Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “compute in memory”

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 667 records · Page 37
All sourcesNASA NTRSDOE OSTI
NASA NTRS1993

A multiblock analysis for shuttle orbiter re-entry heating from Mach 24 to Mach 12

A multiblock, laminar heating analysis for the shuttle orbiter at three trajectory points ranging from Mach 24.3 to Mach 12.86 on re-entry is described. The analysis is performed using the Langley Aerothermodynamic Upwind Relaxation Algorithm (LAURA) with both a seven species chemical nonequilibrium model and an equilibrium model. A finite-catalytic-wall model appropriate for shuttle tiles at a radiative equilibrium wall temperature is applied. Computed heating levels are generally in good agreement with the flight data though a few rather large discrepancies remain unexplained. The multiblock relaxation strategy partitions the flowfield into manageable blocks requiring a fraction of the computational resources (time and memory) required by a full domain approach. In hot, the computational cost for a solution at even a single trajectory point would be prohibitively expensive at the given resolution without the multiblock approach. Converged blocks are reassembled to enable a fully coupled converged solution over the entire vehicle, starting from a nearly converged initial condition.

Gnoffo, Peter A.↗
NASA NTRS1994

Multiblock analysis for Shuttle Orbiter reentry heating from Mach 24 to Mach 12

A multiblock, laminar heating analysis for the shuttle orbiter at three trajectory points ranging from Mach 24.3 to Mach 12.86 on reentry is described. The analysis is performed using the Langley Aerothermodynamic Upwind Relaxation Algorithm with a seven species chemical nonequilibrium model. A finite-catalytic-wall model appropriate for shuttle tiles at a radiative equilibrium wall temperature is applied. Computed heating levels are generally in good agreement with the flight data, although a few rather large discrepancies remain unexplained. The multiblock relaxation strategy partitions the flowfield into manageable blocks requiring a fraction of the computational resources (time and memory) required by a full domain approach. In fact, the computational cost for a solution at even a single trajectory point would be prohibitively expensive at the given resolution without the multiblock approach. Converged blocks are reassembled to enable a fully coupled converged solution over the entire vehicle, starting from a nearly converged initial condition.

LANGLEY AEROTHERMODYNAMIC UPWI↗
NASA NTRS2002

Application of Local Discretization Methods in the NASA Finite-Volume General Circulation Model

We present the basic ideas of the dynamics system of the finite-volume General Circulation Model developed at NASA Goddard Space Flight Center for climate simulations and other applications in meteorology. The dynamics of this model is designed with emphases on conservative and monotonic transport, where the property of Lagrangian conservation is used to maintain the physical consistency of the computational fluid for long-term simulations. As the model benefits from the noise-free solutions of monotonic finite-volume transport schemes, the property of Lagrangian conservation also partly compensates the accuracy of transport for the diffusion effects due to the treatment of monotonicity. By faithfully maintaining the fundamental laws of physics during the computation, this model is able to achieve sufficient accuracy for the global consistency of climate processes. Because the computing algorithms are based on local memory, this model has the advantage of efficiency in parallel computation with distributed memory. Further research is yet desirable to reduce the diffusion effects of monotonic transport for better accuracy, and to mitigate the limitation due to fast-moving gravity waves for better efficiency.

Yeh, Kao-San↗
DOE OSTI2025

Homomorphic data compression for real time photon correlation analysis

The construction of highly coherent X-ray sources, combined with next-generation detectors that are larger and faster, has enabled new research opportunities across the scientific landscape. Among the techniques that benefit most from these advancements is X-ray photon correlation spectroscopy (XPCS), where faster acquisition unlocks the ability to study faster dynamics within samples. However, faster acquisition on larger detectors also introduces unprecedented challenges for online data processing and offline data storage. Such challenges are particularly prominent for XPCS, where real time analyses require simultaneous calculation of all the previously acquired data in the time series. We present a homomorphic compression scheme to effectively reduce the computational time and memory space required for XPCS analysis. Leveraging similarities in the mathematical expression between a matrix-based compression algorithm and the correlation calculation, our approach allows direct operation on the compressed data without their decompression. The offline compression scheme extends storage capacity by a factor of 40 while preserving key features in the lossy compressed data. Meanwhile, the online compression scheme reduces the computational time to below 1 ms, enabling real time calculation of the correlation functions at kHz framerate. Our demonstration of a homomorphic compression of scientific data provides an effective solution to the big data challenge at coherent light sources. Beyond the example shown in this work, the framework can be extended to facilitate real-time operations directly on a compressed data stream for other techniques.

