Search NASA⌕ Search

SEARCH · Search NASA

Results for “accelerated computing”

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 631 records · Page 35

Online and Scalable Data Compression Pipeline with Guarantees on Quantities of Interest

Data compression is becoming critical for data-intensive scientific applications. Scientists require compression techniques that accurately preserve derived quantities of interest (QoIs). Prior work has shown that a pipeline can be built to guarantee error on the primary data (PD) within user-defined bounds and achieve near-floating point QoI errors. In this paper, we present novel computational approaches for accelerating the pipeline and demonstrate results that enable concurrent execution of compression in parallel with the simulation nodes. This allows compression, including the writing of the required compression data, for the previous time step to be completed while the simulation proceeds with the current time step. Overall, the approach presented in this paper results in a 6–8 times improvement in computational overhead compared to previous work. These results were obtained using data generated by a large-scale fusion code called XGC, which produces hundreds of terabytes of data in a single day.

Banerjee, Tania↗

Audacity of huge: overcoming challenges of data scarcity and data quality for machine learning in computational materials discovery

Machine learning (ML)-accelerated discovery requires large amounts of high-fidelity data to reveal predictive structure–property relationships. For many properties of interest in materials discovery, the challenging nature and high cost of data generation has resulted in a data landscape that is both scarcely populated and of dubious quality. Data-driven techniques starting to overcome these limitations include the use of consensus across functionals in density functional theory, the development of new functionals or accelerated electronic structure theories, and the detection of where computationally demanding methods are most necessary. When properties cannot be reliably simulated, large experimental data sets can be used to train ML models. In the absence of manual curation, increasingly sophisticated natural language processing and automated image analysis are making it possible to learn structure–property relationships from the literature. Finally, models trained on these data sets will improve as they incorporate community feedback.

36 MATERIALS SCIENCE↗

WE-G-18A-01: JUNIOR INVESTIGATOR WINNER - Low-Dose C-Arm Cone-Beam CT with Model-Based Image Reconstruction for High-Quality Guidance of Neurosurgical Intervention

Purpose: To address the challenges of image quality, radiation dose, and reconstruction speed in intraoperative cone-beam CT (CBCT) for neurosurgery by combining model-based image reconstruction (MBIR) with accelerated algorithmic and computational methods. Methods: Preclinical studies involved a mobile C-arm for CBCT imaging of two anthropomorphic head phantoms that included simulated imaging targets (ventricles, soft-tissue structures/bleeds) and neurosurgical procedures (deep brain stimulation (DBS) electrode insertion) for assessment of image quality. The penalized likelihood (PL) framework was used for MBIR, incorporating a statistical model with image regularization via an edgepreserving penalty. To accelerate PL reconstruction, the ordered-subset, separable quadratic surrogates (OS-SQS) algorithm was modified to incorporate Nesterov's method and implemented on a multi-GPU system. A fair comparison of image quality between PL and conventional filtered backprojection (FBP) was performed by selecting reconstruction parameters that provided matched low-contrast spatial resolution. Results: CBCT images of the head phantoms demonstrated that PL reconstruction improved image quality (∼28% higher CNR) even at half the radiation dose (3.3 mGy) compared to FBP. A combination of Nesterov's method and fast projectors yielded a PL reconstruction run-time of 251 sec (cf., 5729 sec for OS-SQS, 13 sec for FBP). Insertion of a DBS electrode resulted in severe metal artifact streaks in FBP reconstructions, whereas PL was intrinsically robust against metal artifact. The combination of noise and artifact was reduced from 32.2 HU in FBP to 9.5 HU in PL, thereby providing better assessment of device placement and potential complications. Conclusion: The methods can be applied to intraoperative CBCT for guidance and verification of neurosurgical procedures (DBS electrode insertion, biopsy, tumor resection) and detection of complications (intracranial hemorrhage). Significant improvement in image quality, dose reduction, and reconstruction time of ∼4 min will enable practical deployment of low-dose C-arm CBCT within the operating room. AAPM Research Seed Funding (2013-2014); NIH Fellowship F32EB017571; Siemens Healthcare (XP Division)

60 APPLIED LIFE SCIENCES↗

Investigation of Portable Event-Based Monte Carlo Transport Using the NVIDIA Thrust Library

