Search NASA⌕ Search

SEARCH · Search NASA

Results for “Low Precision”

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 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2013

Precise Truss Assembly using Commodity Parts and Low Precision Welding

We describe an Intelligent Precision Jigging Robot (IPJR), which allows high precision assembly of commodity parts with low-precision bonding. We present preliminary experiments in 2D that are motivated by the problem of assembling a space telescope optical bench on orbit using inexpensive, stock hardware and low-precision welding. An IPJR is a robot that acts as the precise "jigging", holding parts of a local assembly site in place while an external low precision assembly agent cuts and welds members. The prototype presented in this paper allows an assembly agent (in this case, a human using only low precision tools), to assemble a 2D truss made of wooden dowels to a precision on the order of millimeters over a span on the order of meters. We report the challenges of designing the IPJR hardware and software, analyze the error in assembly, document the test results over several experiments including a large-scale ring structure, and describe future work to implement the IPJR in 3D and with micron precision.

Komendera, Erik↗
NASA NTRS2014

Precise Truss Assembly Using Commodity Parts and Low Precision Welding

Hardware and software design and system integration for an intelligent precision jigging robot (IPJR), which allows high precision assembly using commodity parts and low-precision bonding, is described. Preliminary 2D experiments that are motivated by the problem of assembling space telescope optical benches and very large manipulators on orbit using inexpensive, stock hardware and low-precision welding are also described. An IPJR is a robot that acts as the precise "jigging", holding parts of a local structure assembly site in place, while an external low precision assembly agent cuts and welds members. The prototype presented in this paper allows an assembly agent (for this prototype, a human using only low precision tools), to assemble a 2D truss made of wooden dowels to a precision on the order of millimeters over a span on the order of meters. The analysis of the assembly error and the results of building a square structure and a ring structure are discussed. Options for future work, to extend the IPJR paradigm to building in 3D structures at micron precision are also summarized.

Komendera, Erik↗
DOE OSTI2024

Low Precision for Lower Energy Consumption: Preprint

Low-precision numeric types offer significant efficiency and energy benefits for computing applications. Mixed-precision algorithms, combining low and high precision types, maintain accuracy while improving performance. Despite advantages, there exist challenges on adapting existing mixed-precision algorithms to new technologies, such as new hardware architectures and new low-precision data types. This paper presents current challenges and opportunities to advance science in this domain targetting more energy efficient solutions.

energy efficiency↗
DOE OSTI2023

Mixed-Precision S/DGEMM Using the TF32 and TF64 Frameworks on Low-Precision AI Tensor Cores

Using NVIDIA graphics processing units (GPUs) equipped with Tensor Cores has enabled the significant acceleration of general matrix multiplication (GEMM) for applications in machine learning (ML) and artificial intelligence (AI) and in high-performance computing (HPC) generally. The use of such power-efficient, specialized accelerators can provide a performance increase between 8 × and 20 ×, albeit with a loss in precision. However, a high level of precision is required in many large scientific and HPC applications, and computing in single or double precision is still necessary for many of these applications to maintain accuracy. Fortunately, mixed-precision methods can be employed to maintain a higher level of numerical precision while also taking advantage of the performance increases from computing with lower-precision AI cores. With this in mind, we extend the state of the art by using NVIDIA’s new TF32 framework. This new framework not only burdens some constraints of the previous frameworks, such as costly 32 16-bit castings but also provides an equivalent precision and performance by using a much simpler approach. We also propose a new framework called TF64 that attempts double-precision arithmetic with low-precision Tensor Cores. Although this framework does not exist yet, we validated the correctness of this idea and achieved an equivalent of 64-bit precision on 32-bit hardware.

Valero Lara, Pedro↗
DOE OSTI2024

Low Precision and Efficient Programming Languages for Sustainable AI: Final Report for the Summer Project of 2024

This document contains all relevant material generated during the authors' summer internship at NREL in 2024. This report shows how to improve energy efficiency of a few code samples by using low-precision data types combined with mixed-precision algorithms. The main applications considered here are (i) linear system solvers using mixed precision, and (ii) neural networks using mixed precision. This report also discusses how programming languages affect energy consumption of algorithms, energy metrics for a code and tools, and the available current software and hardware infrastructure.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

HD-Bind: Encoding of Molecular Structure with Low Precision, Hyperdimensional Binary Representations