36 MATERIALS SCIENCE↗
NASA NTRS1991

Parallelized solvers for heat conduction formulations

Based on multilevel partitioning, this paper develops a structural parallelizable solution methodology that enables a significant reduction in computational effort and memory requirements for very large scale linear and nonlinear steady and transient thermal (heat conduction) models. Due to the generality of the formulation of the scheme, both finite element and finite difference simulations can be treated. Diverse model topologies can thus be handled, including both simply and multiply connected (branched/perforated) geometries. To verify the methodology, analytical and numerical benchmark trends are verified in both sequential and parallel computer environments.

Padovan, Joe↗
NASA NTRS1997

Development of Improved Surface Integral Methods for Jet Aeroacoustic Predictions

The accurate prediction of aerodynamically generated noise has become an important goal over the past decade. Aeroacoustics must now be an integral part of the aircraft design process. The direct calculation of aerodynamically generated noise with CFD-like algorithms is plausible. However, large computer time and memory requirements often make these predictions impractical. It is therefore necessary to separate the aeroacoustics problem into two parts, one in which aerodynamic sound sources are determined, and another in which the propagating sound is calculated. This idea is applied in acoustic analogy methods. However, in the acoustic analogy, the determination of far-field sound requires the solution of a volume integral. This volume integration again leads to impractical computer requirements. An alternative to the volume integrations can be found in the Kirchhoff method. In this method, Green's theorem for the linear wave equation is used to determine sound propagation based on quantities on a surface surrounding the source region. The change from volume to surface integrals represents a tremendous savings in the computer resources required for an accurate prediction. This work is concerned with the development of enhancements of the Kirchhoff method for use in a wide variety of aeroacoustics problems. This enhanced method, the modified Kirchhoff method, is shown to be a Green's function solution of Lighthill's equation. It is also shown rigorously to be identical to the methods of Ffowcs Williams and Hawkings. This allows for development of versatile computer codes which can easily alternate between the different Kirchhoff and Ffowcs Williams-Hawkings formulations, using the most appropriate method for the problem at hand. The modified Kirchhoff method is developed primarily for use in jet aeroacoustics predictions. Applications of the method are shown for two dimensional and three dimensional jet flows. Additionally, the enhancements are generalized so that they may be used in any aeroacoustics problem.

Pilon, Anthony R.↗
DOE OSTI2025

ChatPORT: Fine-Tuned LLM for Easy Code {PORT}ing

Fine-tuning existing LLMs for specialized tasks has become a very attractive alternative due to its low cost and quick development cycle. With many pre-trained LLMs available, it is an increasingly complex task to choose the correct model as the starting point or base model. In this work we discuss ChatPORT - a specialized fine-tuned LLM geared towards providing correctly translated codes from one programming model to another. We evaluate a number of base models and compare and contrast their features and characteristics that make them a viable starting point. In this paper, we focus on the OpenMP offload porting capabilities of ChatPORT. We build our training data using kernels from the Heterogeneous Computing Benchmarks (HeCBench) [12] and the OpenMP Validation and Verification suite [5] to fine-tune the base models. We then test the model using unseen kernels extracted from the HeCBench benchmark suite. Our results show that: (1) not all open LLMs geared towards HPC are aware of programming models like OpenMP, (2) although all base models benefit from fine-tuning they learn differently and produce different correctness rates, (3) depending on the memory size and compute resource available, different base models can be used for fine-tuning without significantly affecting the quality of transpiled code they generate, (4) fine-tuning improved the correctness rate of the LLM by an average of 43.2%, and (5) feedback-based training data further increased the correctness rate by an average of 6% over the LLMs tested.

Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗
DOE OSTI2026

Two-Level Sketching Alternating Anderson Acceleration for Complex Physics Applications

We present a novel two-level sketching extension of the Alternating Anderson–Picard (AAP) method for accelerating fixed-point iterations in challenging single- and multiphysics simulations governed by discretized PDEs. Our approach combines a static, physics-based projection that reduces the least-squares (LS) problem to the most informative field (e.g., via Schur-complement insight) with a dynamic, algebraic sketching stage driven by a backward stability analysis under Lipschitz continuity. We introduce inexpensive estimators for stability thresholds and cache-aware randomized selection strategies to balance computational cost against memory access overhead. The resulting algorithm solves reduced LS systems in place, minimizes memory footprints, and seamlessly alternates between low-cost Picard updates and Anderson mixing. Implemented in Julia, our two-level sketching AAP achieves up to 50% time-to-solution reductions compared to standard Anderson acceleration—without degrading convergence rates—on benchmark problems including Stokes, 𝑝-Laplacian, bidomain, and Navier–Stokes formulations at varying problem sizes. These results demonstrate the method’s robustness, scalability, and potential for integration into high-performance scientific computing frameworks. Our implementation is available open source in the AAP.jl library.