Power consumption considerations are driving future high performance computing platforms toward many-core computing architectures. Los Alamos National Laboratory's Trinity machine, available in 2016, will use both Intel Xeon Haswell processors and Intel Xeon Phi Knights Landing many integrated core (MIC) architecture coprocessors. Lawrence Livermore National Laboratory's Sierra machine, available in 2018, will use an IBM PowerPC architecture along with Nvidia graphics processing unit (GPU) architecture accelerators. These different advanced architectures make the computing landscape in upcoming years complex. Traditional approaches to Monte Carlo transport do not work efficiently on these new computing platforms. MIC architectures require vectorization to operate efficiently, and vectorization is difficult to achieve in Monte Carlo transport. GPU architectures require additional code to explicitly use the hardware, requiring significant code changes or hardware specific branches in the source code. A significant challenge for Monte Carlo transport projects is to simultaneously support within a single source code base efficient simulations for both the current generation of architectures and the different advanced computing architectures. In order to address these challenges, two important changes are typically required: a new algorithmic approach for solving Monte Carlo transport, and explicit use of hardware specific software. In this paper, we describe initial research investigations of an event-based Monte Carlo transport algorithm implemented using the Nvidia Thrust library on a GPU for a Monte Carlo test code. The event-based algorithm targets many-core architectures by increasing SIMD (single instruction multiple data) parallelism, while Thrust potentially provides portable performance by allowing one source code base to compile code targeted for both CPUs and GPUs. We described preliminary investigations of portable event-based Monte Carlo algorithms implemented using the Nvidia Thrust library in a research Monte Carlo test code. We found that an explicit CUDA implementation of an event-based Monte Carlo algorithm performed significantly more efficiently than a Thrust implementation on GPU platforms, most likely as a result of additional flexibility in access to different memory spaces on the GPU. Additionally, we showed that on GPU platforms and at large enough problem sizes the event-based implementations perform more efficiently than the serial history-based implementation running on the host CPU. While investigating this problem, we also discovered that the performance of the event-based algorithm is affected by what tallies are being used. A zonal scalar flux tally requires atomic operations that significantly impacted the performance of the code, in some cases producing slowdowns instead of speedups. We decided to remove the tally in order to focus on the effectiveness of the event-based algorithm. Future work will be required to research more effective ways of handling such tallies. Additionally, we would like to consider new ways for optimizing both the Thrust and CUDA versions, in order to see how much performance we have yet to achieve. The potential trade-off between portability and performance was demonstrated in this investigation. Thrust provides both CPU and GPU versions of the code in one code base, but it does so at a cost. We discovered approximately a factor of 2-5 performance difference between Thrust and CUDA on each GPU platform we tested. Thrust provides a tool to access the GPUs with less effort and specialization, but it does so by giving up fine grained control where extra performance can be found for this application. Future work will be required to determine whether this performance differential between Thrust and CUDA can be reduced for event-based Monte Carlo transport. (authors)

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

ASPECT RATIO DEPENDENCE OF THE FREE-FALL TIME FOR NON-SPHERICAL SYMMETRIES

We investigate the collapse of non-spherical substructures, such as sheets and filaments, which are ubiquitous in molecular clouds. Such non-spherical substructures collapse homologously in their interiors but are influenced by an edge effect that causes their edges to be preferentially accelerated. We analytically compute the homologous collapse timescales of the interiors of uniform-density, self-gravitating filaments and find that the homologous collapse timescale scales linearly with the aspect ratio. The characteristic timescale for an edge-driven collapse mode in a filament, however, is shown to have a square-root dependence on the aspect ratio. For both filaments and circular sheets, we find that selective edge acceleration becomes more important with increasing aspect ratio. In general, we find that lower dimensional objects and objects with larger aspect ratios have longer collapse timescales. We show that estimates for star formation rates, based upon gas densities, can be overestimated by an order of magnitude if the geometry of a cloud is not taken into account.