Publicly available collections of drug-like molecules have grown to comprise tens of billions of compounds due to advances in combinatorial chemistry. Traditional methods for identifying "hit" molecules from a large collection of potential drug-like candidates have relied on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug and its protein target. These approaches have the major drawback that they require exceptional computing capabilities for even relatively small collections of molecules. Hyperdimensional Computing (HDC) is a recently-proposed learning paradigm that represents data with high-dimension binary vectors; this allows the use of low-precision binary vector arithmetic to create models of the data that can be learned without the need for the gradient-based optimization required in many conventional machine learning and deep learning methods. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated in a range of application areas. We consider existing HDC approaches for molecular property classification and introduce two novel encodings of a commonly-used molecular representation, the extended connectivity fingerprint (ECFP). We show that HDC-based inference methods are as much as 91 times more efficient than traditional machine learning methods, and achieve an acceleration of nearly nine orders of magnitude compared to molecular docking. Our results show that HDC accelerated methods retain competitive accuracy on a number of well-studied tasks such as molecular property predictions using the MoleculeNet dataset, and bind/no-bind activity classification using the DUD-E and LIT-PCBA datasets. Our work thus motivates further investigation into molecular representation learning to develop ultraefficient pre-screening tools.

Jones, William↗
NASA NTRS1986

High precision low resolution spectrophotometry of Comets Giacobini-Zinner and Halley

Optical window (300 to 1000 nm) observations were made of Comet Halley during 12 to 14 Mar. 1986 by a scanning spectrometer. The results provide accurate spectrophotometric measurements of the principal molecular bands from the 308 nm OH through the 918 nm CN emissions. The observations can be used to tie space derived ultraviolet and groundbased infrared observations to the optical observations and to one another. Additional observations were made of comet Giacobini-Zinner on 30 September 1985 of the same OH band and the 388 nm band of CN. The Swan band sequence ratios are used to test the best models of C2, with different ratios favoring different models, calling into question the assumptions of these very complete models.

Odell, C. R.↗
NASA NTRS1990

Precise Hinge Has Low Friction

Precise hinge rotates with minimal friction and without "slop". Axis of rotation at central axis of concentric, self-retaining assembly. Blades in same plane, and both edges of blades and apexes of grooves lie along same line, allowing free rotation without either binding or slop. Blades on rotor engage grooves on stator. Blades pivot about edges through arc defined by slotted openings in stator housing.

Collins, Earl R., Jr.↗
DOE OSTI2024

CryoTransformer: a transformer model for picking protein particles from Cryo-EM micrographs

Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structures of large protein complexes. Picking single protein particles from cryo-EM micrographs (images) is a crucial step in reconstructing protein structures from them. However, the widely used template-based particle picking process requires some manual particle picking and is labor-intensive and time-consuming. Though machine learning and artificial intelligence (AI) can potentially automate particle picking, the current AI methods pick particles with low precision or low recall. The erroneously picked particles can severely reduce the quality of reconstructed protein structures, especially for the micrographs with low signal-to-noise-ratio (SNR).

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

A GPU accelerated mixed-precision Smoothed Particle Hydrodynamics framework with cell-based relative coordinates

Smoothed Particle Hydrodynamics (SPH) is essential for modeling complex large-deformation problems across various applications, requiring significant computational power. A major portion of SPH computation time is dedicated to the Nearest Neighboring Particle Search (NNPS) process. While advanced NNPS algorithms have been developed to enhance SPH efficiency, the potential efficiency gains from modern computation hardware remain underexplored. Here, this study investigates the impact of GPU parallel architecture, low-precision computing on GPUs, and GPU memory management on NNPS efficiency. Our approach employs a GPU-accelerated mixed-precision SPH framework, utilizing low precision float-point 16 (FP16) for NNPS while maintaining high precision for other components. To ensure FP16 accuracy in NNPS, we introduce a Relative Coordinated-based Link List (RCLL) algorithm, storing FP16 relative coordinates of particles within background cells. Our testing results show three significant speedup rounds for CPU-based NNPS algorithms. The first comes from parallel GPU computations, with up to a 1000x efficiency gain. The second is achieved through low-precision GPU computing, where the proposed FP16-based RCLL algorithm offers a 1.5x efficiency improvement over the FP64-based approach on GPUs. By optimizing GPU memory bandwidth utilization, the efficiency of the FP16 RCLL algorithm can be further boosted by 2.7x, as demonstrated in an example with 1 million particles. Our code is released at https://github.com/pnnl/lpNNPS4SPH.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1990

Indexing system for optical beam steering

This paper describes the design and testing of an indexing system for optical-beam steering. The cryogenic beam-steering mechanism is a 360-degree rotation device capable of discrete, high-precision alignment positions. It uses low-precision components for its rough alignment and kinematic design to meet its stringent repeatability and stability requirements (of about 5 arcsec). The principal advantages of this design include a decoupling of the low-precision, large angular motion from the high-precision alignment, and a power-off alignment position that potentially extends the life or hold time of cryogenic systems. An alternate design, which takes advantage of these attributes while reducing overall motion, is also presented. Preliminary test results show the kinematic mount capable of sub-arc second repeatability.

