Search NASA⌕ Search

SEARCH · Search NASA

Results for “Global Arrays”

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 55 records · Page 3

Fault Tolerant Communication Runtime Support for Data-Centric Programming Models

The largest supercomputers in the world today consist of hundreds of thousands of processing cores and many more other hardware components. At such scales, hardware faults are a common place necessitating the need for fault-resilient software systems. While different fault resilient models are available today, most of them focus on allowing the computational processes to survive faults. On the other hand, we have recently started investigating fault resilience techniques for data-centric programming models such as the partitioned global address space (PGAS) models. The primary difference in data-centric models is the decoupling of computation and data locality. That is, data placement is decoupled from the executing processes allowing us to view process failure (a physical node hosting a process is dead) separately from data failure (a physical node hosting data is dead). In this paper, we take a first step towards data centric fault resilience by designing and implementing a fault resilient one-sided communication runtime framework using Global Arrays and its communication system, ARMCI. The framework consists of a fault resilient process manager, low overhead and network assisted remote node fault detection module, non-data moving collective communication primitives and providing failure semantics and error codes for one-sided communication runtime systems. Our performance evaluation indicates that our framework incurs little overhead compared to state of the art designs and provides a fundamental framework of fault resiliency for PGAS models. Keywords

Vishnu, Abhinav↗

On the Suitability of MPI as a PGAS Runtime

Partitioned Global Address Space (PGAS) models are emerging as a popular alternative to MPI models for designing scalable applications. At the same time, MPI remains a ubiquitous communication subsystem due to its standardization, high performance, and availability on leading platforms. In this paper, we explore the suitability of using MPI as a scalable PGAS communication subsystem. We focus on the Remote Memory Access (RMA) communication in PGAS models which typically includes {\em get, put,} and {\em atomic memory operations}. We perform an in-depth exploration of design alternatives based on MPI. These alternatives include using a semantically-matching interface such as MPI-RMA, as well as not-so-intuitive interfaces such as MPI two-sided with a combination of multi-threading and dynamic process management. With an in-depth exploration of these alternatives and their shortcomings, we propose a novel design which is facilitated by the data-centric view in PGAS models. This design leverages a combination of highly tuned MPI two-sided semantics and an automatic, user-transparent split of MPI communicators to provide asynchronous progress. We implement the asynchronous progress ranks approach and other approaches within the Communication Runtime for Exascale which is a communication subsystem for Global Arrays. Our performance evaluation spans pure communication benchmarks, graph community detection and sparse matrix-vector multiplication kernels, and a computational chemistry application. The utility of our proposed PR-based approach is demonstrated by a 2.17x speed-up on 1008 processors over the other MPI-based designs.

Computational modeling↗

Evaluating the Potential of Cray Gemini Interconnect for PGAS Communication Runtime Systems

The Cray Gemini Interconnect has been recently introduced as the next generation network for building scalable multi-petascale supercomputers. The Cray XE6 systems, which use the Gemini Interconnect are becoming available with Message Passing Interface (MPI) and Partitioned Global Address Space (PGAS) Models such as as Global Arrays, Unified Parallel C, Co-Array Fortran and Cascade High Performance Language. These PGAS models use one-sided communication runtime systems such as MPI-Remote Memory Access, Aggregate Remote Memory Copy Interface and proprietary communication runtime systems. The primary objective of our work is to study the potential of Cray Gemini Interconnect by designing application specific micro-benchmarks using the DMAPP userspace library provided by the Gemini Interconnect. To meet this objective, we design micro-benchmarks to study the performance of simple communication primitives and application specific micro-benchmarks to understand the behavior of Gemini Interconnect at scale. In our experiments, the Gemini Interconnect can achieve a peak bandwidth of 6911 MB/s and a latency of 1us for get communication primitive. Scalability tests for atomic memory operations and shift communication operation up to 65536 processes shows the efficacy of the Gemini Interconnect.

Vishnu, Abhinav↗

Scioto: A Framework for Global-ViewTask Parallelism

We introduce Scioto, Shared Collections of Task Objects, a framework for supporting task-parallelism in one-sided and global-view parallel programming models. Scioto provides lightweight, locality aware dynamic load balancing and interoperates with existing parallel models including MPI, SHMEM, CAF, and Global Arrays. Through task parallelism, the Scioto framework provides a solution for overcoming load imbalance and heterogeneity as well as dynamic mapping of computation onto emerging multicore architectures. In this paper, we present the design and implementation of the Scioto framework and demonstrate its effectiveness on the Unbalanced Tree Search (UTS) benchmark and two quantum chemistry codes: the closed shell Self-Consistent Field (SCF) method and a sparse tensor contraction kernel extracted from a coupled cluster computation. We explore the efficiency and scalability of Scioto through these sample applications and demonstrate that is offers low overhead, achieves good performance on heterogeneous and multicore clusters, and scales to hundreds of processors.

