Search NASA⌕ Search

SEARCH · Search NASA

Results for “data parallel”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

The parallelism motifs of genomic data analysis

Genomic datasets are growing dramatically as the cost of sequencing continues to decline and small sequencing devices become available. Enormous community databases store and share these data with the research community, but some of these genomic data analysis problems require large-scale computational platforms to meet both the memory and computational requirements. These applications differ from scientific simulations that dominate the workload on high-end parallel systems today and place different requirements on programming support, software libraries and parallel architectural design. For example, they involve irregular communication patterns such as asynchronous updates to shared data structures. We consider several problems in high-performance genomics analysis, including alignment, profiling, clustering and assembly for both single genomes and metagenomes. We identify some of the common computational patterns or ‘motifs’ that help inform parallelization strategies and compare our motifs to some of the established lists, arguing that at least two key patterns, sorting and hashing, are missing. This article is part of a discussion meeting issue ‘Numerical algorithms for high-performance computational science’.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Large Scale Caching and Streaming of Training Data for Online Deep Learning

The training of deep neural network models on large data remains a difficult problem, despite progress towards scalable techniques. In particular, there is a mismatch between the random but predetermined order in which AI flows select training samples and the streaming I/O patterns for which traditional HPC data storage (e.g., parallel file systems) are designed. In addition, as more data are obtained, it is feasible neither simply to train learning models incrementally, due to catastrophic forgetting (i.e., bias towards new samples), nor to train frequently from scratch, due to prohibitive time and/or resource constraints. In this paper, we study data management techniques that combine caching and streaming with rehearsal support in order to enable efficient access to training samples in both offline training and continual learning. We revisit state-of-art streaming approaches based on data pipelines that transparently handle prefetching, caching, shuffling, and data augmentation, and discuss the challenges and opportunities that arise when combining these methods with data-parallel training techniques. We also report on preliminary experiments that evaluate the I/O overheads involved in accessing the training samples from a parallel file system (PFS) under several concurrency scenarios, highlighting the impact of the PFS on the design of the data pipelines.

data pipelines↗
NASA NTRS1990

Competitive Parallel Processing For Compression Of Data

Momentarily-best compression algorithm selected. Proposed competitive-parallel-processing system compresses data for transmission in channel of limited band-width. Likely application for compression lies in high-resolution, stereoscopic color-television broadcasting. Data from information-rich source like color-television camera compressed by several processors, each operating with different algorithm. Referee processor selects momentarily-best compressed output.

Diner, Daniel B.↗
DOE OSTI2020

Striped Data Analysis Framework

A columnar data representation is known to be an efficient way for data storage, specifically in cases when the analysis is often done based only on a small fragment of the available data structures. A data representation like Apache Parquet is a step forward from a columnar representation, which splits data horizontally to allow for easy parallelization of data analysis. Based on the general idea of columnar data storage, working on the [LDRD Project], we have developed a striped data representation, which, we believe, is better suited to the needs of High Energy Physics data analysis. A traditional columnar approach allows for efficient data analysis of complex structures. While keeping all the benefits of columnar data representations, the striped mechanism goes further by enabling easy parallelization of computations without requiring special hardware. We will present an implementation and some performance characteristics of such a data representation mechanism using a distributed no-SQL database or a local file system, unified under the same API and data representation model. The representation is efficient and at the same time simple so that it allows for a common data model and APIs for wide range of underlying storage mechanisms such as distributed no-SQL databases and local file systems. Striped storage adopts Numpy arrays as its basic data representation format, which makes it easy and efficient to use in Python applications. The Striped Data Server is a web service, which allows to hide the server implementation details from the end user, easily exposes data to WAN users, and allows to utilize well known and developed data caching solutions to further increase data access efficiency. We are considering the Striped Data Server as the core of an enterprise scale data analysis platform for High Energy Physics and similar areas of data processing. We have been testing this architecture with a 2TB dataset from a CMS dark matter search and plan to expand it to multiple 100 TB or even PB scale. We will present the striped format, Striped Data Server architecture and performance test results.

