Flow Ordering and Hierarchical Bottleneck Identification for High-Speed Data Networks - Phase II Final Report
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
SEARCH · Search NASA
Results for “Network, Bottlenecks, Performance, Optimization”
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.
Computing Bottleneck Structures at Scale for High-Precision Network Performance Analysis
The Theory of Bottleneck Structures is a recently-developed framework for studying the performance of data networks. It describes how local perturbations in one part of the network propagate and interact with others. This framework is a powerful analytical tool that allows network operators to make accurate predictions about network behavior and thereby optimize performance. Previous work implemented a software package for bottleneck structure analysis, but applied it only to toy examples. In this work, we introduce the first software package capable of scaling bottleneck structure analysis to production-size networks. Here, we benchmark our system using logs from ESnet, the Department of Energy's high-performance data network that connects research institutions in the U.S. Using the previously published tool as a baseline, we demonstrate that our system achieves vastly improved performance, constructing the bottleneck structure graphs in 0.21 s and calculating link derivatives in 0.09 s on average. We also study the asymptotic complexity of our core algorithms, demonstrating good scaling properties and strong agreement with theoretical bounds. These results indicate that our new software package can maintain its fast performance when applied to even larger networks. They also show that our software is efficient enough to analyze rapidly changing networks in real time. Overall, we demonstrate the feasibility of applying bottleneck structure analysis to solve practical problems in large, real-world data networks.
benchmark↗
Achieving High Throughput for Data Transfer over ATM Networks
File-transfer rates for ftp are often reported to be relatively slow, compared to the raw bandwidth available in emerging gigabit networks. While a major bottleneck is disk I/O, protocol issues impact performance as well. Ftp was developed and optimized for use over the TCP/IP protocol stack of the Internet. However, TCP has been shown to run inefficiently over ATM. In an effort to maximize network throughput, data-transfer protocols can be developed to run over UDP or directly over IP, rather than over TCP. If error-free transmission is required, techniques for achieving reliable transmission can be included as part of the transfer protocol. However, selected image-processing applications can tolerate a low level of errors in images that are transmitted over a network. In this paper we report on experimental work to develop a high-throughput protocol for unreliable data transfer over ATM networks. We attempt to maximize throughput by keeping the communications pipe full, but still keep packet loss under five percent. We use the Bay Area Gigabit Network Testbed as our experimental platform.
Johnson, Marjory J.↗
Optimizing the hypre solver for manycore and GPU architectures
The solution of large-scale combustion problems with codes such as Uintah on modern computer architectures requires the use of multithreading and GPUs to achieve performance. Uintah uses a low-Mach number approximation that requires iteratively solving a large system of linear equations. The Hypre iterative solver has solved such systems in a scalable way for Uintah, but the use of OpenMP with Hypre leads to at least slowdown due to OpenMP overheads. The proposed solution uses the MPI Endpoints within Hypre, where each team of threads acts as a different MPI rank. This approach minimizes OpenMP synchronization overhead and performs as fast or (up to 1.44) faster than Hypre's MPI-only version, and allows the rest of Uintah to be optimized using OpenMP. The profiling of the GPU version of Hypre shows the bottleneck to be the launch overhead of thousands of micro-kernels. The GPU performance was improved by fusing these micro-kernels and was further optimized by using Cuda-aware MPI, resulting in an overall speedup of 1.16—1.44 compared to the baseline GPU implementation. The above optimization strategies were published in the International Conference on Computational Science 2020 [1]. This work extends the previously published research by carrying out the second phase of communication-centered optimizations in Hypre to improve its scalability on large-scale supercomputers. Additionally, this includes an efficient non-blocking inter-thread communication scheme, communication-reducing patch assignment, and expression of logical communication parallelism to a new version of the MPICH library that utilizes the underlying network parallelism [2]. The above optimizations avoid communication bottlenecks previously observed during strong scaling and improve performance by up to 2 on 256 nodes of Intel Knight's Landing processor.
97 MATHEMATICS AND COMPUTING↗
4K High Definition Video and Audio Streaming Across High-rate Delay Tolerant Space Networks
Audio and video streaming across delay tolerant networks are relatively new phenomena. During the Apollo 11 mission, video and audio were streamed directly back to Earth using fully analog radios. This streaming capability atrophied over time due to the gradual conversion to digital electronics accompanied with higher resolutions causing the required bit rates to outpace communication link performance. Additionally, 21st century space systems face the new requirement of interconnectedness. Delay Tolerant Networking (DTN) attempts to solve this requirement by uniting traditional point to point links into a robust and dynamic network. However, In order to avoid system bottlenecks, the High-Rate Delay Tolerant Networking (HDTN) implementation focuses on performance-optimization of the standards. This work extends the functionality of HDTN by implementing audio and video streaming, with the goal of demonstrating the practical application of high definition media streaming across space networks. A series of network topologies were created including simple point to point links and multi-node multi-hop networks. Test media in the form of prerecorded and live footage was streamed across the network. A set of objective quality metrics were established in order to measure the stream quality. A lunar network was emulated using a mixture of embedded ARM platforms.
