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 397 records · Page 22

A memory-distributed quasi-Newton solver for nonlinear programming problems with a small number of general constraints

We approach the problem of parallelizing state-of-the-art nonlinear programming optimization algorithms.Specifically, we focus on parallelizing quasi-Newton interior-point methods that use limited-memory secant Hessian approximations. Such interior-point methods are known to have better convergence properties and to be more effective on large-scale problems than gradient-based and derivative-free optimization algorithms. We target nonlinear and potentially nonconvex optimization problems with an arbitrary number of bound constraints and a small number of general equality and inequality constraints on the optimization variables. These problems occur for example in the form of optimal control, optimal design, and inverse problems governed by ordinary or partial differential equations, whenever they are expressed in a “reduced-space” optimization approach. We introduce and analyze the time and space complexity of a decomposition method for solving the quasi-Newton linear systems that leverages the fact that the quasi-Newton Hessian matrix has a small number of dense blocks that border a low-rank update of a diagonal matrix. This enables an efficient parallelization on memory-distributed computers of the iterations of the optimization algorithm, a state-of-the-art filter line-search interior-point algorithm by Wächter et. al. We illustrate the efficiency of the proposed method by solving structural topology optimization problems on up to 4608 cores on a parallel machine.

97 MATHEMATICS AND COMPUTING↗

Numerical homogenization of concrete microstructures without explicit meshes

Life management of electric hydro or nuclear power plants requires to estimate long-term concrete properties on facilities, for obvious safety and serviceability reasons. Decades-old structures are foreseen to be operational for several more decades. As a large number of different concrete formulations are found in EDF facilities, empirical models based on many experiments cannot be an option for a large fleet of power plant buildings. To build predictive models, homogenization techniques offer an appealing alternative. To properly upscale creep, especially at long term, a rather precise description of the microstructure is required. However, the complexity of the morphology of concrete poses several challenges. In particular, concrete is formulated to maximize the packing density of the granular skeleton, leading to aggregates spanning several length scales with small inter particle spacings. Thus, explicit meshing of realistic concrete microstructures is either out of reach of current meshing algorithms or would produce a number of degrees of freedom far higher than the current generic FEM codes capabilities. This paper proposes a method to deal with complex matrix-inclusions microstructures such as the ones encountered at the mortar or concrete scales, without explicitly meshing them. The microstructure is superimposed to an independent mesh, which is a regular Cartesian grid. This inevitably yields so called 'gray elements', spanning across multiple phases. As the reliability of the estimate of the effective properties highly depends on the behavior affected to these gray elements, special attention is paid to them. As far as the question of the solvers is concerned, generic FEM codes are found to lack efficiency: they cannot reach high enough levels of discretization with classical free meshes, and they do not take advantage of the regular structure of the mesh. Thus, a specific finite differences/finite volumes solver has been developed. At first, generic off-the-shelf linear system solvers were used. To further improve the efficiency in terms of memory requirements, specific variants of the preconditioned conjugate gradient were implemented. This allowed to homogenize the conductivity of a concrete-like microstructure using more than 10{sup 9} degrees of freedom on a rather common hardware for 2010 (a PC embedding 48 GB of RAM). Taking benefit of the properties of the regular Cartesian grid we have also investigated a multi-level method to improve the CPU efficiency of the code.

36 MATERIALS SCIENCE↗

MIQS v0.6

In this research, we propose a novel Metadata Indexing and Querying for Self-describing formats (MIQS), which removes the external DBMS and utilizes in-memory index to achieve efficient metadata searching. MIQS follows the self-contained data management paradigm and provides portable and schema-free metadata indexing and querying functionalities for self-describing file formats. We have evaluated MIQS with the state-of-the-art MongoDB-based metadata indexing solution. MIQS achieved up to 99% time reduction in index construction and up to 172,000X search performance improvement with up to 75% reduction in memory footprint.

Byna, Suren↗

MIQS v0.6

In this research, we propose a novel Metadata Indexing and Querying for Self-describing formats (MIQS), which removes the external DBMS and utilizes in-memory index to achieve efficient metadata searching. MIQS follows the self-contained data management paradigm and provides portable and schema-free metadata indexing and querying functionalities for self-describing file formats. We have evaluated MIQS with the state-of-the-art MongoDB-based metadata indexing solution. MIQS achieved up to 99% time reduction in index construction and up to 172,000X search performance improvement with up to 75% reduction in memory footprint.

