Search NASA⌕ Search

SEARCH · Search NASA

Results for “avoiding communication”

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 73 records · Page 4

Parallel multiple-chain DRAM MCMC for large-scale geosteering inversion and uncertainty quantification

Geosteering is the proactive control of a wellbore placement based on the downhole measurements, aiming at maximizing economic production from the well. We report the recent development of azimuthal resistivity logging-whiledrilling (LWD) tools have a much larger depth of detection, thus sets higher demands for geosteering inversion as more unknown parameters need to be taken into account in the earth model to be inverted. For complicated nonlinear problems, traditional deterministic inversion methods are more likely to be trapped near local optima. In general, Markov chain Monte Carlo (MCMC) inversion methods are more capable of finding the global optimal solution and providing additional uncertainty analyses by sampling from the target distribution. However, MCMC methods usually have the problem of slow convergence. Even though optimization methods like delayed rejection (DR) and adaptive Metropolis (AM) were proposed to speed up the convergence, using MCMC methods to solve geosteering inversion problems may still incur unacceptable time cost. To reduce the sampling cost of MCMC methods, we use parallel multiple-chain DRAM MCMC methods to solve geosteering inverse problems and estimate the corresponding uncertainty. A clustering method, density-based spatial clustering of applications with noise (DBSCAN), is applied to select the best solution among many results. Lastly, the simulation results show that running many relatively short MCMC chains for one problem can obtain a similar result as running a long single chain. Besides, avoiding communications between multiple Markov chains during the sampling process yields almost linear scalability.

97 MATHEMATICS AND COMPUTING↗

Distributed-Memory Parallel JointNMF

Joint Nonnegative Matrix Factorization (JointNMF) is a hybrid method for mining information from datasets that contain both feature and connection information. We propose distributed-memory parallelizations of three algorithms for solving the JointNMF problem based on Alternating Nonnegative Least Squares, Projected Gradient Descent, and Projected Gauss-Newton. We extend well-known communication-avoiding algorithms using a single processor grid case to our coupled case on two processor grids. We demonstrate the scalability of the algorithms on up to 960 cores (40 nodes) with 60% parallel efficiency. The more sophisticated Alternating Nonnegative Least Squares (ANLS) and Gauss-Newton variants outperform the first-order gradient descent method in reducing the objective on large-scale problems. We perform a topic modelling task on a large corpus of academic papers that consists of over 37 million paper abstracts and nearly a billion citation relationships, demonstrating the utility and scalability of the methods.

Eswar, Srinivas↗

ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads

The Message Passing Interface (MPI) standard plays a crucial role in enabling scientific applications for parallel computing and is an essential component in high-performance computing (HPC). However, implementing MPI code manually—especially applying a proper domain decomposition and communication pattern—is a challenging and error-prone task. We present ChatMPI, an AI assistant for MPI parallelization of sequential C codes. In our analysis, we focus on testing six essential HPC workloads, which are based on Basic Linear Algebra Subprograms levels 1, 2, and 3 as well as sparse, stencil, and iterative operations. We analyze the process of creating ChatMPI by using the ChatHPC library. This lightweight large language model (LLM)–based infrastructure enables HPC experts to efficiently create and supervise trustworthy AI capabilities for critical HPC software tasks. We study the data required for training (fine-tuning) ChatMPI to generate parallel codes that not only use MPI syntax correctly but also apply HPC techniques to reduce memory communication and maximize performance by using proper work decomposition. With a relatively small training dataset composed of a few dozen prompts and fewer than 15 minutes of fine-tuning on one node equipped with two NVIDIA H100 GPUs, ChatMPI elevates trustworthiness for MPI code generation of current LLMs (e.g., Code Llama, ChatGPT-4o and ChatGPT 5). Additionally, we evaluate the performance of the MPI codes generated by ChatMPI in comparison with the ones generated by ChatGPT-4o and ChatGPT-5. The codes generated by ChatMPI provide up to a 4 × boost in performance by using better problem decomposition, communication patterns, and HPC techniques (e.g., communication avoiding).