Barnafi, Nicolas [University of Chile, Santiago]↗
DOE OSTI2022

Evaluating HPC Kernels for Processing in Memory

Memory subsystems contribute significantly to the performance and energy efficiency of high-performance computing (HPC) applications. Traditional memory technologies with conventional organization (e.g., DRAM) are struggling to keep up with the increasing memory requirements of modern applications. Techniques such as multilayer cache hierarchy and out-of-order execution are still falling short of mitigating the penalty incurred by memory accesses. Processing-in-memory (PIM), which involves moving memory-intensive kernels to memory for execution instead of bringing the data to the processing unit, is emerging as a promising technique. PIM has recently received traction among computer architecture researchers, and the increasing research activity surrounding this technique indicates its potential to alleviate main memory performance bottlenecks. In this paper, we characterize and identify memory-intensive HPC kernels, perform a first-order evaluation of the PIM technique for selected HPC kernels, quantify performance deviation, and analyze the key factors that affect PIM efficiency.

Asifuzzaman, Kazi↗
DOE OSTI2021

Computational Complexity of Neuromorphic Algorithms

Neuromorphic computing has several characteristics that make it an extremely compelling computing paradigm for post Moore computation. Some of these characteristics include intrinsic parallelism, inherent scalability, collocated processing and memory, and event-driven computation. While these characteristics impart energy efficiency to neuromorphic systems, they do come with their own set of challenges. One of the biggest challenges in neuromorphic computing is to establish the theoretical underpinnings of the computational complexity of neuromorphic algorithms. In this paper, we take the first steps towards defining the space and time complexity of neuromorphic algorithms. Specifically, we describe a model of neuromorphic computation and state the assumptions that govern the computational complexity of neuromorphic algorithms. Next, we present a theoretical framework to define the computational complexity of a neuromorphic algorithm. We explicitly define what space and time complexities mean in the context of neuromorphic algorithms based on our model of neuromorphic computation. Finally, we leverage our approach and define the computational complexities of six neuromorphic algorithms: constant function, successor function, predecessor function, projection function, neuromorphic sorting algorithm and neighborhood subgraph extraction algorithm.

Date, Prasanna↗
DOE OSTI2025

Performance Impact and Trade-Offs for Tuning Key Architectural Parameters on CPU+GPU Systems

In this work, we performed an initial design space exploration of an accelerated processing unit (APU)—a hybrid CPU+GPU architecture that integrates both compute units (CUs) and memory into a unified system. This integration aims to reduce data movement, enhance memory locality, and improve energy efficiency by enabling the CPU and GPU to share memory directly. This effort focused on the interplay of key design components—cache line size, the number of CUs, and main memory technology—and the trade-offs of each configuration were analyzed. This paper highlights the various configurations’ impact on memory accesses, data reuse, and power utilization. The results provide valuable insights that can be leveraged to optimize APU architectures for high-performance and energy-efficient computing and thus create a balanced architecture. This optimization can be achieved by adopting dynamic cache management, runtime CU scaling, and advanced memory integration, highlighting the potential of APUs to address critical challenges in compute, data movement, and memory power consumption.

Asifuzzaman, Kazi [ORNL] (ORCID:0000000240044791)↗
DOE OSTI2021

InversionNet3D: Efficient and Scalable Learning for 3-D Full-Waveform Inversion

Seismic full-waveform inversion (FWI) techniques aim to find a high-resolution subsurface geophysical model provided with waveform data. Some recent effort in data-driven FWI has shown some encouraging results in obtaining 2-D velocity maps. However, due to high computational complexity and large memory consumption, the reconstruction of 3-D high-resolution velocity maps via deep networks is still a great challenge. Here, in this article, we present InversionNet3D (InvNet3D), an efficient and scalable encoder–decoder network for 3-D FWI. The proposed method employs group convolution in the encoder to establish an effective hierarchy for learning information from multiple sources while cutting down unnecessary parameters and operations at the same time. The introduction of invertible layers further reduces the memory consumption of intermediate features during training and, thus, enables the development of deeper networks with more layers and higher capacity as required by different application scenarios. Experiments on the 3-D Kimberlina dataset demonstrate that InvNet3D achieves state-of-the-art reconstruction performance with lower computational cost and lower memory footprint compared to the baseline.

