Search

Oak Ridge National Laboratory (ORNL) experimental neutron science facilities produce 1.2\,TB a day of raw event-based data that is stored using the standard metadata-rich NeXus schema built on top of the HDF5 file format. Performance of several data reduction workflows is largely determined by the amount of time spent on the loading and processing algorithms in Mantid, an open-source data analysis framework used across several neutron sciences facilities around the world. The present work introduces new data management algorithms to address identified input output (I/O) bottlenecks on Mantid. First, we introduce an in-memory binary-tree metadata index that resemble NeXus data access patterns to provide a scalable search and extraction mechanism. Second, data encapsulation in Mantid algorithms is optimally redesigned to reduce the total compute and memory runtime footprint associated with metadata I/O reconstruction tasks. Results from this work show speed ups in wall-clock time on ORNL data reduction workflows, ranging from 11\% to 30\% depending on the complexity of the targeted instrument-specific data. Nevertheless, we highlight the need for more research to address reduction challenges as experimental data volumes increase., Comment: 7 pages, 4 figures, International Workshop on Big Data Reduction held with 2020 IEEE International Conference on Big Data

The term “in situ processing” has evolved over the last decade to mean both a specific strategy for visualizing and analyzing data and an umbrella term for a processing paradigm. The resulting confusion makes it difficult for visualization and analysis scientists to communicate with each other and with their stakeholders. To address this problem, a group of over 50 experts convened with the goal of standardizing terminology. This paper summarizes their findings and proposes a new terminology for describing in situ systems. An important finding from this group was that in situ systems are best described via multiple, distinct axes: integration type, proximity, access, division of execution, operation controls, and output type. This paper discusses these axes, evaluates existing systems within the axes, and explores how currently used terms relate to the axes.

Author(s): Godoy, WF; Podhorszki, N; Wang, R; Atkins, C; Eisenhauer, G; Gu, J; Davis, P; Choi, J; Germaschewski, K; Huck, K; Huebl, A; Kim, M; Kress, J; Kurc, T; Liu, Q; Logan, J; Mehta, K; Ostrouchov, G; Parashar, M; Poeschel, F; Pugmire, D; Suchyta, E; Takahashi, K; Thompson, N; Tsutsumi, S; Wan, L; Wolf, M; Wu, K; Klasky, S | Abstract: We present ADIOS 2, the latest version of the Adaptable Input Output (I/O) System. ADIOS 2 addresses scientific data management needs ranging from scalable I/O in supercomputers, to data analysis in personal computer and cloud systems. Version 2 introduces a unified application programming interface (API) that enables seamless data movement through files, wide-area-networks, and direct memory access, as well as high-level APIs for data analysis. The internal architecture provides a set of reusable and extendable components for managing data presentation and transport mechanisms for new applications. ADIOS 2 bindings are available in C++11, C, Fortran, Python, and Matlab and are currently used across different scientific communities. ADIOS 2 provides a communal framework to tackle data management challenges as we approach the exascale era of supercomputing.

Complex workflows consisting of multiple simulation and analysis codes running concurrently through in-memory coupling is becoming popular due to inherent advantages in online management of large-scale data, resilience, and the code development process. However, orchestrating such a multi-application workflow to efficiently utilize resources on a heterogeneous architecture is challenging. In this paper, we present our results with running the Fusion Whole Device Modeling benchmark workflow on Summit, a pre-exascale supercomputer at Oak Ridge National Laboratory. We explore various resource distribution and process placement mechanisms, including sharing compute nodes between processes from separate applications. We show that fine-grained process placement can have a significant impact towards efficient utilization of the compute power of a node on Summit, and conclude that sophisticated tools for performing co-design studies of multi-application workflows can play an important role towards efficient orchestration of such workflows.

One of the core issues across computer and computational science today is adapting to, managing, and learning from the influx of "Big Data". In the commercial space, this problem has led to a huge investment in new technologies and capabilities that are well adapted to dealing with the sorts of human-generated logs, videos, texts, and other large-data artifacts that are processed and resulted in an explosion of useful platforms and languages (Hadoop, Spark, Pandas, etc.). However, translating this work from the enterprise space to the computational science and HPC community has proven somewhat difficult, in part because of some of the fundamental differences in type and scale of data and timescales surrounding its generation and use. We describe a forward-looking research and development plan which centers around the concept of making Input/Output (I/O) intelligent for users in the scientific community, whether they are accessing scalable storage or performing in situ workflow tasks. Much of our work is based on our experience with the Adaptable I/O System (ADIOS 1.X), and our next generation version of the software ADIOS 2.X [1].

As the memory and storage hierarchy get deeper and more complex, it is important to have new benchmarks and evaluation tools that allow us to explore the emerging middleware solutions to use this hierarchy. Skel is a tool aimed at automating and refining this process of studying HPC I/O performance. It works by generating application I/O kernel/benchmarks as determined by a domain-specific model. This paper provides some techniques for extending Skel to address new situations and to answer new research questions. For example, we document use cases as diverse as using Skel to troubleshoot I/O performance issues for remote users, refining an I/O system model, and facilitating the development and testing of a mechanism for runtime monitoring and performance analytics. We also discuss data oriented extensions to Skel to support the study of compression techniques for Exascale scientific data management.