Valero Lara, Pedro [ORNL] (ORCID:0000000214794310)↗

Evolution of the SLATE linear algebra library

SLATE (Software for Linear Algebra Targeting Exascale) is a distributed, dense linear algebra library targeting both CPU-only and GPU-accelerated systems, developed over the course of the Exascale Computing Project (ECP). While it began with several documents setting out its initial design, significant design changes occurred throughout its development. In some cases, these were anticipated: an early version used a simple consistency flag that was later replaced with a full-featured consistency protocol. In other cases, performance limitations and software and hardware changes prompted a redesign. Sequential communication tasks were parallelized; host-to-host MPI calls were replaced with GPU device-to-device MPI calls; more advanced algorithms such as Communication Avoiding LU and the Random Butterfly Transform (RBT) were introduced. Early choices that turned out to be cumbersome, error prone, or inflexible have been replaced with simpler, more intuitive, or more flexible designs. Applications have been a driving force, prompting a lighter weight queue class, nonuniform tile sizes, and more flexible MPI process grids. Of paramount importance has been building a portable library that works across several different GPU architectures – AMD, Intel, and NVIDIA – while keeping a clean and maintainable codebase. Here we explore the evolving design choices and their effects, both in terms of performance and software sustainability.

Gates, Mark↗

Simulated Half-Precision Implementation of Blocked QR Factorization and Graph Clustering Applications

We explored half-precision implementation of blocked QR algorithms with the following motivations: 1. New GPUs perform fast half-precision arithmetic (4 to 16 times as fast as doubleprecision). 2. QR factorization is a basic linear algebra tool useful for many physics and data analysis applications. 3. Communication-avoiding, parallelizable QR algorithms already exist for talland- skinny matrices. While the standard QR algorithms are highly unstable in half-precision, our numerical simulations show that the Tall-and-Skinny QR (TSQR) algorithm can improve the backward error of QR factorization. When using subspace iteration for graph clustering applications, half-precision accuracy in forming the eigenspace is sufficient for clustering with high precision and recall for some medium-scale benchmark problems. Note that all half-precision arithmetic were simulated with conversions to single-precision floats. Therefore, the results from this work are somewhat optimistic.

97 MATHEMATICS AND COMPUTING↗

The fusion code XGC: Enabling kinetic study of multi-scale edge turbulent transport in ITER [Book Chapter]

The XGC fusion gyrokinetic code combines state-of-the-art, portable computational and algorithmic technologies to enable complicated multiscale simulations of turbulence and transport dynamics in ITER edge plasma on the largest US open-science computer, the CRAY XK7 Titan, at its maximal heterogeneous capability, which have not been possible before due to a factor of over 10 shortage in the time-to-solution for less than 5 days of wall-clock time for one physics case. Frontier techniques such as nested OpenMP parallelism, adaptive parallel I/O, staging I/O and data reduction using dynamic and asynchronous applications interactions, dynamic repartitioning for balancing computational work in pushing particles and in grid related work, scalable and accurate discretization algorithms for non-linear Coulomb collisions, and communication-avoiding subcycling technology for pushing particles on both CPUs and GPUs are also utilized to dramatically improve the scalability and time-to-solution, hence enabling the difficult kinetic ITER edge simulation on a present-day leadership class computer.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Multi-agent motion planning with sporadic communications for collision avoidance

Here, a novel multi-vehicle motion planning and collision avoidance algorithm is proposed and analyzed. The algorithm aims to reduce the amount of onboard calculations and inter-agent communications needed for each vehicle to successfully navigate through an environment with static obstacles and reach their goals. To this end, each agent first calculates a path to the goal by means of an asymptotically optimal rapidly-exploring random tree (RRT*) with respect to the static obstacles. Then, other agents are treated as dynamic obstacles and potential collisions are determined by means of collision cones. Collision cones depend on the position and velocity from other agents and are grown conservatively between inter-agent communications. Based on the available information, each agent determines if a deconfliction maneuver is needed, if it can continue along its current path, or if communication is needed to make a decision about a conflict. With probability one, our algorithm guarantees that the agents keep from colliding with each other. Under an assumption on the existence of a solution for a vehicle to its goal, this algorithm also solves the planning problem with probability one. Simulations illustrate a group of agents successfully reaching their goal configurations and examine how the uncertainty affects the communication frequency of the multi-agent system.

