Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “compute in memory”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 955 records · Page 53
All sourcesNASA NTRSDOE OSTI
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↗
DOE OSTI2024

Small tensor product distributed active space (STP-DAS) framework for relativistic and non-relativistic multiconfiguration calculations: Scaling from 10 9 on a laptop to 10 12 determinants on a supercomputer

Despite the power and flexibility of configuration interaction (CI) based methods in computational chemistry, their broader application is limited by an exponential increase in both computational and storage requirements, particularly due to the substantial memory needed for excitation lists that are crucial for scalable parallel computing. Here, the objective of this work is to develop a new CI framework, namely, the small tensor product distributed active space (STP-DAS) framework, aimed at drastically reducing memory demands for extensive CI calculations on individual workstations or laptops, while simultaneously enhancing scalability for extensive parallel computing. Moreover, the STP-DAS framework can support various CI-based techniques, such as complete active space (CAS), restricted active space, generalized active space, multireference CI, and multireference perturbation theory, applicable to both relativistic (two- and four-component) and non-relativistic theories, thus extending the utility of CI methods in computational research. We conducted benchmark studies on a supercomputer to evaluate the storage needs, parallel scalability, and communication downtime using a realistic exact-two-component CASCI (X2C-CASCI) approach, covering a range of determinants from 10 9 to 10 12 . Additionally, we performed large X2C-CASCI calculations on a single laptop and examined how the STP-DAS partitioning affects performance.

Complete-active space self-consistent field↗
DOE OSTI2026

Multifunctional electrochemical memory stabilized by phase coexistence

Our growing computing needs, especially in applications that heavily rely on artificial intelligence (AI), motivate a search for new components that could substantially augment the performance of general-purpose digital computers. Beyond ON/OFF switching, new components with linear multistate analog resistive tuning, nonlinear volatile switching, spiking, oscillatory, stochastic and other complex functionalities could enable highly efficient neuromorphic computing schemes for AI information processing. Compared to the extreme multifunctionality of biological neurons, realizing all the above characteristics in a single, scalable analog component remains a grand challenge. Here we investigate electrochemical gating combined with localized thermal activation to program and switch a single, vertically integrated and dimensionally scaled electrothermal chemical random access memory (ETCRAM) with a channel and reservoir composed of phase-separated vanadium oxide. Closely related to electrochemical RAM (ECRAM), ETCRAM uses an integrated gate-heater electrode to overcome kinetic barriers that help retain states at ambient temperatures. In addition to synapse-like stable and programmable analog resistance states arising from redox-tunable phase coexistence, a single component exhibits neuron-like nonlinear conductance switching with a tunable threshold and self-driven dynamics owing to the thermally driven metal-insulator phase transition in vanadium dioxide. More broadly, we demonstrate that electrochemically stabilized phase coexistence could unlock analog electronics with novel functionality, stability, reconfigurability, and scalability.

Oh, Sangheon [Sandia National Lab. (SNL-CA), Liver↗
DOE OSTI2025

LATTE: open-source, high-performance traveltime computation, tomography and source location in acoustic and elastic media

Traveltime-based tomography and source location are fundamental approaches for imaging subsurface structures and understanding the spatiotemporal distribution of seismicity from local to global scales. We present an open-source, high-performance framework integrating eikonal equation solvers and adjoint-state theory for traveltime computation, velocity tomography, source location and joint tomography-location in 2-D/3-D acoustic and elastic media. We introduce novel regularization schemes based on total generalized p-variation, structural similarity and multitask machine learning to enhance the fidelity and interpretability of inverted models and source locations. Key features of our implementation also include the ability to leverage both absolute-difference and double-difference traveltime misfits for high-fidelity velocity tomography and source parameter estimation; support for traveltime computation and inversion in diverse 2-D/3-D scenarios with arbitrary source and receiver distributions; and a perturbation-based optimal step-size estimation method to reduce computational costs. In addition, our implementation employs shared-memory and distributed-memory parallelization to provide an efficient solution for traveltime computation, tomography, and source location. In conclusion, we validate the efficacy and accuracy of our approach through multiple synthetic data examples.

