Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed 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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Distributed coherence directory subsystem with exclusive data regions

A processing system includes a first set of one or more processing units including a first processing unit, a second set of one or more processing units including a second processing unit, and a memory having an address space shared by the first and second sets. The processing system further includes a distributed coherence directory subsystem having a first coherence directory to support a first subset of one or more address regions of the address space and a second coherence directory to support a second subset of one or more address regions of the address space. In some implementations, the first coherence directory is implemented in the system so as to have a lower access latency for the first set, whereas the second coherence directory is implemented in the system so as to have a lower access latency for the second set.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Distributed coherence directory subsystem with exclusive data regions

A processing system includes a first set of one or more processing units including a first processing unit, a second set of one or more processing units including a second processing unit, and a memory having an address space shared by the first and second sets. The processing system further includes a distributed coherence directory subsystem having a first coherence directory to support a first subset of one or more address regions of the address space and a second coherence directory to support a second subset of one or more address regions of the address space. In some implementations, the first coherence directory is implemented in the system so as to have a lower access latency for the first set, whereas the second coherence directory is implemented in the system so as to have a lower access latency for the second set.

Eckert, Yasuko↗
DOE OSTI2021

Productive Programming of Distributed Systems with the SHAD C++ Library

High-performance computing (HPC) is often perceived as a matter of making large-scale systems (e.g., clusters) run as fast as possible, regardless the required programming effort. However, the idea of "bringing HPC to the masses" has recently emerged. Inspired by this vision, we have designed SHAD, the Scalable High-performance Algorithms and Data-structures library. SHAD is open source software, written in C++, for C++ developers. Unlike other HPC libraries for distributed systems, which rely on SPMD models, SHAD adopts a shared-memory programming abstraction, to make C++ programmers feel at home. Underneath, SHAD manages tasking and data-movements, moving the computation where data resides and taking advantage of asynchrony to tolerate network latency. At the bottom of his stack, SHAD can interface with multiple runtime systems: this not only improves developer’s productivity, by hiding the complexity of such software and of the underlying hardware, but also greatly enhance code portability. Thanks to its abstraction layers, SHAD can indeed target different systems, ranging from laptops to HPC clusters, without any need for modifying the user-level code. We have prototyped and open-sourced the implementation of (a subset of) the C++ standard library (STL) targeting multi-node HPC clusters. Our work allows plain STL-based C++ code to scale on HPC systems, with no need for rewriting the code to exploit the complex hardware. SHAD is available under Apache v2 License at https://github.com/pnnl/SHAD. In this paper we overview the design of the SHAD library, depicting its main components: runtime systems abstractions for tasking; parallel and distributed data-structures; STL-compliant interfaces and algorithms.

Castellana, Vito G.↗
DOE OSTI2021

Communication-Avoiding and Memory-Constrained Sparse Matrix-Matrix Multiplication at Extreme Scale

Sparse matrix-matrix multiplication (SpGEMM) is a widely used kernel in various graph, scientific computing and machine learning algorithms. In this paper, we consider SpGEMMs performed on hundreds of thousands of processors generating trillions of nonzeros in the output matrix. Distributed SpGEMM at this extreme scale faces two key challenges: (1) high communication cost and (2) inadequate memory to generate the output. Furthermore, we address these challenges with an integrated communication-avoiding and memory-constrained SpGEMM algorithm that scales to 262,144 cores (more than 1 million hardware threads) and can multiply sparse matrices of any size as long as inputs and a fraction of output fit in the aggregated memory. As we go from 16,384 cores to 262,144 cores on a Cray XC40 supercomputer, the new SpGEMM algorithm runs 10x faster when multiplying large-scale protein-similarity matrices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Numerically exact configuration interaction at quadrillion-determinant scale

The combinatorial growth of configuration interaction (CI) has long limited this formally exact quantum chemistry method to only the smallest molecules. Here, we report a numerically exact CI calculation exceeding one quadrillion (10 15 ) determinants, made possible by a lossless categorical compression strategy within the small-tensor-product distributed active space (STP-DAS) framework. This approach overcomes the traditional memory bottlenecks of CI by a numerically exact compression of the wavefunction representation and reformulating the most computationally demanding matrix–vector operations. Using this method, we performed a fully relativistic CI calculation of the ground state of HBrTe with over 10 15 complex-valued determinants in just 34.5 h on 1000 computing nodes—the largest CI calculation ever reported. We further achieved fast computation for systems with hundreds of billions of determinants on only a few compute nodes. Extensive benchmarks confirm that the method retains full numerical exactness while cutting memory and computational cost by orders of magnitude. Compared to previous state-of-the-art CI calculations, this work achieves a 1000 times increase in CI space, a 10 6 -fold increase in floating-point operations performed, and a 10 6 -fold improvement in computational speed.