Gutsche, Oliver↗
DOE OSTI2015

Data communications for a collective operation in a parallel active messaging interface of a parallel computer

Algorithm selection for data communications in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI composed of data communications endpoints, each endpoint including specifications of a client, a context, and a task, endpoints coupled for data communications through the PAMI, including associating in the PAMI data communications algorithms and bit masks; receiving in an origin endpoint of the PAMI a collective instruction, the instruction specifying transmission of a data communications message from the origin endpoint to a target endpoint; constructing a bit mask for the received collective instruction; selecting, from among the associated algorithms and bit masks, a data communications algorithm in dependence upon the constructed bit mask; and executing the collective instruction, transmitting, according to the selected data communications algorithm from the origin endpoint to the target endpoint, the data communications message.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Managing genomic variant calling workflows with Swift/T

Bioinformatics research is frequently performed using complex workflows with multiple steps, fans, merges, and conditionals. This complexity makes management of the workflow difficult on a computer cluster, especially when running in parallel on large batches of data: hundreds or thousands of samples at a time. Scientific workflow management systems could help with that. Many are now being proposed, but is there yet the “best” workflow management system for bioinformatics? Such a system would need to satisfy numerous, sometimes conflicting requirements: from ease of use, to seamless deployment at peta- and exa-scale, and portability to the cloud. We evaluated Swift/T as a candidate for such role by implementing a primary genomic variant calling workflow in the Swift/T language, focusing on workflow management, performance and scalability issues that arise from production-grade big data genomic analyses. In the process we introduced novel features into the language, which are now part of its open repository. Additionally, we formalized a set of design criteria for quality, robust, maintainable workflows that must function at-scale in a production setting, such as a large genomic sequencing facility or a major hospital system. The use of Swift/T conveys two key advantages. (1) It operates transparently in multiple cluster scheduling environments (PBS Torque, SLURM, Cray aprun environment, etc.), thus a single workflow is trivially portable across numerous clusters. (2) The leaf functions of Swift/T permit developers to easily swap executables in and out of the workflow, which makes it easy to maintain and to request resources optimal for each stage of the pipeline. While Swift/T’s data-level parallelism eliminates the need to code parallel analysis of multiple samples, it does make debugging more difficult, as is common for implicitly parallel code. Nonetheless, the language gives users a powerful and portable way to scale up analyses in many computing architectures.

Science & Technology - Other Topics↗
DOE OSTI2017

Limits on the Efficiency of Event-Based Algorithms for Monte Carlo Neutron Transport

The traditional form of parallelism in Monte Carlo particle transport simulations, wherein each individual particle history is considered a unit of work, does not lend itself well to data-level parallelism. Event-based algorithms, which were originally used for simulations on vector processors, may offer a path toward better utilizing data-level parallelism in modern computer architectures. In this study, a simple model is developed for estimating the efficiency of the event-based particle transport algorithm under two sets of assumptions. Data collected from simulations of four reactor problems using OpenMC was then used in conjunction with the models to calculate the speedup due to vectorization as a function of two parameters: the size of the particle bank and the vector width. When each event type is assumed to have constant execution time, the achievable speedup is directly related to the particle bank size. We observed that the bank size generally needs to be at least 20 times greater than vector size in order to achieve vector efficiency greater than 90%. When the execution times for events are allowed to vary, however, the vector speedup is also limited by differences in execution time for events being carried out in a single event-iteration. For some problems, this implies that vector effciencies over 50% may not be attainable. While there are many factors impacting performance of an event-based algorithm that are not captured by our model, it nevertheless provides insights into factors that may be limiting in a real implementation.

