in this report. The combined analysis of simulation and data confirms that electrode plasmas have the most detrimental impact on current delivery. Experiments over the last three years have tested the theoretical current-loss mechanisms of enhanced ion current, plasma gap closure, and Hall-related current. These mechanisms are not mutually exclusive and may be coincident in the final feed as well as in upstream transmission lines. The final-feed geometries tested here, however, observe lower-density plasmas without dominant ion currents which is consistent with a Hall-related current. The picture of plasma formation and transport formed from experiment and simulation is informing hardware designs being fielded on Z now and being proposed for the Next-Generation Pulsed Power (NGPP) facility. In this picture, the strong magnetic fields that heat the electrodes above particle emission thresholds also confine the charged particles near the surface. Some portion of the plasmas thus formed is transported into the transmission-line gap under the force of the electric field, with aid from plasma instabilities. The gap plasmas are then transported towards the load by a cross-field drift, where they accumulate and contribute to a likely Hall-related cross-gap current. The achievements in experimental execution, model validation, and physical analysis presented in this report set the stage for continued progress in power flow and load diagnostics on Z. The planned shot schedule for Z and Mykonos will provide data for extrapolation to higher current to ensure the predicted performance and efficiency of a NGPP facility.
Fermilab Italian Student Program (Final Report)
I participated to the 2019 Fermilab Italian Student Program under the supervision of Anadi Canepa and Lorenzo Uplegger. I worked with the Fermilab research group that is involved with the R&D of the CMS Outer Tracker. The Compact Muon Solenoid (CMS) is a a general-purpose detector located at the Large Hadron Collider (LHC), the world's most powerful particle accelerator. In the next years LHC will undergo the High-Luminosity LHC upgrade, which will bring its luminosity from 1 × 10 34 cm -2 s -1 to 1.5 × 10 34 cm -2 s -1 . This increase in luminosity will require an upgrade of CMS as well, in order to comply with the augmented rate of particles which will cross the detector. The CMS tracker is a detector, composed of various modules made of silicon pixel trackers and silicon strip trackers, whose aim is to reconstruct the trajectories of the particles produced by the collisions in LHC. The tracker is ideally divided in Inner Tracker and Outer Tracker. The HL-LHC upgrade put important challenges in the designing of the tracker. It will have to withstand the irradiation of a large fluence of particles, without suffering a too severe deterioration of its performance. In addition to this, in order to comply with the increased rate of events that CMS will need to detect, the tracker will be exploited for triggering at the fully hardware Level 1 Trigger, in contrast to the current tracker, whose data are only used for the software High-Level Trigger. This feature is managed by the "stub logic", which will be explained in chapter 2. During the months of August and September at Fermilab I carried out the data analysis of three test beam runs performed in the last two years on the 2S Outer Tracker Minimules. The 2S Minimoule consists of two silicon strip trackers placed one upon the other with the strips kept parallel.
Geant4 Event Biasing and Fast Simulation
Geant4 offers advanced event biasing techniques to significantly accelerate simulations involving rare events. Various biasing methods, such as leading particle selection, cross-section biasing, radioactive decay enhancement, and bremsstrahlung splitting, enable efficient event sampling, though they require careful handling. Additionally, Geant4 provides a Fast Simulation Interface, allowing the replacement of standard processes in specific region and for selected particles, enabling faster execution or external code integration. Applications of fast simulation include electromagnetic shower modeling in calorimeters, machine learning inference, and offloading tasks to specialized hardware like GPUs, making Geant4 a powerful tool for computationally demanding simulations.
