Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “supercomputers”

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 865 records · Page 48

TensorFlow at Scale: Performance and productivity analysis of distributed training with Horovod, MLSL, and Cray PE ML

Summary Deep learning has proven to be a successful tool for solving a large variety of problems in various scientific fields and beyond. In recent years, the models as well as the available datasets have grown bigger and more complicated, and thus, an increasing amount of computing resources is required in order to train these models in a reasonable amount of time. Besides being able to use HPC resources, deep learning model developers want flexible frameworks which allow for rapid prototyping. One of the most important of these frameworks is Google TensorFlow, which provides both features, ie, good performance as well as flexibility. In this paper, we discuss different solutions for scaling the TensorFlow Framework to thousands of nodes on contemporary Cray XC supercomputing systems.

Kurth, Thorsten↗

A performance analysis of the first generation of HPC‐optimized Arm processors

Summary In this paper, we present performance results from Isambard, the first production supercomputer to be based on Arm CPUs that have been optimized specifically for HPC. Isambard is the first Cray XC50 “Scout” system, combining Cavium ThunderX2 Arm‐based CPUs with Cray's Aries interconnect. The full Isambard system will be delivered in the summer of 2018, when it will contain over 10 000 Arm cores. In this work, we present node‐level performance results from eight early‐access nodes that were upgraded to B0 beta silicon in March 2018. We present node‐level benchmark results comparing ThunderX2 with mainstream CPUs, including Intel Skylake and Broadwell, as well as Xeon Phi. We focus on a range of applications and mini‐apps important to the UK national HPC service, ARCHER, as well as to the Isambard project partners and the wider HPC community. We also compare performance across three major software toolchains available for Arm: Cray's CCE, Arm's version of Clang/Flang/LLVM, and GNU.

97 MATHEMATICS AND COMPUTING↗

Node failure resiliency for Uintah without checkpointing

The frequency of failures in upcoming exascale supercomputers may well be greater than at present due to many-core architectures if component failure rates remain unchanged. This potential increase in failure frequency coupled with I/O challenges at exascale may prove problematic for current resiliency approaches such as checkpoint restarting, although the use of fast intermediate memory may help. Algorithm-Based Fault Tolerance (ABFT) using Adaptive Mesh Refinement (AMR) is one resiliency approach used to address these challenges. For adaptive mesh codes, a coarse mesh version of the solu- tion may be used to restore the fine mesh solution. This paper addresses the implementation of the ABFT approach within the Uintah software framework: both at a software level within Uintah and in the data reconstruction method used for the recovery of lost data. This method has two problems: inaccuracies introduced during the reconstruction propagate forward in time, and the physical consistency of variables such as positivity or boundedness may be violated during interpolation. These challenges can be addressed by the combination of two techniques: 1. a fault-tolerant MPI implementation to recover from runtime node failures, and 2. high-order interpolation schemes to preserve the physical solution and reconstruct lost data. Here, the approach considered here uses a "Limited Essentially Non-Oscillatory" (LENO) scheme along with AMR to rebuild the lost data without checkpointing using Uintah. Experiments were carried out using a fault-tolerant MPI - ULFM to recover from runtime failure, and LENO to recover data on patches belonging to failed ranks, while the simulation was continued to the end. Results show that this ABFT approach is up to 10x faster than the traditional checkpointing method. The new interpolation approach is more accurate than linear interpolation and not subject to the overshoots found in other interpolation methods.

97 MATHEMATICS AND COMPUTING↗

Hierarchical Roofline analysis for GPUs: Accelerating performance optimization for the NERSC‐9 Perlmutter system

Summary The Roofline performance model provides an intuitive and insightful approach to identifying performance bottlenecks and guiding performance optimization. In preparation for the next‐generation supercomputer Perlmutter at NERSC, this paper presents a methodology to construct a hierarchical Roofline on NVIDIA GPUs and extends it to support reduced precision and Tensor Cores. The hierarchical Roofline incorporates L1, L2, device memory, and system memory bandwidths into one single figure, and it offers more profound insights into performance analysis than the traditional DRAM‐only Roofline. We use our Roofline methodology to analyze three proxy applications: GPP from BerkeleyGW, HPGMG from AMReX, and conv2d from TensorFlow. In doing so, we demonstrate the ability of our methodology to readily understand various aspects of performance and performance bottlenecks on NVIDIA GPUs and motivate code optimizations.