Sullivan, Mark T.↗
DOE OSTI2022

QONNX: Representing Arbitrary-Precision Quantized Neural Networks

We present extensions to the Open Neural Network Exchange (ONNX) intermediate representation format to represent arbitrary-precision quantized neural networks. We first introduce support for low precision quantization in existing ONNX-based quantization formats by leveraging integer clipping, resulting in two new backward-compatible variants: the quantized operator format with clipping and quantize-clip-dequantize (QCDQ) format. We then introduce a novel higher-level ONNX format called quantized ONNX (QONNX) that introduces three new operators -- Quant, BipolarQuant, and Trunc -- in order to represent uniform quantization. By keeping the QONNX IR high-level and flexible, we enable targeting a wider variety of platforms. We also present utilities for working with QONNX, as well as examples of its usage in the FINN and hls4ml toolchains. Finally, we introduce the QONNX model zoo to share low-precision quantized neural networks.

Pappalardo, Alessandro↗
DOE OSTI2022

Multistage mixed precision iterative refinement

Abstract Low precision arithmetic, in particular half precision (16‐bit) floating point arithmetic, is now available in commercial hardware. Using lower precision can offer significant savings in computation and communication costs with proportional savings in energy. Motivated by this, there has been a renewed interest in mixed precision iterative refinement schemes for solving linear systems , and new variants of GMRES‐based iterative refinement have been developed. Each particular variant with a given combination of precisions leads to different condition number‐based constraints for convergence of the backward and forward errors, and each has different performance costs. The constraints for convergence given in the literature are, as an artifact of the analyses, often overly strict in practice, and thus could lead a user to select a more expensive variant when a less expensive one would have sufficed. In this work, we develop a multistage mixed precision iterative refinement solver which aims to combine existing mixed precision approaches to balance performance and accuracy and improve usability. For a user‐specified initial combination of precisions, the algorithm begins with the least expensive approach and convergence is monitored via inexpensive computations with quantities produced during the iteration. If slow convergence or divergence is detected using particular stopping criteria, the algorithm switches to use a more expensive, but more reliable variant. A novel aspect of our approach is that, unlike existing implementations, our algorithm first attempts to use “stronger” GMRES‐based solvers for the solution update before resorting to increasing the precision(s). In some scenarios, this can avoid the need to refactorize the matrix in higher precision. We perform extensive numerical experiments on a variety of random dense problems and problems from real applications which confirm the benefits of the multistage approach.