79 ASTRONOMY AND ASTROPHYSICS↗

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classication is found to be easily misled by increasingly complex image features due to the usage of pooling operations, hence unable to preserve accurate position and pose information of the objects. To address this challenge, a novel neural network structure called Capsule Network has been proposed, which introduces equivariance through capsules to signicantly enhance the learning ability for image segmentation and object detection. Due to its requirement of performing a high volume of matrix operations, CapsNets have been generally accelerated on modern GPU platforms that provide highly optimized software library for common deep learning tasks. However, based on our performance characterization on modern GPUs, CapsNets exhibit low effciency due to the special program and execution features of their routing procedure, including massive unshareable intermediate variables and intensive syn- chronizations, which are very dicult to optimize at software level. To address these challenges, we propose a hybrid computing architecture design named PIM-CapsNet. It preserves GPU's on-chip computing capability for accelerating CNN types of layers in CapsNet, while pipelining with an off-chip in-memory acceleration solution that effectively tackles routing procedure's ineffciency by leveraging the processing-in-memory capability of today's 3D stacked memory. Using routing procedure's inherent parallellization feature, our design enables hierarchical improvements on CapsNet inference effciency through minimizing data movement and maximizing parallel processing in memory. Evaluation results demonstrate that our proposed design can achieve substantial improvement on both performance and energy savings for CapsNet inference, with almost zero accuracy loss. The results also suggest good performance scalability in optimizing the routing procedure with increasing network size.

Zhang, Xingyao↗

Experimental evaluation of a flexible I/O architecture for accelerating workflow engines in ultrascale environments

The increasing volume of scientific data and the limited scalability and performance of storage systems are currently presenting a significant limitation for the productivity of the scientific workflows running on both high-performance computing (HPC) and cloud platforms. Clearly needed is better integration of storage systems and workflow engines to address this problem. This paper presents and evaluates a novel solution that leverages codesign principles for integrating Hercules—an in-memory data store—with a workflow management system. We consider four main aspects: workflow representation, task scheduling, task placement, and task termination. As a result, the experimental evaluation on both cloud and HPC systems demonstrates significant performance and scalability improvements over existing state-of-the-art approaches.

97 MATHEMATICS AND COMPUTING↗

Generating clock signals for a cycle accurate, cycle reproducible FPGA based hardware accelerator

A method, system and computer program product are disclosed for generating clock signals for a cycle accurate FPGA based hardware accelerator used to simulate operations of a device-under-test (DUT). In one embodiment, the DUT includes multiple device clocks generating multiple device clock signals at multiple frequencies and at a defined frequency ratio; and the FPG hardware accelerator includes multiple accelerator clocks generating multiple accelerator clock signals to operate the FPGA hardware accelerator to simulate the operations of the DUT. In one embodiment, operations of the DUT are mapped to the FPGA hardware accelerator, and the accelerator clock signals are generated at multiple frequencies and at the defined frequency ratio of the frequencies of the multiple device clocks, to maintain cycle accuracy between the DUT and the FPGA hardware accelerator. In an embodiment, the FPGA hardware accelerator may be used to control the frequencies of the multiple device clocks.

Asaad, Sameh W.↗

Generating clock signals for a cycle accurate, cycle reproducible FPGA based hardware accelerator

A method, system and computer program product are disclosed for generating clock signals for a cycle accurate FPGA based hardware accelerator used to simulate operations of a device-under-test (DUT). In one embodiment, the DUT includes multiple device clocks generating multiple device clock signals at multiple frequencies and at a defined frequency ratio; and the FPG hardware accelerator includes multiple accelerator clocks generating multiple accelerator clock signals to operate the FPGA hardware accelerator to simulate the operations of the DUT. In one embodiment, operations of the DUT are mapped to the FPGA hardware accelerator, and the accelerator clock signals are generated at multiple frequencies and at the defined frequency ratio of the frequencies of the multiple device clocks, to maintain cycle accuracy between the DUT and the FPGA hardware accelerator. In an embodiment, the FPGA hardware accelerator may be used to control the frequencies of the multiple device clocks.

Asaad, Sameh W.↗

Understanding Portability of a High-Level Programming Model on Contemporary Heterogeneous Architectures

Accelerator-based heterogeneous computing is gaining momentum in the high-performance computing arena. However, the increased complexity of heterogeneous architectures demands more generic, high-level programming models. OpenACC is one such attempt to tackle this problem. Although the abstraction provided by OpenACC offers productivity, it raises questions concerning both functional and performance portability. In this article, the authors propose HeteroIR, a high-level, architecture-independent intermediate representation, to map high-level programming models, such as OpenACC, to heterogeneous architectures. They present a compiler approach that translates OpenACC programs into HeteroIR and accelerator kernels to obtain OpenACC functional portability. They then evaluate the performance portability obtained by OpenACC with their approach on 12 OpenACC programs on Nvidia CUDA, AMD GCN, and Intel Xeon Phi architectures. They study the effects of various compiler optimizations and OpenACC program settings on these architectures to provide insights into the achieved performance portability.

