Search NASA⌕ Search

SEARCH · Search NASA

Results for “memory efficiency”

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 1,729 records · Page 96

Scaling soft matter physics to thousands of graphics processing units in parallel

We describe a multi-graphics processing unit (GPU) implementation of the Ludwig application, which specialises in simulating a variety of complex fluids via lattice Boltzmann fluid dynamics coupled to additional physics describing complex fluid constituents. We describe our methodology in augmenting the original central processing unit (CPU) version with GPU functionality in a maintainable fashion. We present several optimisations that maximise performance on the GPU architecture through tuning for the GPU memory hierarchy. We describe how we implement particles within the fluid in such a way to avoid a major diversion of the CPU and GPU codebases, whilst minimising data transfer at each time step. We detail our halo-exchange communication phase for the code, which exploits overlapping to allow efficient parallel scaling to many GPUs. We present results showing that the application demonstrates excellent scaling to at least 8192 GPUs in parallel, the largest system tested at the time of writing. The GPU version (on NVIDIA K20X GPUs) is around 3.5–5 times faster that the CPU version (on fully utilised AMD Opteron 6274 16-core CPUs), comparing equal numbers of CPUs and GPUs.

Computer Science↗

Application of an efficient hybrid scheme for aeroelastic analysis of advanced propellers

An efficient 3-D hybrid scheme is applied for solving Euler equations to analyze advanced propellers. The scheme treats the spanwise direction semi-explicitly and the other two directions implicitly, without affecting the accuracy, as compared to a fully implicit scheme. This leads to a reduction in computer time and memory requirement. The calculated power coefficients for two advanced propellers, SR3 and SR7L, and various advanced ratios showed good correlation with experiment. Spanwise distribution of elemental power coefficient and steady pressure coefficient differences also showed good agreement with experiment. A study of the effect of structural flexibility on the performance of the advanced propellers showed that structural deformation due to centrifugal and aero loading should be included for better correlation.

Srivastava, R.↗

Application of an efficient hybrid scheme for aeroelastic analysis of advanced propellers

An efficient 3-D hybrid scheme is applied for solving Euler equations to analyze advanced propellers. The scheme treats the spanwise direction semi-explicitly and the other two directions implicitly, without affecting the accuracy, as compared to a fully implicit scheme. This leads to a reduction in computer time and memory requirement. The calculated power coefficients for two advanced propellers, SR3 and SR7L, and various advanced ratios showed good correlation with experiment. Spanwise distribution of elemental power coefficient and steady pressure coefficient differences also showed good agreement with experiment. A study of the effect of structural flexibility on the performance of the advanced propellers showed that structural deformation due to centrifugal and aero loading should be included for better correlation.

Srivastava, R.↗

CFD code evaluation for internal flow modeling

Research on the computational fluid dynamics (CFD) code evaluation with emphasis on supercomputing in reacting flows is discussed. Advantages of unstructured grids, multigrids, adaptive methods, improved flow solvers, vector processing, parallel processing, and reduction of memory requirements are discussed. As examples, researchers include applications of supercomputing to reacting flow Navier-Stokes equations including shock waves and turbulence and combustion instability problems associated with solid and liquid propellants. Evaluation of codes developed by other organizations are not included. Instead, the basic criteria for accuracy and efficiency have been established, and some applications on rocket combustion have been made. Research toward an ultimate goal, the most accurate and efficient CFD code, is in progress and will continue for years to come.

Chung, T. J.↗

Efficient Algorithm for Rectangular Spiral Search

An algorithm generates grid coordinates for a computationally efficient spiral search pattern covering an uncertain rectangular area spanned by a coordinate grid. The algorithm does not require that the grid be fixed; the algorithm can search indefinitely, expanding the grid and spiral, as needed, until the target of the search is found. The algorithm also does not require memory of coordinates of previous points on the spiral to generate the current point on the spiral.

Brugarolas, Paul↗

The Tiny Median Filter: A Small Size, Flexible Arbitrary Percentile Finder Scheme Suitable for FPGA Implementation

This document reports the design, implementation and testing of a small silicon resource usage, very flexible arbitrary percentile finding scheme called the Tiny Median Filter. It can be used not only as a median filter in image processing with square filtering windows, but also for applications of any percentile filter or maximum or minimum finder with any size of data set as long as the number of bits of the data is finite. It opens possibilities for image processing tasks with non-square or irregular filter windows. In this scheme, data swapping or data bit manipulating are avoided and high functional efficiency of the logic components is applied to save silicon resources. Some logic functions are absorbed into other functions to further reduce the complexity. The combinational logic paths are designed to be sufficiently short so that the firmware can be compiled to the maximum operating frequency allowed by the block memories of the FPGA devices. The Tiny Median Filter receives, processes and output data in non-stop manner with no irregular timing which helps to simplify design of surrounding stages.