58 GEOSCIENCES↗
DOE OSTI2024

Understanding Mixed Precision GEMM with MPGemmFI: Insights into Fault Resilience

Emerging deep learning workloads urgently need fast general matrix multiplication (GEMM). Thus, one of the critical features of machine-learning-specific accelerators such as NVIDIA Tensor Cores, AMD Matrix Cores, and Google TPUs is the support of mixed-precision enabled GEMM. For DNN models, lower-precision FP data formats and computation offer acceptable correctness but significant performance, area, and memory footprint improvement. While promising, the mixed-precision computation on error resilience remains unexplored. To this end, we develop a fault injection framework that systematically injects fault into the mixed-precision computation results. We investigate how the faults affect the accuracy of machine learning applications. Based on the characteristics of error resilience, we offer lightweight error detection and correction solutions that significantly improve the overall model accuracy by 75% if the models experience hardware faults. The solutions can be efficiently integrated into the accelerator's pipelines.

Fang, Bo↗
DOE OSTI2022

Asynchronous domain decomposition methods for nonlinear PDEs

One- and two-level parallel asynchronous methods for the numerical solution of nonlinear systems of equations, especially those arising from (nonlinear) partial differential equations, are studied. The proposed methods are based on domain decomposition techniques. Local convergence theorems are presented in several cases, with appropriate hypotheses. Computational results on a shared memory multiprocessor machine for various problems exhibiting nonlinearities are reported, illustrating the potential of these asynchronous methods, especially for heterogeneous clusters.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1988

Development of a personal-computer-based intelligent tutoring system

A large number of Intelligent Tutoring Systems (ITSs) have been built since they were first proposed in the early 1970's. Research conducted on the use of the best of these systems has demonstrated their effectiveness in tutoring in selected domains. A prototype ITS for tutoring students in the use of CLIPS language: CLIPSIT (CLIPS Intelligent Tutor) was developed. For an ITS to be widely accepted, not only must it be effective, flexible, and very responsive, it must also be capable of functioning on readily available computers. While most ITSs have been developed on powerful workstations, CLIPSIT is designed for use on the IBM PC/XT/AT personal computer family (and their clones). There are many issues to consider when developing an ITS on a personal computer such as the teaching strategy, user interface, knowledge representation, and program design methodology. Based on experiences in developing CLIPSIT, results on how to address some of these issues are reported and approaches are suggested for maintaining a powerful learning environment while delivering robust performance within the speed and memory constraints of the personal computer.

Mueller, Stephen J.↗
NASA NTRS1978

Fault-tolerant building-block computer study

Ultra-reliable core computers are required for improving the reliability of complex military systems. Such computers can provide reliable fault diagnosis, failure circumvention, and, in some cases serve as an automated repairman for their host systems. A small set of building-block circuits which can be implemented as single very large integration devices, and which can be used with off-the-shelf microprocessors and memories to build self checking computer modules (SCCM) is described. Each SCCM is a microcomputer which is capable of detecting its own faults during normal operation and is described to communicate with other identical modules over one or more Mil Standard 1553A buses. Several SCCMs can be connected into a network with backup spares to provide fault-tolerant operation, i.e. automated recovery from faults. Alternative fault-tolerant SCCM configurations are discussed along with the cost and reliability associated with their implementation.

Rennels, D. A.↗
DOE OSTI2024

Studying CPU and memory utilization of applications on Fujitsu A64FX and Nvidia Grace Superchip

