SEARCH · Search NASA

Results for “hardware design”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4

All sources NASA NTRS DOE OSTI

DOE OSTI2026

NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning

Spiking Neural Networks (SNNs) are computational models inspired by the event-driven communication and connectivity patterns of biological neural circuits. They enable high energy efficiency and natural support for diverse architectures ranging from layered networks to small-world and graphstructured topologies. In this work, we introduce NeuroCoreX, an open-source, FPGA-based spiking neural network emulator that provides real-time, on-chip learning and flexible network organization. NeuroCoreX supports both feedforward sensory inputs streamed directly from sensors or PCs via UART and recurrent on-chip connectivity, enabling simultaneous processing and learning from external stimuli and internal network dynamics-capabilities rarely available in existing FPGA SNN platforms. The system implements a Leaky Integrate-and-Fire (LIF) neuron model with current-based synapses and supports pair-based STDP learning on both feedforward and recurrent synapses. A lightweight Python interface enables interactive configuration, live monitoring, weight read-back, and experiment control. Importantly, NeuroCoreX is tightly integrated with the SuperNeuroMAT simulator, allowing SNN models to be transferred seamlessly from software to hardware for hardware-in-the-loop development. By combining real-time plasticity, flexible connectivity, and an open-source VHDL implementation, NeuroCoreX provides an extensible and accessible platform for neuromorphic research, algorithm-hardware co-design, and energy-efficient edge intelligence.

Gautam, Ashish [ORNL]↗

DOE OSTI2024

A Simulation Study of 120V Heat Pump Water Heaters

A 120 V heat pump water heater (HPWH) is a direct plug-in option to replace gas water heater (WH) without needing expensive electric panel upgrade to 220 V. To enable the smooth transition, the HPWH should provide comparable water heating capacity as the gas WH. WH capacities are rated in the form of first hour rating (FHR). Typical home gas WHs have FHRs > 65 gallon with a 40-gallon water tank. It imposes a major challenge on 120V HPWHs. Most 120V circuits in US can provide 1,800 to 2,400W, not adequate to drive electric resistance heat to boost FHRs. Thus, all the heat needs to come from the heat pump with its top power below 1500 Watts, which is constraint by the installation footprint. This study uses a hardware based, HPWH design model, i.e. the DOE/ORNL Heat Pump Design Model to design a 120V unit with a brazed plate condenser, fin-and-tube evaporator and an adequately sized compressor. To maximize the FHR, multiple strategies were simulated, including use of a mixing valve, overheating the tank temperature to 140F, a new sensing method for quicker response, and an innovative water circulation path. We also simulated 24-hour unform energy factors (UEF) to show the tradeoff between the capacity and operation efficiency. Additionally, we evaluated the impact of insulation thickness on FHR and UEF, to seek further footprint reduction or stretch the tank volume.

Shen, Bo↗

DOE OSTI2026

Introduction to the Demonstration of Pyroshock Response Prediction Methods Using NASA ShockSat Data Virtual Collection

Mechanical shocks, particularly pyroshocks, are environments that all spacecraft and launch vehicles experience. Pyroshocks can be challenging design environments for space hardware because these events are often high frequency, high intensity transients. Furthermore, since design decisions must be made relatively early in the design phase, understanding, and accurately defining pyroshock excitation and the loads that it imparts on components is important to ensure the high reliability required of spacecraft and rockets. Here, general guidelines about shock transmission through spacecraft structures are provided in NASA and MIL handbooks and standards, but these are relatively broad guidelines, and recent studies have shown that more accurate and less-conservative predictions are needed. However, predicting shock response accurately is still a challenge because of the high frequencies in a pyroshock excitation.

