Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “communication and synchronization reducing”

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
DOE OSTI2021

xSDK: Building an ecosystem of highly efficient math libraries for exascale

Current efforts to build increasingly powerful computer architectures are opening up new avenues for more complex and higher fidelity simulations coupled with data analytics and learning, leading to new scientific insights and deeper understanding. At one extreme, exascale computers will be much faster than previous computer generations (performing 10 18 operations per second—that is, 1,000 times faster than petascale). To achieve these performance improvements, computer architectures are becoming increasingly complex, with deep memory hierarchies, very high node and core counts, and heterogeneous features such as graphics processing units (GPUs). Such architectural changes impact the full breadth of computing scales, as heterogeneity pervades even current-generation laptops, workstations, and moderate-sized clusters. While emerging advanced architectures provide unprecedented opportunities, they also present significant challenges for developers of scientific applications, such as multiphysics and multiscale codes, who must adapt their software to handle disruptive changes in architectures and new programming models that have not yet stabilized. Developers must consider increasing concurrency while reducing communication and synchronization, and other complexities such as the potential for using mixed precision to leverage the compute power available in low-precision tensor cores. On one hand, developers must implement new scientific capabilities, which in turn increase code complexity. On the other hand, the codes must be ported to new architectures, requiring the inclusion of new programming models and the restructuring of code to achieve good performance. Addressing these issues is beyond the capability of any single person or team—leading to the need for collaboration among many teams, who encapsulate their expertise in reusable software and work together to create sustainable software ecosystems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Designing a parallel Feel-the-Way clustering algorithm on HPC systems

This paper introduces a new parallel clustering algorithm, named Feel-the-Way clustering algorithm, that provides better or equivalent convergence rate than the traditional clustering methods by optimizing the synchronization and communication costs. Our algorithm design centers on how to optimize three factors simultaneously: reduced synchronizations, improved convergence rate, and retained same or comparable optimization cost. To compare the optimization cost, we use the Sum of Square Error (SSE) cost as the metric, which is the sum of the square distance between each data point and its assigned clusters. Compared with the traditional MPI k-means algorithm, the new Feel-the-Way algorithm requires less communications among participating processes. As for the convergence rate, the new algorithm requires fewer number of iterations to converge. As for the optimization cost, it obtains the SSE costs that are close to the k-means algorithm. In the paper, we first design the full-step Feel-the-Way k-means clustering algorithm that can significantly reduce the number of iterations that are required by the original k-means clustering method. Next, we improve the performance of the full-step algorithm by adopting an optimized sampling-based approach, named reassignment-history-aware sampling. Our experimental results show that the optimized sampling-based Feel-the-Way method is significantly faster than the widely used k-means clustering method, and can provide comparable optimization costs. More extensive experiments with several synthetic datasets and real-world datasets (e.g., MNIST, CIFAR-10, ENRON, and PLACES-2) show that the new parallel algorithm can outperform the open source MPI k-means library by up to 110% on a high-performance computing system using 4,096 CPU cores. In addition, the new algorithm can take up to 51% fewer iterations to converge than the k-means clustering algorithm.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Lion Cub: Minimizing Communication Overhead in Distributed Lion

Communication overhead is a key challenge in distributed deep learning, especially on slower Ethernet intercon nects, and given current hardware trends, communication is likely to become a major bottleneck. While gradient compression techniques have been explored for SGD and Adam, the Lion optimizer has the distinct advantage that its update vectors are the output of a sign operation, enabling straightforward quantization. However, simply compressing updates for communication and using techniques like majority voting fails to lead to end-to-end speedups due to inefficient communication algorithms and reduced convergence. We analyze three factors critical to distributed learning with Lion: optimizing communication methods, identifying effective quantization methods, and assessing the necessity of momentum synchronization. Our findings show that quantization techniques adapted to Lion and selective momentum synchronization can significantly reduce communication costs while maintaining convergence. We combine these into Lion Cub, which enables up to 5x speedups in end-to-end training compared to Lion. This highlights Lion’s potential as a communication-efficient solution for distributed training.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Optimization of Asynchronous Communication Operations through Eager Notifications