Computational chemistry↗
DOE OSTI2022

Pressure-induced creation and annihilation of Weyl points in T d - Mo 0.5 W 0.5 Te 2 and 1 T " - Mo 0.5 W 0.5 Te 2

By means of first-principles density-functional theory calculations, we investigate the role of hydrostatic pressure in the electronic structure of the T d (Pmn2 1 ) and 1T" (Pm) phases of the Weyl semimetal Mo 0.5 W 0.5 Te 2 , which is a promising material for phase-change memory technology and superconductivity. We particularly focus on changes occurring in the distribution of the gapless Weyl points (WPs) within the 0 to 45 GPa pressure range. Here we further investigate the structural phase transition and lattice dynamics of the T d and 1T" phases within the aforementioned pressure range. Our calculations suggest that both the T d and 1T" phases of Mo 0.5 W 0.5 Te 2 host four WPs in their full Brillouin zone at zero pressure. The total number of WPs increases to 44 (36) with increasing pressure via pair creation up to 20 (15) GPa for the T d (1T") phase, and beyond this pressure pair annihilation of WPs starts occurring, leaving only 16 WPs at 45 GPa in both phases. The enthalpy versus pressure data reveal that the 1T" phase is more favorable below the critical pressure of 7.5 GPa; however, beyond this critical pressure the T d phase becomes enthalpically favorable. We also provide the calculated x-ray diffraction spectra along with the calculated Raman- and infrared-active phonon frequencies to facilitate the experimental identification of the studied phases

36 MATERIALS SCIENCE↗
DOE OSTI2024

Distributed Order Recording Techniques for Efficient Record-and-Replay of Multi-threaded Programs

After all these years and all these other shared memory programming frameworks, OpenMP is still the most popular one. However, its greater levels of non-deterministic execution makes debugging and testing more challenging. The ability to record and deterministically replay the program execution is key to address this challenge. However, scalably replaying OpenMP programs is still an unresolved problem. In this paper, we propose two novel techniques that use Distributed Clock (DC) and Distributed Epoch (DE) recording schemes to eliminate excessive thread synchronization for OpenMP record and replay. Our evaluation on representative HPC applications with ReOMP, which we used to realize DC and DE recording, shows that our approach is 2-5x more efficient than traditional approaches that synchronize on every shared-memory access. Furthermore, we demonstrate that our approach can be easily combined with MPI-level replay tools to replay non-trivial MPI+OpenMP applications. We achieve this by integrating ReOMP into ReMPI, an existing scalable MPI record-and-replay tool, with only a small MPI-scale-independent runtime overhead.

Fu, Xiang↗
DOE OSTI2021

GPU-based Image Compression for Efficient Compositing in Distributed Rendering Applications

Visualizations of large-scale data sets are often created on graphics clusters that distribute the rendering task amongst many processes. When using real-time GPU-based graphics algorithms, the most time-consuming aspect of distributed rendering is typically the com-positing phase - combining all partial images from each rendering process into the final visualization. Compo siting requires image data to be copied off the GPU and sent over a network to other processes. While compression has been utilized in existing distributed rendering compositors to reduce the data being sent over the network, this compression tends to occur after the raw images are transferred from the GPU to main memory. In this paper, we present work that leverages OpenGL / CUDA interoperability to compress raw images on the GPU prior to transferring the data to main memory. This approach can significantly reduce the device-to-host data transfer time, thus enabling more efficient compositing of images generated by distributed rendering applications.

Lipinksi, Riley↗
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

Deep Learning Reconstruction of Daily Soil CO 2 Efflux Reveals Biogeochemical Insights and Reduces Annual Estimate Uncertainty Despite Limited Daily Predictability

Soil CO 2 efflux is commonly measured monthly or seasonally, leaving daily dynamics poorly resolved and contributing to global estimation uncertainty. We trained a single Long Short-Term Memory (LSTM) model to predict daily soil CO 2 efflux across 82 globally distributed sites in COSORE, with 0.2%–46.9% daily data coverage from 2003 to 2020. Despite using far fewer sites than are typically used to train a single deep learning model, with observations biased toward temperate mesic sites, the LSTM model performed well at approximately one-third of sites, reconstructed nearly 2 decades of daily efflux, and outperformed commonly used approaches for estimating daily efflux when applied to the same data set. Performance was weakest at pronounced peaks and troughs and at non-temperate sites with <1.5 years of observations and irregular data patterns. Nevertheless, annual efflux from reconstructed daily data had <40% error even at underperforming sites, substantially improving estimates derived from monthly and seasonal sampling (maximum errors of 95% and 136%, respectively). Temperature sensitivity (Q 10 ) estimated from reconstructed daily predictions closely matched estimates from daily observations, whereas Q 10 values derived from monthly or seasonal observations deviated substantially, suggesting that coarse temporal sampling may contribute to uncertainty in reported Q 10 values. Consistent daily reconstructions further enabled trend analyses for well-performing, predominantly temperate sites and showed increasing soil CO 2 efflux at most sites from 2003 to 2020, with more variable summer trends. Despite limitations, these results demonstrate the potential of LSTM models to reconstruct daily soil CO 2 efflux and reduce estimation uncertainties from sparse observations.