Byna, Suren↗

Performance tuning of CEED software and 1st and 2nd wave apps

The goal of this milestone was the performance tuning of the CEED software, as well as the use and tuning of CEED to accelerate the first and second wave of targeted ECP applications. In this milestone, the CEED team developed optimization techniques and tuned for performance the CEED software to accelerate the first and second wave target ECP applications. Specifically, the focus was on the following: (1) Efficient use of the memory sub-system for managing data motion and interactions among different physics packages and libraries; this included integration of the new developments in a libCEED 0.5 software release; (2) Enhancing the CEED libraries with GPU and AMD GPU support in close interaction with vendors; (3) Optimal data locality and motion, and enhanced scalability and parallelism; this included vendors interactions for improvements in data motion and making strong scaling easier and more efficient; and (4) Continue boosting performance for the first-wave and second-wave of ECP target applications, including ExaSMR, ExaWind, Urban, MARBL, E3SM, and ExaAM. A main part of this milestone was the performance tuning of the CEED first-wave and second-wave ECP applications. This included the ExaSMR application – Coupled Monte Carlo Neutronics and Fluid Flow Simulation of Small Modular Reactors (ORNL), the MARBL application – Next-Gen Multi-physics Simulation Code (LLNL), and the ExaAM ExaConstit – a miniapp for the Transforming Additive Manufacturing through Exascale Simulation applications project (ExaAM), as well as ExaWind, Urban, and E3SM. The artifacts delivered include performance improvements in CEED’s 1st and 2nd wave of applications, and tuned CEED software for various architectures through a number of backends, freely available in the CEED’s repository on GitHub. See the CEED website, http://ceed.exascaleproject.org and the CEED GitHub organization, http://github.com/ceed for more details. In addition to details and results from the above R&D efforts, in this document we are also reporting on other project-wide activities performed in Q4 of FY19 including: CEED’s third annual meeting, MFEM GPU kernels scaling improvements, libCEED 0.5 and NekRS releases, an overview paper covering latest results on a set of bake-off high-order finite element problems (BPs), and other outreach efforts.

97 MATHEMATICS AND COMPUTING↗

High performance graphics processor based computed tomography reconstruction algorithms for nuclear and other large scale applications.

The goal of this work is to develop a fast computed tomography (CT) reconstruction algorithm based on graphics processing units (GPU) that achieves significant improvement over traditional central processing unit (CPU) based implementations. The main challenge in developing a CT algorithm that is capable of handling very large datasets is parallelizing the algorithm in such a way that data transfer does not hinder performance of the reconstruction algorithm. General Purpose Graphics Processing (GPGPU) is a new technology that the Science and Technology (S&T) community is starting to adopt in many fields where CPU-based computing is the norm. GPGPU programming requires a new approach to algorithm development that utilizes massively multi-threaded environments. Multi-threaded algorithms in general are difficult to optimize since performance bottlenecks occur that are non-existent in single-threaded algorithms such as memory latencies. If an efficient GPU-based CT reconstruction algorithm can be developed; computational times could be improved by a factor of 20. Additionally, cost benefits will be realized as commodity graphics hardware could potentially replace expensive supercomputers and high-end workstations. This project will take advantage of the CUDA programming environment and attempt to parallelize the task in such a way that multiple slices of the reconstruction volume are computed simultaneously. This work will also take advantage of the GPU memory by utilizing asynchronous memory transfers, GPU texture memory, and (when possible) pinned host memory so that the memory transfer bottleneck inherent to GPGPU is amortized. Additionally, this work will take advantage of GPU-specific hardware (i.e. fast texture memory, pixel-pipelines, hardware interpolators, and varying memory hierarchy) that will allow for additional performance improvements.

97 MATHEMATICS AND COMPUTING↗

Implementing Directive-Based Deferred Execution for Effective Network Aggregation

Remote direct memory access technology provides an efficient mechanism for one-sided communication that can be leveraged to implement a distributed shared memory programming model. However, when applications generate large numbers of small, irregular messages, network congestion often arises. Existing solutions address this small message problem by facilitating message aggregation but typically require disruptive code transformations that detract from the algorithmic intent of applications, or can be limited by dependent operations on aggregated data between synchronisation points. A solution is to use a directive-assisted approach that enables compilers to transform code dependent on aggregated communication for deferred execution. This paper presents an algorithm that a compiler can use to implement and optimise deferred execution for code dependent on aggregated data, based on an "aggregation context" extension for the OpenSHMEM partitioned global address space library. This new capability addresses a key challenge of message aggregation, allowing its full potential to reduce network congestion and enhance programmability to be realised.