97 MATHEMATICS AND COMPUTING↗

FAIR Data and Interpretable AI Framework for Architectured Metamaterials

Our interdisciplinary effort successfully generated FAIR (Findable, Accessible, Interoperable, and Reusable) benchmark datasets for mechanical metamaterials while introducing a novel Artificial Intelligence (AI) framework known as Learning Refined Compositional Rules (LRCR). This framework was specifically designed to bridge the gap across varying computational length scales and extract the underlying physical mechanisms that connect a material's structural geometry to its bulk acoustic properties. Historically, the discovery of such structured materials relied heavily on human intuition or opaque, black-box optimization algorithms that were difficult to generalize. By combining interpretable machine learning techniques with rigorous experimental validation, this project established clear, generalizable design guidelines for tuning wave dispersion and controlling vibrations. Ultimately, the public availability of these structured datasets and algorithms will significantly reduce computational costs and accelerate the design of advanced multi-functional acoustic devices, offering broad societal impacts across fields like aerospace engineering, telecommunications, and biomedical implant design.

36 MATERIALS SCIENCE↗

A physics-constrained neural ordinary differential equations approach for robust learning of stiff chemical kinetics

The high computational cost associated with solving for detailed chemistry poses a significant challenge for predictive computational fluid dynamics (CFD) simulations of turbulent reacting flows. While deep learning techniques have been explored to develop faster surrogate models, they often fail to integrate reliably with CFD solvers. This instability arises because traditional deep learning approaches optimize for training error without ensuring compatibility with ordinary differential equation (ODE) solvers, resulting in accumulation of errors over time. Recently, neuralODE (NODE) based approaches have been shown to be a promising technique to emulate and accelerate detailed chemistry computations. Here, in the present work, we extend this NODE framework for stiff chemical kinetics by incorporating mass conservation constraints directly into the loss function during training. This ensures that the total mass as well as the individual elemental species masses are conserved in an a-posteriori manner. Proof-of-concept studies are performed with the novel physics-constrained NODE (PC-NODE) approach for homogeneous autoignition of hydrogen-air mixture over a range of composition and thermodynamic conditions. It is demonstrated that the PC-NODE framework not only improves the physical consistency of the resulting data-driven model with respect to mass conservation criteria, but also improves training efficiency. PC-NODE is shown to achieve 2–100× speedup relative to the hydrogen-air detailed chemical mechanism depending on the type of the ODE solver (implicit or explicit) used during autoregressive inference tests. Lastly, a-posteriori studies are performed wherein the trained PC-NODE model is coupled with a CFD solver. It is shown that higher accuracy is achieved with PC-NODE relative to the purely data-driven NODE approach. Moreover, PC-NODE also exhibits robustness and generalizability to unseen initial conditions from within (interpolative capability) as well as outside (extrapolative capability) the training regime.

computational combustion↗

Quantum magic and multipartite entanglement in the structure of nuclei

Motivated by the Gottesman-Knill theorem, we present a detailed study of the quantum complexity of p -shell and s d -shell nuclei. Valence-space nuclear shell-model wave functions generated by the code are mapped to qubit registers using the Jordan-Wigner mapping (12 qubits for the p shell and 24 qubits for the s d shell), from which measures of the many-body entanglement ( n -tangles) and magic (nonstabilizerness) are determined. While exact evaluations of these measures are possible for nuclei with a modest number of active nucleons, Monte Carlo simulations are required for the more complex nuclei. The broadly applicable Pauli-string I ̂ Z ̂ exact (PSIZe) Markov chain Monte Carlo (MCMC) technique is introduced to accelerate the evaluation of measures of magic in deformed nuclei (with hierarchical wave functions), by factors of ≈ 8 for some nuclei. Significant multinucleon entanglement is found in the s d shell, dominated by proton-neutron configurations, along with significant measures of magic. This is evident not only for the deformed states, but also for nuclei on the path to instability via regions of shape coexistence and level inversion. These results indicate that quantum-computing resources will accelerate precision simulations of such nuclei and beyond. Published by the American Physical Society 2025