UPC++ is a C++ library implementing the Asynchronous Partitioned Global Address Space (APGAS) model. We propose an enhancement to the completion mechanisms of UPC++ used to synchronize communication operations that is designed to reduce overhead for on-node operations. Our enhancement permits eager delivery of completion notification in cases where the data transfer semantics of an operation happen to complete synchronously, for example due to the use of shared-memory bypass. This semantic relaxation allows removing significant overhead from the critical path of the implementation in such cases. We evaluate our results on three different representative systems using a combination of microbenchmarks and five variations of the the HPCChallenge RandomAccess benchmark implemented in UPC++ and run on a single node to accentuate the impact of locality. We find that in RMA versions of the benchmark written in a straightforward manner (without manually optimizing for locality), the new eager notification mode can provide up to a 25% speedup when synchronizing with promises and up to a 13.5x speedup when synchronizing with conjoined futures. We also evaluate our results using a graph matching application written with UPC++ RMA communication, where we measure overall speedups of as much as 11% in single-node runs of the unmodified application code, due to our transparent enhancements.

Kamil, Amir↗
DOE OSTI2026

torch-einshard v1.0

torch-einshard is a Python library for describing local and distributed PyTorch tensor computations with compact, einsum-like notation. Its expressions name logical axes, specify how they are sharded across a PyTorch DeviceMesh, and represent partial reductions. The library automatically performs contractions, permutations, reshaping, splitting, gathering, reduction, reduce-scatter, and repartitioning while preserving autograd. Additional features include sharding-aware FFTs, tensor rolls, halo exchange, sliding windows, 1D–3D convolutions, uneven-shard handling, parameter initialization and gradient management, and cost-based execution planning. It is designed for scientific machine learning and large-model workloads, including tensor-, sequence-, and spatial-parallel MLPs, attention, convolutions, and spectral operations. Compared with manually combining torch.einsum and distributed collectives, torch-einshard expresses both the mathematical operation and data placement in one readable formula. This reduces boilerplate and synchronization errors, keeps forward and backward communication consistent, and allows the library to select optimized collective strategies without changing model code.

Morozov, Dmitriy [Lawrence Berkeley National Labor↗
DOE OSTI2021

Scalable In Situ Computation of Lagrangian Representations via Local Flow Maps

In situ computation of Lagrangian flow maps to enable post hoc time-varying vector field analysis has recently become an active area of research. However, the current literature is largely limited to theoretical settings and lacks a solution to address scalability of the technique in distributed memory. To improve scalability, we propose and evaluate the benefits and limitations of a simple, yet novel, performance optimization. Our proposed optimization is a communication-free model resulting in local Lagrangian flow maps, requiring no message passing or synchronization between processes, intrinsically improving scalability, and thereby reducing overall execution time and alleviating the encumbrance placed on simulation codes from communication overheads. To evaluate our approach, we computed Lagrangian flow maps for four time-varying simulation vector fields and investigated how execution time and reconstruction accuracy are impacted by the number of GPUs per compute node, the total number of compute nodes, particles per rank, and storage intervals. Our study consisted of experiments computing Lagrangian flow maps with up to 67M particle trajectories over 500 cycles and used as many as 2048 GPUs across 512 compute nodes. In all, our study contributes an evaluation of a communication-free model as well as a scalability study of computing distributed Lagrangian flow maps at scale using in situ infrastructure on a modern supercomputer.

Sane, Sudhanshu↗
DOE OSTI2025

Reducing Communication Overhead in Federated Learning for Network Anomaly Detection with Adaptive Client Selection

Communication overhead in federated learning (FL) poses a significant challenge for network anomaly detection systems, where the myriad of client configurations and network conditions can severely impact system efficiency and detection accuracy. While existing approaches attempt to address this through individual optimization techniques, they often fail to maintain the delicate balance between reduced overhead and detection performance. This paper presents an adaptive FL framework that dynamically combines batch size optimization, client selection, and asynchronous updates to achieve efficient anomaly detection. Through extensive profiling and experimental analysis on two distinct datasets-UNSW-NBIS for general network traffic and ROAD for automotive networks-our framework reduces communication overhead by 97.6%; (from 700.0s to 16.8s) compared to synchronous baseline approaches while maintaining comparable detection accuracy (95.10%; vs. 95.12%;). Statistical validation using Mann-Whitney U test confirms significant improvements (p < 0.05) over existing FL approaches across both datasets, demonstrating the framework's adaptability to different network security contexts. Detailed profiling analysis reveals the efficiency gains through dramatic reductions in GPU operations and memory transfers while maintaining robust detection performance under varying client conditions.