Romano, Paul K.↗
NASA NTRS1983

Massively parallel processor computer

An apparatus for processing multidimensional data with strong spatial characteristics, such as raw image data, characterized by a large number of parallel data streams in an ordered array is described. It comprises a large number (e.g., 16,384 in a 128 x 128 array) of parallel processing elements operating simultaneously and independently on single bit slices of a corresponding array of incoming data streams under control of a single set of instructions. Each of the processing elements comprises a bidirectional data bus in communication with a register for storing single bit slices together with a random access memory unit and associated circuitry, including a binary counter/shift register device, for performing logical and arithmetical computations on the bit slices, and an I/O unit for interfacing the bidirectional data bus with the data stream source. The massively parallel processor architecture enables very high speed processing of large amounts of ordered parallel data, including spatial translation by shifting or sliding of bits vertically or horizontally to neighboring processing elements.

Fung, L. W.↗
NASA NTRS1981

Memory-based frame synchronizer

A frame synchronizer for use in digital communications systems wherein data formats can be easily and dynamically changed is described. The use of memory array elements provide increased flexibility in format selection and sync word selection in addition to real time reconfiguration ability. The frame synchronizer comprises a serial-to-parallel converter which converts a serial input data stream to a constantly changing parallel data output. This parallel data output is supplied to programmable sync word recognizers each consisting of a multiplexer and a random access memory (RAM). The multiplexer is connected to both the parallel data output and an address bus which may be connected to a microprocessor or computer for purposes of programming the sync word recognizer. The RAM is used as an associative memory or decorder and is programmed to identify a specific sync word. Additional programmable RAMs are used as counter decoders to define word bit length, frame word length, and paragraph frame length.

Stattel, R. J.↗
NASA NTRS1979

Some flow characteristics of conventional and tapered high pressure drop simulated seals

The leak rates through shaft seals with large pressure drops were simulated using gaseous hydrogen, or nitrogen flowing through an annulus with a nonrotating centerbody. The flows were choked. For concentric or eccentric position of the rotor and parallel or convergent tapered flow passages, data and analysis revealed that mass flux or leak rate can be determined from a relation whose normalizing parameters depend on the thermodynamic critical constants of the working fluid and an average flow area expressed in terms of the inlet and exit cross-sectional areas. Using these normalized relations, the flow data for parallel and three convergent tapered shaft seal configurations are in good agreement. Generalization to any simple gas or gas mixture is implied and demonstrated.

Hendricks, R. C.↗
NASA NTRS1979

Some flow characteristics of conventional and tapered high-pressure-drop simulated seals

The leak rates through shaft seals with large pressure drops were simulated using gaseous hydrogen, or nitrogen flowing through an annulus with a nonrotating centerbody. The flows were choked. For concentric or eccentric position of the rotor and parallel or convergent tapered flow passages, data and analysis revealed that mass flux or leak rate can be determined from a relation whose normalizing parameters depend on the thermodynamic critical constants of the working fluid and an average flow area expressed in terms of the inlet and exit cross-sectional areas. Using these normalized relations, the flow data for parallel and three convergent, tapered, shaft-seal configurations are in good agreement. Generalization to any simple gas or gas mixtures is implied and demonstrated in part.

Hendricks, R. C.↗
DOE OSTI2017

A Pervasive Parallel Processing Framework for Data Visualization and Analysis at Extreme Scale

Most of today’s visualization libraries and applications are based off of what is known today as the visualization pipeline. In the visualization pipeline model, algorithms are encapsulated as “filtering” components with inputs and outputs. These components can be combined by connecting the outputs of one filter to the inputs of another filter. The visualization pipeline model is popular because it provides a convenient abstraction that allows users to combine algorithms in powerful ways. Unfortunately, the visualization pipeline cannot run effectively on exascale computers. Experts agree that the exascale machine will comprise processors that contain many cores. Furthermore, physical limitations will prevent data movement in and out of the chip (that is, between main memory and the processing cores) from keeping pace with improvements in overall compute performance. To use these processors to their fullest capability, it is essential to carefully consider memory access. This is where the visualization pipeline fails. Each filtering component in the visualization library is expected to take a data set in its entirety, perform some computation across all of the elements, and output the complete results. The process of iterating over all elements must be repeated in each filter, which is one of the worst possible ways to traverse memory when trying to maximize the number of executions per memory access. This project investigates a new type of visualization framework that exhibits a pervasive parallelism necessary to run on exascale machines. Our framework achieves this by defining algorithms in terms of functors, which are localized, stateless operations. Functors can be composited in much the same way as filters in the visualization pipeline. But, functors’ design allows them to be concurrently running on massive amounts of lightweight threads. Only with such fine-grained parallelism can we hope to fill the billions of threads we expect will be necessary for efficient computation on an exascale computer. This project concludes with a functional prototype containing pervasively parallel algorithms that perform demonstratively well on many-core processors. These algorithms are fundamental for performing data analysis and visualization at extreme scale.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2013