ARM-based manycore CPU architectures are well-positioned to provide the rising memory throughput requirements of modern data intensive scientific applications in High Performance Computing (HPC). The Fujitsu A64FX CPU platform is based on the ARM v8.2A architecture, and is the processor of the flagship Japanese supercomputer - "Fugaku", which was previously ranked as the #1 supercomputer in the world according to the Top500 list. The Nvidia Grace superchip features 144 Neoverse V2 cores based on the ARMv9 architecture with 4x128b SVE2, providing exceptional computational power. The chip supports up to 480GB of memory, making it ideal for AI, machine learning, and scientific computing workloads. In this paper, we conduct a thorough performance exploration of a variety of parallel bandwidth-sensitive benchmarks and applications compiled with the native Fujitsu compiler on a Fugaku A64FX compute node and ARM (LLVM) Compiler on an NVIDIA Grace superchip compute node, engaging all the computational cores per cluster using OpenMP multithreading (assuming the cores can drive the available bandwidth). Our ultimate goals are to study the resource utilization of scientific applications and benchmarks on A64FX and Grace superchip, considering graph application scenarios ( GAP Benchmark suite) and eleven appli- cation proxies from the Rodinia heterogeneous benchmark suite (considering domains such as Data Mining, Bioinformatics, Fluid Dynamics, Pattern Recognition, etc.). Through exhaustive performance monitoring, we quantify the resource utilization of diverse OpenMP-based HPC applications on both the Fujitsu A64FX and the Nvidia Grace Superchip platforms.

benchmarking, Performance Analysis, High performan↗
DOE OSTI2021

Sparse Approximate Multifrontal Factorization with Butterfly Compression for High-Frequency Wave Equations

In this work, we present a fast and approximate multifrontal solver for large-scale sparse linear systems arising from finite-difference, finite-volume or finite-element discretization of high-frequency wave equations. The proposed solver leverages the butterfly algorithm and its hierarchical matrix extension for compressing and factorizing large frontal matrices via graph-distance guided entry evaluation or randomized matrix-vector multiplication-based schemes. Complexity analysis and numerical experiments demonstrate $\mathcal{O}(N\log^2 N)$ computation and $\mathcal{O}(N)$ memory complexity when applied to an $N\times N$ sparse system arising from 3D high-frequency Helmholtz and Maxwell problems.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1987

Space station integrated wall design and penetration damage control

The analysis code BUMPER executes a numerical solution to the problem of calculating the probability of no penetration (PNP) of a spacecraft subject to man-made orbital debris or meteoroid impact. The codes were developed on a DEC VAX 11/780 computer that uses the Virtual Memory System (VMS) operating system, which is written in FORTRAN 77 with no VAX extensions. To help illustrate the steps involved, a single sample analysis is performed. The example used is the space station reference configuration. The finite element model (FEM) of this configuration is relatively complex but demonstrates many BUMPER features. The computer tools and guidelines are described for constructing a FEM for the space station under consideration. The methods used to analyze the sensitivity of PNP to variations in design, are described. Ways are suggested for developing contour plots of the sensitivity study data. Additional BUMPER analysis examples are provided, including FEMs, command inputs, and data outputs. The mathematical theory used as the basis for the code is described, and illustrates the data flow within the analysis.

Coronado, A. R.↗
NASA NTRS2013

Mobile Thread Task Manager

The Mobile Thread Task Manager (MTTM) is being applied to parallelizing existing flight software to understand the benefits and to develop new techniques and architectural concepts for adapting software to multicore architectures. It allocates and load-balances tasks for a group of threads that migrate across processors to improve cache performance. In order to balance-load across threads, the MTTM augments a basic map-reduce strategy to draw jobs from a global queue. In a multicore processor, memory may be "homed" to the cache of a specific processor and must be accessed from that processor. The MTTB architecture wraps access to data with thread management to move threads to the home processor for that data so that the computation follows the data in an attempt to avoid L2 cache misses. Cache homing is also handled by a memory manager that translates identifiers to processor IDs where the data will be homed (according to rules defined by the user). The user can also specify the number of threads and processors separately, which is important for tuning performance for different patterns of computation and memory access. MTTM efficiently processes tasks in parallel on a multiprocessor computer. It also provides an interface to make it easier to adapt existing software to a multiprocessor environment.