Babuska, Vit [Sandia National Laboratories (SNL-NM↗

DOE OSTI2025

Development of Hydrogen Burner for FT4000® Aeroderivative Engine - Final Report

This report details an effort to develop a retrofittable fuel/air injector for the FT4000® aeroderivative gas turbine that enables use of hydrogen as a carbon-free fuel for efficient power generation. The FT4000 engine’s low-NOx combustor was developed by Pratt & Whitney and RTX Technology Research Center with core technology from the Pratt & Whitney PW4000 turbofan aircraft engine. The current FT4000 production engine operates on either natural gas or No. 2 fuel oil with water injection to achieve high thermal efficiency and low emissions. This engine is fielded by Mitsubishi Power Aero and delivers 70 MW of power with a simple-cycle efficiency of over 41% when operating with wet compression. The work reported here advances the technology readiness level of the FT4000 combustor for operation with hydrogen, starting with an experimental assessment of the current production hardware with increasing hydrogen content mixed with natural gas and ending with improved nozzle concepts for fully robust operation with 100% hydrogen. High-pressure single-sector combustor rig tests have been completed, demonstrating the ability for the dual fuel nozzle to operate an FT4000 combustor on 100% hydrogen with low nitrogen oxide (NOx) emissions. Metal temperature measurements and video images of the flame structure from zero to 100% hydrogen highlight opportunities to improve the fuel nozzle robustness for high hydrogen conditions. The design of new fuel/air mixer concepts to improve durability and operability with high hydrogen levels was also completed. A total of eleven new concepts were developed and analyzed, ranging from modifications to the bill-of-materials nozzle to fully clean sheet designs. The concepts were evaluated with non-reacting and reacting flow evaluations to assess the performance of the new hardware designs. Non-reacting tests included Phase Doppler Particle Analysis (PDPA) for droplet size and velocity, mechanical patternation for liquid water flux, and planar laser induced fluorescence (PLIF) with acetone-seeding for gaseous fuel/air mixing characterization. Five scaled candidate fuel nozzle designs, in addition to a scaled bill-of-materials nozzle, were then successfully evaluated in an atmospheric pressure burner rig. The nozzles were evaluated for performance with natural gas, hydrogen/natural gas blends, and pure hydrogen. For 100% hydrogen, the nozzles were evaluated with and without water injection. Optical and infrared imaging of the flame and fuel nozzle was captured. NOx emissions were sampled from fixed emissions probes. The results show measurable differences between the various designs, and the data was used to down-select the two most promising designs to advance to future full pressure rig testing. Results from this study have cleared the current production FT4000 engines with dual fuel nozzles to operate at baseload power on blends of hydrogen mixed with natural gas and water. Two promising nozzle designs have been developed to enable fully robust operation with up to 100% hydrogen. These nozzles require validation at full baseload operating conditions before they can be introduced to the field.

03 NATURAL GAS↗

DOE OSTI2026

Intelligent Experiments through Real-Time AI: Fast Data Processing and Autonomous Detector Control for High-Energy Nuclear Experiments

The aim of this project is to develop software and hardware for fast real-time data processing and autonomous detector control and calibration for the sPHENIX and the future EIC experiments. Below summarizes Georgia Tech team efforts in the past year: 1. We developed a real-time clustering algorithm and FPGA-based pipeline architecture for processing fired pixel data from ALPIDE sensors in sPHENIX experiments. Our Columnar Clustering Co-Design introduces a hardware-aware, stream-friendly approach that segments pixel data by column pairs using a Column Pair Clustering (CPC) strategy, followed by Cluster Stitching to merge adjacent subclusters. Implemented in Vitis HLS, the pipeline comprises five stages—read-in, subclustering, stitching, analysis, and write-out—connected by tagged HLS streams with custom end-of-event signaling for robust synchronization. We designed a pipelined dataflow model optimized for throughput, low latency, and minimal buffering, enabling scalable clustering across events of arbitrary size. Our system maintains spatial precision via center-of-mass and shape key extraction and efficiently handles edge cases such as fragmented or nested clusters. Compared against DBSCAN in both software and hardware, our approach demonstrates competitive performance under FPGA constraints. 2. We also conducted a comprehensive algorithm-to-hardware co-design of connected component analysis tailored for sPHENIX experiments, focusing on real-time, low-latency processing using FPGAs and High-Level Synthesis (HLS). Starting from a Python-based particle tracking pipeline, the team translated the core logic—graph traversal via DFS and Union-Find—into an HLS-compatible C++ model, replacing dynamic memory and recursion with static arrays and pipelined control flow. The final design includes a fully streamed and dataflow-compatible Union-Find kernel optimized across five iterations, incorporating loop pipelining, array partitioning, AXI/FIFO interface tuning, and function flattening. Experimental results show up to 14.8× speedup over the CPU baseline, reducing per-graph latency to 1.58 μs and demonstrating strong resource efficiency with only ~7k LUTs and zero BRAM usage. The design maintains functional correctness against the Python reference using a Python-based C-simulation framework and Mean Squared Error metrics. This work validates the potential of HLS-driven FPGA designs for edge-level HEP data acquisition, laying a scalable foundation for future integration with real-time detector pipelines and multi-graph processing systems.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2025