Yang, Charlene↗

Interfacing HDF5 with a scalable object‐centric storage system on hierarchical storage

Summary Object storage technologies that take advantage of multitier storage on HPC systems are emerging. However, to use these technologies at present, applications have to be modified significantly from current I/O libraries. HDF5, a widely used I/O middleware on HPC systems, provides a virtual object layer (VOL) that allows applications to connect to different storage mechanisms transparently without requiring significant code modifications. We recently designed the proactive data containers (PDC) object‐centric storage system that provides the capabilities of transparent, asynchronous, and autonomous data movement taking advantage of multiple storage tiers—a decision that has so far been left upon the user on most current systems. To enable PDC's features through HDF5 without modifying application codes, we have developed an HDF5 VOL connector that interfaces with PDC. We present in this article the connector interface and evaluate its performance on Cori, a Cray XC40 supercomputer located at the National Energy Research Scientific Computing Center (NERSC). Our evaluation demonstrates up to an 8× improvement compared with HDF5 that has the most recent optimizations.

Mu, Jingqing↗

A Co-design Framework for Online Data Analysis and Reduction

Science applications preparing for the exascale era are increasingly exploring in situ computations comprising of simulation-analysis-reduction pipelines coupled in-memory. Efficient composition and execution of such complex pipelines for a target platform is a codesign process that evaluates the impact and tradeoffs of various application- and system-specific parameters. In this article, we describe a toolset for automating performance studies of composed HPC applications that perform online data reduction and analysis. We describe Cheetah, a new framework for composing parametric studies on coupled applications, and Savanna, a runtime engine for orchestrating and executing campaigns of codesign experiments. Furthermore, this toolset facilitates understanding the impact of various factors such as process placement, synchronicity of algorithms, and storage versus compute requirements for online analysis of large data. Ultimately, we aim to create a catalog of performance results that can help scientists understand tradeoffs when designing next-generation simulations that make use of online processing techniques. We illustrate the design of Cheetah and Savanna, and present application examples that use this framework to conduct codesign studies on small clusters as well as leadership class supercomputers.

97 MATHEMATICS AND COMPUTING↗

A step towards the final frontier: Lessons learned from acceptance testing of the first HPE/Cray EX 3000 system at ORNL

Summary In this article, we summarize the deployment of the Air Force Weather (AFW) HPC11 system at Oak Ridge National Laboratory (ORNL) including the process followed to successfully complete acceptance testing of the system. HPC11 is the first HPE/Cray EX 3000 system that has been successfully released to its user community in a federal facility. HPC11 consists of two identical 800‐node supercomputers, Fawbush and Miller, with access to two independent and identical lustre parallel file systems. HPC11 is equipped with Slingshot 10 interconnect technology and relies on the HPE Performance Cluster Manager software for system configuration. ORNL has a clearly defined acceptance testing process used to ensure that every new system deployed can provide the necessary capabilities to support user workloads. We worked closely with HPE and AFW to develop a set of tests that used the United Kingdom's Meteorological Office's Unified Model and 4‐dimensional variational data assimilation. We also included benchmarks and applications from the Oak Ridge Leadership Computing Facility portfolio to fully exercise the HPE/Cray programming environment and evaluate the functionality and performance of the system. Acceptance testing of HPC11 required parallel execution of each element on Fawbush and Miller. In addition, careful coordination was needed to ensure successful acceptance of the newly deployed lustre file systems alongside the compute resources. In this work, we present test results from specific system components and provide an overview of the issues identified, challenges encountered, and the lessons learned along the way.