58 GEOSCIENCES↗
DOE OSTI2024

A Diffusion‐Based Uncertainty Quantification Method to Advance E3SM Land Model Calibration

Abstract Calibrating land surface models and accurately quantifying their uncertainty are crucial for improving the reliability of simulations of complex environmental processes. This, in turn, advances our predictive understanding of ecosystems and supports climate‐resilient decision‐making. Traditional calibration methods, however, face challenges of high computational costs and difficulties in accurately quantifying parameter uncertainties. To address these issues, we develop a diffusion‐based uncertainty quantification (DBUQ) method. Unlike conventional generative diffusion methods, which are computationally expensive and memory‐intensive, DBUQ innovates by formulating a parameterized generative model and approximates this model through supervised learning, which enables quick generation of parameter posterior samples to quantify its uncertainty. DBUQ is effective, efficient, and general‐purpose, making it suitable for site‐specific ecosystem model calibration and broadly applicable for parameter uncertainty quantification across various earth system models. In this study, we applied DBUQ to calibrate the Energy Exascale Earth System Model land model at the Missouri Ozark AmeriFlux forest site. Results indicated that DBUQ produced accurate parameter posterior distributions similar to those from Markov Chain Monte Carlo sampling but with 30 times less computing time. This significant improvement in efficiency suggests that DBUQ can enable rapid, site‐level model calibration at a global scale, enhancing our predictive understanding of climate impacts on terrestrial ecosystems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Computing rank‐revealing factorizations of matrices stored out‐of‐core

This paper describes efficient algorithms for computing rank-revealing factorizations of matrices that are too large to fit in main memory (RAM), and must instead be stored on slow external memory devices such as disks (out-of-core or out-of-memory). Traditional algorithms for computing rank-revealing factorizations (such as the column pivoted QR factorization and the singular value decomposition) are very communication intensive as they require many vector-vector and matrix-vector operations, which become prohibitively expensive when data is not in RAM. Randomization allows to reformulate new methods so that large contiguous blocks of the matrix are processed in bulk. The paper describes two distinct methods. The first is a blocked version of column pivoted Householder QR, organized as a “left-looking” method to minimize the number of the expensive write operations. The second method results employs a UTV factorization. It is organized as an algorithm-by-blocks to overlap computations and I/O operations. As it incorporates power iterations, it is much better at revealing the numerical rank. Numerical experiments on several computers demonstrate that the new algorithms are almost as fast when processing data stored on slow memory devices as traditional algorithms are for data stored in RAM.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

A Fast Algorithm for Scanning Transmission Electron Microscopy Imaging and 4D-STEM Diffraction Simulations

Scanning transmission electron microscopy (STEM) is an extremely versatile method for studying materials on the atomic scale. Many STEM experiments are supported or validated with electron scattering simulations. However, using the conventional multislice algorithm to perform these simulations can require extremely large calculation times, particularly for experiments with millions of probe positions as each probe position must be simulated independently. Recently, the plane-wave reciprocal-space interpolated scattering matrix (PRISM) algorithm was developed to reduce calculation times for large STEM simulations. Here, we introduce a new method for STEM simulation: partitioning of the STEM probe into “beamlets,” given by a natural neighbor interpolation of the parent beams. This idea is compatible with PRISM simulations and can lead to even larger improvements in simulation time, as well requiring significantly less computer random access memory (RAM). We have performed various simulations to demonstrate the advantages and disadvantages of partitioned PRISM STEM simulations. We find that this new algorithm is particularly useful for 4D-STEM simulations of large fields of view. We also provide a reference implementation of the multislice, PRISM, and partitioned PRISM algorithms.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1988

Navier-Stokes calculations for DFVLR F5-wing in wind tunnel using Runge-Kutta time-stepping scheme

A three-dimensional Navier-Stokes code using an explicit multistage Runge-Kutta type of time-stepping scheme is used for solving the transonic flow past a finite wing mounted inside a wind tunnel. Flow past the same wing in free air was also computed to assess the effect of wind-tunnel walls on such flows. Numerical efficiency is enhanced through vectorization of the computer code. A Cyber 205 computer with 32 million words of internal memory was used for these computations.

Vatsa, V. N.↗
NASA NTRS2016

Processing Device for High-Speed Execution of an Xrisc Computer Program

A processing device for high-speed execution of a computer program is provided. A memory module may store one or more computer programs. A sequencer may select one of the computer programs and controls execution of the selected program. A register module may store intermediate values associated with a current calculation set, a set of output values associated with a previous calculation set, and a set of input values associated with a subsequent calculation set. An external interface may receive the set of input values from a computing device and provides the set of output values to the computing device. A computation interface may provide a set of operands for computation during processing of the current calculation set. The set of input values are loaded into the register and the set of output values are unloaded from the register in parallel with processing of the current calculation set.

Ng, Tak-Kwong↗
DOE OSTI2021

Flexible optimized data handling in systems with multiple memories

Methods and systems for optimizing an application for a computing system having multiple distinct memory locations that are interconnected by one or more communication channels include determining one or more data handling properties for a data region in an application. One or more data handling policies for the data region are determined based on the one or more data handling properties. Data setup costs are determined for a scope in the application that uses the data region in different memory locations based on the one or more data handling properties. The application is optimized in accordance with the one or more data handling policies and the data setup costs for the different memory locations.

Chen, Tong↗