Kyle J Vernyi↗
Secure mmWave Spectrum Sharing with Autonomous Beam Scheduling for 5G and Beyond
Spectrum Sharing (SS) has seen a renewed set of initiatives in 5G with the availability of shared and unlicensed spectrum bands that can be used by multiple cellular service providers and private cellular networks. Beam based transmission, instead of the traditional sector based transmission in conjunction with the spectrum agility of the 5G New Radio (NR) has brought new opportunities to optimized sharing of spectrum. Currently in the U.S., a centralized Spectrum Access Server (SAS) is used to co-ordinate spectrum sharing among networks sharing the same spectrum band. However, SAS becomes a focal point for security attacks and a performance bottleneck. In addition, SAS relies on an Environmental Sensor Network (ESN), separate from the 5G network. Without trusted spectral occupancy information, false reporting of spectrum sensing data can create sub-optimal and unfair spectrum usage. This paper summarizes our recent research findings in using a decentralized scheme for multiple networks to securely share spectrum with autonomous beam scheduling : 1) A new stochastic network framework based on Lyapunov Optimization approach is developed to optimize scheduling at the base stations; 2) Game theoretic (GT) approach is used to formulate the distributed scheduler; 3) Another distributed scheduler with Q-learning is presented that utilizes the Reinforcement Learning (RL) approach; 4) The performance and convergence rate of these distributed solutions to use shared and unlicensed spectrum are compared with existing solutions. Conditions under which the performance of these schedulers approach the theoretical upper bound, which is the performance possible with no interference among the operators sharing the spectrum, are presented; 5) The ability of a base station to use its own user equipment as sensors, for optimal spectrum sharing with base stations in other operator networks, is demonstrated to be an effective approach.
5G↗
Moving small files in a networked environment
Globally distributed computing infrastructures, such as clouds and supercomputers, are currently used to manage data that is generated with an unprecedented speed from a variety of resources. Coping with this trend, the volume of data exchanged across distant sites increases substantially. To accelerate data transfer, high-speed networks are provided to connect remote sites. Most existing data movement solutions are optimized for moving large files. However, it is still challenging to transfer a large number of small files across networks. This disadvantage not only lowers data transfer performance, but also decreases overall system utilization. Here, we identify that moving small files is mainly constrained by degraded file system throughput, not just network performance as might be suspected. We have built a data transfer pipeline model to analyze the impact of small network I/O and storage I/O on data movement. Extending one of the widely used open source data movement solutions, GridFTP, we demonstrate several appropriate engineering approaches that mitigate the bottleneck and increase data transfer efficiency. We show optimizations that improve data transfer performance more than 5 times. In comparison to existing solutions, our approaches can save a significant amount of system resources for moving lots of small files.
97 MATHEMATICS AND COMPUTING↗
GradientGraph
Under this SBIR Phase II, Reservoir Labs has developed G2 Analytics, a new technology that allows network operators to analyze bottleneck and flow performance with high precision. G2 delivers a new analytical approach and framework to resolve a variety of key problems found in modern communication networks, including: traffic engineering, routing, flow scheduling, network design, capacity planning, resiliency analysis, network slicing, or service level agreement (SLA) management, among others. G2 leverages the bottleneck structure of congestion-controlled communication networks, a recent mathematical discovery by the Reservoir team [RL19b, RL20a, RL20b, RL21a]. Bottleneck structures reveal how perturbations on flows and links propagate through the network, providing an analytical framework to measure (qualitatively and quantitatively) the ripple effects induced as they traverse the network. Leveraging the mathematics of bottleneck structures, Reservoir Labs is developing the G2 technology to provide network operators with a framework to design, optimize and troubleshoot network performance. This delivery includes the G2 software stack.
