SEARCH · Search NASA
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.
Computer system monitors inputs from checkout devices. The comparing, addressing, and controlling functions are performed in the I/O unit. This leaves the computer main frame free to handle memory, access priority, and interrupt instructions.
A software package was developed for use with micro and minicomputers, particularly the LSI-11/DPD-11 series. The package has a number of Fortran-callable subroutines which perform a variety of frequently needed tasks for biomedical applications. All routines are well documented, flexible, easy to use and modify, and require minimal programmer knowledge of peripheral hardware. The package is also economical of memory and CPU time. A single subroutine call can perform any one of the following functions: (1) plot an array of integer values from sampled A/D data, (2) plot an array of Y values versus an array of X values; (3) draw horizontal and/or vertical grid lines of selectable type; (4) annotate grid lines with user units; (5) get coordinates of user controlled crosshairs from the terminal for interactive graphics; (6) sample any analog channel with program selectable gain; (7) wait a specified time interval, and (8) perform random access I/O of one or more blocks of a sequential disk file. Several miscellaneous functions are also provided.
A universal computer control system (UCCS) is under development for all motor elements of a space telerobot. The basic hardware architecture and software design of UCCS are described, together with the rich motor sensing, control, and self-test capabilities of this all-computerized motor control system. UCCS is integrated into a multibus computer environment with direct interface to higher level control processors, uses pulsewidth multiplier power amplifiers, and one unit can control up to sixteen different motors simultaneously at a high I/O rate. UCCS performance capabilities are illustrated by a few data.
Although the basic idea may be traced back to the earlier X-ray diffraction studies of Sir W. L. Bragg, the holographic method as we know it was invented by D. Gabor in 1948 as a two-step lensless imaging technique to enhance the resolution of electron microscopy, for which he received the 1971 Nobel Prize in physics. The distinctive feature of holography is the recording of the object phase variations that carry the depth information, which is lost in conventional photography where only the intensity (= squared amplitude) distribution of an object is captured. Since all photosensitive media necessarily respond to the intensity incident upon them, an ingenious way had to be found to convert object phase into intensity variations, and Gabor achieved this by introducing a coherent reference wave along with the object wave during exposure. Gabor's in-line recording scheme, however, required the object in question to be largely transmissive, and could provide only marginal image quality due to unwanted terms simultaneously reconstructed along with the desired wavefront. Further handicapped by the lack of a strong coherent light source, optical holography thus seemed fated to remain just another scientific curiosity, until the field was revolutionized in the early 1960s by some major breakthroughs: the proposition and demonstration of the laser principle, the introduction of off-axis holography, and the invention of volume holography. Consequently, the remainder of that decade saw an exponential growth in research on theory, practice, and applications of holography. Today, holography not only boasts a wide variety of scientific and technical applications (e.g., holographic interferometry for strain, vibration, and flow analysis, microscopy and high-resolution imagery, imaging through distorting media, optical interconnects, holographic optical elements, optical neural networks, three-dimensional displays, data storage, etc.), but has become a prominent am advertising, and security medium as well. The evolution of holographic optical memories has followed a path not altogether different from holography itself, with several cycles of alternating interest over the past four decades. P. J. van Heerden is widely credited for being the first to elucidate the principles behind holographic data storage in a 1963 paper, predicting bit storage densities on the order of 1/lambda(sup 3) with source wavelength lambda - a fantastic capacity of nearly 1 TB/cu cm for visible light! The science and engineering of such a storage paradigm was heavily pursued thereafter, resulting in many novel hologram multiplexing techniques for dense data storage, as well as important advances in holographic recording materials. Ultimately, however, the lack of such enabling technologies as compact laser sources and high performance optical data I/O devices dampened the hopes for the development of a commercial product. After a period of relative dormancy, successful applications of holography in other arenas sparked a renewed interest in holographic data storage in the late 1980s and the early 1990s. Currently, with most of the critical optoelectronic device technologies in place and the quest for an ideal holographic recording medium intensified, holography is once again considered as one of several future data storage paradigms that may answer our constantly growing need for higher-capacity and faster-access memories.