Wu, Jinyuan [Fermilab] (ORCID:0000000344329521)↗

Efficient Management of Complex Striped Files in Active Storage

Active Storage provides an opportunity for reducing the band- width requirements between the storage and compute elements of cur- rent supercomputing systems, and leveraging the processing power of the storage nodes used by some modern file systems. To achieve both objec- tives, Active Storage allows certain processing tasks to be performed directly on the storage nodes, near the data they manage. However, Active Storage must also support key requirements of scientific applications. In particular, Active Storage must be able to support striped files and files with complex formats (e.g., netCDF). In this paper, we describe how these important requirements can be addressed. The experimental results on a Lustre file system not only show that our proposal can re- duce the network traffic to near zero and scale the performance with the number of storage nodes, but also that it provides an efficient treatment of striped files and can manage files with complex data structures.

97 MATHEMATICS AND COMPUTING↗

Detection of correlated fragments in a sequence of images by superimposed Fourier holograms

The problem of detecting correlated fragments in a sequence of images recorded by the superimposing holograms within the Fourier holography scheme with angular multiplication of a spatially modulated reference beam is considered. The approach to the solution of this problem is based on the properties of the variance of the image sum. It is shown that this problem can be solved by providing a constant distance between the signal and reference images when recording superimposed holograms and a partial mutual correlatedness of reference images. The detection efficiency is analysed from the point of view of estimated image data capacity, the degree of mutual correlation of reference images, and the hologram recording conditions. The results of a numerical experiment under the most complicated conditions (representation of images by realisations of homogeneous random fields) confirm the theoretical conclusions. (holographic memory)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Semantic Property Graph for Scalable Knowledge Graph Analytics

Graphs are a natural and fundamental representation to describe entities, relationships, activities, and evolution of complex systems. Many domains such as communication, citation, procurement, biology, social media, and transportation can be modeled as a set of entities and their relationships. Resource Description Framework (RDF) and Labeled Property Graph (LPG) are two of the most used data models to encode information in a graph. Both models are similar in terms of using basic graph elements such as nodes and edges but differ in terms of the modeling approach, expressibility, serialization, and target applications. RDF is a flexible data exchange model for expressing information about entities but it tends to a have high memory footprint and inefficient storage, which does not make it a natural choice to perform scalable graph analytics. In contrast, LPG has gained traction as a reliable model to perform scalable graph analytic tasks such as sub-graph matching, network alignment, and real-time knowledge graph query. It provides efficient storage, fast traversal, and flexibility to model various real-world domains. At the same time, the LPG lacks the support of a formal knowledge representation such as an ontology to provide automated knowledge inference. We propose Semantic Property Graph (SPG) as a logical projection of reified RDF into the LPG model. SPG continues to use RDF ontology to define the type hierarchy of the projected graph and validate it against a given ontology. We present a framework to convert reified RDF graphs into SPG using two different computing environments. We also present cloud-based graph migration capabilities using Amazon Web Services.

Purohit, Sumit↗

Parallel Nonnegative CP Decomposition of Dense Tensors

The CP tensor decomposition is a low-rank approximation of a tensor. We present a distributed-memory parallel algorithm and implementation of an alternating optimization method for computing a CP decomposition of dense tensors that can enforce nonnegativity of the computed low-rank factors. The principal task is to parallelize the Matricized-Tensor Times Khatri-Rao Product (MTTKRP) bottleneck subcomputation. The algorithm is computation efficient, using dimension trees to avoid redundant computation across MTTKRPs within the alternating method. Our approach is also communication efficient, using a data distribution and parallel algorithm across a multidimensional processor grid that can be tuned to minimize communication. We benchmark our software on synthetic as well as hyperspectral image and neuroscience dynamic functional connectivity data, demonstrating that our algorithm scales well to 100s of nodes (up to 4096 cores) and is faster and more general than the currently available parallel software.