Yellamraju, Sruthi↗
New Horizons for a Practical and Performance-Optimized Solar System Internet
The High-rate Delay Tolerant Networking (HDTN) project at the NASA Glenn Research Center (GRC) is developing a performance-optimized Delay Tolerant Networking (DTN) implementation using the Bundle Protocol (BP) both for infusion in modern, distributed spacecraft systems and for foundational network research purposes. While one purpose of networking is to enable a returns-to-scale with communicating assets, it is recognized that neither the protocol nor its implementations may impose a bottleneck on data delivery if expected to be implemented. With this in mind, this paper explores the current status of the HDTN software, including its capabilities and also various performance metrics at the bundle layer, the convergence layers (e.g. performance-optimized Licklider Transmission Protocol, or LTP), and bundle storage and retrieval. This includes goals of software implementations that support multi-gigabit per second communications regardless of payload size. A discussion on the current software architecture and internal scheduling and routing is included. Interoperability with such extant DTN implementations as Interplanetary Overlay Network (ION) and DTN Marshall Enterprise Implementation (DTNME) are included. The research goals of the project are also listed, including Software-Defined Networking (SDN) and the theory of DTNs. A table-based filtration system for the Bundle Protocol (BP), called BP Filter, is also explored: this addition enables table-based policies within the context of a DTN for management purposes. Infusion begins with systems testing in the Johnson Space Center (JSC) Software Development and Integration Laboratory (SDIL), which supports International Space Station (ISS) Flight Software development, integration, and verification. Observations made from the results of testing in the SDIL and in flight testing are also discussed, pointing to a path for infusion into high data return low-earth orbit (LEO) missions. The paper concludes with areas for future work.
Delay Tolerant Networking↗
Lossy checkpoint compression in full waveform inversion: a case study with ZFPv0.5.5 and the overthrust model
This paper proposes a new method that combines checkpointing methods with error-controlled lossy compression for large-scale high-performance full-waveform inversion (FWI), an inverse problem commonly used in geophysical exploration. This combination can significantly reduce data movement, allowing a reduction in run time as well as peak memory. In the exascale computing era, frequent data transfer (e.g., memory bandwidth, PCIe bandwidth for GPUs, or network) is the performance bottleneck rather than the peak FLOPS of the processing unit. Like many other adjoint-based optimization problems, FWI is costly in terms of the number of floating-point operations, large memory footprint during backpropagation, and data transfer overheads. Past work for adjoint methods has developed checkpointing methods that reduce the peak memory requirements during backpropagation at the cost of additional floating-point computations. Combining this traditional checkpointing with error-controlled lossy compression, we explore the three-way tradeoff between memory, precision, and time to solution. We investigate how approximation errors introduced by lossy compression of the forward solution impact the objective function gradient and final inverted solution. Empirical results from these numerical experiments indicate that high lossy-compression rates (compression factors ranging up to 100) have a relatively minor impact on convergence rates and the quality of the final solution.
58 GEOSCIENCES↗
DLIO: A DATA-CENTRIC BENCHMARK FOR DEEP LEARNING APPLICATIONS
SF-22-136 Deep learning has been shown as a successful method for various tasks, and its popularity results in numerous open-source deep learning software tools. Deep learning has been applied to a broad spectrum of scientific domains such as cosmology, particle physics, computer vision, fusion, and astrophysics. Scientists have performed a great deal of work to optimize the computational performance of deep learning frameworks. However, the same cannot be said for I/O performance. As deep learning algorithms rely on big-data volume and variety to effectively train neural networks accurately, I/O is a significant bottleneck on large-scale distributed deep learning training. DLIO, is a novel representative benchmark suite built based on the I/O profiling of the selected workloads. DLIO can be utilized to accurately emulate the I/O behavior of modern deep learning applications. Using DLIO, application developers and system software solution architects can identify potential I/O bottlenecks in their applications and guide optimizations to boost the I/O performance leading to lower training times. The storage vendor can also use DLIO as a guide for designing and optimize the storage and filesystem targeting at deep learning application.
ZHENG, HUIHUO↗
Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields
Tensor datatypes representing field variables like stress, displacement, velocity, etc., have increasingly become a common occurrence in data-driven modeling and analysis of simulations. Numerous methods [such as convolutional neural networks (CNNs)] exist to address the meta-modeling of field data from simulations. As the complexity of the simulation increases, so does the cost of acquisition, leading to limited data scenarios. Modeling of tensor datatypes under limited data scenarios remains a hindrance for engineering applications. Here, in this article, we introduce a direct image-to-image modeling framework of convolutional autoencoders enhanced by information bottleneck loss function to tackle the tensor data types with limited data. The information bottleneck method penalizes the nuisance information in the latent space while maximizing relevant information making it robust for limited data scenarios. The entire neural network framework is further combined with robust hyperparameter optimization. We perform numerical studies to compare the predictive performance of the proposed method with a dimensionality reduction-based surrogate modeling framework on a representative linear elastic ellipsoidal void problem with uniaxial loading. The data structure focuses on the low-data regime (fewer than 100 data points) and includes the parameterized geometry of the ellipsoidal void as the input and the predicted stress field as the output. The results of the numerical studies show that the information bottleneck approach yields improved overall accuracy and more precise prediction of the extremes of the stress field. Additionally, an in-depth analysis is carried out to elucidate the information compression behavior of the proposed framework.