AI Benchmark Democratization and Carpentry

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model architectures, scale, datasets, and deployment contexts makes evaluation a moving target. Large language models often memorize static benchmarks, causing a gap between benchmark results and real-world performance. Beyond traditional static benchmarks, continuous adaptive benchmarking frameworks are needed to align scientific assessment with deployment risks. This calls for skills and education in AI Benchmark Carpentry. From our experience with MLCommons, educational initiatives, and programs like the DOE's Trillion Parameter Consortium, key barriers include high resource demands, limited access to specialized hardware, lack of benchmark design expertise, and uncertainty in relating results to application domains. Current benchmarks often emphasize peak performance on top-tier hardware, offering limited guidance for diverse, real-world scenarios. Benchmarking must become dynamic, incorporating evolving models, updated data, and heterogeneous platforms while maintaining transparency, reproducibility, and interpretability. Democratization requires both technical innovation and systematic education across levels, building sustained expertise in benchmark design and use. Benchmarks should support application-relevant comparisons, enabling informed, context-sensitive decisions. Dynamic, inclusive benchmarking will ensure evaluation keeps pace with AI evolution and supports responsible, reproducible, and accessible AI deployment. Community efforts can provide a foundation for AI Benchmark Carpentry.

von Laszewski, Gregor [Virginia U.]↗

DOE OSTI2025

Nuclear Thermal Rocket Emulator for a Hardware-in-the-Loop Test Bed

To support NASA’s mission to use nuclear thermal rockets for future Mars missions, an instrumentation and control test bed has been built at Oak Ridge National Laboratory. The system is designed as a hardware-in-the-loop test bed for testing control elements and autonomous control algorithms for nuclear thermal propulsion rockets. The mock reactor system consists of a modular and scalable framework, using inexpensive components and open-source software. The hardware system consists of a two-phase flow loop and a mock reactor with six control drums. A single-board computer (NVIDIA Jetson) handles reactor core emulation and hosts a message queuing telemetry transport broker that allows user-deployed control algorithms to interact with the system hardware. The reactor emulator receives sensor data from the hardware and provides the simulated performance of the reactor under steady-state, transient, and fault conditions. The emulator uses a reactivity lookup table and the point kinetics equations to solve for the reactor dynamics in real time. Emulated reactor dynamics and sensor input inform the autonomous control algorithm’s decision-making in a closed-loop manner. The current system is capable of operating at 10 Hz, but faster cycle rates are an area of ongoing research. This test bed will enable NASA and other space vendors to rigorously test their autonomous control systems for NTP rockets under transient (reactor startup and shutdown), steady-state, and fault conditions to reduce development time and risk for autonomous control systems in future missions.

autonomous control↗

DOE OSTI2025

Triangular cross-section grating couplers for integrated quantum nanophotonic hardware in silicon carbide

We design, fabricate, and characterize fishbone grating couplers for triangular cross-section photonics in silicon carbide compatible with color center integration. The periodic and aperiodic grating coupler designs are optimized to outcouple up to 31% of light in the fundamental TE mode of a triangular waveguide. The devices are fabricated using an ion beam etching process in a 4H–SiC sample implanted with NV center ensembles. The room-temperature transmission and the cryogenic NV center photoluminescence collection measurements indicate experimental grating coupler efficiency of up to 24%. This result provides a scalable method to efficiently extract color center light from SiC quantum nanophotonic devices to free-space optics.

