Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “MapReduce”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Map reduce using coordination namespace hardware acceleration

A system and method for supporting data MapReduce operations in a tuple space/coordinated namespace (CNS) extended memory storage architecture. The system-wide CNS provides an efficient means for storing and communicating data generated by local processes running at the nodes, and coordinated to provide MapReduce operations in a multi-nodal system. A hardware accelerated mechanism supports map reduce sorting/shuffle operations and reduce operations according to an aggregate function. Local processes running at a node generate a tuple corresponding to data generated by a process, each tuple having a tuple name and tuple data value corresponding to the generated data. Each tuple is processed and stored at the node or another node, dependent upon its tuple name. Tuple records associated with a tuple name are accumulated at one or more nodes according to a linked list structure at each that is accessible via a hash table index pointer at the node.

Jacob, Philip↗
DOE OSTI2014

Streaming data analytics via message passing with application to graph algorithms

The need to process streaming data, which arrives continuously at high-volume in real-time, arises in a variety of contexts including data produced by experiments, collections of environmental or network sensors, and running simulations. Streaming data can also be formulated as queries or transactions which operate on a large dynamic data store, e.g. a distributed database. We describe a lightweight, portable framework named PHISH which enables a set of independent processes to compute on a stream of data in a distributed-memory parallel manner. Datums are routed between processes in patterns defined by the application. PHISH can run on top of either message-passing via MPI or sockets via ZMQ. The former means streaming computations can be run on any parallel machine which supports MPI; the latter allows them to run on a heterogeneous, geographically dispersed network of machines. We illustrate how PHISH can support streaming MapReduce operations, and describe streaming versions of three algorithms for large, sparse graph analytics: triangle enumeration, subgraph isomorphism matching, and connected component finding. Lastly, we also provide benchmark timings for MPI versus socket performance of several kernel operations useful in streaming algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Rendezvous algorithms for large-scale modeling and simulation

Rendezvous algorithms encode a communication pattern that is useful when processors sending data do not know who the receiving processors should be, or vice versa. The idea is to define an intermediate decomposition where datums from different sending processors can ”rendezvous” to perform a computation, in a manner that both the senders and eventual receivers of the results can identify the appropriate rendezvous processor. Though they were originally designed for interpolating between overlaid grids with independent parallel decompositions (Plimpton et al., 2004), we have recently found rendezvous algorithms useful for a variety of operations in particle- or grid-based simulation codes when running large problems on large numbers of processors. In particular, we show they can perform well when a load-balanced intermediate decomposition is randomized and not spatial, requiring all-to-all communication to move data between processors. In this case rendezvous algorithms leverage the large bisection communication bandwidths which parallel machines provide. We describe how rendezvous algorithms work in a scientific computing context and give specific examples for molecular dynamics and Direct Simulation Monte Carlo codes which result in dramatic performance improvements versus simpler algorithms which do not scale as well. We explain how a generic rendezvous algorithm can be implemented, and also point out similarities with the MapReduce paradigm popularized by Google and Hadoop.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Design-time performance modeling of compositional parallel programs

Performance models are powerful instruments for understanding the performance of parallel systems and uncovering their bottlenecks. Already during system design, performance models can help ponder alternative development options. However, creating a performance model – whether theoretically or empirically – for an entire application that does not exist yet is challenging. In this paper, we propose to generate performance models of full programs from performance models of their components using formal composition operators derived from parallel design patterns. As long as the design of the overall system follows such a pattern, its performance model can be predicted with reasonable accuracy without an actual implementation. In conclusion, we demonstrate our approach with design patterns of varying complexity, including pipeline, task pool, and eventually MapReduce, which is representative of a broad class of data-analytics applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

YARNsim: Simulating Hadoop YARN

Despite the popularity of the Apache Hadoop system, its success has been limited by issues such as single points of failure, centralized job/task management, and lack of support for programming models other than MapReduce. The next generation of Hadoop, Apache Hadoop YARN, is designed to address these issues. In this paper, we propose YARNsim, a simulation system for Hadoop YARN. YARNsim is based on parallel discrete event simulation and provides protocol-level accuracy in simulating key components of YARN. YARNsim provides a virtual platform on which system architects can evaluate the design and implementation of Hadoop YARN systems. Also, application developers can tune job performance and understand the tradeoffs between different configurations, and Hadoop YARN system vendors can evaluate system efficiency under limited budgets. To demonstrate the validity of YARNsim, we use it to model two real systems and compare the experimental results from YARNsim and the real systems. The experiments include standard Hadoop benchmarks, synthetic workloads, and a bioinformatics application. The results show that the error rate is within 10% for the majority of test cases. The experiments prove that YARNsim can provide what-if analysis for system designers in a timely manner and at minimal cost compared with testing and evaluating on a real system.