Smykalov, Valerie [Pennsylvania State University, ↗
DOE OSTI2022

Development of a phonon-based sampling method for thermal neutron scattering data

Simulations of reactor systems require access to accurate nuclear data. For many systems, thermal neutron scattering data can have large effects on the eigenvalue and neutron flux distributions. Inelastic thermal neutron scattering can excite or de-excite vibrational, rotational, and translational modes in a material, so thermal scattering evaluations are often obtained by summing over the number of phonons created/destroyed by a scattering event. In recent years, the thermal scattering cross sections and angular distributions have greatly improved in accuracy, but the format in which this data is delivered to simulation codes has remained virtually unchanged. Thermal scattering data is typically either compiled into large tables and sorted by incoming neutron energy, outgoing neutron energy, scattering angle, and material temperature, or represented as cumulative distribution functions of momentum exchange or energy exchange. Either method can be quite memory intensive when fine bins are used. In an effort to decrease the amount of space that processed thermal scattering data requires, an alternate format is proposed. The phonon-based sampling method introduced here can sample the number of phonons excited for each collision, the change in neutron energy, and the scattering angle while avoiding pre-computed angular bins and limiting the amount of data that is dependent on incoming energy. Through this method, the generation and storage of large interpolation tables is avoided, which could have benefits in both memory storage and accuracy. While the initial implementation of this method is slower than current alternatives, it is significantly more resistant to grid coarseness errors and has good potential for improvement. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Operator learning for predicting multiscale bubble growth dynamics

We report simulating and predicting multiscale problems that couple multiple physics and dynamics across many orders of spatiotemporal scales is a great challenge that has not been investigated systematically by deep neural networks (DNNs). Herein, we develop a framework based on operator regression, the so-called deep operator network (DeepONet), with the long-term objective to simplify multiscale modeling by avoiding the fragile and time-consuming “hand-shaking” interface algorithms for stitching together heterogeneous descriptions of multiscale phenomena. To this end, as a first step, we investigate if a DeepONet can learn the dynamics of different scale regimes, one at the deterministic macroscale and the other at the stochastic microscale regime with inherent thermal fluctuations. Specifically, we test the effectiveness and accuracy of the DeepONet in predicting multirate bubble growth dynamics, which is described by a Rayleigh–Plesset (R–P) equation at the macroscale and modeled as a stochastic nucleation and cavitation process at the microscale by dissipative particle dynamics (DPD). First, we generate data using the R–P equation for multirate bubble growth dynamics caused by randomly time-varying liquid pressures drawn from Gaussian random fields (GRFs). Our results show that properly trained DeepONets can accurately predict the macroscale bubble growth dynamics and can outperform long short-term memory networks. We also demonstrate that the DeepONet can extrapolate accurately outside the input distribution using only very few new measurements. Subsequently, we train the DeepONet with DPD data corresponding to stochastic bubble growth dynamics. Although the DPD data are noisy and we only collect sparse data points on the trajectories, the trained DeepONet model is able to predict accurately the mean bubble dynamics for time-varying GRF pressures. Taken together, our findings demonstrate that DeepONets can be employed to unify the macroscale and microscale models of the multirate bubble growth problem, hence providing new insight into the role of operator regression via DNNs in tackling realistic multiscale problems and in simplifying modeling with heterogeneous descriptions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Short-Term Forecasting of Thermostatic and Residential Loads Using Long Short-Term Memory Recurrent Neural Networks

Internet of Things (IoT) devices in smart grids enable intelligent energy management for grid managers and personalized energy services for consumers. Investigating a smart grid with IoT devices requires a simulation framework with IoT devices modeling. However, there lack comprehensive study on the modeling of IoT devices in smart grids. This paper investigates the IoT device modeling of a thermostatic load and implements the recurrent neural networks model for short-term load forecasting in this IoT-based thermostatic load. The recurrent neural network structure is leveraged to build a load forecasting model on temporal correlation. The temporal recurrent neural network layers including long short-term memory cells are employed to learn the data from both the simulation platform and New South Wales residential datasets. The simulation results are provided for demonstration.