Tandem Photovoltaics Core Program Final Technical Report
The Tandem Photovoltaics Core Program was a multi-year initiative aimed at advancing hybrid tandem solar cell technologies to enhance solar module efficiency beyond the limits of single junction devices. This project focused on the development, testing, and scaling of prototype photovoltaic devices, with the goal of achieving commercial relevance and driving industry adoption. The work was divided into three tasks: 1) Comparative Analysis of Tandem Technologies: This task focused on quantifying energy yield under real-world conditions and assessing economic viability of tandems relative to silicon-based modules. The project's modeling framework incorporated performance data, cost of materials, and manufacturing process impacts to optimize tandem designs 2) Tandem Integration and Prototyping: In this task, we developed innovative tandem designs by combining metal halide perovskite (MHP) top cells and silicon (Si) bottom cells. The project focuses on both mechanical integration and direct deposition techniques to enable compatibility with commercially relevant Si technologies, such as passivated contact or PERC cells. 3) Scale-up and Reliability: This task addressed the challenges of large-area fabrication by developing scalable deposition methods and robust interconnection schemes for tandems. The project looked at different accelerated testing such as thermal cycling, damp heat exposure, and potential induced degradation, to ensure long-term stability of devices in field conditions. Tandem solar cells can greatly increase module efficiency beyond conventional single junction (SJ) devices, which are approaching their theoretical limit. There are many ways to fabricate a tandem cell or module in terms of materials used, configuration, and terminal connection. This SETO core project focused critical factors in enabling tandems to enter the market, including hardware integration, technoeconomic analysis (TEA), and energy yield analysis. We focused on MHP/Si hybrid tandem solar cells and modules as a model system for their versatility in module design comparisons, providing valuable insights for other tandem options. While champion cells with areas <1cm2 are regularly demonstrated by groups around the world, it is significantly more challenging to translate these advances into modules, and fewer institutions and companies are working at the module level. This project addressed questions about module fabrication, testing, and reliability that are hard to answer without actually fabricating prototypes. We also performed analysis and road-mapping activities to understand the potential for a wider variety of tandems, including all-perovskite tandems fabricated in collaboration with the Perovskite PV core program. Detailed technical results from this project are described for each task in Section 7.
AutoLabs: cognitive multi-agent systems with self-correction for autonomous chemical experimentation
The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs approaches expert-authored reference procedures on the benchmark (F1-score > 0.89) on challenging multi-plate syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code: https://github.com/pnnl/autolabs
Methane Mitigation Thermoelectric Generator (MMTEG) (Final Scientific/ Technical Report)
Gas Technology Institute (GTI) has completed a $1.815M (plus $500K cost share), 54-month Co-operative agreement with the Department of Energy’s National Energy Technology Laboratory to develop a Methane Mitigation Thermoelectric Generator (MMTEG) system for gas field applications. This novel system uses fugitive gas to produce electrical power and consists of Thermoelectric Generators (TEG) driven by a linear burner, an air compressor, an accumulator, valves, batteries, and power electronics. The electrical power generated by the system is used to compress air and, in turn, the air is used to operate the pneumatic valves at the well site instead of using natural gas (NG) which would then be vented. The team completed the project objectives which included (1) Design, fabricate and test an integrated 6We nominal MMTEG prototype system, (2) Design a “retrofit kit” MMTEG system capable of being field tested at a gas well production site, and (3) build and test the field MMTEG system in a laboratory environment. Multiple system options were developed prior to selecting a “Passive” system which meets cost, NG savings, and greenhouse gas (GHG) reduction targets although not as efficient as initially planned. The MMTEG system is built primarily from commercial off-the-shelf parts (in some cases re-purposed) including the heat exchanger, heat rejection, electronic components, and also the TEGs. The team developed and implemented a novel system including the control system developed by Morrison Applied Sciences (MAS). The team completed incremental demonstrations of the hardware prior to the MMTEG system demonstration. A one-year simulation of the air delivery and battery charging subsystems was completed prior to the integration into the MMTEG system. In addition, the team simulated two-years of thermal cycles for integrated Burner/TEG/heat rejection subsystem. Finally, the entire MMTEG system was assembled, and troubleshooting was completed over a two-week period. Next, the MMTEG system was tested to simulate over 15 weeks of entire system operation over approximately four weeks in an accelerated test fashion with minimal intervention (such as changing fuel tanks). The MMTEG system met the key goals of a unit cost of under $1500 while saving 97% of NG expended today (including leakage) on average by pneumatic systems venting to the atmosphere. The MMTEG system reduced GHG emissions by 1000X (using the methane intensification factor of 28 relative to CO2). GTI is currently pursuing a field test of the MMTEG system. Interfacing with producers has provided additional insight into system improvements. Planned improvements include additional weather protection and control system improvements including the implementation of a long- range radio capability to notify operators if there is a fault.