Melesse Vergara, Verónica G.↗

Evaluating integration and performance of containerized climate applications on a Hewlett Packard Enterprise Cray system

Containers have taken over large swaths of cloud computing as the most convenient way of packaging and deploying applications. The features that containers offer for packaging and deploying applications translate to high performance computing (HPC) as well. At The National Oceanic and Atmospheric Administration, containers provide an easy way to build and distribute complex HPC applications, allowing faster collaboration, portability, and experiment computer environment reproducibility amongst the scientific community. The challenge arises when applications rely on message passing interface (MPI). This necessitates investigation into how to properly run these applications with their own unique requirements and produce performance on par with native runs. We investigate the MPI performance for benchmarks and containerized climate models for various containers covering selection of compiler and MPI library combinations from the Cray provided programming environments on the Cray XC supercomputer GAEA. Performance from the benchmarks and the climate models shows that for the most part containerized applications perform on par with the natively built applications when the system optimized Cray MPICH libraries are bound into the container, and the hybrid model containers have poor performance in comparison. We also describe several challenges and our solutions in running these containers, particularly challenges with heterogeneous jobs for the containerized model runs.

Abraham, Subil↗

Bringing HPE Slingshot 11 support to Open MPI

The Cray HPE Slingshot 11 network is used on the new exascale systems arriving at the U.S. Department of Energy (DoE) laboratories (e.g., Frontier, Aurora, Perlmutter). As such, the support of this network is an important capability to meet the needs of exascale applications. Here, this article highlights recent work to develop supporting infrastructure to enable Open MPI to efficiently support these new platforms. A key component of this effort involves development of a new Open Fabrics Interface (OFI) provider, LinkX. We discuss the design and development of enhancements that take advantage of the new Slingshot 11 network and AMD GPUs. We include performance data from tests on the Frontier supercomputer using synthetic communication benchmarks, and the vendor provided MPI as a baseline for comparison. The tests demonstrate full functionality of Open MPI on the system and initial results show favorable performance when compared to the highly tuned vendor implementation.

97 MATHEMATICS AND COMPUTING↗

Massively parallel quantum chemical density matrix renormalization group method

Here, we present, to the best of our knowledge, the first attempt to exploit the supercomputer platform for quantum chemical density matrix renormalization group (QCDMRG) calculations. We have developed the parallel scheme based on the in-house MPI global memory library, which combines operator and symmetry sector parallelisms, and tested its performance on three different molecules, all typical candidates for QC-DMRG calculations. In case of the largest calculation, which is the nitrogenase FeMo cofactor cluster with the active space comprising 113 electrons in 76 orbitals and bond dimension equal to 6000, our parallel approach scales up to approximately 2000 CPU cores.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

ppdx : Automated modeling of protein–protein interaction descriptors for use with machine learning

This paper describes ppdx, a python workflow tool that combines protein sequence alignment, homology modeling, and structural refinement, to compute a broad array of descriptors for characterizing protein–protein interactions. The descriptors can be used to predict various properties of interest, such as protein–protein binding affinities, or inhibitory concentrations (IC 50 ), using approaches that range from simple regression to more complex machine learning models. The software is highly modular. It supports different protocols for generating structures, and 95 descriptors can be currently computed. More protocols and descriptors can be easily added. The implementation is highly parallel and can fully exploit the available cores in a single workstation, or multiple nodes on a supercomputer, allowing many systems to be analyzed simultaneously. As an illustrative application, ppdx is used to parametrize a model that predicts the IC 50 of a set of antigens and a class of antibodies directed to the influenza hemagglutinin stalk.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A Parallel Computing Framework for Finding the Supported Solutions to a Biobjective Network Optimization Problem

Abstract Solving multi‐objective combinatorial optimization problems can quickly become computationally challenging when applied to large networks generated from big data. Present‐day first‐rate Mixed Integer Programming (MIP) solvers have parallelism built‐in to take advantage of multicore architectures; but specialized network optimization algorithms that can often solve graph problems more efficiently than a general MIP solver are typically programmed serially. Thus, these network algorithm implementations do not take full advantage of modern multicore computer capabilities. Many parallel computing languages include a fork/join framework into their concurrency packages that allow for simple conversion of recursive serial algorithms to operate in parallel without having to use complicated low‐level message‐passing interfaces. Fork/join is particularly well suited to divide and conquer algorithms such as Non‐Inferior Set Estimation (NISE) method for computing the supported Pareto front of a multi‐objective optimization problem. This work develops a simple general parallel NISE (pNISE) implementation using the Java 7 concurrency tools, and then offers results from a specific implementation of solving a bi‐objective shortest path problem. The results indicate that this method is capable of sizeable speed‐ups on both small‐scale personal computers as well as large‐scale shared memory supercomputers. Finally, other network problems suitable to this method are discussed, including multi‐objective variants of the minimum spanning tree problem, transportation problem, assignment problem, maximum flow problem, and the minimum‐cost flow problem. Copyright © 2015 John Wiley & Sons, Ltd.

