SEARCH · Engineering Papers
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.
The transport of charge carriers throughout an active conjugated polymer (CP) host, characterized by a heterogeneous morphology of locally varying degrees of order and disorder, profoundly influences the performance of CP-based electronic devices.
Krylov methods are a key way of solving large sparse linear systems of equations but suffer from poor strong scalability on distributed memory machines. Furthermore, this is due to high synchronization costs from large numbers of collective communication calls alongside a low computational workload. Enlarged Krylov methods address this issue by decreasing the total iterations to convergence, an artifact of splitting the initial residual and resulting in operations on block vectors. In this article, we present a performance study of an enlarged Krylov method, Enlarged Conjugate Gradients (ECG), noting the impact of block vectors on parallel performance at scale. Most notably, we observe the increased overhead of point-to-point communication as a result of denser messages in the sparse matrix-block vector multiplication kernel. Additionally, we present models to analyze expected performance of ECG, as well as motivate design decisions. Most importantly, we introduce a new point-to-point communication approach based on node-aware communication techniques that increases efficiency of the method at scale.
Here, we present a new software system PETSc TSAdjoint for first-order and second order adjoint sensitivity analysis of time-dependent nonlinear differential equations. The derivative calculation in PETSc TSAdjoint is essentially a high-level algorithmic differentiation process. The adjoint models are derived by differentiating the timestepping algorithms and implementing them based on the parallel infrastructure in PETSc. Full differentiation of the library code, including MPI routines, is avoided, and users do not need to derive their own adjoint models for their specific applications. PETSc TSAdjoint can compute the first-order derivative, that is, the gradient of a scalar functional, and the Hessian-vector product, which carries second-order derivative information, while requiring minimal input (a few callbacks) from the users. The adjoint model employs optimal checkpointing schemes in a manner that is transparent to users. Finally, usability, efficiency, and scalability are demonstrated through examples from a variety of applications.
Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Loss scaling studies have demonstrated the superior performance of larger LLMs compared to their smaller counterparts. Nevertheless, training LLMs with billions of parameters poses significant challenges and requires considerable computational resources. For example, training a one trillion parameter GPT-style model on 20 trillion tokens requires a staggering 120 million exaflops. This research explores efficient distributed training strategies to extract this computation from Frontier, the world's first exascale supercomputer. We enable and investigate various model and data parallel training techniques, such as tensor parallelism, pipeline parallelism, and sharded data parallelism, to facilitate training a trillion-parameter model on Frontier. We empirically assess these techniques and their associated parameters to determine their impact on memory footprint, communication latency, and GPU's computational efficiency. We analyze the complex interplay among these techniques and find a strategy to combine them to achieve high throughput through hyperparameter tuning. We have identified efficient strategies for training large LLMs of varying sizes through empirical analysis and hyperparameter tuning. For 22 Billion, 175 Billion, and 1 Trillion parameters, we achieved GPU throughputs of 38.38%, 36.14%, and 31.96%, respectively. For the training of the 175 Billion parameter model and the 1 Trillion parameter model, we achieved 100% weak scaling efficiency on 1024 and 3072 Mi250X GPUs, respectively. We also achieved strong scaling efficiencies of 89% and 87% for these two models. We trained these models only tens of iterations instead of training till completion.
Materials with strong magnetoresistive responses are the backbone of spintronic technology, magnetic sensors, and hard drives. Among them, manganese oxides with a mixed valence and a cubic perovskite structure stand out due to their colossal magnetoresistance (CMR). A double exchange interaction underlies the CMR in manganates, whereby charge transport is enhanced when the spins on neighboring Mn 3+ and Mn 4+ ions are parallel. Prior efforts to find different materials or mechanisms for CMR resulted in a much smaller effect. Here an enormous CMR at low temperatures in EuCd 2 P 2 without manganese, oxygen, mixed valence, or cubic perovskite structure is shown. EuCd 2 P 2 has a layered trigonal lattice and exhibits antiferromagnetic ordering at 11 K. The magnitude of CMR (10(4)%) in as-grown crystals of EuCd 2 P 2 rivals the magnitude in optimized thin films of manganates. In this work, the magnetization, transport, and synchrotron X-ray data suggest that strong magnetic fluctuations are responsible for this phenomenon. The realization of CMR at low temperatures without heterovalency leads to a new regime for materials and technologies related to antiferromagnetic spintronics.
The PRO-X program is actively supporting the design of nuclear systems by developing a framework to both optimize the fuel cycle infrastructure for advanced reactors (ARs) and minimize the potential for production of weapons-usable nuclear material. Three study topics are currently being investigated by Sandia National Laboratories (SNL) with support from Argonne National Laboratories (ANL). This multi-lab collaboration is focused on three study topics which may offer proliferation resistance opportunities or advantages in the nuclear fuel cycle. These topics are: 1) Transportation Global Landscape, 2) Transportation Avoidability, and 3) Parallel Modular Systems vs Single Large System (Crosscutting Activity).