Marfo, William [University of Texas at El Paso]↗
DOE OSTI2021

Synchrophasor spoofing detection and remediation for wide-area damping control

Evolving cyber-attack threats put at risk automatic closed-loop systems to be incorporated in the smart grid. Wide-area control systems are particularly vulnerable to signal spoofing attacks due to sensor remoteness and dependence on satellite communication for time synchronization. A successful cyber-attack on a wide-area controller has the potential to reduce relative stability of the power system or worse, destabilize it. As such, detection algorithms must be deployed as defense against such attacks with the ability to autonomously correct for detected tampering or misoperation. The Spoof Catch and Restore Routine (SCR 2 ), a combination of three real-time spoof detectors, each requiring limited information about the plant, is reported here. Nonlinear simulations of a compromised wide-area control system deployed in the Western Interconnection show the effectiveness of SCR 2 in detecting both delay-type and counterfeit-type spoofing attacks on wide-area sensors.

42 ENGINEERING↗
DOE OSTI2026

CORE-BFS: Communication-Optimized REctangular-partitioned BFS Achieving 160.845 TeraTEPS on Frontier Supercomputer

Distributed Breadth-First Search (BFS) is fundamental to many large-scale graph applications, but its performance on parallel systems is often limited by high communication overhead. This paper presents CORE-BFS, an extremely scalable GPU-based BFS implementation that introduces a unique rectangular 2D partitioning-based design for Frontier supercomputer. To further improve performance, we propose four key optimizations: (1) Rectangular 2D-partition specific data formats that use two compressed row and one compressed column status array bitmaps combined with a Double Compressed Sparse Row (DCSR) format per partition, reducing memory footprint and inter-rank traffic; (2) Adaptive frontier & communication strategy that unifies top-down and bottom-up traversal on the rectangular layout, uses lazy synchronization in top-down levels, and switches variants based on frontier size to minimize communication overhead; (3) Frontier-split degree-aware update that maps frontier vertices to thread-centric, wavefront-centric, and block-centric kernels based on their degree to improve GPU utilization and memory coalescing; (4) Row-reduction pipeline that overlaps bottom-up adjacency list processing with row-wise bitmap reduction to hide inter-rank latency. Together, these techniques increase parallelism while reducing memory and communication overhead. On the Graph500 benchmark, CORE - BFS scales up to 9,248 Frontier nodes with scale-42 graphs and reaches 160.845 TTEPS, delivering a 5.42 × speedup over our previous Frontier implementation.

Yang, Haoshen [Rutgers University]↗
DOE OSTI2023

Unified Communication Optimization Strategies for Sparse Triangular Solver on CPU and GPU Clusters

This paper presents a unified communication optimization framework for sparse triangular solve (SpTRSV) algorithms on CPU and GPU clusters. The framework builds upon a 3D communication-avoiding (CA) layout of Px × Py × Pz processes that divides a sparse matrix into Pz submatrices, each handled by a Px × Py 2D grid with block-cyclic distribution. We propose three communication optimization strategies: First, a new 3D SpTRSV algorithm is developed, which trades the inter-grid communication and synchronization with replicated computation. This design requires only one inter-grid synchronization, and the inter-grid communication is efficiently implemented with sparse allreduce operations. Second, broadcast and reduction communication trees are used to reduce message latency of the intra-grid 2D communication on CPU clusters. Finally, we leverage GPU-initiated one-sided communication to implement the communication trees on GPU clusters. With these nested inter- and intra-grid communication optimization strategies, the proposed 3D SpTRSV algorithm can attain up to 3.45x speedups compared to the baseline 3D SpTRSV algorithm using up to 2048 Cori Haswell CPU cores. In addition, the proposed GPU 3D SpTRSV algorithm can achieve up to 6.5x speedups compared to the proposed CPU 3D SpTRSV algorithm with Pz up to 64. Finally it is remarkable that the proposed GPU 3D SpTRSV can scale to 256 GPUs using the Perlmutter system while the existing 2D SpTRSV algorithm can only scale up to 4 GPUs.