Hadoop↗
NASA NTRS2014

MERRA Analytic Services: Meeting the Big Data Challenges of Climate Science Through Cloud-enabled Climate Analytics-as-a-service

Climate science is a Big Data domain that is experiencing unprecedented growth. In our efforts to address the Big Data challenges of climate science, we are moving toward a notion of Climate Analytics-as-a-Service (CAaaS). We focus on analytics, because it is the knowledge gained from our interactions with Big Data that ultimately produce societal benefits. We focus on CAaaS because we believe it provides a useful way of thinking about the problem: a specialization of the concept of business process-as-a-service, which is an evolving extension of IaaS, PaaS, and SaaS enabled by Cloud Computing. Within this framework, Cloud Computing plays an important role; however, we it see it as only one element in a constellation of capabilities that are essential to delivering climate analytics as a service. These elements are essential because in the aggregate they lead to generativity, a capacity for self-assembly that we feel is the key to solving many of the Big Data challenges in this domain. MERRA Analytic Services (MERRAAS) is an example of cloud-enabled CAaaS built on this principle. MERRAAS enables MapReduce analytics over NASAs Modern-Era Retrospective Analysis for Research and Applications (MERRA) data collection. The MERRA reanalysis integrates observational data with numerical models to produce a global temporally and spatially consistent synthesis of 26 key climate variables. It represents a type of data product that is of growing importance to scientists doing climate change research and a wide range of decision support applications. MERRAAS brings together the following generative elements in a full, end-to-end demonstration of CAaaS capabilities: (1) high-performance, data proximal analytics, (2) scalable data management, (3) software appliance virtualization, (4) adaptive analytics, and (5) a domain-harmonized API. The effectiveness of MERRAAS has been demonstrated in several applications. In our experience, Cloud Computing lowers the barriers and risk to organizational change, fosters innovation and experimentation, facilitates technology transfer, and provides the agility required to meet our customers' increasing and changing needs. Cloud Computing is providing a new tier in the data services stack that helps connect earthbound, enterprise-level data and computational resources to new customers and new mobility-driven applications and modes of work. For climate science, Cloud Computing's capacity to engage communities in the construction of new capabilies is perhaps the most important link between Cloud Computing and Big Data.

Data Analytics↗
NASA NTRS2011

Leveraging the Cloud for Robust and Efficient Lunar Image Processing

The Lunar Mapping and Modeling Project (LMMP) is tasked to aggregate lunar data, from the Apollo era to the latest instruments on the LRO spacecraft, into a central repository accessible by scientists and the general public. A critical function of this task is to provide users with the best solution for browsing the vast amounts of imagery available. The image files LMMP manages range from a few gigabytes to hundreds of gigabytes in size with new data arriving every day. Despite this ever-increasing amount of data, LMMP must make the data readily available in a timely manner for users to view and analyze. This is accomplished by tiling large images into smaller images using Hadoop, a distributed computing software platform implementation of the MapReduce framework, running on a small cluster of machines locally. Additionally, the software is implemented to use Amazon's Elastic Compute Cloud (EC2) facility. We also developed a hybrid solution to serve images to users by leveraging cloud storage using Amazon's Simple Storage Service (S3) for public data while keeping private information on our own data servers. By using Cloud Computing, we improve upon our local solution by reducing the need to manage our own hardware and computing infrastructure, thereby reducing costs. Further, by using a hybrid of local and cloud storage, we are able to provide data to our users more efficiently and securely. 12 This paper examines the use of a distributed approach with Hadoop to tile images, an approach that provides significant improvements in image processing time, from hours to minutes. This paper describes the constraints imposed on the solution and the resulting techniques developed for the hybrid solution of a customized Hadoop infrastructure over local and cloud resources in managing this ever-growing data set. It examines the performance trade-offs of using the more plentiful resources of the cloud, such as those provided by S3, against the bandwidth limitations such use encounters with remote resources. As part of this discussion this paper will outline some of the technologies employed, the reasons for their selection, the resulting performance metrics and the direction the project is headed based upon the demonstrated capabilities thus far.