The analysis of connected data is an increasingly important application in high-performance computing. Such analyses can reveal fraudulent patterns in financial transactions, optimize telecommunications networks, predict information flow in social networks, etc. However, the landscape of graph analytics is highly diverse. Graph algorithms stress processor architectures differently, and no one graph can represent all topologies. Consequently, no single approach or framework is expected to be optimal for all graph analytics problems. To help make sense of this diverse landscape, we evaluated four approaches to graph analytics: GraphBLAS, Galois, BGL17, GraphIt; and compare them against hand-tuned implementations that take advantage of hardware features on our test platform. Graph- BLAS formulates graph analytics as sparse linear algebra. Galois provides syntactic constructs for data parallelism over irregular data structures. BGL17 is a generic C++ template library for implementing graph algorithms. GraphIt provides a domain- specific language to describe and optimize graph algorithms. We use the GAP Benchmark Suite to establish baseline performance and guide the side-by-side evaluation of each framework. GAP consists of 30 tests: six graph analytics algorithms (breadth- first search, single-source shortest path, PageRank, betweenness centrality, connected components, and triangle counting) run on five graphs, each with different topological characteristics (e.g., high diameter, skewed degree distribution, high average degree). High-performance reference implementations are included for each benchmark algorithm. Because a graph can be loaded into memory a number of ways (e.g., flat file on disk, compressed sparse format, data frames, retrieved from SQL or NoSQL databases), our evaluation focused on computational performance rather than I/O. Our results show the relative strengths of each framework.
The rapid growth in the size of datasets has caused a serious imbalance in I/O and storage system performance and functionality relative to application requirements and the capabilities of other system components. The High Performance Storage System (HPSS) is a scalable, next-generation storage system that will meet the functionality and performance requirements or large-scale scientific and commercial computing environments. Our goal is to improve the performance and capacity of storage by two orders of magnitude or more over what is available in the general or mass marketplace today. We are also providing corresponding improvements in architecture and functionality. This paper describes the architecture and functionality of HPSS.
As the disparity between compute and I/O on high-performance computing systems has continued to widen, it has become increasingly difficult to perform post-hoc data analytics on full-resolution scientific simulation data due to the high I/O cost. Error-bounded data decomposition and progressive data retrieval framework has recently been developed to address such a challenge by performing data decomposition before storage and reading only part of the decomposed data when necessary. However, the performance of the progressive retrieval framework has been suffering from the over-pessimistic error control theory, such that the achieved maximum error of recomposed data is significantly lower than the required error. Therefore, more data than required is fetched for recomposition, incurring additional I/O overhead. In order to tackle this issue, we propose a DNN-based progressive retrieval framework that can better identify the minimum amount of data to be retrieved. Our contributions are as follows: 1) We provide an in-depth investigation of the recently developed progressive retrieval framework; 2) We propose two designs of prediction models (named D-MGARD and E-MGARD) to estimate the amount of retrieved data size based on error bounds. 3) We evaluate our proposed solutions using scientific datasets generated by real-world simulations from two domains. Evaluation results demonstrate the effectiveness of our solution in accurately predicting the amount of retrieval data size, as well as the advantages of our solution over the traditional approach to reducing the I/O overhead. Based on our evaluation, our solution is shown to read significantly less data (5% - 40% with D-MGARD, 20% - 80% with E-MGARD).
We identified a fairness problem in a network-based key-value storage system using Intel Storage Performance Development Kit (SPDK) in a multitenant environment. In such an environment, each tenant’s I/O service rate is not fairly guaranteed compared to that of other tenants. To address the fairness problem, we propose OctoFAS, a two-level fair scheduler designed to improve overall throughput and fairness among tenants. The two-level scheduler of OctoFAS consists of (i) inter-core scheduling and (ii) intra-core scheduling. Through inter-core scheduling, OctoFAS addresses the load imbalance problem that is inherent in SPDK on the storage server by dynamically migrating I/O requests from overloaded cores to underloaded cores, thereby increasing overall throughput. Intra-core scheduling prioritizes handling requests from starving tenants over well-fed tenants within core-specific event queues to ensure fair I/O services among multiple tenants. OctoFAS is deployed on a Linux cluster with SPDK. Through extensive evaluations, we found that OctoFAS ensures that the total system throughput remains high and balanced, while enhancing fairness by approximately 10% compared to the baseline, when both scheduling levels operate in a hybrid fashion.