99 GENERAL AND MISCELLANEOUS↗

Barrier elision for production parallel programs

Large scientific code bases are often composed of several layers of runtime libraries, implemented in multiple programming languages. In such situation, programmers often choose conservative synchronization patterns leading to suboptimal performance. In this paper, we present context-sensitive dynamic optimizations that elide barriers redundant during the program execution. In our technique, we perform data race detection alongside the program to identify redundant barriers in their calling contexts; after an initial learning, we start eliding all future instances of barriers occurring in the same calling context. We present an automatic on-the-fly optimization and a multi-pass guided optimization. We apply our techniques to NWChem - a 6 million line computational chemistry code written in C/C++/Fortran that uses several runtime libraries such as Global Arrays, ComEx, DMAPP, and MPI. Our technique elides a surprisingly high fraction of barriers (as many as 63%) in production runs. This redundancy elimination translates to application speedups as high as 14% on 2048 cores. Our techniques also provided valuable insight about the application behavior, later used by NWChem developers. Overall, we demonstrate the value of holistic context-sensitive analyses that consider the domain science in conjunction with the associated runtime software stack.

97 MATHEMATICS AND COMPUTING↗

Scalable fault tolerance runtime technology for petascale computers (Final Project Report)

With the massive number of components comprising the forthcoming petascale computer systems, hardware failures will be routinely encountered during execution of large-scale applications. Due to the multidisciplinary, multiresolution, and multiscale nature of scientific problems that drive the demand for high end systems, applications place increasingly differing demands on the system resources: disk, network, memory, and CPU. In addition to MPI, future applications are expected to use advanced programming models such as those developed under the DARPA HPCS program as well as existing global address space programming models such as Global Arrays, UPC, and Co-Array Fortran. While there has been a considerable amount of work in fault tolerant MPI with a number of strategies and extensions for fault tolerance proposed, virtually none of advanced models proposed for emerging petascale systems is currently fault aware. To achieve fault tolerance, development of underlying runtime and OS technologies able to scale to petascale level is needed. This project has evaluated range of runtime techniques for fault tolerance for advanced programming models.

97 MATHEMATICS AND COMPUTING↗

Determination of Venus winds by ground-based radio tracking of the VEGA balloons

A global array of 20 radio observatories was used to measure the three-dimensional position and velocity of the two meteorological balloons that were injected into the equatorial region of the Venus atmosphere near Venus midnight by the VEGA spacecraft on 11 and 15 June 1985. Initial analysis of only radial velocities indicates that each balloon was blown westward about 11,500 kilometers (8,000 kilometers on the night side) by zonal winds with a mean speed of about 70 meters per second. Excursions of the data from a model of constant zonal velocity were generally less than 3 meters per second; however, a much larger variation was evident near the end of the flight of the second balloon. Consistent systematic trends in the residuals for both balloons indicate the possibility of a solar-fixed atmospheric feature. Rapid variations in balloon velocity were often detected within a single transmission (330 seconds); however, they may represent not only atmospheric motions but also self-induced aerodynamic motions of the balloon.

R A Preston↗

The Vega balloon experiment - Initial results from the global radio tracking

A unique global array of 20 radio telescopes provided 24-h telemetry acquisition of meteorological data from the Vega balloons and differential VLBI measurements of their trajectories. Initial Doppler-tracking analysis indicates mean zonal wind velocities of 69 + or - 1 and 66 + or - 1 m/sec at the Vega 1 and Vega 2 float heights, and discloses an anomaly in the Vega 2 trajectory above the mountains in Aphrodite Terra.

Preston, R. A.↗

Initial estimates of Venus winds from ground-based radio tracking of the Vega balloons

A global array of 20 radio observatories was used to measure the three-dimensional position and velocity of the two meteorological balloons that were injected into the equatorial region of the Venus atmosphere by the Vega spacecraft. Initial analysis of only radial velocities indicates that each balloon was blown westward about 11,500 kilometers (8000 kilometers on the night side) by zonal winds with a mean speed of about 70 meters per second. Excursions of the data from a model of constant zonal velocity are generally less than 3-meters per second; however, a much larger variation is evident near the end of the flight of the second balloon. Consistent systematic trends in the residual for both balloons indicate the possibility of a solar-fixed atmospheric feature.