A time-parallel multiple-shooting method for large-scale quantum optimal control
Quantum optimal control plays a crucial role in quantum computing by providing the interface between compiler and hardware. Solving the optimal control problem is particularly challenging for multi-qubit gates, due to the exponential growth in computational complexity with the system's dimensionality and the deterioration of optimization convergence. To ameliorate the computational complexity of time-integration, this paper introduces a multiple-shooting approach in which the time domain is divided into multiple windows and the intermediate states at window boundaries are treated as additional optimization variables. Further, this enables parallel computation of state evolution across time-windows, significantly accelerating objective function and gradient evaluations. Since the initial state matrix in each window is only guaranteed to be unitary upon convergence of the optimization algorithm, the conventional gate trace infidelity is replaced by a generalized infidelity that is convex for non-unitary state matrices. Continuity of the state across window boundaries is enforced by equality constraints. A quadratic penalty optimization method is used to solve the constrained optimal control problem, and an efficient adjoint technique is employed to calculate the gradients in each iteration. We demonstrate the effectiveness of the proposed method through numerical experiments on quantum Fourier transform gates in systems with 2, 3, and 4 qubits, noting a speedup of 80x for evaluating the gradient in the 4-qubit case, highlighting the method's potential for optimizing control pulses in multi-qubit quantum systems.
Analog In-Memory Computing for the Synthetic Aperture Radar Polar Format Algorithm
As the utility of synthetic aperture radar (SAR) systems increases in autonomous vehicles, satellites, and other power- and space-constrained edge applications, there is a growing need for processors that can form SAR images at low power. In recent years, analog in-memory compute (AIMC) has shown immense promise for accelerating neural networks and other matrix-vector multiplication (MVM) heavy workloads at the edge. Here, in this work, we examine how the polar format algorithm (PFA), a popular SAR image formation algorithm, can be mapped to these AIMC systems. The PFA maps readily onto analog MVMs because it primarily consists of two linear operations: interpolation of frequency-domain data to a Cartesian grid, followed by a 2-D Fourier transform. This work presents two approaches to map the interpolation operation onto MVMs in analog hardware: a chirp transform and a modified form of sinc interpolation. These mappings introduce algorithmic errors, and their effect on the quality of SAR image formation is examined, both quantitatively and qualitatively. In addition, the impact of errors introduced by the analog hardware is explored to determine which approach is optimal under varying assumptions about the underlying analog memory devices and circuits.
Error and Correction Analysis for the FFA@CEBAF Energy Upgrade
An energy upgrade design for the Continuous Electron Beam Accelerator Facility (CEBAF) is under development, using fixed field alternating gradient (FFA) return arcs to recirculate electron beam up to an additional five times through the accelerating structures at CEBAF. A necessary component of any large accelerator is a beam steering and optical correction system. Small environmental changes and system errors can lower beam quality or even shut down the machine; and in pursuit of the scientific mission of JLab, high quality electron beams must be delivered to the experimental halls on a predictable schedule. Correction in the novel FFA arcs of the current upgrade design is complicated by several factors. These complexities inform the choice of correction algorithm structure and parameter values. A baseline algorithm in addition to diagnostic and correction hardware configuration is presented. The effect of this correction protocol is shown with respect to estimated errors, and several possible extensions of the algorithm are discussed. This work presents an important proof of concept for the FFA@CEBAF design effort, and provides a functional correction strategy which may be simply adjusted and optimized for future design changes.
3-center and 4-center 2-particle Gaussian AO integrals on modern accelerated processors
We report an implementation of the McMurchie–Davidson (MD) algorithm for 3-center and 4-center 2-particle integrals over Gaussian atomic orbitals (AOs) with low and high angular momenta l and varying degrees of contraction for graphical processing units (GPUs). This work builds upon our recent implementation of a matrix form of the MD algorithm that is efficient for GPU evaluation of 4-center 2-particle integrals over Gaussian AOs of high angular momenta (l ≥ 4) [A. Asadchev and E. F. Valeev, J. Phys. Chem. A 127, 10889–10895 (2023)]. The use of unconventional data layouts and three variants of the MD algorithm allow for the evaluation of integrals with double precision and sustained performance between 25% and 70% of the theoretical hardware peak. Performance assessment includes integrals over AOs with l ≤ 6 (a higher l is supported). Preliminary implementation of the Hartree–Fock exchange operator is presented and assessed for computations with up to a quadruple-zeta basis and more than 20 000 AOs. The corresponding C++ code is part of the experimental open-source LibintX library available at https://github.com/ValeevGroup/libintx.
