Search NASA⌕ Search

SEARCH · Search NASA

Results for “AMD”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Milestone 49 Report: Batched Sparse LA Phase 5 Implementation

Batched sparse linear algebra operations in general, and solvers in particular, have become the major algorithmic development activity and foremost performance engineering effort in the numerical software libraries work on modern hardware with accelerators such as GPUs. Many applications, ECP and non-ECP alike, require simultaneous solutions of many small linear systems of equations that are structurally sparse in one form or another. In order to move towards high hardware utilization levels, it is important to provide these applications with appropriate interface designs to be both functionally efficient and performance portable and give full access to the appropriate batched sparse solvers running on modern hardware accelerators prevalent across DOE supercomputing sites since the inception of ECP. To this end, we present here a summary of recent advances on the interface designs in use by HPC software libraries supporting batched sparse linear algebra and the development of sparse batched kernel codes for solvers and preconditioners. We also address the potential interoperability opportunities to keep the corresponding software portable between the major hardware accelerators from AMD, Intel, and NVIDIA, while maintaining the appropriate disclosure levels conforming to the active NDA agreements. The presented interface specifications include a mix of batched band, sparse iterative, and sparse direct solvers with their accompanying functionality that is already required by the application codes or we anticipated to be needed in the near future. This report summarizes progress in Kokkos Kernels and the xSDK libraries MAGMA, Ginkgo, hypre, PETSc, and SuperLU.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Deployment of inference as a service at the US CMS Tier-2 data centers

Coprocessors, especially GPUs, will be a vital ingredient of data production workflows at the HL-LHC. At CMS, the GPU-as-a-service approach for production workflows is implemented by the SONIC project (Services for Optimized Network Inference on Coprocessors). SONIC provides a mechanism for outsourcing computationally demanding algorithms, such as neural network inference, to remote servers, where requests from multiple clients are intelligently distributed across multiple GPUs by a load-balancing service. This talk highlights the recent progress in deploying SONIC at selected U.S. CMS Tier-2 data centers. Using realistic CMS Run3 data processing workflows, such as those containing transformer-based algorithms, we demonstrate how SONIC is integrated into the production-like environment to enable accelerated inference offloading. We will present developments from both the client and server sides, including production job and data center configurations for NVIDIA and AMD GPUs. We will also present performance scaling benchmarks and discuss the challenges of operating SONIC in CMS production, such as server discovery, GPU saturation, fallback server logic, etc.

Holzman, Burt↗
DOE OSTI2025

Argonne Leadership Computing Facility 2024 Operational Assessment Report

This Operational Assessment Report describes how the Argonne Leadership Computing Facility (ALCF) met or exceeded every goal set by DOE for the calendar year (CY) 2024. In CY 2024, the ALCF operated Polaris, an AMD and NVIDIA-based Hewlett Packard Enterprise (HPE) Apollo 6500 Gen10+ system that provides a powerful platform for breakthrough science and prepares applications and workloads for Aurora, Argonne National Laboratory’s Intel-HPE exascale computer. Since going into production in August 2022, Polaris has supported research teams from the DOE Exascale Computing Project (ECP), which concluded in 2024, and from ALCF’s Aurora Early Science Program (ESP). Polaris delivered a total of 2555.7K node-hours to 17 Innovative and Novel Computational Impact on Theory and Experiment (INCITE) 2024 projects and 601.6K node-hours to ASCR Leadership Computing Challenge (ALCC) projects (12 of which were awarded during the 2023–2024 ALCC year and 11 of which were awarded during the 2024–2025 ALCC year), as well as providing substantial time for Director’s Discretionary (DD) projects (966.2K node-hours). As Table ES.1 shows, Polaris performed exceptionally well in terms of overall availability (97.7 percent), scheduled availability (99.6 percent), and utilization (94.7 percent; Table 2.1). In CY 2024, ALCF supported more than 2,000 users. As of March 18, 2025, ALCF’s users have published 254 papers in peer-reviewed journals and technical proceedings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Radiation Effects on Network on Chips (NoC) Laboratory Directed Research and Development (LDRD) project