Medrano, Fernando Antonio↗

A fully coupled two-level Schwarz preconditioner based on smoothed aggregation for the transient multigroup neutron diffusion equations

The neutron multigroup diffusion equations is an important approximation of the neutron transport equation, and has been widely used for studying the motion of neutrons and their interactions with the stationary background materials. Solving the multigroup diffusion equations faces challenging because many variables are coupled together and a lot of computing resources are required. In this paper, we focus on the development of a scalable parallel algorithm framework for the system of equations arising from the discretization of the multigroup diffusion equations using a finite element method in space and using an implicit scheme in time. The parallel agorithm framweork consists of an inexact Jacobian-free Newton for the nonlinear equations, a Krylov subspace method for the Jacobian system and a parallel Schwarz preconditioner for the acceleration of the algorithm convergence. A coarse space based on smoothed aggregation is introduced to construct a two-level method to improve the parallel performance of the Schwarz preconditioner. We numerically shown that compared with the one-level method, the proposed two-level method works significantly better in terms of the number of linear iterations and the compute time for a system of equations with millions of unknowns and a supercomputer with thousands of processors.

97 MATHEMATICS AND COMPUTING↗

Limited‐memory adaptive snapshot selection for proper orthogonal decomposition

Summary Reduced order models are useful for accelerating simulations in many‐query contexts, such as optimization, uncertainty quantification, and sensitivity analysis. However, offline training of reduced order models (ROMs) can have prohibitively expensive memory and floating‐point operation costs in high‐performance computing applications, where memory per core is limited. To overcome this limitation for proper orthogonal decomposition, we propose a novel adaptive selection method for snapshots in time that limits offline training costs by selecting snapshots according an error control mechanism similar to that found in adaptive time‐stepping ordinary differential equation solvers. The error estimator used in this work is related to theory bounding the approximation error in time of proper orthogonal decomposition‐based ROMs, and memory usage is minimized by computing the singular value decomposition using a single‐pass incremental algorithm. Results for a viscous Burgers' test problem demonstrate convergence in the limit as the algorithm error tolerances go to zero; in this limit, the full‐order model is recovered to within discretization error. A parallel version of the resulting method can be used on supercomputers to generate proper orthogonal decomposition‐based ROMs, or as a subroutine within hyperreduction algorithms that require taking snapshots in time, or within greedy algorithms for sampling parameter space. Copyright © 2016 John Wiley & Sons, Ltd.

Oxberry, Geoffrey M.↗

Massively parallel solvers for elliptic partial differential equations in numerical weather and climate prediction

The demand for substantial increases in the spatial resolution of global weather and climate prediction models makes it essential to use numerically efficient and highly scalable algorithms to solve the equations of large-scale atmospheric fluid dynamics. For stability and efficiency reasons, several of the operational forecasting centres, in particular the Met Office and the European Centre for Medium-Range Weather Forecasts (ECMWF) in the UK, use semi-implicit semi-Lagrangian time-stepping in the dynamical core of the model. The additional burden with this method is that a three-dimensional elliptic partial differential equation (PDE) for the pressure correction has to be solved at every model time step and this often constitutes a significant proportion of the time spent in the dynamical core. In global models, this PDE must be solved in a thin spherical shell. To run within tight operational time-scales, the solver has to be parallelized and there seems to be a (perceived) misconception that elliptic solvers do not scale to large processor counts and hence implicit time-stepping cannot be used in very high-resolution global models. After reviewing several methods for solving the elliptic PDE for the pressure correction and their application in atmospheric models, we demonstrate the performance and very good scalability of Krylov subspace solvers and multigrid algorithms for a representative model equation with more than 1010 unknowns on 65 536 cores on the High-End Computing Terascale Resource (HECToR), the UK's national supercomputer. Here, we tested and optimized solvers from two existing numerical libraries (the Distributed and Unified Numerics Environment (DUNE) and Parallel High Performance Preconditioners (hypre)) and implemented both a conjugate gradient solver and a geometric multigrid algorithm based on a tensor-product approach, which exploits the strong vertical anisotropy of the discretized equation. We study both weak and strong scalability and compare the absolute solution times for all methods; in contrast to one-level methods, the multigrid solver is robust with respect to parameter variations.