artificial intelligence↗
Data storage and retrieval system abstract
The STX mass storage system design is intended for environments requiring high speed access to large volumes of data (terabyte and greater). Prior to commitment to a product design plan, STX conducted an exhaustive study of the commercially available off-the-shelf hardware and software. STX also conducted research into the area of emerging technologies in networks and storage media so that the design could easily accommodate new interfaces and peripherals as they came on the market. All the selected system elements were brought together in a demo suite sponsored jointly by STX and ALLIANT where the system elements were evaluated based on actual operation using a client-server mirror image configuration. Testing was conducted to assess the various component overheads and results were compared against vendor data claims. The resultant system, while adequate to meet our capacity requirements, fell short of transfer speed expectations. A product team lead by STX was assembled and chartered with solving the bottleneck issues. Optimization efforts yielded a 60 percent improvement in throughput performance. The ALLIANT computer platform provided the I/O flexibility needed to accommodate a multitude of peripheral interfaces including the following: up to twelve 25MB/s VME I/O channels; up to five HiPPI I/O full duplex channels; IPI-s, SCSI, SMD, and RAID disk array support; standard networking software support for TCP/IP, NFS, and FTP; open architecture based on standard RISC processors; and V.4/POSIX-based operating system (Concentrix). All components including the software are modular in design and can be reconfigured as needs and system uses change. Users can begin with a small system and add modules as needed in the field. Most add-ons can be accomplished seamlessly without revision, recompilation or re-linking of software.
Matheson, Barbara↗
Integrated End-to-end Performance Prediction and Diagnosis for Extreme Scientific Workflows
This report details recent progress for the ASCR funded project “Integrated End-to-end Performance Prediction and Diagnosis for Extreme Scientific Workflows”. We refer to the project as IPPD/2, reflecting the 2017 renewal under expanded scope and partners In IPPD/2, we increased our research scope to include data motion. We are focusing on three major aspects: a) observe how data is generated, distributed, and used; b) analyze how data is (repeatedly) consumed with a focus both on repeated patterns and anomalies; and c) explore how to optimize data motion. This new work on data motion will augment and complement IPPD/2’s research that focused on the computational aspects of tasks. We leverage and extend our existing tools and demonstrate our work on the Belle II workflow suite as well as on workflows from NSLS-II. The highlights of our work are as follows: Provenance for Workflows: Provenance is used to provide information enabling quality control, re-run computational workflows, and reproduce results. IPPD/2 has been building a scalable provenance management system that enables the capture of provenance from the high-level workflow through all relevant system levels in one integrated environment. Leveraging this work, our recent efforts have included using provenance as an enabling technique. Workload characterization: Leveraging provenance and analysis, we characterize data movement within network, storage, and memory over a variety of workloads. This characterization enables an understanding by performance analysts and application developers of the range of behaviors that could be expected. Performance Prediction for Workflows: The goal of modeling distributed workflows is to understand performance bottlenecks and enable more intelligent task scheduling to optimize selected metrics of interest (e.g., task throughput or output data rate). IPPD/2 has utilized both analytical and AI/ML modeling methodologies for performance modeling. Advanced Scheduling and Fault Modeling for Workflows: Scheduling of large-scale scientific workflows on geographically distributed resources is a challenging problem. To improve workflow throughput, we combined novel scheduling algorithms with task predictions from performance modeling and fault modeling. Dynamically Alleviating Bottlenecks in Workflows: Exploiting our provenance, analysis, and modeling efforts, we have explored and developed several techniques for dynamically detecting and alleviating bottlenecks in data movement. In particular, we have spent considerable effort demonstrating our techniques on production-like workflow configurations.