Saha, Pranta↗

DOE OSTI2024

Reinforcement learning pulses for transmon qubit entangling gates

The utility of a quantum computer is highly dependent on the ability to reliably perform accurate quantum logic operations. For finding optimal control solutions, it is of particular interest to explore model-free approaches, since their quality is not constrained by the limited accuracy of theoretical models for the quantum processor—in contrast to many established gate implementation strategies. In this work, we utilize a continuous control reinforcement learning algorithm to design entangling two-qubit gates for superconducting qubits; specifically, our agent constructs cross-resonance and CNOT gates without any prior information about the physical system. Using a simulated environment of fixed-frequency fixed-coupling transmon qubits, we demonstrate the capability to generate novel pulse sequences that outperform the standard cross-resonance gates in both fidelity and gate duration, while maintaining a comparable susceptibility to stochastic unitary noise. We further showcase an augmentation in training and input information that allows our agent to adapt its pulse design abilities to drifting hardware characteristics, importantly, with little to no additional optimization. Our results exhibit clearly the advantages of unbiased adaptive-feedback learning-based optimization methods for transmon gate design.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2024

Modernizing Fermilab's Accelerator Control Hardware

Modernizing the Fermilab accelerator control system is essential to future operations of the laboratory's accelerator complex. The existing control system has evolved over four decades and uses hardware that is no longer available.The Accelerator Controls Operations Research Network (ACORN) Project will modernize the control system and replace end-of-life power supplies to enable future accelerator complex operations with megawatt particle beams. The ACORN project is planning to replace Fermilab s obsolete CAMAC crate-and-card controls hardware with modern MicroTCA hardware. There are over 2,000 CAMAC cards and over 250 CAMAC crates serving various functions in Fermilab s control system. We will review the existing CAMAC hardware and provide updates on the status of the ACORN project, which includes the conceptual design of the MicroTCA replacement hardware and software tools for supporting the installation of hundreds of MicroTCA crates.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

SPARTAN (Scalable Probabilistic Application Reconfigurable Tensor Autonomous Network)

The technical founder of Ludwig Computing Inc has been competitively selected for support by Cyclotron Road, a U.S. Department of Energy (DOE) Advanced Manufacturing Office (AMO) Lab-Embedded Entrepreneurship Program (LEEP) through an approved merit review process. Ludwig Computing Inc, supported by the U.S. Department of Energy's Advanced Manufacturing Office through the Cyclotron Road program, has investigated the advantages of probabilistic computing for real-world compute-intensive applications. This research adds to the understanding of alternative computing paradigms by exploring a unique hardware-software co-design that integrates quantum computing methods with nature-inspired problem-solving techniques. The project's focus on areas such as combinatorial optimization, graph analytics, and machine learning demonstrates the potential for significant advancements in computational efficiency and performance. By harnessing natural randomness to streamline large circuits into fewer devices, Ludwig's approach enables massive parallelism, potentially offering higher throughput, speed, and energy efficiency compared to conventional hardware solutions. This work benefits the public by paving the way for more efficient computing solutions that could address complex real-world problems while potentially reducing energy consumption in data-intensive industries.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Efficient Routing of Quantum LDPC Codes on Programmable 2D Toric Architectures

Quantum low-density parity-check codes are promising candidates towards scalable fault-tolerant quantum computation. Among these, bivariate bicycle (BB) codes offer superior encoding rates and large code distance compared to surface codes. However, their requirement on long-range stabilizer measurements poses significant challenges for implementation on realistic hardware with limited connectivity, such as superconducting circuit platforms. In this work, we introduce a novel hardware-software co-design that leverages a programmable communication network architecture to address these limitations. Our approach utilizes a 2D toric network of oscillators as a flexible communication fabric linking qubits at each site. Such architecture significantly reduces the number of long-range couplers required from O ( n ) to O (√ n ). Dual-rail qubits, along with native gates including Swap-Wait-Swap gates and beamsplitter SWAPs, ensure that long-range two-qubit gates can be executed with high fidelity and low latency. To further enhance performance, our qubit layout and routing algorithm utilize symmetries of the codes and enable maximum parallelism for long-range two-qubit gates, maintaining a low syndrome extraction cycle duration and scalability over the code length. We perform circuit-level simulation with realistic noise modeling based on experimental hardware parameters, observing an logical error rate per logical qubit per cycle of 3.06% for [[18,4,4]] BB code, 2.6× less than the existing experimental result. These findings provide a practical roadmap and identify key technological advancements needed to achieve low-overhead fault-tolerant quantum computing at scale.