Clement, Bradley J.↗
DOE OSTI2019

Efficient Multiscale Optoelectronic Prediction for Conjugated Polymers

Conjugated polymers represent a high-potential material class due to the tunability of their optoelectronic properties via straightforward processing protocols. However, to in silico tailor these optoelectronic properties, one must compute the conformationally dependent electronic structure over mesoscopic length and time scales. This task represents a challenging multiscale computational problem in which quantum chemistry and atomistic or coarse-grained molecular dynamics must be integrated. Recently, we introduced a methodology, called electronic coarse graining (ECG), that utilizes artificial neural networks to compute ab initio quality electronic structures using only the reduced degrees of freedom of coarse-grained models. Here, we adapt ECG to variable-molecular weight conjugated oligomers by casting the problem in the framework of sequence detection. A machine-learning (ML) architecture employing one-dimensional convolutional neural networks and long short-term memory networks is utilized to compute ground-state orbital energies, charge density distributions, and optical spectra solely from the coarse-grained model's configurational degrees of freedom. Robust molecular weight transferability for ECG is established via a A-ML approach that leverages model electronic Hamiltonians for ground and excited-state property determination. The accuracy and transferability of the ECG methodology opens the door for scalable optoelectronic property prediction in conjugated polymers directly from coarse-grained degrees of freedom.

36 MATERIALS SCIENCE↗
DOE OSTI2020

JPype

JPype is a Python module to provide full access to Java from within Python. It allows Python to make use of Java only libraries, exploring and visualization of Java structures, development and testing of Java libraries, scientific computing, and much more. By gaining the best of both worlds using Python for rapid prototyping and Java for strong typed production code, JPype provides a powerful environment for engineering and code development. This is achieved not through re-implementing Python, as Jython has done, but rather through interfacing at the native level in both virtual machines. This shared memory based approach achieves decent computing performance, while providing the access to the entirety of CPython and Java libraries.

Nelson, KarlE.↗
NASA NTRS1984

The PDS-VAX intelligent plate scanning system of Trieste Astronomical Observatory

An intelligent subsystem for interfacing a PDS1010A digital microdensitometer to a DEC DR11W DMA 16 bit UNIBUS port in DEC VAX VMS environment was tested. The subsystem employs two MOTOROLA M68000 microprocessors with 128 KB data memory. The PDS primitives and the user defined high level scanning functions and preprocessing modules are loaded from the host computer into two 8 KB RAM memories in the microprocessors using a dedicated PDS control language. The subsystem is planned to employ a nonstandard photomultiplier electronics. Two design schemes were tested: (1) based on three amplifiers of gain 10 cascaded and multiplexed to a 12 bit AD converter, and (2) based on a single amplifier of gain 100 and two 14 bit AD converters.

Pucillo, M.↗
NASA NTRS1978

The IMSL environment for software development

The international mathematical and statistical library (IMSL) developed a set of macros and a file naming convention that automates the subroutine development and testing process over ten computer types. The IMSL software development system is implemented on a Data General Eclipse C330 computer with 256K bytes of central memory and 192M bytes of disk storage using the AOS Operating System. RJE activity is handled by a Data 100 communications computer. The system allows the programmer to work with basis decks. Distribution decks are generated, by the IMSL FORTRAN converter, as they are needed for testing and whenever the basis deck has been modified.

Aird, T. J.↗
DOE OSTI2020

Constructing a conforming Voronoi mesh for an arbitrarily-shaped enclosed geometric domain

A computing system is described herein, where the computing system includes a processor and memory storing instructions that, when executed by the processor, cause the processor to perform the following acts: 1) receiving a computer-implemented definition of an enclosed geometric domain, wherein the geometric domain is two-dimensional; 2) determining locations of seeds for the enclosed geometric domain; 3) decomposing the enclosed geometric domain into a conforming Voronoi mesh based on the locations of the seeds, wherein the conforming Voronoi mesh comprises Voronoi cells, and further wherein the conforming Voronoi mesh is bounded by the enclosed domain; and 4) performing a numerical simulation to generate simulation results, wherein the numerical simulation is based on at least one Voronoi cell in the Voronoi cells of the conforming Voronoi mesh.

97 MATHEMATICS AND COMPUTING↗