Preston, Robert A.↗

Unconditionally stable concurrent procedures for transient finite-element analysis

A family of algorithms was outlined which would appear to be particularly well-suited for implementation in a parallel environment. This is due to the fact that for any partition of the mesh each subdomain in the partition can be processed over a time step simultaneously and independently of the rest. The method eliminates the need for assembling and factorizing large global arrays while retaining the unconditional stability properties of the algorithms used at the local level. To critically appraise the proposed methodology, two limiting cases were considered: element-by-element mesh partitions, and coarse mesh partitions. It was concluded that while the proposed methodology can be useful in sequential machines, it would appear to be promising as it bears on computation. It should also be emphasized that extensions of the method to nonlinear problems are possible.

Ortiz, Michael↗

The parsec-scale jets in 3C 273 and 3C 345

We present recent centimeter-wavelength 'global-array' VLBI images of the quasars 3C 273 and 3C 345 with dynamic ranges in excess of 3000:1. They trace the jet emission on scales from r about 5 parsecs out to about 200 parsecs. The maps of 3C273 at 18 cm wavelength show a well-collimated one-sided jet with a wavy ridge line; these wiggles exist on size scales ranging from about 1 pc to over 10 kpc. We show that the well-known superluminal flow extends to r about 120 pc. Images of 3C 345 at 6 cm wavelength from data taken in 1989 and 1990 show surprising features not seen in lower dynamic-range maps of this otherwise well-studied quasar: the inner part of the jet shows edge-brightening, which is important for modeling of jet confinement. The jet fades out very abruptly at r about 40 pc, then reappears at about 70 pc; beyond 70 pc, the resumed jet flares and is more diffuse than an extrapolation of the inner jet would predict. This morphology is reminiscent of M 87, and is suggestive of a shock wave.

Unwin, Stephen C.↗

The second Caltech-Jodrell Bank VLBI survey. 1: Observations of 91 of 193 sources

We define the sample for the second Caltech-Jodrell Bank very long base interferometry (VLBI) survey. This is a sample of 193 flat- or gigahertz-peaked-spectrum sources selected at 4850 MHz. This paper presents images of 91 sources with a resolution of approximately 1 mas, obtained using VLBI observations at 4992 MHz with a global array. The remaining images and the integrated radio spectra will be presented in a forthcoming paper by Henstock et al.

Taylor, G. B.↗

Commissioning Results on the JWST Testbed Telescope

The one-meter 18 segment JWST Testbed Telescope (TBT) has been developed at Ball Aerospace to facilitate commissioning operations for the JWST Observatory. Eight different commissioning activities were tested on the TBT: telescope focus sweep, segment ID and Search, image array, global alignment, image stacking, coarse phasing, fine phasing, and multi-field phasing. This paper describes recent commissioning results from experiments performed on the TBT.

Dean, Bruce H.↗

Radioastron Discovery of A Mini-Cocoon Around the Restarted Parsec-Scale Jet in 3C 84

We present RadioAstron space-based very long baseline interferometry (VLBI) observations of the nearby radio galaxy 3C 84 (NGC 1275) at the centre of the Perseus cluster. The observations were carried out during a perigee passage of the Spektr-R spacecraft on September 21–22, 2013 and involved a global array of 24 ground radio telescopes observing at 5 GHz and 22 GHz, together with the Space Radio Telescope (SRT). Furthermore, the Very Long Baseline Array (VLBA) and the phased Very Large Array (VLA) observed the source quasi-simultaneously at 15 GHz and 43 GHz. Fringes between the ground array and the SRT were detected on baseline lengths up to 8.1 times the Earth’s diameter, providing unprecedented resolution for 3C 84 at these wavelengths. We note that the corresponding fringe spacing is 125 μas at 5 GHz and 27 μas at 22 GHz. Our space-VLBI images reveal a previously unseen sub-structure inside the compact ∼1 pc long jet that was ejected about ten years earlier. In the 5 GHz image, we detected, for the first time, low-intensity emission from a cocoon-like structure around the restarted jet. Our results suggest that the increased power of the young jet is inflating a bubble of hot plasma as it carves its way through the ambient medium of the central region of the galaxy. Here, we estimate the minimum energy stored in the mini-cocoon, along with its pressure, volume, expansion speed, and the ratio of heavy particles to relativistic electrons, as well as the density of the ambient medium. About half of the energy delivered by the jet is dumped into the mini-cocoon and the quasi-spherical shape of the bubble suggests that this energy may be transferred to a significantly larger volume of the interstellar medium than what would be accomplished by the well-collimated jet on its own. The pressure of the hot mini-cocoon also provides a natural explanation for the almost cylindrical jet profile seen in the 22 GHz RadioAstron image.

galaxies: jets↗

Efficient Extraction of Regional Subsets from Massive Climate Datasets using Parallel IO

The size of datasets produced by current climate models is increasing rapidly to the scale of petabytes. To handle data at this scale parallel analysis tools are required, however the majority of climate analysis software remains at the scale of workstations. Further, many climate analysis tools adequately process regularly gridded data but lack sufficient features when handling unstructured grids. This paper presents a data-parallel subsetter capable of correctly handling unstructured grids while scaling to over 2000 cores. The approach is based on the partitioned global address space (PGAS) parallel programming model and one-sided communication. The paper demonstrates that IO remains the single greatest bottleneck for this domain of applications and that parallel analysis of climate data succeeds in practice.