Profiling and Improving I/O Performance of a Large-Scale Climate Scientific Application

Exascale computing systems are soon to emerge, which will pose great challenges on the huge gap between computing and I/O performance. Many large-scale scientific applications play an important role in our daily life. The huge amounts of data generated by such applications require highly parallel and efficient I/O management policies. In this paper, we adopt a mission-critical scientific application, GEOS-5, as a case to profile and analyze the communication and I/O issues that are preventing applications from fully utilizing the underlying parallel storage systems. Through in-detail architectural and experimental characterization, we observe that current legacy I/O schemes incur significant network communication overheads and are unable to fully parallelize the data access, thus degrading applications' I/O performance and scalability. To address these inefficiencies, we redesign its I/O framework along with a set of parallel I/O techniques to achieve high scalability and performance. Evaluation results on the NASA discover cluster show that our optimization of GEOS-5 with ADIOS has led to significant performance improvements compared to the original GEOS-5 implementation.

Exascale↗
DOE OSTI2024

ATLAS Data Analysis using a Parallel Workflow on Distributed Cloud-based Services with GPUs

A new type of parallel workflow is developed for the ATLAS experiment at the Large Hadron Collider, that makes use of distributed computing combined with a cloud-based infrastructure. This has been developed for a specific type of analysis using ATLAS data, one popularly referred to as Simulation-Based Inference (SBI). The JAX library is used for the parts of the workflow to compute gradients as well as accelerate program execution using just-in-time compilation, which becomes essential in a full SBI analysis and can also offer significant speed-ups in more traditional types of analysis.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Implementing a neural network interatomic model with performance portability for emerging exascale architectures

The two main thrusts of computational science are increasingly accurate predictions and faster calculations; to this end, the zeitgeist in molecular dynamics (MD) simulations is pursuing machine learned and data driven interatomic models, e.g. neural network potentials, and novel hardware architectures, e.g. GPUs. Current implementations of neural network potentials are orders of magnitude slower than traditional interatomic models and while looming exascale computing offers the ability to run large, accurate simulations with these models, achieving portable performance for MD with new and varied exascale hardware requires rethinking traditional algorithms, using novel data structures, and library solutions. We re-implement a neural network interatomic model in CabanaMD, an MD proxy application, built on libraries developed for performance portability. Our implementation shows significantly improved thread scaling in this complex kernel as compared to a current LAMMPS implementation, across both strong and weak scaling. Our single-source solution enables simulations up to 20 million atoms on a single CPU node and 4 million atoms with improved performance on a single GPU. Furthermore, we also explore parallelism and data layout choices (using flexible data structures called AoSoAs) and their effect on performance, seeing up to ~50% and ~5% improvements in performance on a GPU by choosing the right level of parallelism and data layout respectively.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Optical Backplane Interconnection

Optical backplane interconnection (OBIT), method of optically interconnecting many parallel outputs from data processor to many parallel inputs of other data processors by optically changing wavelength of output optical beam. Requires only one command: exact wavelength necessary to make connection between two desired processors. Many features, including smallness advantageous to incorporate OBIT into integrated optical device. Simplifies or eliminates wiring and speeds transfer of data over existing electrical or optical interconnections. Computer hookups and fiber-optical communication networks benefit from concept.

Hendricks, Herbert D.↗