Ballard, Grey↗

A High-Throughput Solver for Marginalized Graph Kernels on GPU

Here, we present the design and optimization of a solver for efficient and high-throughput computation of the marginalized graph kernel on General Purpose GPUs. The graph kernel is computed using the conjugate gradient method to solve a generalized Laplacian of the tensor product between a pair of graphs. To cope with the large gap between the instruction throughput and the memory bandwidth of the GPUs, our solver forms the graph tensor product on-the-fly without storing it in memory. This is achieved by using threads in a warp cooperatively to stream the adjacency and edge label matrices of individual graphs by small square matrix blocks called tiles, which are then staged in registers and the shared memory for later reuse. Warps across a thread block can further share tiles via the shared memory to increase data reuse. We exploit the sparsity of the graphs hierarchically by storing only non-empty tiles using a coordinate format and nonzero elements within each tile using bitmaps. We propose a new partition-based reordering algorithm for aggregating nonzero elements of the graphs into fewer but denser tiles to further exploit sparsity. We carry out extensive theoretical analyses on the graph tensor product primitives for tiles of various density and evaluate their performance on synthetic and real-world datasets. Our solver delivers three to four orders of magnitude speedup over existing CPU-based solvers such as GraKeL and GraphKernels. The capability of the solver enables kernel-based learning tasks at unprecedented scales.

97 MATHEMATICS AND COMPUTING↗

Position Papers for the ASCR Workshop on the Management and Storage of Scientific Data

The purpose of this workshop is to identify priority research directions in the area of data management for high-performance and scientific computing above and beyond HPC’s traditional "the parallel file system is the data-management system" model. Supporting the breadth of the DOE mission, including the explosion of AI uses and the growing needs of experimental and observational science, motivates revisiting our assumptions about data management. There are many facets of this topic to explore including: (1) Interfaces for accessing data that resides on traditional persistent storage as well as memory devices; (2) Storage-system architecture design that supports scientific workflows on varied hierarchical storage and networking devices; (3) Devising metadata management infrastructure to support FAIR principles (Findability, Accessibility, Interoperability, and Reusability); (4) Capturing provenance information about scientific data; (5) Utilizing AI to learn I/O patterns of emerging workloads for efficient data management; (6) Providing data management support for AI and complex workflows; and (7) Understanding the overlap between traditional storage systems and I/O (SSIO) efforts and data management. While the program committee has identified these topics as important areas for discussion, we welcome position papers from the community that propose additional topics of interest for discussion at the workshop. The workshop agenda will include breakout sessions for discussing these and selected topic areas to inform priority research directions for data management for high-performance and scientific computing.

97 MATHEMATICS AND COMPUTING↗

Report for the ASCR Workshop on the Management and Storage of Scientific Data

The purpose of this workshop is to identify priority research directions in the area of data management for high-performance and scientific computing above and beyond HPC’s traditional "the parallel file system is the data-management system" model. Supporting the breadth of the DOE mission, including the explosion of AI uses and the growing needs of experimental and observational science, motivates revisiting our assumptions about data management. There are many facets of this topic to explore including: (1) Interfaces for accessing data that resides on traditional persistent storage as well as memory devices; (2) Storage-system architecture design that supports scientific workflows on varied hierarchical storage and networking devices; (3) Devising metadata management infrastructure to support FAIR principles (Findability, Accessibility, Interoperability, and Reusability); (4) Capturing provenance information about scientific data; (5) Utilizing AI to learn I/O patterns of emerging workloads for efficient data management; (6) Providing data management support for AI and complex workflows; and (7) Understanding the overlap between traditional storage systems and I/O (SSIO) efforts and data management. While the program committee has identified these topics as important areas for discussion, we welcome position papers from the community that propose additional topics of interest for discussion at the workshop. The workshop agenda will include breakout sessions for discussing these and selected topic areas to inform priority research directions for data management for high-performance and scientific computing.

97 MATHEMATICS AND COMPUTING↗

Towards reverse mode automatic differentiation of Kokkos-based codes

Derivative computation is a key component of optimization, sensitivity analysis, uncertainty quantification, and the solving of nonlinear problems. Automatic differentiation (AD) is a powerful technique for evaluating such derivatives, and in recent years, has been integrated into programming environments such as Jax, PyTorch, and TensorFlow to support derivative computations needed for training of machine learning models, facilitating wide-spread use of these technologies. The C++ language has become the de facto standard for scientific computing due to numerous factors, yet language complexity has made the wide-spread adoption of AD technologies for C++ difficult, hampering the incorporation of powerful differentiable programming approaches into C++ scientific simulations. This is exacerbated by the increasing emergence of architectures, such as GPUs, with limited memory capabilities and requiring massive thread-level concurrency. C++ AD tools must effectively use these environments to bring novel scientific simulations to next-generation DOE experimental and observational facilities. In this project, we investigated source transformation-based automatic differentiation using LLVM compiler infrastructure to automatically generate portable and efficient gradient computations of Kokkos-based code. We have demonstrated that our proposed strategy is feasible by investigating the usage of a prototype LLVM-based source transformation tool to generate gradients of simple functions made of sequences of simple Kokkos parallel regions. Speedups of up to 500x compared to Sacado were observed on NVIDIA V100 GPU.