This project was motivated by State-of-the-Art (SOTA) technology that incorporates Network on Chips (NOC) for efficient data communication across the various computer kernels. For example, on the AMD Versal Field Programmable Gate Arrays (FPGA), an NoC has been incorporated for fast data communication from the programmable logic and other computer kernels (processing system, adaptable intelligence engines, etc.). The radiation effects on the legacy technology of this FPGA, such as the programmable logic, are well understood, and established methods exist to measure cross-sections when new families/generations are released; however, newly incorporated technologies, such as the NoC, are not fully understood and could introduce new failure points into the mission space.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Rasterization with Data-Parallel Primitives

Parallel rasterization can suffer from race conditions during fragment generation, which is traditionally addressed by using specialized hardware accessible via vendor graphics APIs. Unfortunately, graphics APIs are increasingly problematic on high-performance computers, either because they are not provided or because of concerns about dependencies with in situ visualization. In response, we present a hardware-agnostic rasterization algorithm that handles race conditions using only data-parallel primitives (DPPs), enabling efficient rendering on HPC systems without graphics API dependencies and aligning with recent efforts to deliver visualization software with DPPs. Our evaluation consists of three phases: (1) evaluating portability across different CPU and GPU architectures, (2) evaluating competitiveness with a community standard, and (3) evaluating performance across varying workloads and available parallelism. The supporting experiments run on both AMD and NVIDIA GPUs, considering data sets as large as 460 million triangles and 160 million pixels. While performance generally falls short of graphics API baselines, it achieves interactive frame rates on most workloads. As a result, we conclude our approach is a viable solution for rasterization on high-performance computers since our approach is portably performant across different architectures without the need for specialized vendor support.

Buckley, Makani [University of Oregon] (ORCID:0009↗
DOE OSTI2024

Enabling Parallel Performance and Portability of Solid Mechanics Simulations Across CPU and GPU Architectures

Efficiently simulating solid mechanics is vital across various engineering applications. As constitutive models grow more complex and simulations scale up in size, harnessing the capabilities of modern computer architectures has become essential for achieving timely results. This paper presents advancements in running parallel simulations of solid mechanics on multi-core CPUs and GPUs using a single-code implementation. This portability is made possible by the C++ matrix and array (MATAR) library, which interfaces with the C++ Kokkos library, enabling the selection of fine-grained parallelism backends (e.g., CUDA, HIP, OpenMP, pthreads, etc.) at compile time. MATAR simplifies the transition from Fortran to C++ and Kokkos, making it easier to modernize legacy solid mechanics codes. We applied this approach to modernize a suite of constitutive models and to demonstrate substantial performance improvements across different computer architectures. This paper includes comparative performance studies using multi-core CPUs along with AMD and NVIDIA GPUs. Results are presented using a hypoelastic–plastic model, a crystal plasticity model, and the viscoplastic self-consistent generalized material model (VPSC-GMM). The results underscore the potential of using the MATAR library and modern computer architectures to accelerate solid mechanics simulations.

Morgan, Nathaniel (ORCID:0000000276118449)↗
DOE OSTI2025

Machine Learning-Driven Conservative-to-Primitive Conversion in Hybrid Piecewise Polytropic and Tabulated Equations of State

We present a novel machine learning (ML)-based method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch (2.0+) and optimized for GPU inference using NVIDIA TensorRT (8.4.1), achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves 𝐿 1 and 𝐿 ∞ errors of 4.54 × 10 −7 and 3.44 × 10−6, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (dual AMD 64-core 2.45 GHz Milan processors and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. By exploiting the underlying symmetries within the equation of state, these findings highlight the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations.

conservative-to-primitive conversion↗
DOE OSTI2026

AthenaK: A Performance-portable Version of the Athena++ Adaptive Mesh Refinement Framework