Sao, Piyush↗
DOE OSTI2026

Anticipating decoherence in quantum systems

Large-scale quantum technologies require coherence across distant nodes, necessitating indistinguishable quantum states. However, environmental disorder, including dephasing, spectral diffusion, and spin-bath interactions, undermines coherence. Using statistical methods, we uncover correlations in decoherence channels induced by slowly varying environments. Spectral diffusion serves as a representative demonstration case that can be extended to other remote, disordered systems such as spins in nitrogen-vacancy centers and quantum-dot spin qubits, as well as flux noise in superconducting qubits. In this work, we employ replica-theory-inspired trajectory analysis to reveal predictable temporal structures in decoherence dynamics, and validate these through an anticipatory systems framework with internal prediction of unseen spectral dynamics in multiple quantum systems, showing that this framework could, if implemented, reduce spectral shift by average factors of approximately 2 to 19, depending on emitter stability, thereby enabling enhanced coherence and multi-node synchronization for scalable quantum communication, computation, imaging, and sensing.

Maan, Pranshu [Purdue University]↗
DOE OSTI2024

A Fully Decentralized Modulation Scheme for Modular Multilevel Converters

As the number of submodules rapidly increase, control architecture of Modular Multilevel Converters (MMCs) is transforming from centralized to distributed in order to address the challenges of tremendous computational burden and massive wiring. In this digest, we propose a modulation scheme for the MMCs with distributed controls, where each submodule is able to handle both controls and modulation in a decentralized manner. It enables the distributed controllers to synchronize in terms of fast-switching pulse width modulation (PWM). Aiming at this key technical challenge, this research develops a physics-informed PWM control strategy of mirroring the spontaneous synchronization feature of coupled oscillator’s behavior at switching frequency. Thanks to less reliance on wirings and communications, the proposed approach has the potential of i) improving reliability of MMC systems, and ii) reducing cost and space requirements for MMCs. The proposed approach has been preliminarily verified through a simulation tool for power electronics systems.

Lu, Minghui [BATTELLE (PACIFIC NW LAB)]↗
DOE OSTI2021

Improving scalability of parallel CNN training by adaptively adjusting parameter update frequency

Synchronous SGD with data parallelism, the most popular parallelization strategy for CNN training, suffers from the expensive communication cost of averaging gradients among all workers. The iterative parameter updates of SGD cause frequent communications and it becomes the performance bottleneck. In this paper, we propose a lazy parameter update algorithm that adaptively adjusts the parameter update frequency to address the expensive communication cost issue. Our algorithm accumulates the gradients if the difference of the accumulated gradients and the latest gradients is sufficiently small. Here, the less frequent parameter updates reduce the per-iteration communication cost while maintaining the model accuracy. Our experimental results demonstrate that the lazy update method remarkably improves the scalability while maintaining the model accuracy. For ResNet50 training on ImageNet, the proposed algorithm achieves a significantly higher speedup (739.6 on 2048 Cori KNL nodes) as compared to the vanilla synchronous SGD (276.6) while the model accuracy is almost not affected (<0.2% difference).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Energy–Performance Trade-offs in Privacy-Preserving Federated Learning on SmartNIC-Enabled HPC Systems