Abstract We present ReactionMechanismSimulator.jl (RMS), a modern differentiable software for the simulation and analysis of chemical kinetic mechanisms, including multiphase systems. RMS has already been applied to problems in combustion, pyrolysis, polymers, pharmaceuticals, catalysis, and electrocatalysis. RMS is written in Julia, making it easy to develop and allowing it to take advantage of Julia's extensive numerical computing ecosystem. In addition to its extensive library of optimized analytic Jacobians, RMS can generate and use Jacobians computed using automatic differentiation and symbolically generated analytic Jacobians. RMS is demonstrated to be faster than Cantera and Chemkin in several benchmarks. RMS also implements an extensive set of features for analyzing chemical mechanisms, including a library of easy‐to‐call plotting functions, molecular structure resolved flux diagram generation, crash analysis, traditional sensitivity analysis, transitory sensitivity analysis, and an automatic mechanism analysis toolkit. RMS implements efficient adjoint and parallel forward sensitivity analyses. We also demonstrate the ease of adding new features to RMS.
Rapid, wide-scale deployment of green process systems, such as carbon capture or water desalination systems, is essential for combatting climate change. Methods relying on traditional design or modularity fail to capture the benefits of both economies of numbers and economies of scale. We have proposed process family design, which designs a family of processes simultaneously exploiting opportunities for common elements. In previous work, we explored different optimization formulations to solve this problem. In this work, we develop a decomposition approach to tackle larger problems efficiently. We solve a water desalination case study, which is too large to solve within a reasonable timeframe with the discretization formulation. We exploit the block angular structure of the discretization problem to decompose and solve using Progressive Hedging (PH). We use the open-source Python package mpi-sppy to execute PH which allows us to leverage parallelization and a HPC cluster to further improve solution time.
Atomic-scale intrinsic defects play a key role in controlling functional electronic properties of two-dimensional (2D) materials. Here, we present a low-temperature scanning–tunneling microscopy and spectroscopy investigation of a common point-defect in monolayer molybdenum disulfide (MoS 2 ). We employ a sample preparation method in which the film surface is never exposed to air so that the native dangling bonds surrounding the defects in the film are preserved. Molybdenum vacancies are identified by their three characteristic in-gap resonances by combining scanning–tunneling measurements with parallel Green’s function-based theoretical modeling. The relative energy shifts between the various in-gap states allow us to identify a relative charge difference between two of the observed vacancies. The role of the substrate on the band structure of the defective MoS 2 monolayer is unveiled. Our study highlights the effects of the substrate on the in-gap states of common defects found in MoS 2 providing a pathway in designing and optimizing 2D materials for electronic applications.
At high concentration, long Watson/Crick (WC) double-helixed DNA forms columnar crystal or liquid crystal phases of linear, parallel duplex chains packed on periodic lattices. This can also be a structural motif of short NA oligomers such as the 5’-GTAC-3’ studied here, which makes four-base WC duplexes having hydrophobic blunt ends. End-to-end aggregation then assembles these duplexes into columns and columnar phases are stabilized, in spite of breaks in the double helix every four bases. But the new degrees of freedom introduced by such breaks also enable opportunities for a more diverse palette of self-assembly modes, producing striking self-assemblies of DNA that would not be achievable with contiguous polymers. These include recently reported three-dimensional (3D) periodic low-density nanoscale networks of GCCG, and the twist grain boundary (TGB) phase presented here. In the TGB, columns of GTAC pairs assemble into monolayer sheets in which the duplex columns are mutually parallel. However, unlike in the columnar crystals, these sheets stack in helical fashion into lamellar arrays in which the column axis of each layer is rotated through a 60° angle with respect to the columns in neighboring layers. This assembly of DNA is unique in that it the fills a 3D volume wherein the major grooves of columns in each layer mutually enter and interlock with the major grooves of columns in neighboring layers. This locking is optimized by small adjustments in structure enabled by the breaks in the duplex backbones.