54 ENVIRONMENTAL SCIENCES↗

Dynamic Time-Variant Connection Management for PGAS Models on InfiniBand

InfiniBand (IB) has established itself as a promising network infrastructure for high-end cluster computing systems as evidenced by its usage in the Top500 supercomputers today. While the IB standard describes multiple communication models (including reliable-connection (RC), and unreliable datagram (UD)), most of its promising features such as remote direct memory access (RDMA), hardware atomics and network fault tolerance are only available for the RC model which requires connections between communicating process pairs. In the past, several researchers have proposed on-demand connection management techniques that establish connections when there is a need to communicate, and not before. While such techniques work well for algorithms and applications that only communicate with a small set of processes in their life-time, there exists a broad set of applications that do not follow this trend. For example, applications that perform dynamic load balancing and adaptive work stealing have a small set of communicating neighbors at any given time, but over time the total number of neighbors can be very high; in some cases, equal to the entire system size. In this paper, we present a dynamic time-variant connection management approach that establishes connections on-demand like previous approaches, but further intelligently tears down some of the unused connections as well. While connection tear-down itself is relevant for any programming model, different models have different complexities. In this paper, we study the Global Arrays (GA) PGAS model for two reasons: (1) the simple one-sided communication primitives provided by GA and other PGAS models ensure that connection requests are always initiated by the origin process without explicit synchronization with the target process---this makes connection tear-down simpler to handle; and (2) GA supports several applications that demonstrate this behavior making it an obvious first target for the proposed enhancements. We evaluate our proposed approach using several micro-benchmarks as well as the NWChem computational chemistry application on more than 6000 processes, and show that our approach can significantly reduce the memory requirements of the communication library while maintaining its performance. To the best of our knowledge, this is the first design, implementation and evaluation of connection tear-down protocols over InfiniBand.

99 GENERAL AND MISCELLANEOUS↗

NWChem

Computational atomistic modeling has emerged as a powerful approach for fundamental studies in chemistry, materials science, geosciences, and biology. It has the ability to provide detailed insights into complex phenomena and over the years has grown into a powerful tool not only to validate experiment, but also to predict new phenomena. In order to harness computational modeling to the fullest, superior computational tools are required that not only offer a broad spectrum of capabilities, but are also capable of taking advantage of modern massively parallel computer architectures efficiently to solve real world problems. The NWChem program suite is an example along these lines. It offers a range of capabilities to perform first-principles electronic structure calculations on molecular and periodic systems, classical molecular dynamics simulations and hybrid QM/MM simulations that permits one to combine quantum and classical methods within a calculation. The code is designed to run on high-performance parallel supercomputers as well as conventional workstation clusters with the goal to provide scalable solutions for large scale atomistic simulations. It has been ported to almost all high-performance computing platforms, workstations, PCs running LINUX, as well as clusters of desktop platforms or workgroup servers. The package is scalable, both in its ability to treat large problems efficiently, and in its utilization of available parallel computing resources. The parallel framework for NWChem is provided by the Global Array (GA) toolkit developed at PNNL. NWChem is developed and maintained by the Environmental Molecular Sciences Laboratory (EMSL) located at the Pacific Northwest National Laboratory (PNNL) in Washington State. The latest release (version 6.0) of the code is distributed under the terms of the Educational Community License (ECL) version 2.0.

99 GENERAL AND MISCELLANEOUS↗

Global-View Coefficients: A Data Management Solution for Parallel Quantum Monte Carlo Applications

Quantum Monte Carlo (QMC) applications perform simulation with respect to an initial state of the quantum mechanical system, which is often captured by using a cubic B-spline basis. This representation is stored as a read-only table of coefficients, and accesses to the table are generated at random as part of the Monte Carlo simulation. Current QMC applications, such as QWalk and QMCPACK, replicate this table at every process or node, which limits scalability because increasing the number of processors does not enable larger systems to be run. We present a partitioned global address space (PGAS) approach to transparently managing this data using Global Arrays in a manner that allows the memory of multiple nodes to be aggregated. We develop an automated data management system that significantly reduces communication overheads, enabling new capabilities for QMC codes. Experimental results with QWalk and QMCPACK demonstrate the effectiveness of the data management system.

Niu, Qingpeng↗