Federated learning (FL) is increasingly deployed on accelerator-rich high-performance computing (HPC) systems, yet the system-level energy cost of privacy-aware FL remains poorly understood, particularly across heterogeneous networking and server-placement options. We present a measurement-driven study of energy–performance trade-offs for FL on GH200-class nodes across three deployment configurations: CPU-Ethernet, CPU-InfiniBand (RDMA-capable), and a DPU-hosted FL server over InfiniBand using a BlueField-3 SmartNIC/DPU. Using NVIDIA FLARE (NVFLARE), we align node-level power telemetry with per-round timing extracted from NVFLARE logs to quantify time-to-solution (TTS), energy-to-solution (ETS), energy-delay product (EDP), and synchronization behavior for three transformer models (ALBERT, DistilBERT, BERT), trained with and without differential privacy (DP). We find that interconnect choice is the dominant driver of runtime and energy: host-managed InfiniBand consistently reduces communication overhead versus Ethernet, yielding lower TTS/ETS/EDP. In contrast, in our NVFLARE deployment, placing the FL server on the DPU does not consistently match CPU-InfiniBand performance and can be slower—especially for larger models—highlighting that server placement alone is not sufficient to guarantee end-to-end gains. Finally, under our fixed-round protocol, DP increases per-round cost and runtime variance; ETS increases largely in proportion to TTS because average node power remains relatively stable across configurations.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2024

Software-Defined Virtual Synchronous Condenser

Synchronous condensers (SCs) play important roles in integrating wind energy into relatively weak power grids. However, the design of SCs usually depends on specific application requirements and may not be adaptive enough to the frequently-changing grid conditions caused by the transition from conventional to renewable power generation. This paper devises a software-defined virtual synchronous condenser (SDViSC) method to address the challenges. Our contributions are fourfold: 1) design of a virtual synchronous condenser (ViSC) to enable full converter wind turbines to provide built-in SC functionalities; 2) engineering SDViSCs to transfer hardware-based ViSC controllers into software services, where a Tustin transformation-based software-defined control algorithm guarantees accurate tracking of fast dynamics under limited communication bandwidth; 3) a software-defined networking-enhanced SDViSC communication scheme to allow enhanced communication reliability and reduced communication bandwidth occupation; and 4) Prototype of SDViSC on our real-time, cyber-in-the-loop digital twin of large-wind-farm in an RTDS environment. Furthermore, extensive test results validate the excellent performance of SDViSC to support reliable and resilient operations of wind farms under various physical and cyber conditions.

17 WIND ENERGY↗
DOE OSTI2025

Consensus-Based Control and Optimization of Power System Inertia

The integration of distributed energy resources (DERs), such as solar, wind, and energy storage systems, into power grids through inverter-based resources reduces power system inertia, leading to faster frequency dynamics and potential grid instability. To address this challenge, this paper proposes a distributed, consensus-based approach for the real-time control and optimization of inertia sources (synchronous generators and/or DERs) during system disturbances, enhancing both system stability and economic performance. The distributed control and optimization approach assumes each inertia source exchanges information solely with its neighbor ones, making it easily scalable to large power grid networks. The impacts of the communication connectivity among the inertia sources as well as their generation capacity limits on the distributed approach are investigated. We also demonstrate the approach’s robustness in scenarios involving communication time delays and packet losses, validating its effectiveness through numerical simulations on a 4-bus test system and a two-area 8-bus test system.

Power system inertia↗
DOE OSTI2022

Provably-Stable Overload Ride-Through Control for Grid-Forming Inverters Using System-Wide Lyapunov Function Analysis

A key challenge associated with a grid-forming (GFM) inverter based resource (IBR) is its behavior during severe grid disturbances: since a GFM inverter regulates voltage in the fast timescale instead of current or power, it may experience a transient overload of current, power and/or energy during a severe grid disturbance. While many promising control strategies for overload ride-through have been proposed over the past two decades, transient stability of the system during and after the transition to an overload ride-through control mode remains difficult to guarantee. In this work, a novel overload ride-through control strategy is proposed for a system of grid-forming inverters that takes both self-protection and system-wide transient stability into account. A proposed system-level supervisory control uses slow communication to pre-emptively assign a set of local ride through control parameters to individual GFM IBR, including a current-limiting virtual reactance, that guarantees that synchronism is still preserved for any set of anticipated grid disturbances. At the core of the supervisory control lies a Lyapunov-function-based routine capable of establishing a strong, albeit conservative, transient stability guarantee for the system. Here, the proposed overload ride-through control strategy is validated via numerical integration of a reduced-order model, as well as through detailed electromagnetic transient (EMT) simulation.

30 DIRECT ENERGY CONVERSION↗