SUMMARY Knowledge of the fracturing processes can be important for the optimization of pressurized fluid injection operations in the deep underground rock mass. Active and passive seismic monitoring techniques have been used in the field for tracking or mapping the propagating hydraulic fracture. Although both these monitoring techniques provide valuable information about the generated fracture network, it is difficult for either technique to comprehensibly identify the different processes associated with hydraulic fracturing. The combined active and passive monitoring has the potential for better characterization of the complex hydraulic fracturing phenomena. In this study, laboratory hydraulic fracturing experiments with combined active and passive seismic monitoring were conducted on true triaxially loaded Barre granite cubes with different fluid injection rates. The seismic inelastic fracturing was detected by 16 passive acoustic emission sensors, where 3678 and 2370 seismic source events were detected for the high and low injection rate experiments, respectively. For active monitoring, strong variations in the attributes of signals were observed which were transmitted through four source–receiver pairs, placed both perpendicular and parallel to the generated hydraulic fracture. Positive velocity changes were observed for active sensor pairs with ray paths passing through the generated hydraulic fracture indicating fluid permeation, whereas isolated dry deformation was characterized by a slight but permanent velocity decrease. Compared to velocity, the energy of the active signals was 1–2 orders of magnitude more sensitive to different hydraulic fracturing processes. However, the sensitivity and signatures of the active signal attributes were found to be dependent on the frequency range and direction of ray path with respect to the location of the generated fracture network. Using the coupled evaluation of the active and passive signals we were able to systematically identify various hydraulic fracturing processes including: (1) aseismic deformation, (2) fracture initiation and fluid permeation, (3) pressure build-up, (4) fracture propagation and (5) pressure release and leak-off. The results of this study showed that combining the respective advantages of active and passive seismic techniques and using both of them to monitor the failure processes can facilitate a more comprehensive understanding and better control of the hydraulic stimulations in subsurface operations.
Here, we present a framework for calibration of parameters in elastoplastic constitutive models that is based on the use of automatic differentiation (AD). The model calibration problem is posed as a partial differential equation-constrained optimization problem where a finite element (FE) model of the coupled equilibrium equation and constitutive model evolution equations serves as the constraint. The objective function quantifies the mismatch between the displacement predicted by the FE model and full-field digital image correlation data, and the optimization problem is solved using gradient-based optimization algorithms. Forward and adjoint sensitivities are used to compute the gradient at considerably less cost than its calculation from finite difference approximations. Through the use of AD, we need only to write the constraints in terms of AD objects, where all of the derivatives required for the forward and inverse problems are obtained by appropriately seeding and evaluating these quantities. We present three numerical examples that verify the correctness of the gradient, demonstrate the AD approach's parallel computation capabilities via application to a large-scale FE model, and highlight the formulation's ease of extensibility to other classes of constitutive models.
The crystal structure of danofloxacin mesylate has been solved and refined using synchrotron X-ray powder diffraction data and optimized using density functional theory techniques. Danofloxacin mesylate crystallizes in space group P1 (#1) with a = 6.77474(8), b = 12.4973(4), c = 12.82826(28) Å, α = 84.8709(29), β = 87.7501(10), γ = 74.9916(4)°, V = 1044.723(11) Å 3 , and Z = 2. The protonation of the danofloxacin cations was established by the analysis of potential intermolecular interactions and differs from that expected from isolated-cation calculations. The crystal structure consists of alternating layers of cations and anions parallel to the ac-plane. There is parallel stacking of the oxoquinoline rings along the a-axis. The expected N–H∙∙∙O hydrogen bonds between the cations and anions are not present. Each cation makes an N–H∙∙∙O hydrogen bond with the other cation, resulting in zig-zag chains along the a-axis. Both cations have strong intramolecular O–H∙∙∙O hydrogen bonds. There are several C–H∙∙∙O hydrogen bonds between the danofloxacin cations and mesylate anions. The powder pattern has been submitted to ICDD® for inclusion in the Powder Diffraction File™ (PDF®).
Scientific workflows drive most modern large-scale science breakthroughs by allowing scientists to define their computations as a set of jobs executed in a given order based on their data dependencies. Workflow management systems (WMSs) have become key to automating scientific workflows-executing computational jobs and orchestrating data transfers between those jobs running on complex high-performance computing (HPC) platforms. Traditionally, WMSs use files to communicate between jobs: a job writes out files that are read by other jobs. However, HPC machines face a growing gap between their storage and compute capabilities. To address that concern, the scientific community has adopted a new approach called in situ, which bypasses costly parallel filesystem I/O operations with faster in-memory or in-network communications. When using in situ approaches, communication and computations can be interleaved. In this work, we leverage the Decaf in situ dataflow framework to accelerate task-based scientific workflows managed by the Pegasus WMS, by replacing file communications with faster MPI messaging. We propose a new execution engine that uses Decaf to manage communications within a sub-workflow (i.e., set of jobs) to optimize inter-job communications. We consider two workflows in this study: (i) a synthetic workflow that benchmarks and compares file- and MPI-based communication; and (ii) a realistic bioinformatics workflow that computes mu-tational overlaps in the human genome. Experiments show that in situ communication can improve the bioinformatics workflow execution time by 22% to 30% compared with file communication. Our results motivate further opportunities and challenges for bridging traditional WMSs with in situ frameworks.