Welch, Aaron [ORNL]↗

Out-of-Core Streamline Visualization on Large Unstructured Meshes

It's advantageous for computational scientists to have the capability to perform interactive visualization on their desktop workstations. For data on large unstructured meshes, this capability is not generally available. In particular, particle tracing on unstructured grids can result in a high percentage of non-contiguous memory accesses and therefore may perform very poorly with virtual memory paging schemes. The alternative of visualizing a lower resolution of the data degrades the original high-resolution calculations. This paper presents an out-of-core approach for interactive streamline construction on large unstructured tetrahedral meshes containing millions of elements. The out-of-core algorithm uses an octree to partition and restructure the raw data into subsets stored into disk files for fast data retrieval. A memory management policy tailored to the streamline calculations is used such that during the streamline construction only a very small amount of data are brought into the main memory on demand. By carefully scheduling computation and data fetching, the overhead of reading data from the disk is significantly reduced and good memory performance results. This out-of-core algorithm makes possible interactive streamline visualization of large unstructured-grid data sets on a single mid-range workstation with relatively low main-memory capacity: 5-20 megabytes. Our test results also show that this approach is much more efficient than relying on virtual memory and operating system's paging algorithms.

Ueng, Shyh-Kuang↗

Options for Radiation Tolerant High-Performance Memory

Memory technologies were reviewed for radiation effects performance in order to determine the most cost-efficient target for a possible memory investment targeted at creating a memory component of general applicability for space use. TID and SEL trends that had indicated improvement in intrinsic performance based on scaling cannot be trusted. SEE hardening of memory arrays is prohibitive in terms of cell-level power and area requirements. Radiation-hardened cells and custom controllers are recommended for future memory developments.

Some, Raphael↗

Scalable Triadic Analysis of Large-Scale Graphs: Multi-Core vs. Multi-Processor vs. Multi-Threaded Shared Memory Architectures

Triadic analysis encompasses a useful set of graph mining methods that is centered on the concept of a triad, which is a subgraph of three nodes and the configuration of directed edges across the nodes. Such methods are often applied in the social sciences as well as many other diverse fields. Triadic methods commonly operate on a triad census that counts the number of triads of every possible edge configuration in a graph. Like other graph algorithms, triadic census algorithms do not scale well when graphs reach tens of millions to billions of nodes. To enable the triadic analysis of large-scale graphs, we developed and optimized a triad census algorithm to efficiently execute on shared memory architectures. We will retrace the development and evolution of a parallel triad census algorithm. Over the course of several versions, we continually adapted the code’s data structures and program logic to expose more opportunities to exploit parallelism on shared memory that would translate into improved computational performance. We will recall the critical steps and modifications that occurred during code development and optimization. Furthermore, we will compare the performances of triad census algorithm versions on three specific systems: Cray XMT, HP Superdome, and AMD multi-core NUMA machine. These three systems have shared memory architectures but with markedly different hardware capabilities to manage parallelism.

Triadic analysis, triads, triad census, large-scal↗

Suppressing heating rate-dependent martensitic stabilization in ductile Cu-Al-Mn shape memory alloys by Ni addition: An experimental and first-principles study

Highlights: • Additional nearest neighbor bond between Ni and Al atoms was produced theoretically in the Cu-Al-Mn-Ni (Ni≤2 at.%) alloys. • Shape memory effect of Cu-Al-Mn alloys heated at 20 K/min was improved from 85% to 92% after the addition of 2 at.% Ni. • Addition of 2 at.% Ni can suppress heating rate-dependent martensitic stabilization in Cu-Al-Mn alloys heated at 0.01 K/min. - Abstract: The present paper aims to suppress the heating rate-dependent martensitic stabilization of ductile Cu-Al-Mn shape memory alloys through restricting the mobility and thus the behavior of vacancies. A combined study based on first-principles calculation and experimental results were presented to unveil the effect of Ni addition into ternary Cu-Al-Mn alloys on the bonding force between atoms. The results showed that additional nearest neighbor bond between Ni and Al atoms in quaternary Cu-Al-Mn-Ni alloys can be produced. The addition of Ni (≤2 at.%) into ternary Cu-Al-Mn alloys can not only efficiently increase the shape memory effect, but also suppress the occurrence of heating rate-dependent martensitic stabilization. The addition of 2 at.% Ni improved the shape memory effect of ternary Cu-Al-Mn alloys from 85% to 92% when heated at 20 k/min. The shape memory effect of ternary Cu-Al-Mn alloys dropped to 10% as the heating rate decreased to 1 K/min, but it remain at 92% even when the heating rate was sufficiently lowered to 0.01 K/min after the addition of 2 at.% Ni.