97 MATHEMATICS AND COMPUTING↗
Optimizing High Performance Markov Clustering for Pre-Exascale Architectures
HipMCL is a high-performance distributed memory implementation of the popular Markov Cluster Algorithm (MCL) and can cluster large-scale networks within hours using a few thousand CPU-equipped nodes. It relies on sparse matrix computations and heavily makes use of the sparse matrix-sparse matrix multiplication kernel (SpGEMM). The existing parallel algorithms in HipMCL are not scalable to Exascale architectures, both due to their communication costs dominating the runtime at large concurrencies and also due to their inability to take advantage of accelerators that are increasingly popular. In this work, we systematically remove scalability and performance bottlenecks of HipMCL. We enable GPUs by performing the expensive expansion phase of the MCL algorithm on GPU. Additionally, we propose a CPU-GPU joint distributed SpGEMM algorithm called pipelined Sparse SUMMA and integrate a probabilistic memory requirement estimator that is fast and accurate. Furthermore, we develop a new merging algorithm for the incremental processing of partial results produced by the GPUs, which improves the overlap efficiency and the peak memory usage. We also integrate a recent and faster algorithm for performing SpGEMM on CPUs. We validate our new algorithms and optimizations with extensive evaluations. With the enabling of the GPUs and integration of new algorithms, HipMCL is up to 12.4x faster, being able to cluster a network with 70 million proteins and 68 billion connections just under 15 minutes using 1024 nodes of ORNL's Summit supercomputer.
97 MATHEMATICS AND COMPUTING↗
Automated ICRF heating surrogate modeling via machine learning
This work introduces automated machine learning workflows that address critical bottlenecks in surrogate model development for Ion Cyclotron Range of Frequencies (ICRF) heating applications. The automated framework includes data analysis tools that transform raw datasets into actionable insights in seconds, replacing weeks of manual exploratory effort and ensuring consistent, reproducible dataset characterization. By integrating advanced hyperparameter optimization (HPO) methods including Bayesian optimization via BoTorch and Tree-structured Parzen Estimators (TPE), the framework significantly reduces model development time from weeks to hours, decreasing computational cost and required expertise, while enabling high-accuracy surrogate models. Compared to traditional hyperparameter scanning (HPS) techniques such as methodical, randomized, and grid searches, HPO methods achieve superior convergence and predictive performance, even when compared to already well-tuned reference models. On NSTX High Harmonic Fast Wave (HHFW) heating datasets, both Random Forest Regressor (RFR) and neural network surrogates demonstrate improved accuracy, achieving R 2 values beyond 0.97 and 0.98, respectively. The results show that while HPO gains are modest for robust architectures like RFR, they become essential for more sensitive models such as neural networks, highlighting the trade-offs across optimization strategies. Through automated workflows that eliminate manual hyperparameter tuning and require minimal ML expertise, this work enables widespread adoption of high-fidelity surrogate models across the fusion community for real-time plasma control, uncertainty quantification, rapid experimental scenario development, and integrated system optimization.
Sanchez-Villar, Alvaro [Princeton Plasma Physics L↗
Systems and methods for quality of service (QoS) based management of bottlenecks and flows in networks
Techniques based on the Theory of Bottleneck Ordering can reveal the bottleneck structure of a network, and the Theory of Flow ordering can take advantage of the revealed bottleneck structure to manage and configure network flows so as to improve the overall network performance. These two techniques provide insights into the inherent topological properties of a network at least in three areas: (1) identification of the regions of influence of each bottleneck; (2) the order in which bottlenecks (and flows traversing them) may converge to their steady state transmission rates in distributed congestion control algorithms; and (3) the design of optimized traffic engineering policies.
97 MATHEMATICS AND COMPUTING↗
Onboard Hyperspectral Image Classification via Transfer Learning for Communication-Limited Spacecraft
Employing deep-learning and artificial-intelligence (AI) techniques onboard spacecraft can dramatically improve priority data selection to ensure more effective use of the available downlink. However, deployment of effective deep-learning models requires significant training on the ground, which may not be feasible, due to limited data available in an unexplored environment. Therefore, this research explores building robust classification models for onboard data processing where training data is highly limited using transfer-learning techniques. In this paper, we focus on the use case of hyperspectral imaging for remote sensing, a domain where the high dimensionality of the data from the sensor can rapidly saturate the downlink bandwidth. With this bottleneck, there is an impending need to autonomously and robustly classify data onboard to optimize downlink of high-impact measurements, thus maximizing the scientific utility per bit transmitted to the ground. This paper examines the use of deep neural networks onboard for hyperspectral image classification in a communication-limited scenario to analyze how the models perform with limited training data. The use of transfer learning can ameliorate the issue of poor generalization by transferring features learned from training on a large source dataset for one classification task to the target classification task with limited training data. For two deep-learning models from literature, we compare the accuracy of the models trained using transfer learning to models trained from scratch using a random weight initialization with varying amounts of training data. We demonstrate the feasibility and performance of running inference of the deep-learning models on representative flight-like hardware.
Advanced Avionics, Machine Learning, Data Processi↗