electric load forecasting↗
DOE OSTI2023

Switching current reduction in magnetoresistive random access memories

We present an approach for minimizing the critical current for the magnetization switching in magnetic tunnel junctions by optimizing the spatial distribution of the current density. We show that such a minimization is possible because critical current is determined by the condition of making one of the magnetization eigenstates grow in time. The excitation of the eigenstates is enhanced when the spatial distributions of the eigenstates and current density overlap. Critical current can be viewed as a functional of the current density spatial distribution and it can be minimized by optimizing this distribution. Such an optimization results in a major reduction of the critical current and increase of the switching efficiency, viz. the ratio between the energy barrier and critical current. The minimized critical current increases approximately linearly with the magnetic tunnel junction size, which is much slower than critical current for the case of a uniform current density. The optimized efficiency can be approximately a constant with respect to the magnetic tunnel junction size, which is much higher than the efficiency for the uniform current density. Additional optimization can be achieved by spatially modulating the material parameters, e.g., the saturation magnetization. The presented approach and obtained scaling of the critical current and efficiency offers opportunities for the magnetic tunnel junction optimization.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Variational data augmentation for a learning-based granular predictive model of power outages

As the trend in climate change continues, extreme weather events are expected to occur with increasing frequency and severity and pose a significant threat to the electric power infrastructure. Regardless of the efforts a utility puts towards hardening the grid, storm-induced damage to the utility assets such as cables and distributed energy resources (DERs) that are particularly vulnerable to such events is unavoidable. Access to a highly granular, in space and time, outage forecasting tool with long lead times (i.e., days ahead) will enhance the efficiency of service restoration efforts. Here, in this study, we propose to develop and implement a multi-model framework as an operational tool based on a granular and multi-day outage forecasting model using operational numerical weather prediction model forecasts and detailed component outage information. An innovative two-layered recurrent neural network, i.e., a long-short-term-memory (LSTM)-based variational autoencoder (VAE) framework and a sliding window are used to address the uneven distribution of different types of weather events and make better use of the time-series data. Case studies are performed to demonstrate the performance of the new framework.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Texture Memory in Hexagonal Metals and Its Mechanism

Texture memory is a phenomenon in which retention of initial textures occurs after a complete cycle of forward and backward transformations, and it occurs in various phase-transforming materials including cubic and hexagonal metals such as steels and Ti and Zr alloys. Texture memory is known to be caused by the phenomena called variant selection, in which some of the allowed child orientations in an orientation relationship between the parent and child phases are preferentially selected. Without such variant selection, the phase transformations would randomize preferred orientations. In this article, the methods of prediction of texture memory and mechanisms of variant selections in hexagonal metals are explored. The prediction method using harmonic expansion of orientation distribution functions with the variant selection in which the Burgers orientation relationship, {110}β//{0001} α-hex <1$\bar{1}$1>β//$\langle2\bar{11}0\rangle$ α-hex , is held with two or more adjacent parent grains at the same time, called “double Burgers orientation relation (DBOR)”, is introduced. This method is shown to be a powerful tool by which to analyze texture memory and ultimately provide predictive capabilities for texture changes during phase transformations. Variation in nucleation and growth rates on special boundaries and an extensive growth of selected variants are also described. Analysis of textures of commercially pure Ti observed in situ by pulsed neutron diffraction reveals that the texture memory in CP-Ti is indeed quite well predicted by consideration of the mechanism of DBOR. The analysis also suggests that the nucleation and growth rates on the special boundary of 90° rotation about $\langle2\bar{11}0\rangle$ α-hex should be about three times larger than those of the other special boundaries, and the selected variants should grow extensively into not only one parent grain but also other grains in α-hex(hexagonal)→β(bcc) transformation. The model calculations of texture development during two consecutive cycles of α-hex→β→α-hex transformation in CP-Ti and Zr are also shown.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Object Proxy Patterns for Accelerating Distributed Applications

Workflow and serverless frameworks have empowered new approaches to distributed application design by abstracting compute resources. However, their typically limited or one-size-fits-all support for advanced data flow patterns leaves optimization to the application programmer—optimization that becomes more difficult as data become larger. The transparent object proxy, which provides wide-area references that can resolve to data regardless of location, has been demonstrated as an effective low-level building block in such situations. Here we propose three high-level proxy-based programming patterns—distributed futures, streaming, and ownership—that make the power of the proxy pattern usable for more complex and dynamic distributed program structures. We motivate these patterns via careful review of application requirements and describe implementations of each pattern. As a result, we evaluate our implementations through a suite of benchmarks and by applying them in three meaningful scientific applications, in which we demonstrate substantial improvements in runtime, throughput, and memory usage.

Distributed Computing↗