36 MATERIALS SCIENCE↗

Lifeline-based Global Load Balancing

On shared-memory systems, Cilk-style work-stealing has been used to effectively parallelize irregular task-graph based applications such as Unbalanced Tree Search (UTS). There are two main difficulties in extending this approach to distributed memory. In the shared memory approach, thieves (nodes without work) constantly attempt to asynchronously steal work from randomly chosen victims until they find work. In distributed memory, thieves cannot autonomously steal work from a victim without disrupting its execution. When work is sparse, this results in performance degradation. In essence, a direct extension of traditional work-stealing to distributed memory violates the work-first principle underlying work-stealing. Further, thieves spend useless CPU cycles attacking victims that have no work, resulting in system inefficiencies in multi-programmed contexts. Second, it is non-trivial to detect active distributed termination (detect that programs at all nodes are looking for work, hence there is no work). This problem is well-studied and requires careful design for good performance. Unfortunately, in most existing languages/frameworks, application developers are forced to implement their own distributed termination detection. In this paper, we develop a simple set of ideas that allow work-stealing to be efficiently extended to distributed memory. First, we introduce lifeline graphs: low-degree, low diameter, fully connected directed graphs. Such graphs can be constructed from k-dimensional hypercubes. When a node is unable to find work after w unsuccessful steals, it quiesces after informing the outgoing edges in its lifeline graph. Quiescent nodes do not disturb other nodes. A quiesced node is reactivated when work arrives from a lifeline and itself shares this work with those of its incoming lifelines that are activated. Termination occurs precisely when computation at all nodes has quiesced. In a language such as X10, such passive distributed termination can be detected automatically using the finish construct -- no application code is necessary.

99 GENERAL AND MISCELLANEOUS↗

Adaptive and Efficient Computing for Subsurface Simulation within ParFlow

This project is concerned with the PF.WRF model as a means to enable more accurate predictions of wind fluctuations and subsurface storage. As developed at LLNL, PF.WRF couples a groundwater (subsurface) and surface water flow model (ParFlow) to a mesoscale atmospheric model (WRF, Weather Research and Forecasting Model). It was developed as a unique tool to address coupled water balance and wind energy questions that occur across traditionally separated research regimes of the atmosphere, land surface, and subsurface. PF.WRF is capable of simulating fluid, mass, and energy transport processes in groundwater, vadose zone, root zone, and land surface systems, including overland flow, and allows for the WRF model to both directly drive and respond to surface and subsurface hydrologic processes and conditions. The current PF.WRF model is constrained to have uniform spatial gridding below the land surface and matching areal grids with the WRF model at the land surface. There are often cases where it is advantageous for land surface, overland flow and subsurface models to have finer gridding than their atmospheric counterparts. Finer vertical discretization is also advantageous near the land surface (to properly capture feedbacks) yet many applications have a large vertical extent. However, the surface flow is strongly dependent on topography leading to a need for greater lateral resolution in some regions and the subsurface flow is tightly coupled to the atmospheric model near the surface leading to a need for finer vertical resolution. In addition, the interactions (e.g. rain) will be highly variable in space and time across the problem domain so an adaptive scheme is preferred to a static strategy to efficiently use computing and memory resources. As a result, this project focussed on algorithmic research required for development of an adaptive simulation capability in the PF.WRF system and its subsequent use in an application problem in the Central Valley of California. This report documents schemes of use for a future implementation of an adaptive grid capability within the ParFlow subsurface flow simulator in PF.WRF. The methods describe specific handling of the coarse/fine boundaries within a cell-centered discretization of the nonlinear parabolic Richards equation model for variable saturated flow. In addition, we describe development of a spline fit and table lookup method implemented within ParFlow to enhance computational efficiency of variably saturated flow calculations.