33 ADVANCED PROPULSION SYSTEMS↗

Drone Video Platform—Collision Avoidance, Situational Awareness, and Communications STL-039-17, Year 2 of 2

At the beginning of FY 2018, the collision avoidance task of this project was dropped because it had become a “commercial off-the-shelf” product for rotary drones, but it was still considered a very difficult problem for fixed wing drones. In the second quarter of FY 2018, R. Trainham took over the project and decided to redirect efforts into testing a variety of sensors on a variety of platforms. The core module task was also dropped from the project because it duplicated what was already available commercially. Since last year’s SDRD final review, we have conducted flight tests in Idaho, Montana, Nevada, and Wisconsin. We have flown five different gamma detectors, a chemical detector and sampler, an optical spectrometer, and a point LIDAR on quadcopters, hexcopters, and the fixed wing T-28 and Sandstorm. We have collaborated with H3D, USI, Virginia Tech, and ORNL. In the coming year, we will continue those collaborations, and will add BYU and INL as collaborators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Drone Video Platform--Collision Avoidance, Situational Awareness, and Communications, STL-039-17, Year 1 of 2

This presentation discusses how unmanned aerial systems (UASs) operating in consequence management scenarios can obtain and transmit critical information on various hazards and inform real-time decision making while reducing risks to first responders. The presentation addresses a project using a Sandstorm UAS, a fixed-wing development platform that, although it can enable longer travel and operational times, is subject to maneuverability limitations that complicate the collision avoidance required to avoid post-disaster hazards. A modular situational awareness and communications infrastructure is required to support autonomous UAS mission needs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Reducing Communication in Graph Neural Network Training

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus higher communication costs compared to dense matrices, making GNNs harder to scale to high concurrencies than convolutional or fully-connected neural networks. Here, we introduce a family of parallel algorithms for training GNNs and show that they can asymptotically reduce communication compared to previous parallel GNN training methods. We implement these algorithms, which are based on 1D, 1. 5D, 2D, and 3D sparse-dense matrix multiplication, using torch.distributed on GPU-equipped clusters. Our algorithms optimize communication across the full GNN training pipeline. We train GNNs on over a hundred GPUs on multiple datasets, including a protein network with over a billion edges.

97 MATHEMATICS AND COMPUTING↗

Drone Video Platform—Collision Avoidance, Situational Awareness, and Communications

Small unmanned aerial systems are ideal for delivering sensors into areas that are inaccessible or too dangerous for human entry or manned aircraft over-flights. The systems can fly low and slow for enhanced sensitivity and in tight spaces where ordinary aircraft could never fit. We have configured and flown sensor payloads for radiation, chemical, and optical detection on small fixed-wing and rotary-wing aircraft. All the sensor packages provide telemetry, GPS coordinates, LIDAR distance ranging, and absolute time of day to microsecond accuracy. Payload weights range from less than 1 kg up to 5.5 kg. Currently, communications are over 2.4 GHz and 915 MHz radios, as well as over 4G LTE cellular data links. Real-time data feeds from the sensor payloads to web browser clients anywhere in the world are possible via a virtual EC2 server on the Amazon AWS cloud. In FY 2019, the Nevada National Security Site teamed with Virginia Tech, H3D Corp., and Unmanned Systems, Inc. to accomplish the four flight missions described in this report. A large part of this year’s mission goals were to demonstrate the ability to fly beyond visual line of sight (BVLOS).