Oktay, Eda↗
DOE OSTI2023

NbTaV_BCC_SolidSolution_128atoms_VASP6

We performed density functional theory (DFT) calculations for body-centered-cubic (BCC) structures with 128 lattices sites of solid solution ternary alloys niobium-tantalum-vanadium (Nb-Ta-V). The first-principle code that has been used to run the calculations is the closed-source Vienna Ab-Initio Simulation Package (VASP). The calculations have been collected by sampling chemical compositions across the entire compositional range. The chemical compositions have been sampled by progressively changing the number of atoms per constituent by 8. For each chemical composition of binaries and ternaries, the first-principle calculations have been run for 100 randomized arrangements of the constituents on the BCC lattice sites. We collected data for a total of 10,500 randomized atomic structures over 105 chemical compositions. The calculations have been collected on NERSC-Perlmutter using the VASP 6.3.2. The VASP calculations for every atomic structure have been performed in 2 main steps: 1. Starting from an ideal body-centered-cubic (BCC) structure, geometry optimization with low precision has been executed to perform a preliminary optimization of the atomic structure. The output for this calculations is available in the files 0.CONTCAR, 0.OUTCAR, rlx1.out. 2. Using the atomic structure resulting from the preliminary geometry optimization, a second geometry optimization has been performed using normal precision. The output for this calculations is available in the files CONTCAR, OUTCAR, rlx2.out, vaspout.h5, and vasprun.xml. Every chemical composition sampled across the composition range in the dataset has its own directory. The convention used to name the directories for ternary alloys is AXBYCZ, where A, B, and C refer to the constituents, and X, Y, and Z are positive integers that represent the number of atoms for each constituent and their values still sum up to 128. Each atomic structure associated with a specific chemical composition has its own sub-directory within the directory of the corresponding chemical composition. The sub-directories for each atomic structure for each chemical composition are named 'case-*', where * is a positive integer that spans all the values from 1 through 100, extremes included. The files contained in each sub-directory 'case-*' for each atomic structure are as follows: 1. INCAR: input file that contains various parameters and settings for controlling the behavior of the electronic structure calculations 2. 0.POSCAR: input file that defines the atomic structure of a system 3. 0.CONTCAR: output file that provides the atomic positions and cell parameters after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 4. 0.OUTCAR: output file that contains detailed information about the progress of a calculation after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 5. rlx1.out: file with diagnostic information about the execution of the first geometry optimization with precision variable set to PREC=Low in the INCAR file 6. POSCAR: input file that defines the atomic structure of a system after the first geometry optimization has been run at low precision. This represents the input for the second geometry optimization run with the precision variable set to PREC=Normal in the INCAR file 7. CONTCAR: output file that provides the atomic positions and cell parameters after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 8. OUTCARL: output file that contains detailed information about the progress of a calculation after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 9. rlx2.out: file with diagnostic information about the execution of the second geometry optimization with precision variable set to PREC=Normal in the INCAR file 10. vaspout.h5: hierarchical HDF5 file containing the inputs and outputs of a VASP calculation. To analyze the data in this file we recommend using py4vasp. This file is only produced if the VASP version used is compiled with HDF5 support 11. vasprun.xml: contains similar information to OUTCAR, but in an xml format. This research is sponsored by the Artificial Intelligence Initiative as part of the Laboratory Directed Research and Development (LDRD) Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the US Department of Energy under contract DE-AC05-00OR22725. This work used resources of the Oak Ridge Leadership Computing Facility, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725, under Directorate Discretionary awards MAT025 (Materials Science) and LRN026 (Machine Learning), and INCITE award MAT201. This work also used resources of the National Energy Research Scientific Computing Center, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231, under award ERCAP0025216.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Precise ROCOF estimation algorithm for low inertia power grids

The precise estimation of Rate Of Change Of Frequencies (ROCOFs) in a generation trip event can be helpful on power system inertia estimation, fast system response, and accurate event capturing. However, the ROCOF estimations from the existing Synchronized Measurement Devices (SMDs) are usually simply calculated by the finite difference between two adjacent frequency measurement points. The ineluctable noises, disturbances, and spikes from real-world frequency measurements can bring large dynamics to the ROCOF estimation and thus can result in an inaccurate estimation of the initial ROCOF. This issue becomes more serious when the target power grid has low inertia, and a large amount of distributed energy sources are deployed. To address this issue, a precise ROCOF estimation algorithm is designed based on least square method with flexible window size. In addition, a median filter is also designed and applied on the frequency measurements before using the proposed algorithm. The window size and thresholds in the proposed algorithm are determined with historical event data analysis. The proposed algorithm is deployed in a low cost, flexible, and distribution level universal grid analyzer (UGA) platform. In conclusion, multiple experiments are conducted in both a laboratory and the Hawaiian Islands to verify the effectiveness of the proposed algorithm.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Accelerating Floating-Point Computations with Intel AMX

Intel AMX is a built-in component of recent Intel CPU architectures, first supported by the Intel Sapphire Rapids in 2023, that enables efficient dense matrix multiplications using mixed precision with low-precision data types. The popularity of mixed-precision algorithms has grown recently, primarily due to their use on GPUs to enhance the efficiency of HPC applications, particularly for the training of large language models. The availability of mixed precision on CPUs represents a cost-effective solution for applications where high speed is not critical. This report shows how to use the Intel AMX accelerator through examples in C++ and Python. The examples will focus on mixed-precision floating-point operations obtained by the use of bfloat16 (or BF16) to accelerate code in single precision. We employ a bottom-up methodology, starting from specific register instructions (TMUL operation) to higher-level applications in libraries such as Intel MKL, PyTorch, and TensorFlow, ensuring a comprehensive understanding of the accelerator's potential. Additionally, we provide insights into the expected performance gains when leveraging the accelerator on the Kestrel HPC machine at the National Renewable Energy Laboratory.

97 MATHEMATICS AND COMPUTING↗