We describe AthenaK: a new implementation of the Athena++ block-based adaptive mesh refinement framework using the Kokkos programming model. Finite volume methods for Newtonian, special relativistic, and general relativistic (GR) hydrodynamics and magnetohydrodynamics (MHD), and GR-radiation hydrodynamics and MHD, as well as a module for evolving Lagrangian tracer or charged test particles (e.g., cosmic rays) are implemented using the framework. In two companion papers, we describe (1) a new solver for the Einstein equations based on the Z4c formalism, and (2) a GRMHD solver in dynamical spacetimes also implemented using the framework, enabling new applications in numerical relativity. By adopting Kokkos, the code can be run on virtually any hardware, including CPUs, GPUs from multiple vendors, and emerging Advanced RISC Machine processors. AthenaK shows excellent performance and weak scaling, achieving over 1 billion cell updates per second for hydrodynamics in three dimensions on a single NVIDIA Grace Hopper processor. It does this with a typical parallel efficiency of 80% on 65,536 AMD GPUs on the OLCF Frontier system. Such performance portability enables AthenaK to leverage modern exascale computing systems for challenging applications in astrophysical fluid dynamics, numerical relativity, and multimessenger astrophysics.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Entity—Hardware-agnostic Particle-in-cell Code for Plasma Astrophysics. I. Curvilinear Special Relativistic Module

Entity is a new-generation, fully open-source particle-in-cell (PIC) code developed to overcome key limitations in astrophysical plasma modeling, particularly the extreme separation of scales and the performance challenges associated with evolving, GPU-centric computing infrastructures. It achieves hardware-agnostic performance portability across various GPU and CPU architectures using the Kokkos library. Crucially, Entity maintains a high standard for usability, clarity, and customizability, offering a robust and easy-to-use framework for developing new algorithms and grid geometries, which allows extensive control without requiring edits to the core source code. This paper details the core general-coordinate special relativistic module. Entity is the first PIC code designed to solve the Vlasov–Maxwell system in general coordinates, enabling a coordinate-agnostic framework that provides the foundational structure for straightforward extension to arbitrary coordinate geometries. The core methodology achieves numerical stability by solving particle equations of motion in the global orthonormal Cartesian basis, despite using generalized coordinates like Cartesian, axisymmetric spherical, and quasi-spherical grids. Charge conservation is ensured via a specialized current deposition technique using conformal currents. The code exhibits robust scalability and performance portability on major GPU platforms (AMD MI250X, NVIDIA A100, and Intel Max Series), with the 3D particle pusher and the current deposition operating efficiently at about 2 ns per particle per time step. Functionality is validated through a comprehensive suite of standard Cartesian plasma tests and the accurate modeling of relativistic magnetospheres in curvilinear axisymmetric geometries.

Hakobyan, Hayk [Flatiron Institute, New York, NY (↗
DOE OSTI2026

TChem-atm (v2.0.0): scalable performance-portable multiphase atmospheric chemistry

We present TChem-atm, a performance-portable approach that enables efficient simulation of chemically detailed and multiphase atmospheric chemistry on modern heterogeneous computing architectures. Unlike previous efforts that rely on architecture-specific code or focus exclusively on gas-phase chemistry, TChem-atm supports fully coupled gas–aerosol systems with execution across CPUs, NVIDIA GPUs, and AMD GPUs through the Kokkos programming model. It integrates the flexible multiphase capabilities of the Community Atmospheric Model Chemistry Package (CAMP) with the high-performance kinetic routines of TChem, and includes automatic Jacobian construction with support for a range of stiff ODE solvers. In a proof-of-concept integration with the particle-resolved model PartMC, TChem-atm reproduces the existing PartMC–CAMP implementation within solver tolerances and delivers substantial GPU speedups, especially for large particle populations. Performance benchmarks reveal substantial speedups on GPU platforms, particularly for large particle populations, with consistent results across hardware backends. TChem-atm enables performance-portable execution across CPUs and GPUs, though optimal efficiency may require modest architecture-specific tuning (e.g., team and vector sizes), with up to a twofold improvement on the NVIDIA H100. It directly supports sectional and particle-resolved host models, while modal aerosol schemes require minor adaptation to provide particle-scale quantities such as representative diameters. By enabling chemically detailed, multiphase simulations with performance portability and host-model flexibility, TChem-atm facilitates the incorporation of advanced chemistry into atmospheric models.