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Channel hopping method of interference avoidance for a wireless communication network and wireless communication system employing the same

A wireless communication system includes a wireless master node having a plurality of channels, and a number of wireless slave nodes having a plurality of the channels. The master node and the slave nodes are structured to wirelessly communicate over a particular channel. The master node and the slave nodes are structured to decide to hop to a different channel. The master node and the slave nodes are structured to select: (a) the different channel, in order to be as far away as possible from a number of the channels, which are known to cause interference to wireless communications between the master node and the slave nodes, or (b) the different channel, in order to be as close as possible to one of the channels of a different master node, which is compatible with the former master node, but without the different channel being employed by the different master node.

42 ENGINEERING↗

Scalable Nonlinear Compact Schemes

In this work, we focus on compact schemes resulting in tridiagonal systems of equations, specifically the fifth-order CRWENO scheme. We propose a scalable implementation of the nonlinear compact schemes by implementing a parallel tridiagonal solver based on the partitioning/substructuring approach. We use an iterative solver for the reduced system of equations; however, we solve this system to machine zero accuracy to ensure that no parallelization errors are introduced. It is possible to achieve machine-zero convergence with few iterations because of the diagonal dominance of the system. The number of iterations is specified a priori instead of a norm-based exit criterion, and collective communications are avoided. The overall algorithm thus involves only point-to-point communication between neighboring processors. Our implementation of the tridiagonal solver differs from and avoids the drawbacks of past efforts in the following ways: it introduces no parallelization-related approximations (multiprocessor solutions are exactly identical to uniprocessor ones), it involves minimal communication, the mathematical complexity is similar to that of the Thomas algorithm on a single processor, and it does not require any communication and computation scheduling.

97 MATHEMATICS AND COMPUTING↗

The Metropolis Monte Carlo method with CUDA enabled Graphic Processing Units

We present a CPU–GPU system for runtime acceleration of large molecular simulations using GPU computation and memory swaps. The memory architecture of the GPU can be used both as container for simulation data stored on the graphics card and as floating-point code target, providing an effective means for the manipulation of atomistic or molecular data on the GPU. To fully take advantage of this mechanism, efficient GPU realizations of algorithms used to perform atomistic and molecular simulations are essential. Our system implements a versatile molecular engine, including inter-molecule interactions and orientational variables for performing the Metropolis Monte Carlo (MMC) algorithm, which is one type of Markov chain Monte Carlo. By combining memory objects with floating-point code fragments we have implemented an MMC parallel engine that entirely avoids the communication time of molecular data at runtime. Our runtime acceleration system is a forerunner of a new class of CPU–GPU algorithms exploiting memory concepts combined with threading for avoiding bus bandwidth and communication. The testbed molecular system used here is a condensed phase system of oligopyrrole chains. A benchmark shows a size scaling speedup of 60 for systems with 210,000 pyrrole monomers. Our implementation can easily be combined with MPI to connect in parallel several CPU–GPU duets. -- Highlights: •We parallelize the Metropolis Monte Carlo (MMC) algorithm on one CPU—GPU duet. •The Adaptive Tempering Monte Carlo employs MMC and profits from this CPU—GPU implementation. •Our benchmark shows a size scaling-up speedup of 62 for systems with 225,000 particles. •The testbed involves a polymeric system of oligopyrroles in the condensed phase. •The CPU—GPU parallelization includes dipole—dipole and Mie—Jones classic potentials.