The utility of speech technology was evaluated in terms of three dual task principles: resource competition between the time shared tasks, stimulus central processing response compatibility, and task integrality. Empirical support for these principles was reviewed. Two studies investigating the interactive effects of the three principles were described. Objective performance and subjective workload ratings for both single and dual tasks were examined. It was found that the single task measures were not necessarily good predictors for the dual task measures. It was shown that all three principles played an important role in determining an optimal task configuration. This was reflected in both the performance measures and the subjective measures. Therefore, consideration of all three principles is required to insure proper use of speech technology in a complex environment.
To avoid access to PFS, dedicated BB allocation is preferred despite of severe BB underutilization. Recently, new all-flash HPC storage systems with integrated BB and PFS are proposed, which speed up access to PFS. For this reason, we adopt BB over-subscription allocation method by allowing HPC applications to use BB only for I/O phase for improving BB utilization. Unfortunately, BB over-subscription aggravates I/O interference and demotion overhead from BB to PFS, resulting in degraded performance. To minimize the performance degradation, we develop an I/O scheduler to prevent I/O congestion and a new transparent data management system based on checkpoint/restart characteristics of HPC applications. With the proposed approach, not only the BB utilization can be improved, but also high performance of applications is achieved. In our experiments, we find that BB utilization is improved at least 2.2x, and more stable and higher checkpoint performance is guaranteed compared to other approaches. Besides, we achieve up to 96.4% hit ratio of restart requests on BB and up to 3.1x higher restart performance than others.
The rapid growth in scientific data generation is outpacing advancements in computing systems necessary for efficient storage, transfer, and analysis, particularly in the context of exascale computing. With the deployment of first-generation exascale computing systems and next-generation experimental facilities, this gap is widening and necessitates effective data reduction techniques to manage enormous data volumes. Over the past decade, various data reduction methods, including lossless compression, error-controlled lossy compression, and data refactoring, have been developed to accelerate I/O in scientific workflows. Despite significant reductions in data volume, these methods introduce considerable computational overhead, which can become the new bottleneck in data processing. To mitigate this, GPU-accelerated data reduction algorithms have been introduced. However, challenges remain in their integration into exascale workflows, including limited portability across different GPU architectures, substantial memory transfer overhead, and reduced scalability on dense multi-GPU systems. To address these challenges, we propose HPDR, a high-performance and portable data reduction framework. HPDR is designed to enable the execution of state-of-the-art reduction algorithms across diverse processor architectures while reducing memory transfer overhead to 2.3 % of the original, resulting in up to 3.5× faster throughput compared to existing solutions. It also achieves up to 96% of the theoretical speedup in multi-GPU settings. In addition, evaluations on accelerating I/O operations at scale up to 1,024 nodes of the Frontier supercomputer demonstrate that HPDR can achieve up to 103 TB/s reduction throughput, providing up to 4× acceleration in parallel I/O performance compared to existing data reduction routines. This work highlights the potential of HPDR to significantly enhance data reduction efficiency in exascale computing environments.
With the scaling up of simulation-based scientific discovery on high-performance computing systems, the disparity between compute and I/O has increased, forcing domain scientists to save only a small amount of simulation data to persistent storage. This can result in the loss of essential physics fields that are needed for data analysis. While error-bounded lossy compression has made tremendous progress in bridging the gap between compute and I/O, the lack of understanding of compression performance remains a key hurdle to its wide adoption. Here, in this work, we present zPerf, a statistical gray-box performance modeling approach for scientific lossy compression. Our contributions are threefold: 1) We develop zPerf to estimate the performance of lossy compression techniques, based on in-depth understanding and statistical modeling for data features and core compression metrics; 2) We demonstrate the in-detailed implementation of zPerf using two case studies, where we derive the performance modeling for SZ and ZFP, two leading lossy compressors; 3) We evaluate the effectiveness of zPerf on real-world datasets across various domains. Based on the evaluation, we demonstrate the efficacy of the zPerf performance model; 4) We further discuss three case studies where zPerf is applied to extrapolate the compression ratio of SZ and ZFP with alternative encoding schemes as well as ZFP with an alternative transform scheme. Through the case studies, we demonstrate the potential of zPerf for exploring the design space of lossy compression, which has hardly been studied in the literature.