Early experiences evaluating the HPE/Cray ecosystem for AMD GPUs
Summary The Oak Ridge Leadership Computing Facility (OLCF) has a long history of supporting and promoting GPU‐accelerated computing starting with the deployment of the Titan supercomputer in 2021 and continuing with the Summit supercomputer which has a theoretical peak performance of approximately 200 petaflops. Because the majority of Summit's computational power comes from its 27,972 GPUs, users must port their applications to one of the supported programming models in order to make efficient use of the system. To prepare the transition to Frontier, the OLCF's exascale supercomputer, users will need to adapt to an entirely new ecosystem which will include new hardware and software technologies. First, users will need to familiarize themselves with the AMD Radeon GPU architecture. Furthermore, users who have been previously relying on CUDA will need to transition to the Heterogeneous‐Computing Interface for Portability (HIP) or one of the other supported programming models (e.g., OpenMP, OpenACC). In this work, we describe our initial experiences and lessons learned in porting three applications or proxy apps currently running on Summit to the HPE/Cray ecosystem to leverage the compute power from AMD GPUs: minisweep, GenASiS, and Sparkler. Each one is representative of current production workloads utilized at the OLCF, different programming languages, and different programming models.
Leveraging Compiler-Based Translation to Evaluate a Diversity of Exascale Platforms
Accelerator-based heterogeneous computing is the de facto standard in current and upcoming exascale machines. These heterogeneous resources empower computational scientists to select a machine or platform well-suited to their domain or applications. However, this diversity of machines also poses challenges related to programming model selection: inconsistent availability of programming models across different exascale systems, lack of performance portability for those programming models that do span several systems, and inconsistent performance between different models on a single platform. We explore these challenges on exascale-similar hardware, including AMD MI100 and NVIDIA A100 GPUs. By extending the sourceto-source compiler OpenARC, we demonstrate the power of automated translation of applications written in a single frontend programming model (OpenACC) into a variety of backend models (OpenMP, OpenCL, CUDA, HIP) that span the upcoming exascale environments. This translation enables us to compare performance within and across devices and to analyze programming model behavior with profiling tools.
One-Turn Delay Feedback (OTFB) Implementation for the EIC
This paper discusses the implementation of the One-Turn Delay Feedback (OTFB) for the Electron-Ion Collider (EIC). The theory of the OTFB is well documented, therefore, this paper will mainly discuss the details of the implementation. After a short introduction, the paper will discuss the building-blocks of the OTFB, simulation testing of the OTFB, and finally hardware validation of the OTFB.
ECP SOLLVE: Validation and Verification Testsuite Status Update and Compiler Insight for OpenMP
The OpenMP language continues to evolve with every new specification release, as does the need to validate and verify the new features that have been implemented by the different vendors. With the release of OpenMP 5.0 and OpenMP 5.1, new target offload and host-based features have been introduced to the programming model. While OpenMP continues to grow in maturity, there is an observable growth in the number of compiler and hardware vendors that support OpenMP. In this manuscript, the main focus is on evaluating the conformity and OpenMP implementation progress of various compiler vendors such as Cray, IBM, GNU, Clang/LLVM, NVIDIA, and Intel. More specifically, the 4.5, 5.0, and 5.1 versions of the OpenMP specification are analyzed. For our experimental setup, the Crusher and Summit computing systems hosted by Oak Ridge National Lab’s Computing Facilities are utilized. The effort of vendor agnostic analysis of these implementations is especially valuable for application developers who are using new OpenMP features to accelerate their scientific codes. Insights are presented into the current implementation status of various vendors, the progression of specific compiler’s support for OpenMP overtime, the subset of OpenMP 4.5, 5.0, and 5.1 that is supported by all compilers, and examples of how our test suite has influenced discussion regarding the correct interpretation of the OpenMP specification. By evaluating OpenMP conformity of pre-Exascale computing systems, the aim is to detail progress and status of AMD + Cray ecosystem before the system and their OpenMP implementation is used for mission critical applications when the first Exascale Computer Frontier is made available to applications.