Díaz-Ibarra, Oscar Homero [Sandia National Laborat↗
NASA NTRS1972

The effects of configuration changes on the aerodynamic characteristics of a full-scale mockup of a light twin engine airplane

Wind tunnel tests of a full-scale model of a light twin engine aircraft were conducted. The angle of attack was varied from minus 4 degrees to plus 20 degrees. The sideslip range was plus or minus 8 degrees. Thrust coefficients were 0, 0.20, and 0.44. Tests were made with various nacelle configurations, modes of propeller rotation, orientation of the thrust axis, and airfoil section at Reynolds numbers of 2.96 times one million amd 2.05 times one million.

Fink, M. P.↗
NASA NTRS1974

Preliminary results of fisheries investigation associated with Skylab-3

The author has identified the following significant results. This investigation is to establish the feasibility of utilizing remotely sensed data acquired from aircraft and satellite platforms to provide information concerning the distribution and abundance of oceanic gamefish. Data from the test area in the northeastern Gulf of Mexico has made possible the identification of fisheries significant environmental parameters for white marlin. Predictive models based on catch data and surface truth information have been developed and have demonstrated potential for reducing search significantly by identifying areas which have a high probability of being productive. Three of the parameters utilized by the model, chlorophyll-a, sea surface temperature, and turbidity have been inferred from aircraft sensor data. Cloud cover and delayed receipt have inhibited the use of Skylab data. The first step toward establishing the feasibility of utilizing remotely sensed data to assess amd monitor the distribution of ocean gamefish has been taken with the successful identification of fisheries significant oceanographic parameters and the demonstration of the capability of measuring most of these parameters remotely.

Savastano, K. J.↗
NASA NTRS1975

Dynamic load capacities of graphite fiber: Polyimide composites in oscillating plain bearings to 340 C (650 F)

Load capacities were determined for plain spherical bearings with self-lubricating spherical elements of graphite-fiber-reinforced-polyimide, and for plain cylindrical bearings with thin-wall liners of the composite in the bearing bores. Composites consisted of a 1-to-1 weight ratio of graphite fibers and polyimide. Oscillation was at an amplitude of + or - 15 deg at a frequency of 1 hertz. Bearings with composite ball material had a load capacity of approximately 69 MN/sq m (10 000 psi) at room temperature 25 MN/sq m (3600 psi) at 340 C (650 F). Bearings with thin-wall composite liners had much higher load capacities of 280 MN/sq m (40 000 psi) at room temperature amd 240 MN/sq m (35 000 psi) at 320 C (600 F). Friction coefficients were in the range of 0.12 to 0.19. The addition of 10 wt.% graphite fluoride solid lubricant to the composition of the thin-wall liners reduced friction coefficients into the range of 0.10 to 0.12.

Sliney, H. E.↗
NASA NTRS1976

The cost of energy from utility-owned solar electric systems. A required revenue methodology for ERDA/EPRI evaluations

This methodology calculates the electric energy busbar cost from a utility-owned solar electric system. This approach is applicable to both publicly- and privately-owned utilities. Busbar cost represents the minimum price per unit of energy consistent with producing system-resultant revenues equal to the sum of system-resultant costs. This equality is expressed in present value terms, where the discount rate used reflects the rate of return required on invested capital. Major input variables describe the output capabilities and capital cost of the energy system, the cash flows required for system operation amd maintenance, and the financial structure and tax environment of the utility.