Cloud Computing↗
NASA NTRS2013

MERRA/AS: The MERRA Analytic Services Project Interim Report

MERRA AS is a cyberinfrastructure resource that will combine iRODS-based Climate Data Server (CDS) capabilities with Coudera MapReduce to serve MERRA analytic products, store the MERRA reanalysis data collection in an HDFS to enable parallel, high-performance, storage-side data reductions, manage storage-side driver, mapper, reducer code sets and realized objects for users, and provide a library of commonly used spatiotemporal operations that can be composed to enable higher-order analyses.

MapReduce↗
DOE OSTI2015

Accelerating k-NN Algorithm with Hybrid MPI and OpenSHMEM

Machine Learning algorithms are benefiting from the continuous improvement of programming models, including MPI, MapReduce and PGAS. k-Nearest Neighbors (k-NN) algorithm is a widely used machine learning algorithm, applied to supervised learning tasks such as classification. Several parallel implementations of k-NN have been proposed in the literature and practice. However, on high-performance computing systems with high-speed interconnects, it is important to further accelerate existing designs of the k-NN algorithm through taking advantage of scalable programming models. To improve the performance of k-NN on large-scale environment with InfiniBand network, this paper proposes several alternative hybrid MPI+OpenSHMEM designs and performs a systemic evaluation and analysis on typical workloads. The hybrid designs leverage the one-sided memory access to better overlap communication with computation than the existing pure MPI design, and propose better schemes for efficient buffer management. The implementation based on k-NN program from MaTEx with MVAPICH2-X (Unified MPI+PGAS Communication Runtime over InfiniBand) shows up to 9.0% time reduction for training KDD Cup 2010 workload over 512 cores, and 27.6% time reduction for small workload with balanced communication and computation. Experiments of running with varied number of cores show that our design can maintain good scalability.

Lin, Jian↗
DOE OSTI2017

Combining Hadoop with MPI to Solve Metagenomics Problems that are both Data- and Compute-intensive

Metagenomics, the study of all microbial species cohabitants in an environment, usually produces large amount of sequence data varying from several GBs to a few TBs. Analyzing metagenomics data includes both data-intensive and compute-intensive steps, making the entire process hard to scale. Here we aim to optimize a metagenomics application that partitions the shortgun metagenomics sequences based on their species of origin. Our solution combines MapReduce-based BioPig analytic toolkit with MPI to provide scalability in respective to both data and compute. We also made some improvements to the existing BioPig toolkit by using simplified data types and compressed k-mer storage. These optimizations leads up to 193× speedup for the computing-intensive step and 9.6× speedup over the entire pipeline. Our optimized application is also capable of processing datasets that are 16 times larger on the same hardware platform. These conclusions indicate integrating heterogeneous technologies such as Hadoop and MPI is quite efficient to solve large genomics problems that are both data-intensive and compute-intensive.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Energy-efficient mapping of large-scale workflows under deadline constraints in big data computing systems

Large-scale workflows for big data analytics have become a main consumer of energy in data centers where moldable parallel computing models such as MapReduce are widely applied to meet high computational demands with time-varying computing resources. The granularity of task partitioning in each moldable job of such big data workflows has a significant impact on energy efficiency, which remains largely unexplored. In this paper, we analyze the properties of moldable jobs and formulate a workflow mapping problem to minimize the dynamic energy consumption of a given workflow request under a deadline constraint in big data systems. Since this problem is strongly NP-hard, we design a fully polynomial-time approximation scheme (FPTAS) for a special case with a pipeline-structured workflow on a homogeneous cluster and a heuristic for the generalized problem with an arbitrary workflow on a heterogeneous cluster. The performance superiority of the proposed solution in terms of dynamic energy saving and deadline missing rate is illustrated by extensive simulation results in comparison with existing algorithms, and further validated by real-life workflow implementation and experimental results in Hadoop/YARN systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