We report a resource estimation pipeline that explicitly compiles quantum circuits expressed using the Clifford+T gate set into a surface code lattice surgery instruction set. The cadence of magic state requests from the compiled circuit enables the optimization of magic state distillation and storage requirements in a post-hoc analysis. To compile logical circuits into lattice surgery operations, we build upon the open-source Lattice Surgery Compiler. The revised compiler operates in two stages: the first translates logical gates into an abstract, layout-independent instruction set; the second compiles these into local lattice surgery instructions that are allocated to hardware tiles according to a specified resource layout. The second stage retains logical parallelism while avoiding resource contention in the fault-tolerant layer, aiding realism. Additionally, users can specify dedicated tiles at which magic states are replenished, enabling resource costs from the logical computation to be considered independently from magic state distillation and storage. We demonstrate the applicability of our pipeline to large practical quantum circuits by providing resource estimates for the ground state estimation of molecules. Finally, we find that variable magic state consumption rates in real circuits can cause the resource costs of magic state storage to dominate unless production is varied to suit.
The purpose of the COMMAND code is to provide a flexible, scalable tool for use in developing, integrating, and testing the technologies necessary for achieving autonomous operations of advanced nuclear reactors. The code enables users to efficiently implement custom simulations and experiments by combining key methods from different software modules. These modules are focused on: modeling and simulation tools, such as nuclear simulation tools used for high-fidelity modeling (e.g., Reactor Excursion and Leak Analysis Program [RELAP5-3D] and Monte Carlo N-Particle [MCNP]); machine learning and optimization tools (e.g., anomaly detection and data-driven modeling techniques); advanced control in its digital, high-performance, and supervisory control forms (e.g., proportional integral derivative (PID) control and model predictive control (MPC); and integration with hardware through industrial communication protocols. To ensure flexibility and scalability, COMMAND was designed to be both modular—the software “pieces” all inherit from generic building blocks and can be combined and connected to create complicated simulations—and high performing—designed for parallel processing, enabling simulations and experiments to take advantage of multi-core computers, servers, and nodes. The code is written in the Python programming language due to the language's popularity, active community, and open-source and cross-platform nature. Maintaining consistency with other simulation tools used within the nuclear energy community, users implement simulations and experiments through text input files, which define components, parameters, connections, etc., through lines of text. Given that COMMAND is written in Python, these input files are native Python scripts, and so use the standard Python structure and formatting. This also enables users to take advantage of Python's extensive package library to develop custom capabilities for their specific use cases.
Here, this work seeks to allow for the online operation and training of model-free reinforcement learning (RL) agents but limit the risk to system equipment and personnel. The parallel implementation of RL alongside more conventional process control (CPC) allows for the RL algorithm to learn from CPC. The past performance of both methods are assessed on a continuous basis allowing for a transition from CPC to RL and, if needed, transitioning back to CPC from RL. This allows for the RL algorithm to slowly and safely assume control of the process without significant degradation in control performance. It is shown that the RL can derive a near optimal policy even when coupled with a suboptimal CPC. It is also demonstrated that the coupled RL-CPC algorithm learns at a faster rate than traditional RL methods of exploration while the algorithm’s performance does not deteriorate below CPC, even when exposed to an unknown operating condition.
The National Spherical Torus Experiment Upgrade (NSTX-U) is preparing to resume operation, representing a crucial step toward realizing compact, cost-effective fusion pilot plants. In advance of this, extensive modeling and data analysis have been conducted to advance the physics basis for low-aspect-ratio, high-performance plasma regimes, focusing on three core objectives: confinement and stability, power and particle handling, and steady-state operation. Significant progress has been made in understanding the electron temperature flattening in high-β plasmas, which is shown to be driven by a complex interplay of magnetohydrodynamic instabilities (e.g. non-resonant infernal modes), fast-ion-driven Alfvén eigenmodes, and electron and ion-scale micro-instabilities, particularly Kinetic Ballooning Modes (KBMs), whose destabilization is strongly dependent on parallel magnetic field fluctuations (δB ∥ ). Furthermore, a new gyrokinetic critical pedestal model was developed, accurately predicting pedestal structure by identifying KBMs as the primary stability limit, offering a critical constraint for future high-confinement scenarios. To address the challenge of high heat flux, novel liquid lithium plasma-facing components were modeled. The analysis confirmed that lithium vapor shielding is a self-regulating mechanism for heat mitigation, while also emphasizing that strong main ion parallel flow is essential to minimize core lithium contamination. Finally, progress toward steady-state operation was anchored by developing the required physics basis and control tools. This includes predictive modeling for reversed magnetic shear sustainment, demonstrating that magnetic island-induced bootstrap current reduction is negligible in STs, and advancing real-time control and disruption avoidance capabilities. The development of high-speed surrogate models (e.g. MMMNet) provides computationally efficient tools vital for non-inductive scenario optimization and integrated, low-disruptivity operations planned for NSTX-U.