97 MATHEMATICS AND COMPUTING↗

Hierarchical memories: Simulating quantum LDPC codes with local gates

Constant-rate low-density parity-check (LDPC) codes are promising candidates for constructing efficient fault-tolerant quantum memories. However, if physical gates are subject to geometric-locality constraints, it becomes challenging to realize these codes. In this paper, we construct a new family of [[N,K,D]] codes, referred to as hierarchical codes, that encode a number of logical qubits K=Ω(N/log(N) 2 ). The N th element of this code family is obtained by concatenating a constant-rate quantum LDPC code with a surface code; nearest-neighbor gates in two dimensions are sufficient to implement the corresponding syndrome-extraction circuit and achieve a threshold. Below threshold the logical failure rate vanishes superpolynomially as a function of the distance D(N). We present a bilayer architecture for implementing the syndrome-extraction circuit, and estimate the logical failure rate for this architecture. Under conservative assumptions, we find that the hierarchical code outperforms the basic encoding where all logical qubits are encoded in the surface code.

Pattison, Christopher A. [California Institute of ↗

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗

A GPU-based compressible combustion solver for applications exhibiting disparate space and time scales

High-speed chemically active flows pose significant computational challenges due to their disparate space and time scales, with stiff chemistry often dominating simulation time. While modern scientific computing programs achieve exascale performance by leveraging graphics processing units (GPUs), existing GPU-based compressible combustion solvers face critical limitations in memory management, load balancing, and handling the highly localized nature of chemical reactions. To this end, we present a high-performance compressible reacting flow solver built on the AMReX framework and optimized for multi-GPU settings. Here, our approach addresses three GPU performance bottlenecks: memory access patterns through column-major storage optimization, computational workload variability via a bulk-sparse integration strategy for chemical kinetics, and multi-GPU load distribution for adaptive mesh refinement applications. The solver adapts existing matrix-based chemical kinetics formulations to multi-grid contexts. Using representative combustion applications, including 2D and 3D detonations and a 3D jet-in-crossflow configuration, we demonstrate 1.4–5× performance improvements over initial implementations on an in-house cluster of NVIDIA H100 GPUs, and near-ideal weak scaling on the Frontier supercomputer (Oak Ridge Leadership Computing Facility) with up to 1024 AMD Instinct MI250X GPUs. Roofline analysis reveals substantial improvements in arithmetic intensity for both convection (∼ 10 ×) and chemistry (∼ 4 ×) routines, confirming efficient utilization of GPU memory bandwidth and computational resources.

42 ENGINEERING↗

Parallel programming of an ionic floating-gate memory array for scalable neuromorphic computing

Neuromorphic computers could overcome efficiency bottlenecks inherent to conventional computing through parallel programming and readout of artificial neural network weights in a crossbar memory array. However, selective and linear weight updates and <10-nanoampere read currents are required for learning that surpasses conventional computing efficiency. We introduce an ionic floating-gate memory array based on a polymer redox transistor connected to a conductive-bridge memory (CBM). Selective and linear programming of a redox transistor array is executed in parallel by overcoming the bridging threshold voltage of the CBMs. Synaptic weight readout with currents <10 nanoamperes is achieved by diluting the conductive polymer with an insulator to decrease the conductance. The redox transistors endure >1 billion write-read operations and support >1-megahertz write-read frequencies.

bio-inspired, energy storage (including batteries ↗

Low Power, Radiation Resilient Synchronous Edge Processing for Remote Monitoring

Next-generation space remote sensing systems may be equipped with imaging arrays that sense data at a rate that outstrips the processing capability of any computing hardware that can operate within a satellite’s power budget. This project developed novel convolutional and recurrent neural networks to detect and estimate point-like events amid clutter, and investigated their efficient and accurate implementation on analog in-memory computing systems that are 10-1000× more energy-efficient than digital processors. This project leveraged two memory devices at different levels of technological maturity: a large-scale analog computing prototype using commercial SONOS charge-trap memory, and electrochemical memory (ECRAM) with intrinsic radiation hardness. We experimentally demonstrated end-to-end analog processing of our neural networks on SONOS and characterized the radiation response of both SONOS and ECRAM. We advanced the state-of-the-art in ECRAM precision and reliability, and developed co-design methods to enable accurate long-term operation of SONOS analog accelerators in space radiation environments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