A quantitative model of application slow-down in multi-resource shared systems

Scheduling multiple jobs onto a platform enhances system utilization by sharing resources. The benefits from higher resource utilization include reduced cost to construct, operate, and maintain a system, which often include energy consumption. Maximizing these benefits comes at a price-resource contention among jobs increases job completion time. In this study, we analyze slow-downs of jobs due to contention for multiple resources in a system; referred to as dilation factor. We observe that multiple-resource contention creates non-linear dilation factors of jobs. From this observation, we establish a general quantitative model for dilation factors of jobs in multi-resource systems. A job is characterized by a vector-valued loading statistics and dilation factors of a job set are given by a quadratic function of their loading vectors. We demonstrate how to systematically characterize a job, maintain the data structure to calculate the dilation factor (loading matrix), and calculate the dilation factor of each job. We validate the accuracy of the model with multiple processes running on a native Linux server, virtualized servers, and with multiple MapReduce workloads co-scheduled in a cluster. Evaluation with measured data shows that the D-factor model has an error margin of less than 16%. We extended the D-factor model to capture the slow-down of applications when multiple identical resources exist such as multi-core environments and multi-disks environments. Finally, validation results of the extended D-factor model with HPC checkpoint applications on the parallel file systems show that D-factor accurately captures the slow down of concurrent applications in such environments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Exploiting analytics techniques in CMS computing monitoring

The CMS experiment has collected an enormous volume of metadata about its computing operations in its monitoring systems, describing its experience in operating all of the CMS workflows on all of the Worldwide LHC Computing Grid Tiers. Data mining efforts into all these information have rarely been done, but are of crucial importance for a better understanding of how CMS did successful operations, and to reach an adequate and adaptive modelling of the CMS operations, in order to allow detailed optimizations and eventually a prediction of system behaviours. These data are now streamed into the CERN Hadoop data cluster for further analysis. Specific sets of information (e.g. data on how many replicas of datasets CMS wrote on disks at WLCG Tiers, data on which datasets were primarily requested for analysis, etc) were collected on Hadoop and processed with MapReduce applications profiting of the parallelization on the Hadoop cluster. We present the implementation of new monitoring applications on Hadoop, and discuss the new possibilities in CMS computing monitoring introduced with the ability to quickly process big data sets from mulltiple sources, looking forward to a predictive modeling of the system.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2019

Co-location Pattern Mining of Geosocial Data to Characterize Urban Functional Spaces

Spatial Co-location Pattern (SCP) mining continues to play a critical role in understanding the morphology of urban functional spaces of world cities. It requires a large amount of fine-granular data and computing efficiency to handle the combinatorial explosion of co-location patterns. To this end, this work has two main contributions - i) We showcase a novel approach to perform SCP mining to characterize intra-city scale structure of urban functionality or co-located activity patterns using geosocial Points-of-Interest (POI) vector data. ii) We present a generalized and optimized parallel/distributed SCP mining algorithm implemented on a Hadoop MapReduce system and demonstrate the utility of our approach using the city of Berlin (Germany) as an example. The SCPs tend to vary across Berlin's municipal boroughs and at different spatial scales. Our findings on Berlin's functional structure conform to existing urban geography models. Such a data-driven exploration of massive urban POIs using distributed computing is first of its kind and can help better understand the changing dynamics of urban functionality, as well as physical, and social network structure around the world.

Masrur, Arif↗
DOE OSTI2014

PLAStiCC: Predictive Look-Ahead Scheduling for Continuous dataflows on Clouds

Scalable stream processing and continuous dataflow systems are gaining traction with the rise of big data due to the need for processing high velocity data in near real time. Unlike batch processing systems such as MapReduce and workflows, static scheduling strategies fall short for continuous dataflows due to the variations in the input data rates and the need for sustained throughput. The elastic resource provisioning of cloud infrastructure is valuable to meet the changing resource needs of such continuous applications. However, multi-tenant cloud resources introduce yet another dimension of performance variability that impacts the application’s throughput. In this paper we propose PLAStiCC, an adaptive scheduling algorithm that balances resource cost and application throughput using a prediction-based look-ahead approach. It not only addresses variations in the input data rates but also the underlying cloud infrastructure. In addition, we also propose several simpler static scheduling heuristics that operate in the absence of accurate performance prediction model. These static and adaptive heuristics are evaluated through extensive simulations using performance traces obtained from public and private IaaS clouds. Our results show an improvement of up to 20% in the overall profit as compared to the reactive adaptation algorithm.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