97 MATHEMATICS AND COMPUTING↗

A Large-Scale Analysis to Optimize the Control and V2V Communication Protocols for CDA Agreement-Seeking Cooperation

Cooperative driving automation (CDA) Class C, agreement-seeking cooperation, is an innovative and practical solution that can promote cooperation among general passenger vehicles on the road. However, more comprehensive studies are needed before establishing the standard protocols of agreement-seeking cooperation, such as communication frequency and the duration of cooperation. Here, this article presents an initiative study on the impacts of communication capabilities on agreement-seeking cooperation. Through a large-scale analysis by regulating vehicle-to-vehicle (V2V) communication metrics, this work suggests desirable system parameters that can maximize the benefits of cooperation and ensure reliable operability while avoiding exhaustive communication loads. As the first step, an example agreement-seeking cooperation system is created for a car-following scenario, including decision-making and control algorithms for autonomous vehicles. Then, software-in-the-loop tests explore the performance of the developed system as it encounters various communication risks, such as latency and message packet drops. The system performance metrics are evaluated from various angles, including the time consumed for the agreement-seeking process, cooperation ratio, and the ratio of faulty cooperation. Energy saving from the cooperation is assessed by using simulation software that can run multiple high-fidelity vehicle models simultaneously. Based on the analyses, this article suggests the V2V communication requirements for the reliable operation of CDA agreement-seeking, which can be referred to when developing the standard protocols of agreement-seeking cooperation.

42 ENGINEERING↗

A Scalable O(N) Algorithm for Large-Scale Parallel First-Principles Molecular Dynamics Simulations

Traditional algorithms for first-principles molecular dynamics (FPMD) simulations only gain a modest capability increase from current petascale computers, due to their O(N 3 ) complexity and their heavy use of global communications. To address this issue, we are developing a truly scalable O(N) complexity FPMD algorithm, based on density functional theory (DFT), which avoids global communications. The computational model uses a general nonorthogonal orbital formulation for the DFT energy functional, which requires knowledge of selected elements of the inverse of the associated overlap matrix. We present a scalable algorithm for approximately computing selected entries of the inverse of the overlap matrix, based on an approximate inverse technique, by inverting local blocks corresponding to principal submatrices of the global overlap matrix. The new FPMD algorithm exploits sparsity and uses nearest neighbor communication to provide a computational scheme capable of extreme scalability. Accuracy is controlled by the mesh spacing of the finite difference discretization, the size of the localization regions in which the electronic orbitals are confined, and a cutoff beyond which the entries of the overlap matrix can be omitted when computing selected entries of its inverse. We demonstrate the algorithm's excellent parallel scaling for up to O(100K) atoms on O(100K) processors, with a wall-clock time of O(1) minute per molecular dynamics time step.

36 MATERIALS SCIENCE↗

Leveraging Intelligent Vehicle Technologies to Maximize Fuel Economy (Presentation)

Advancements in vehicle electronics, along with communication and sensing technologies, have led to a growing number of intelligent vehicle applications. Example systems include those for advanced driver information, route planning and prediction, driver assistance, and crash avoidance. The National Renewable Energy Laboratory is exploring ways to leverage intelligent vehicle systems to achievefuel savings. This presentation discusses several potential applications, such as providing intelligent feedback to drivers on specific ways to improve their driving efficiency, and using information about upcoming driving to optimize electrified vehicle control strategies for maximum energy efficiency and battery life. The talk also covers the potential of Advanced Driver Assistance Systems(ADAS) and related technologies to deliver significant fuel savings in addition to providing safety and convenience benefits.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Fault Resilient Domain Decomposition Preconditioner for PDEs

The move towards extreme-scale computing platforms challenges scientific simulations in many ways. Given the recent tendencies in computer architecture development, one needs to reformulate legacy codes in order to cope with large amounts of communication, system faults and requirements of low-memory usage per core. In this work, we develop a novel framework for solving partial differential equations (PDEs) via domain decomposition that reformulates the solution as a state-of-knowledge with a probabilistic interpretation. Such reformulation allows resiliency with respect to potential faults without having to apply fault detection, avoids unnecessary communication and is generally well-positioned for rigorous uncertainty quantification studies that target improvements of predictive fidelity of scientific models. We demonstrate our algorithm for one-dimensional PDE examples where artificial faults have been implemented as bit-flips in the binary representation of subdomain solutions.

97 MATHEMATICS AND COMPUTING↗