Source record↗
NASA NTRS1976

Roller bearing geometry design

A theory of kinematic stabilization of rolling cylinders is extended and applied to the design of cylindrical roller bearings. The kinematic stabilization mechanism puts a reverse skew into the rolling elements by changing the roller taper. Twelve basic bearing modification designs are identified amd modeled. Four have single transverse convex curvature in their rollers while eight have rollers which have compound transverse curvature made up of a central cylindrical band surrounded by symmetric bands with slope and transverse curvature. The bearing designs are modeled for restoring torque per unit axial displacement, contact stress capacity, and contact area including dynamic loading, misalignment sensitivity and roller proportion. Design programs are available which size the single transverse curvature roller designs for a series of roller slopes and load separations and which design the compound roller bearings for a series of slopes and transverse radii of curvature. The compound rollers are proportioned to have equal contact stresses and minimum size. Design examples are also given.

Savage, M.↗
NASA NTRS1983

Cloud cover typing from environmental satellite imagery. Discriminating cloud structure with Fast Fourier Transforms (FFT)

The use of two dimensional Fast Fourier Transforms (FFTs) subjected to pattern recognition technology for the identification and classification of low altitude stratus cloud structure from Geostationary Operational Environmental Satellite (GOES) imagery was examined. The development of a scene independent pattern recognition methodology, unconstrained by conventional cloud morphological classifications was emphasized. A technique for extracting cloud shape, direction, and size attributes from GOES visual imagery was developed. These attributes were combined with two statistical attributes (cloud mean brightness, cloud standard deviation), and interrogated using unsupervised clustering amd maximum likelihood classification techniques. Results indicate that: (1) the key cloud discrimination attributes are mean brightness, direction, shape, and minimum size; (2) cloud structure can be differentiated at given pixel scales; (3) cloud type may be identifiable at coarser scales; (4) there are positive indications of scene independence which would permit development of a cloud signature bank; (5) edge enhancement of GOES imagery does not appreciably improve cloud classification over the use of raw data; and (6) the GOES imagery must be apodized before generation of FFTs.

Logan, T. L.↗
NASA NTRS1983

Single cell performance studies on the FE/CR Redox Energy Storage System using mixed reactant solutions at elevated temperature

Experimental studies in a 14.5 sq cm single cell system using mixed reactant solutions at 65 C are described. Systems were tested under isothermal conditions, i.e., reactants and the cell were at the same temperature. Charging and discharging performance were evaluated by measuring watt-hour and coulombic efficiencies, voltage-current relationships, hydrogen evolution and membrane resistivity. Watt-hour efficiencies ranged from 86 percent at 43 ma/sq cm to 75 percent at 129 ma/sq cm with corresponding coulombic efficiencies of 92 percent and 97 percent, respectively. Hydrogen evolution was less than 1 percent of the charge coulumbic capacity during charge-discharge cycling. Bismuth amd bismuth-lead catalyzed chromium electrodes maintained reversible performance and low hydrogen evolution under normal and adverse cycling conditions. Reblending of the anode and cathode solutions was successfully demonstrated to compensate for osmotic volume changes. Improved performance was obtained with mixed reactant systems in comparison to the unmixed reactant systems. Previously announced in STAR as N83-25042

Gahn, R. F.↗
NASA NTRS1985

Rain volume estimation over areas using satellite and radar data

An investigation of the feasibility of rain volume estimation using satellite data following a technique recently developed with radar data called the Arera Time Integral was undertaken. Case studies were selected on the basis of existing radar and satellite data sets which match in space and time. Four multicell clusters were analyzed. Routines for navigation remapping amd smoothing of satellite images were performed. Visible counts were normalized for solar zenith angle. A radar sector of interest was defined to delineate specific radar echo clusters for each radar time throughout the radar echo cluster lifetime. A satellite sector of interest was defined by applying small adjustments to the radar sector using a manual processing technique. The radar echo area, the IR maximum counts and the IR counts matching radar echo areas were found to evolve similarly, except for the decaying phase of the cluster where the cirrus debris keeps the IR counts high.

Doneaud, A. A.↗