97 MATHEMATICS AND COMPUTING↗

Advanced Facility Design and AI/ML Enabled Safeguards to Establish Secure, Economical Recycling of Fast Reactor Fuels (Final Scientific/Technical Report)

The project, "Advanced Facility Design and AI/ML Enabled Safeguards to Establish Secure, Economical Recycling of Fast Reactor Fuels," represents a significant advancement in nuclear fuel recycling technology. It integrates cutting-edge multimodal sensor fusion, machine learning (ML), and digital twin (DT) technologies to address challenges in material safeguarding, process optimization, and regulatory compliance for pyroprocessing facilities. This research has significantly enhanced the understanding of pyrochemical fuel recycling processes by developing innovative tools and methodologies. The Multimodal Safeguards Monitoring Unit (MSMU) combines electroanalytical techniques, Raman spectroscopy, and differential thermal analysis (DTA) to enable high-fidelity, near-real-time material accountancy measurements. Machine learning techniques, such as Long Short-Term Memory (LSTM) autoencoders, are utilized to detect anomalies in material balances and sensor data, improving the reliability of safeguards monitoring. Additionally, digital twin technology has been established to provide real-time system-level monitoring and diagnostics, integrating physics-based models with sensor data to optimize process safety and efficiency.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning

Continuum reverberation mapping (CRM) of active galactic nuclei (AGN) monitors multiwavelength variability signatures to constrain accretion disk structure and supermassive black hole (SMBH) properties. The upcoming Vera Rubin Observatory’s Legacy Survey of Space and Time will survey tens of millions of AGN over the next decade, with thousands of AGN monitored with almost daily cadence in the deep drilling fields. However, existing CRM methodologies often require long computation time and are not designed to handle such large amounts of data. In this paper, we present a fast and flexible inference framework for CRM using simulation-based inference (SBI) with deep learning to estimate SMBH properties from AGN light curves. We use a long short-term memory summary network to reduce the high dimensionality of the light curve data and then use a neural density estimator to estimate the posterior of SMBH parameters. Using simulated light curves, we find SBI can produce more accurate SMBH parameter estimation with 10 3 –10 5 times speed up in inference efficiency compared to traditional methods. The SBI framework is particularly suitable for wide-field CRM surveys as the light curves will have identical observing patterns, which can be incorporated into the SBI simulation. We explore the performance of our SBI model on light curves with irregular-sampled, realistic observing cadence and alternative variability characteristics to demonstrate the flexibility and limitation of the SBI framework.

79 ASTRONOMY AND ASTROPHYSICS↗

Transonic Navier-Stokes wing solutions using a zonal approach. Part 2: High angle-of-attack simulation

A computer code is under development whereby the thin-layer Reynolds-averaged Navier-Stokes equations are to be applied to realistic fighter-aircraft configurations. This transonic Navier-Stokes code (TNS) utilizes a zonal approach in order to treat complex geometries and satisfy in-core computer memory constraints. The zonal approach has been applied to isolated wing geometries in order to facilitate code development. Part 1 of this paper addresses the TNS finite-difference algorithm, zonal methodology, and code validation with experimental data. Part 2 of this paper addresses some numerical issues such as code robustness, efficiency, and accuracy at high angles of attack. Special free-stream-preserving metrics proved an effective way to treat H-mesh singularities over a large range of severe flow conditions, including strong leading-edge flow gradients, massive shock-induced separation, and stall. Furthermore, lift and drag coefficients have been computed for a wing up through CLmax. Numerical oil flow patterns and particle trajectories are presented both for subcritical and transonic flow. These flow simulations are rich with complex separated flow physics and demonstrate the efficiency and robustness of the zonal approach.

Chaderjian, N. M.↗

A parallel householder tridiagonalization stratagem using scattered row decomposition

Householder's method for tridiagonalizing a real symmetric matrix, a major step in evaluating eigenvalues of the matrix, is modified into a parallel algorithm for a concurrent machine of message passing type. Each processor of the concurrent machine has its own CPU, communications control and local memory. Messages are passed through connections between processors. Although the basic algorithm is inherently serial, the computations can be spread over all processors by scattering different rows of the matrix into processors, hence the term 'Scattered Row Decomposition'. The steps in the serial and the parallel algorithms are identified. Expressions for efficiency and speedup are given in terms of problem and machine parameters. For a concurrent machine of ring type interconnection, a selected representative problem of large order exhibits efficiency approaching 66 per cent.

Chang, H. Y.↗