The present study introduces a parallel Jacobian-free Newton Krylov (JFNK) general minimal residual (GMRES) solution for the discretized radiative transfer equation (RTE) in 3D, absorbing, emitting and scattering media. For the angular and spatial discretization of the RTE, the discrete ordinates method (DOM) and the finite volume method (FVM) including flux limiters are employed, respectively. Instead of forming and storing a large Jacobian matrix, JFNK methods allow for large memory savings as the required Jacobian-vector products are rather approximated by semiexact and numerical formulations, for which convergence and computational times are presented. Parallelization of the GMRES solution is introduced in a combined memory-shared/memory-distributed formulation that takes advantage of the fact that only large vector arrays remain in the JFNK process. Results are presented for 3D test cases including a simple homogeneous, isotropic medium and a more complex non-homogeneous, non-isothermal, absorbing-emitting and anisotropic scattering medium with collimated intensities. Additionally, convergence and stability of Gram-Schmidt and Householder orthogonalizations for the Arnoldi process in the parallel GMRES algorithms are discussed and analyzed. Overall, the introduction of JFNK methods results in a parallel, yet scalable to the tested 2048 processors, and memory affordable solution to 3D radiative transfer problems without compromising the accuracy and convergence of a Newton-like solution.

General-purpose computing on graphics processing units (GPGPU) is a recent technique that allows the parallel graphics processing unit (GPU) to accelerate calculations performed sequentially by the central processing unit (CPU). To introduce GPGPU to radiative transfer, the Gauss-Seidel solution of the well-known expressions for 1-D and 3-D homogeneous, isotropic media is selected as a test case. Different algorithms are introduced to balance memory and GPU-CPU communication, critical aspects of GPGPU. Results show that speed-ups of one to two orders of magnitude are obtained when compared to sequential solutions. The underlying value of GPGPU is its potential extension in radiative solvers (e.g., Monte Carlo, discrete ordinates) at a minimal learning curve.

The application of flux limiters to the discrete ordinates method (DOM), S"N, for radiative transfer calculations is discussed and analyzed for 3D enclosures for cases in which the intensities are strongly coupled to each other such as: radiative equilibrium and scattering media. A Newton-Krylov iterative method (GMRES) solves the final systems of linear equations along with a domain decomposition strategy for parallel computation using message passing libraries in a distributed memory system. Ray effects due to angular discretization and errors due to domain decomposition are minimized until small variations are introduced by these effects in order to focus on the influence of flux limiters on errors due to spatial discretization, known as numerical diffusion, smearing or false scattering. Results are presented for the DOM-integrated quantities such as heat flux, irradiation and emission. A variety of flux limiters are compared to ''exact'' solutions available in the literature, such as the integral solution of the RTE for pure absorbing-emitting media and isotropic scattering cases and a Monte Carlo solution for a forward scattering case. Additionally, a non-homogeneous 3D enclosure is included to extend the use of flux limiters to more practical cases. The overall balance of convergence, accuracy, speed and stability using flux limiters is shown to be superior compared to step schemes for any test case.

This study concerns the prediction of radiation heat transfer in evaporating water sprays for a 1D planar media. The spray evolution is described by a Lagrangian sectional approach with the initial diameter size classes defined by normal and log–normal distributions. The spray and the gas-phase radiative properties are recast in terms of cumulative distribution functions (CDF) for use with a correlated-k approach to solve the radiative transfer equation (RTE). The spectral properties required for constructing the CDFs for the droplets and gas are determined using Mie theory and the HITEMP databases, respectively. Cases are conducted to explore the sensitivity of radiative energy attenuation to time evolving droplet size distributions as a function of initial distribution, distance to the energy source, volume fraction and temperature. Results from this study show that the PDFs generate a positive skewness due to the size dependent absorption properties of the droplet. These findings suggest that the droplet size distribution can be adequately described by prescribed, non-symmetrical PDFs that are parameterized by lower order moments. 2008 Elsevier Ltd. All rights reserved.

Analytical expressions are developed to scale the extinction, scattering and absorption coefficients as a function of the Sauter mean diameter for polydisperse water sprays in fire suppression systems. A scaling procedure is introduced to avoid prohibitive exact integration of the functions obtained from Mie theory resulting in several orders in magnitude of computational savings. Spectral-based and total transmission of real spray distributions using the scaling procedure are compared to exact results and experimental data. Results show the proposed scaling procedure yields significant computational savings with little loss in accuracy for predictions of spectral and total transmission.

This study uses the correlated-k (c-k) and Mie scattering theory to evaluate absorption and scattering properties of participating media for fire suppression environments. In this approach the irregular spectral distribution of the radiative properties is reordered into cumulative distribution functions on a narrow band basis increasing the speed of property evaluation when compared to line-by-line calculations. The spectral properties are determined from the HITEMP database for carbon dioxide and water vapor, along with Mie and Rayleigh scattering theories for water droplets and soot particles, respectively. Results are presented for radiative heat transfer in a 1D domain for several mixtures and show that the attenuation of the radiation is highly sensitive to the water droplet size, mass loading and soot particle concentration.Copyright © 2005 by ASME

Performance of data reduction workflows at the High Flux Isotope Reactor (HFIR) and the Spallation Neutron Source (SNS) at Oak Ridge National Laboratory (ORNL) is mainly determined by the time spent loading raw measurement events stored in large and sparse datasets. This paper describes: (1) our long-term view to leverage SNS and HFIR data management needs with our experience at ORNL’s world-class high performance computing (HPC) facilities, and (2) our short-term efforts to speed up current workflows using Mantid, a data analysis and reduction community framework used across several neutron scattering facilities. We show that minimally invasive short-term improvements in metadata management have a moderate impact in speeding up current production workflows. We propose a more disruptive domain-specific solution: the No Cost Input Output (NCIO) framework, we provide an overview, the risks and challenges in NCIO’s adoption by HFIR and SNS stakeholders.