Liu, Kun [Yale Univ., New Haven, CT (United States↗

DOE OSTI2025

Automating Testing of DUNE Electronics via a Finite State Machine

The Deep Underground Neutrino Experiment (DUNE) is a flagship international collaboration designed to study neutrinos—tiny, nearly massless particles that may hold answers to fundamental questions about the Universe. Fermilab’s Robotic Test Stand (RTS) plays a critical role in ensuring the quality of approximately 50,000 Application-Specific Integrated Circuit (ASIC) chips that will be used in DUNE’s massive liquid argon detectors. These electronics will be inside the cryostat; therefore, they will need to have a high yield of working chips and low noise. To improve the automation and reliability of the RTS, this project focused on designing and implementing a Python-based finite state machine (FSM) to manage chip handling workflows. The FSM was developed as a modular software framework to coordinate robotic arm movements, manage chip tray positions, and monitor system states during testing. Key features include robust error handling routines, a pause/resume system for safe mid-cycle interruptions, and a simulation mode for iterative testing without hardware dependencies. The system was designed to prepare for seamless integration with RTS hardware components such as the robotic arm and vision system. This integration will streamline collaboration and enable efficient deployment of updates across the six institutions performing testing. The outcomes of this internship contribute to Fermilab’s mission to advance high-energy physics and support the DOE’s national goals by directly improving the testing of equipment to be used in DUNE. The project also provided valuable experience in software design and contributing to the success of DUNE.

Kang, Caleb [Fermilab]↗

DOE OSTI2025

Automating Testing of DUNE Electronics via a Finite State Machine

The Deep Underground Neutrino Experiment (DUNE) is a flagship international collaboration designed to study neutrinos tiny, nearly massless particles that may hold answers to fundamental questions about the Universe. Fermilab s Robotic Test Stand (RTS) plays a critical role in ensuring the quality of approximately 50,000 Application-Specific Integrated Circuit (ASIC) chips that will be used in DUNE s massive liquid argon detectors. These electronics will be inside the cryostat; therefore, they will need to have a high yield of working chips and low noise. To improve the automation and reliability of the RTS, this project focused on designing and implementing a Python-based finite state machine (FSM) to manage chip handling workflows. The FSM was developed as a modular software framework to coordinate robotic arm movements, manage chip tray positions, and monitor system states during testing. Key features include robust error handling routines, a pause/resume system for safe mid-cycle interruptions, and a simulation mode for iterative testing without hardware dependencies. The system was designed to prepare for seamless integration with RTS hardware components such as the robotic arm and vision system. This integration will streamline collaboration and enable efficient deployment of updates across the six total institutions performing testing. The outcomes of this internship contribute to Fermilab s mission to advance high-energy physics and support the DOE s national goals by directly improving the testing of equipment to be used in DUNE. The project also provided valuable experience in software design and contributing to the success of DUNE.

Kang, Caleb [William Rainey Harper Coll.]↗

DOE OSTI2025

The Psyche Gamma-Ray and Neutron Spectrometer

A Gamma-Ray and Neutron Spectrometer (GRNS) instrument has been developed as part of the science payload for NASA’s Discovery Program Psyche mission to the M-class asteroid (16) Psyche. The GRNS instrument is designed to measure the elemental composition of Psyche with the goal to understand the origin of this mysterious, potentially metal-rich planetary body. The GRNS will measure the near-surface abundances for the elements Ni, Fe, Si, K, S, Al, and Ca, as well as the spatial distribution of Psyche’s metal-to-silicate fraction (or metal fraction). These measurements address three of the five Psyche mission science objectives: determine if Psyche is a core; determine whether small metal bodies incorporate light elements into the metal phase; and determine whether Psyche was formed under reducing conditions. The Gamma-Ray Spectrometer (GRS) uses a cryocooled, high-purity Ge (HPGe) sensor to detect cosmic-ray generated gamma rays in the 60 to 9000-keV energy range. The HPGe sensor is surrounded by a borated plastic anticoincidence shield that provides three functions: active background rejection from charged particle interactions in the HPGe sensor; fast neutron measurements; and direct measurements of the incident galactic cosmic ray flux. The Neutron Spectrometer (NS) uses three 3 He gas proportional sensors, each with different material wraps to measure thermal (<0.4 eV), low-energy epithermal (0.4 eV to 1 keV), and high-energy epithermal (up to 100 keV) neutrons. This paper provides an overview of the Psyche GRNS, including: its science and measurement objectives; the design of the instrument hardware, software, and operation; pre-launch performance measurements and its initial performance in space; and an overview of its data products and expected operation for different Psyche mission phases.