Training in Deep learning (DL) remains highly compute- and data-intensive, with I/O becoming a critical bottleneck as models and datasets scale. Recent studies report that data loading can dominate training time, especially on large-scale HPC systems with shared parallel file systems (PFS). Existing caching approaches either rely on single-tier designs or require intrusive modifications to training pipelines, limiting their portability and effectiveness. In this work, we present FitCache, a transparent drop-in framework for multi-tier caching to accelerate distributed DL training by coordinating fast local memory (e.g., DRAM, Persistent Memory (PMem)) and NVMe as hierarchical caches atop PFS. Our design adapts to hardware diversity, i.e., if NVMe is missing, memory transparently acts as a caching tier, ensuring stable performance. FitCache transparently intercepts I/O requests and issues concurrent fetches across all tiers, returning data from the fastest responder without centralized metadata or static redirection paths. FitCache adapts to dynamic workloads and heterogeneous clusters while maintaining POSIX compatibility. Experiments on Frontier (2048 GPUs) and smaller research clusters show that FitCache reduces training time by up to 40% and per-batch I/O latency by up to 71.6% compared to Lustre Orion PFS, offering a drop-in solution for scalable DL training.
Reduced Instruction Set Computer (RISC) workstations and Personnel Computers (PC) are very popular tools for office automation, command and control, scientific analysis, database management, and many other applications. However, when using Input/Output (I/O) intensive applications, the RISC workstations and PC's are often overburdened with the tasks of collecting, staging, storing, and distributing data. Also, by using standard high-performance peripherals and storage devices, the I/O function can still be a common bottleneck process. Therefore, the high-performance mass storage system, developed by Loral AeroSys' Independent Research and Development (IR&D) engineers, can offload a RISC workstation of I/O related functions and provide high-performance I/O functions and external interfaces. The high-performance mass storage system has the capabilities to ingest high-speed real-time data, perform signal or image processing, and stage, archive, and distribute the data. This mass storage system uses a hierarchical storage structure, thus reducing the total data storage cost, while maintaining high-I/O performance. The high-performance mass storage system is a network of low-cost parallel processors and storage devices. The nodes in the network have special I/O functions such as: SCSI controller, Ethernet controller, gateway controller, RS232 controller, IEEE488 controller, and digital/analog converter. The nodes are interconnected through high-speed direct memory access links to form a network. The topology of the network is easily reconfigurable to maximize system throughput for various applications. This high-performance mass storage system takes advantage of a 'busless' architecture for maximum expandability. The mass storage system consists of magnetic disks, a WORM optical disk jukebox, and an 8mm helical scan tape to form a hierarchical storage structure. Commonly used files are kept in the magnetic disk for fast retrieval. The optical disks are used as archive media, and the tapes are used as backup media. The storage system is managed by the IEEE mass storage reference model-based UniTree software package. UniTree software will keep track of all files in the system, will automatically migrate the lesser used files to archive media, and will stage the files when needed by the system. The user can access the files without knowledge of their physical location. The high-performance mass storage system developed by Loral AeroSys will significantly boost the system I/O performance and reduce the overall data storage cost. This storage system provides a highly flexible and cost-effective architecture for a variety of applications (e.g., realtime data acquisition with a signal and image processing requirement, long-term data archiving and distribution, and image analysis and enhancement).
Growing interest in Artificial Intelligence (AI) has resulted in a surge in demand for faster methods of Machine Learning (ML) model training and inference. This demand for speed has prompted the use of high performance computing (HPC) systems that excel in managing distributed workloads. Because data is the main fuel for AI applications, the performance of the storage and I/O subsystem of HPC systems is critical. In the past, HPC applications accessed large portions of data written by simulations or experiments or ingested data for visualizations or analysis tasks. ML workloads perform small reads spread across a large number of random files. This shift of I/O access patterns poses several challenges to modern parallel storage systems. In this paper, we survey I/O in ML applications on HPC systems, and target literature within a 6-year time window from 2019 to 2024. We define the scope of the survey, provide an overview of the common phases of ML, review available profilers and benchmarks, examine the I/O patterns encountered during offline data preparation, training, and inference, and explore I/O optimizations utilized in modern ML frameworks and proposed in recent literature. Lastly, we seek to expose research gaps that could spawn further R&D.