58 GEOSCIENCES↗

Multithreaded parallelization of the energy and analytic gradient in the fragment molecular orbital method

The fragment molecular orbital method in GAMESS is parallelized in a multithreaded OpenMP implementation combined with the MPI version of the two-level generalized distributed data interface. The energy and analytic gradient in gas phase and the polarizable continuum model of solvation are parallelized in this hybrid three-level scheme, achieving a large memory footprint reduction and a high parallel efficiency on Intel Xeon Phi processors. The parallel efficiency is demonstrated on the Stampede2 and Theta supercomputers using up to 2048 nodes (262 144 threads).

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Three practical workflow schedulers for easy maximum parallelism

Runtime scheduling and workflow systems are an increasingly popular algorithmic component in HPC because they allow full system utilization with relaxed synchronization requirements. There are so many special-purpose tools for task scheduling, one might wonder why more are needed. Use cases seen on the Summit supercomputer needed better integration with MPI and greater flexibility in job launch configurations. Preparation, execution, and analysis of computational chemistry simulations at the scale of tens of thousands of processors revealed three distinct workflow patterns. A separate job scheduler was implemented for each one using extremely simple and robust designs: file-based, task-list based, and bulk-synchronous. Comparing to existing methods shows unique benefits of this work, including simplicity of design, suitability for HPC centers, short startup time, and well-understood per-task overhead. All three new tools have been shown to scale to full utilization of Summit, and have been made publicly available with tests and documentation. This work presents a complete characterization of the minimum effective task granularity for efficient scheduler usage scenarios. Here, these schedulers have the same bottlenecks, and hence similar task granularities as those reported for existing tools following comparable paradigms.

97 MATHEMATICS AND COMPUTING↗

ExaWind: Open‐source CFD for hybrid‐RANS/LES geometry‐resolved wind turbine simulations in atmospheric flows

Abstract Predictive high‐fidelity modeling of wind turbines with computational fluid dynamics, wherein turbine geometry is resolved in an atmospheric boundary layer, is important to understanding complex flow accounting for design strategies and operational phenomena such as blade erosion, pitch‐control, stall/vortex‐induced vibrations, and aftermarket add‐ons. The biggest challenge with high‐fidelity modeling is the realization of numerical algorithms that can capture the relevant physics in detail through effective use of high‐performance computing. For modern supercomputers, that means relying on GPUs for acceleration. In this paper, we present ExaWind, a GPU‐enabled open‐source incompressible‐flow hybrid‐computational fluid dynamics framework, comprising the near‐body unstructured grid solver Nalu‐Wind, and the off‐body block‐structured‐grid solver AMR‐Wind, which are coupled using the Topology Independent Overset Grid Assembler. Turbine simulations employ either a pure Reynolds‐averaged Navier–Stokes turbulence model or hybrid turbulence modeling wherein Reynolds‐averaged Navier–Stokes is used for near‐body flow and large eddy simulation is used for off‐body flow. Being two‐way coupled through overset grids, the two solvers enable simulation of flows across a huge range of length scales, for example, 10 orders of magnitude going from O(μm) boundary layers along the blades to O(10 km) across a wind farm. In this paper, we describe the numerical algorithms for geometry‐resolved turbine simulations in atmospheric boundary layers using ExaWind. We present verification studies using canonical flow problems. Validation studies are presented using megawatt‐scale turbines established in literature. Additionally presented are demonstration simulations of a small wind farm under atmospheric inflow with different stability states.

17 WIND ENERGY↗