A Nonrelational Data Warehouse for the Analysis of Field and Laboratory Data From Multiple Heterogeneous Photovoltaic Test Sites

A nonrelational, distributed computing, data warehouse, and analytics environment (Energy-CRADLE) was developed for the analysis of field and laboratory data from multiple heterogeneous photovoltaic (PV) test sites. This data informatics and analytics infrastructure was designed to process diverse formats of PV performance data and climatic telemetry time-series data collected from a PV outdoor test network, i.e., the Solar Durability and Lifetime Extension global SunFarm network, as well as point-in-time laboratory spectral and image measurements of PV material samples. Using Hadoop/HBase for the distributed data warehouse, Energy-CRADLE does not have a predefined data table schema, which enables ingestion of data in diverse and changing formats. For easy data ingestion and data retrieval, Energy-CRADLE utilizes Hadoop streaming to enable Python MapReduce and provides a graphical user interface, i.e., py-CRADLE. By developing the Hadoop distributed computing platform and the HBase NoSQL database schema for solar energy, Energy-CRADLE exemplifies an integrated, scalable, secure, and user-friendly data informatics and analytics system for PV researchers. Furthermore, an example of Energy-CRADLE enabled scalable, data-driven, analytics is presented, where machine learning is used for anomaly detection across 2.2 million real-world current-voltage (I–V) curves of PV modules in three distinct Koppen–Geiger climatic zones.

14 SOLAR ENERGY↗
DOE OSTI2019

DECA: scalable XHMM exome copy-number variant calling with ADAM and Apache Spark

Abstract Background XHMM is a widely used tool for copy-number variant (CNV) discovery from whole exome sequencing data but can require hours to days to run for large cohorts. A more scalable implementation would reduce the need for specialized computational resources and enable increased exploration of the configuration parameter space to obtain the best possible results. Results DECA is a horizontally scalable implementation of the XHMM algorithm using the ADAM framework and Apache Spark that incorporates novel algorithmic optimizations to eliminate unneeded computation. DECA parallelizes XHMM on both multi-core shared memory computers and large shared-nothing Spark clusters. We performed CNV discovery from the read-depth matrix in 2535 exomes in 9.3 min on a 16-core workstation (35.3× speedup vs. XHMM), 12.7 min using 10 executor cores on a Spark cluster (18.8× speedup vs. XHMM), and 9.8 min using 32 executor cores on Amazon AWS’ Elastic MapReduce. We performed CNV discovery from the original BAM files in 292 min using 640 executor cores on a Spark cluster. Conclusions We describe DECA’s performance, our algorithmic and implementation enhancements to XHMM to obtain that performance, and our lessons learned porting a complex genome analysis application to ADAM and Spark. ADAM and Apache Spark are a performant and productive platform for implementing large-scale genome analyses, but efficiently utilizing large clusters can require algorithmic optimizations and careful attention to Spark’s configuration parameters.

Linderman, Michael D. (ORCID:0000000296437148)↗
DOE OSTI2016

A Demonstration of Concrete Structural Health Monitoring Framework for Degradation due to Alkali-Silica Reaction

Assessment and management of aging concrete structures in nuclear power plants require a more systematic approach than simple reliance on existing code margins of safety. Structural health monitoring of concrete structures aims to understand the current health condition of a structure based on heterogeneous measurements to produce high-confidence actionable information regarding structural integrity that supports operational and maintenance decisions. This ongoing research project is seeking to develop a probabilistic framework for health diagnosis and prognosis of aging concrete structures in a nuclear power plant that is subjected to physical, chemical, environment, and mechanical degradation. The proposed framework consists of four elements: monitoring, data analytics, uncertainty quantification and prognosis. This report focuses on degradation caused by ASR (alkali-silica reaction). Controlled specimens were prepared to develop accelerated ASR degradation. Different monitoring techniques – thermography, digital image correlation (DIC), mechanical deformation measurements, nonlinear impact resonance acoustic spectroscopy (NIRAS), and vibro-acoustic modulation (VAM) -- were used to detect the damage caused by ASR. Heterogeneous data from the multiple techniques was used for damage diagnosis and prognosis, and quantification of the associated uncertainty using a Bayesian network approach. Additionally, MapReduce technique has been demonstrated with synthetic data. This technique can be used in future to handle large amounts of observation data obtained from the online monitoring of realistic structures.

36 MATERIALS SCIENCE↗