Vast volumes of data are produced by today's scientific simulations and advanced instruments. These data cannot be stored and transferred efficiently because of limited I/O bandwidth, network speed, and storage capacity. Error-bounded lossy compression can be an effective method for addressing these issues: not only can it significantly reduce data size, but it can also control the data distortion based on user-defined error bounds. In practice, many scientific applications have specific requirements or constraints for lossy compression, in order to guarantee that the reconstructed data are valid for post hoc analysis. For example, some datasets contain irrelevant data that should be isolated in particular and users often have intuition regarding value ranges, geospatial regions, and other data subsets that are crucial for subsequent analysis. Existing state-of-the-art error-bounded lossy compressors, however, do not consider these constraints during compression, resulting in inferior compression ratios with respect to user's post hoc analysis, due to the fact that the data itself provides little or no value for post hoc analysis. In this work we address this issue by proposing an optimized framework that can preserve diverse constraints during the error-bounded lossy compression, e.g., cleaning the irrelevant data, efficiently preserving different precision for multiple value intervals, and allowing users to set diverse precision over both regular and irregular regions. We perform our evaluation on a supercomputer with up to 2,100 cores. Experiments with six real-world applications show that our proposed diverse constraints based error-bounded lossy compressor can obtain a higher visual quality or data fidelity on reconstructed data with the same or even higher compression ratios compared with the traditional state-of-the-art compressor SZ. Furthermore, our experiments also demonstrate very good scalability in compression performance compared with the I/O throughput of the parallel file system.
Handling large-scale scientific data in high-performance computing (HPC) environments poses significant challenges, including excessive I/O, high storage costs, and slow query performance. Traditional approaches often require full data decompression and scans, making them impractical for real-time or interactive analysis. To address these limitations, we introduce Eureka, a unified data-index co-compression framework that enables fine-grained access and efficient range queries on compressed scientific datasets. Eureka integrates spatial domain decomposition with block-wise error-bounded lossy compression to support selective decompression. It constructs a hierarchical AVL-tree index during compression to capture block-level value ranges, enabling fast pruning during query execution. To reduce metadata overhead, the index itself is also compressed while ensuring recall-preserving results. Experiments on six diverse HPC simulation datasets show that Eureka achieves up to 25x data compression and over 300x index compression, surpassing state-of-the-art compressors such as SZ3 and ZFP in rate-distortion performance. Additionally, Eureka delivers over 30x speedup for low-selectivity range queries, making it a scalable and efficient solution for modern scientific data analysis.
Efficient data compression is becoming increasingly critical for storing scientific data because many scientific applications produce vast amounts of data. This paper presents an end-to-end algorithmic and software pipeline for data compression that guarantees both error bounds on primary data (PD) and derived data, known as Quantities of Interest (QoI).We demonstrate the effectiveness of the pipeline by compressing fusion data generated by a large-scale fusion code, XGC, which produces tens of petabytes of data in a single day. We demonstrate that the compression is conducted by setting aside computational resources known as staging nodes, and does not impact the simulation performance. For efficient parallel I/O, the pipeline uses ADIOS2, which many codes such as XGC already use for their parallel I/O. We show that our approach can compress the data by two orders of magnitude while guaranteeing high accuracy on both the PD and the QoIs. Further, the amount of resources required by compression is a few percent of the resources required by simulation while ensuring that the compression time for each stage is less than the corresponding simulation time.This pipeline consists of three main steps. The first step decomposes the data using domain decomposition into small subdomains. Each subdomain is then compressed independently to achieve a high level of parallelism. The second step uses existing techniques that guarantee error bounds on the primary data for each subdomain. The third step uses a post-processing optimization technique based on Lagrange multipliers to reduce the QoI errors for data corresponding to each subdomain. The Lagrange multipliers generated can be further quantized or truncated to increase the compression level. All of the above characteristics of our approach make it highly practical to apply on-the-fly compression while guaranteeing errors on QoIs that are critical to the scientists.