Engineering - Instrumentation related to nuclear s↗

DOE OSTI2026

Optimization-based approaches to control of connected and automated vehicles: Principles, complexities, applications, challenges, and outlook

Safe and optimal motion control for connected and automated vehicles (CAVs) poses a fundamental optimization challenge at the intersection of system complexity, environmental uncertainty, and stringent real-time constraints. Existing surveys address this challenge in isolation – focusing either on specific control techniques or individual uncertainty sources – without providing a unified framework that characterizes the trade-offs among computational tractability, performance verifiability, and adaptive generalization across paradigms. This review addresses that gap by presenting a cohesive analytical framework concentrated on the decision-making and trajectory optimization layers of the CAV autonomy stack. We systematically analyze three major optimization paradigms – first-principles model-based optimization, data-driven methods, and hybrid synergistic architectures – evaluating each against four core complexity axes: problem formulation, constraint handling, optimality guarantees, and robustness. Key applications including platooning, trajectory planning, collision avoidance, and cooperative control are examined to reveal recurring methodological patterns and critical operational constraints that limit real-world performance. Our synthesis identifies verifiable hybrid architectures, incentive-aligned multi-agent cooperation, and hardware-algorithm co-design as the defining research frontiers, and distills a targeted agenda for developing CAV control systems that are simultaneously safe, computationally efficient, and deployable in the full complexity of real-world traffic environments.

Muzahid, Abu Jafar Md [University of Tennessee, Kn↗

DOE OSTI2024

Integration of RNTuple in ATLAS Athena

After using ROOT’s TTree I/O subsystem for over two decades and storing more than an exabyte of compressed High Energy Physics (HEP) data, advances in technology have motivated a complete redesign, RNTuple, which breaks backward-compatibility to take better advantage of these storage options. The RNTuple I/O subsystem has been designed to address performance bottlenecks and other shortcomings of TTree. Specifically, RNTuple comes with an updated, more compact binary data format that can be stored both in ROOT files and natively in object stores. It is designed for modern storage hardware (e.g. high-throughput low-latency NVMe SSDs), and provides robust and easy to use interfaces. The binary format of RNTuple is scheduled to become production grade in 2024, and recently has become mature enough to start exploring the integration into software used by HEP experiments. In this contribution, we discuss the developments to support the features as required by the ATLAS analysis Event Data Model (EDM) in RNTuple, which will enable its integration into the Athena software framework. With these developments in place, we evaluate the performance of the current most recent versions of RNTuple-based ATLAS data sets and compare this to that of TTree.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

The Artificial Scientist: in-Transit Machine Learning of Plasma Simulations

Large-scale simulations or scientific experiments produce petabytes of data per run. This poses massive challenges for I/O and storage when scientific analysis workflows are run manually offline. Unsupervised deep learning-based techniques to extract patterns and non-linear relations from these large amounts of data provide a way to build scientific understanding from raw data, reducing the need for manual pre-selection of analysis steps, but require exascale compute and memory to process the full dataset available. In this paper, we demonstrate a heterogeneous streaming workflow in which plasma simulation data is streamed directly to a Machine Learning (ML) application training a model on the simulation data in-transit, completely circumventing the capacity-constrained filesystem bottleneck. This workflow employs openPMD to provide a high level interface to describe scientific data and also uses ADIOS2, to transfer volumes of data that exceed the capabilities of the filesystem. We employ experience replay to avoid catastrophic forgetting in learning from this non-steady state process in a continual manner and adapt it to improve model convergence while learning in-transit. As a proof-of-concept, we approach the ill-posed inverse problem of predicting particle dynamics from radiation in a particle-incell (PIConGPU) simulation of the Kelvin-Helmholtz instability (KHI). We detail hardware-software co-design challenges as we scale PIConGPU to full Frontier, the Top-1 system as of June 2024 Top500 list.

Kelling, Jeffrey [Helmholtz-Zentrum Dresden Rossen↗