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

In Situ Methods, Infrastructures, and Applications on High Performance Computing Platforms, a State-of-the-art (STAR) Report

The considerable interest in the high performance computing (HPC) community regarding analyzing and visualization data without first writing to disk, i.e., in situ processing, is due to several factors. First is an I/O cost savings, where data is analyzed /visualized while being generated, without first storing to a filesystem. Second is the potential for increased accuracy, where fine temporal sampling of transient analysis might expose some complex behavior missed in coarse temporal sampling. Third is the ability to use all available resources, CPU’s and accelerators, in the computation of analysis products. This STAR paper brings together researchers, developers and practitioners using in situ methods in extreme-scale HPC with the goal to present existing methods, infrastructures, and a range of computational science and engineering applications using in situ analysis and visualization.

97 MATHEMATICS AND COMPUTING↗

Synthesis of optimal adsorptive carbon capture processes.

Solid sorbent carbon capture systems have the potential to require significantly lower regeneration energy compared to aqueous monoethanol amine (MEA) systems. To date, the majority of work on solid sorbents has focused on developing the sorbent materials themselves. In order to advance these technologies, it is necessary to design systems that can exploit the full potential and unique characteristics of these materials. The Department of Energy (DOE) recently initiated the Carbon Capture Simulation Initiative (CCSI) to develop computational tools to accelerate the commercialization of carbon capture technology. Solid sorbents is the first Industry Challenge Problem considered under this initiative. An early goal of the initiative is to demonstrate a superstructure-based framework to synthesize an optimal solid sorbent carbon capture process. For a given solid sorbent, there are a number of potential reactors and reactor configurations consisting of various fluidized bed reactors, moving bed reactors, and fixed bed reactors. Detailed process models for these reactors have been modeled using Aspen Custom Modeler; however, such models are computationally intractable for large optimization-based process synthesis. Thus, in order to facilitate the use of these models for process synthesis, we have developed an approach for generating simple algebraic surrogate models that can be used in an optimization formulation. This presentation will describe the superstructure formulation which uses these surrogate models to choose among various process alternatives and will describe the resulting optimal process configuration.

97 MATHEMATICS AND COMPUTING↗

Modeling of Thermal Quench in Superconducting RF Cavities

Superconducting radio frequency (SRF) cavities are often limited by thermal quench, which is an excessive electromagnetic heating that occurs in the high magnetic field area and expands thereafter forcing the cavity to lose its superconducting state. In this paper, we demonstrate how the quench phenomena can be modeled using a coupled electromagnetic thermal analysis. The proposed model takes into account the nonlinearity of the material properties at cryogenic temperature and the effect of Kapitza resistance. The proposed approach is used to compute the thermal quench field of a 3.9 GHz 9-cell accelerating cavity, a 2.815 GHz deflecting cavity, and a 1.3GHz 9-cell accelerating cavity. Here, the computed values of quenchfield are in good agreement with the measured ones observedduring vertical testing at 2 K. Without loss of generality, theproposed methodology can be applied to other cavity geometries.

43 PARTICLE ACCELERATORS↗

Performance analysis and acceleration of explicit integration for large kinetic networks using batched GPU computations

Abstract—We demonstrate the systematic implementation of recently-developed fast explicit kinetic integration algorithms that solve efficiently N coupled ordinary differential equations (subject to initial conditions) on modern GPUs. We take representative test cases (Type Ia supernova explosions) and demonstrate two or more orders of magnitude increase in efficiency for solving such systems (of realistic thermonuclear networks coupled to fluid dynamics). This implies that important coupled, multiphysics problems in various scientific and technical disciplines that were intractable, or could be simulated only with highly schematic kinetic networks, are now computationally feasible. As examples of such applications we present the computational techniques developed for our ongoing deployment of these new methods on modern GPU accelerators. We show that similarly to many other scientific applications, ranging from national security to medical advances, the computation can be split into many independent computational tasks, each of relatively small-size. As the size of each individual task does not provide sufficient parallelism for the underlying hardware, especially for accelerators, these tasks must be computed concurrently as a single routine, that we call batched routine, in order to saturate the hardware with enough work.

Haidar Ahmad, Azzam↗