Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “CRAY COMPUTERS”

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 685 records · Page 38

s-Step Krylov Subspace Methods as Bottom Solvers for Geometric Multigrid

Geometric multigrid solvers within adaptive mesh refinement (AMR) applications often reach a point where further coarsening of the grid becomes impractical as individual sub domain sizes approach unity. At this point the most common solution is to use a bottom solver, such as BiCGStab, to reduce the residual by a fixed factor at the coarsest level. Each iteration of BiCGStab requires multiple global reductions (MPI collectives). As the number of BiCGStab iterations required for convergence grows with problem size, and the time for each collective operation increases with machine scale, bottom solves in large-scale applications can constitute a significant fraction of the overall multigrid solve time. In this paper, we implement, evaluate, and optimize a communication-avoiding s-step formulation of BiCGStab (CABiCGStab for short) as a high-performance, distributed-memory bottom solver for geometric multigrid solvers. This is the first time s-step Krylov subspace methods have been leveraged to improve multigrid bottom solver performance. We use a synthetic benchmark for detailed analysis and integrate the best implementation into BoxLib in order to evaluate the benefit of a s-step Krylov subspace method on the multigrid solves found in the applications LMC and Nyx on up to 32,768 cores on the Cray XE6 at NERSC. Overall, we see bottom solver improvements of up to 4.2x on synthetic problems and up to 2.7x in real applications. This results in as much as a 1.5x improvement in solver performance in real applications.

97 MATHEMATICS AND COMPUTING↗

Particle simulation in a multiprocessor environment

A parallel implementation of a particle simulation method that is portable between a wide class of multiprocessor computers is presented. A fine grain spatial decomposition is utilized where several subdomains having a regular structure are computed at each processing node. This leads directly to an efficient and straightforward load balancing scheme if the number of subdomains at each processor is permitted to vary in an appropriate manner. Three dimensional simulations incorporating full thermochemical nonequilibrium are possible using the resulting code. Vectorizable algorithms are retained from earlier work allowing efficient use of deeply pipelined node processors where available. Performance results are presented from three different machine architectures demonstrating the portability of the code. On a 128-node Intel iPSC/860, performance is twice that of a single Cray-Y/MP CPU running a highly vectorized simulation code. Speedup is linear over the full range of number of processors on all target machines, indicating scalability of the method to higher degrees of parallelism.

Mcdonald, Jeffrey D.↗

Queue wait time prediction in high performance computing (HPC) systems

High Performance Computing (HPC) systems are critical enablers for groundbreaking scientific research across various domains. Efficient resource allocation, facilitated by job scheduling, is paramount for maximizing the utilization of HPC systems. However, the variability in wait times for queued jobs poses challenges for users, necessitating accurate job wait time estimation. This paper explores the influence of job characteristics, including job size (the number of nodes requested and walltime), the queue to which the job is submitted and other resource requirements, on job wait times in leadership-class HPC systems. Focusing on the Theta Cray XC40 and Polaris machines at Argonne National Laboratory, the study evaluates the performance of different supervised learning algorithms in predicting job wait times. It also evaluates the impact of data preprocessing, including outlier detection, Principal Component Analysis (PCA), and feature selection, on the performance of wait time prediction models. The findings reveal insights into the relationship between job characteristics and wait times, offering a foundation for optimizing resource allocation and enhancing user experience. The methodologies and tools developed in this study are adaptable to other leadership-class HPC systems, providing a valuable contribution to the broader HPC community aiming to improve job scheduling efficiency and user satisfaction.

Okafor, Nwamaka↗

Taming parallel I/O complexity with auto-tuning

We present an auto-tuning system for optimizing I/O performance of HDF5 applications and demonstrate its value across platforms, applications, and at scale. The system uses a genetic algorithm to search a large space of tunable parameters and to identify effective settings at all layers of the parallel I/O stack. The parameter settings are applied transparently by the auto-tuning system via dynamically intercepted HDF5 calls. To validate our auto-tuning system, we applied it to three I/O benchmarks (VPIC, VORPAL, and GCRM) that replicate the I/O activity of their respective applications. We tested the system with different weak-scaling configurations (128, 2048, and 4096 CPU cores) that generate 30 GB to 1 TB of data, and executed these configurations on diverse HPC platforms (Cray XE6, IBM BG/P, and Dell Cluster). In all cases, the auto-tuning framework identified tunable parameters that substantially improved write performance over default system settings. In conclusion, we consistently demonstrate I/O write speedups between 2x and 100x for test configurations.

97 MATHEMATICS AND COMPUTING↗

Experiments with Memory-to-Memory Coupling for End-to-End fusion Simulation Workflows

Scientific applications are striving to accurately simulate multiple interacting physical processes that comprise complex phenomena being modeled. Efficient and scalable parallel implementations of these coupled simulations present challenging interaction and coordination requirements, especially when the coupled physical processes are computationally heterogeneous and progress at different speeds. In this paper, we present the design, implementation and evaluation of a memory-to-memory coupling framework for coupled scientific simulations on high-performance parallel computing platforms. The framework is driven by the coupling requirements of the Center for Plasma Edge Simulation, and it provides simple coupling abstractions as well as efficient asynchronous (RDMA-based) memory-to-memory data transport mechanisms that complement existing parallel programming systems and data sharing frameworks. The framework enables flexible coupling behaviors that are asynchronous in time and space, and it supports dynamic coupling between heterogeneous simulation processes without enforcing any synchronization constraints. We evaluate the performance and scalability of the coupling framework using a specific coupling scenario, on the Jaguar Cray XT5 system at Oak Ridge National Laboratory.

99 GENERAL AND MISCELLANEOUS↗

Transonic Navier-Stokes solutions for a fighter-like configuration

The Transonic Navier-Stokes wing code is extended to a 16-zone TNS wing-fuselage code and used to solve the transonic viscous flow over a modified F-16A. The computer code, called Transonic Navier-Stokes Wing/Fuselage uses a zonal approach to solve the three-dimensional Euler and Navier-Stokes equations. With the zonal implementation, clustering suitable for viscous calculations is achieved on all solid surfaces. The transonic case has flow conditions of free-stream M = 0.9, alpha = 4.12 deg, and a Reynolds number based on root chord of 4.5 million. This case required about 3,000 iterations to reduce the L2-norm of the residual by three orders, which takes about 15 hr of cpu time on the Cray X-MP/48 processor. Pressure distributions, as well as separaton patterns, compare favorably with experiment for this transonic case.

Flores, Jolen↗

Design and implementation of a parallel unstructured Euler solver using software primitives

This paper is concerned with the implementation of a three-dimensional unstructured-grid Euler solver on massively parallel distributed-memory computer architectures. The goal is to minimize solution time by achieving high computational rates with a numerically efficient algorithm. An unstructured multigrid algorithm with an edge-based data structure has been adopted, and a number of optimizations have been devised and implemented to accelerate the parallel computational rates. The implementation is carried out by creating a set of software tools, which provide an interface between the parallelization issues and the sequential code, while providing a basis for future automatic run-time compilation support. Large practical unstructured grid problems are solved on the Intel iPSC/860 hypercube and Intel Touchstone Delta machine. The quantitative effects of the various optimizations are demonstrated, and we show that the combined effect of these optimizations leads to roughly a factor of 3 performance improvement. The overall solution efficiency is compared with that obtained on the Cray Y-MP vector supercomputer.

Das, R.↗

Exploring versioned distributed arrays for resilience in scientific applications: Global view resilience

Exascale studies project reliability challenges for future HPC systems. We present the Global View Resilience (GVR) system, a library for portable resilience. GVR begins with a subset of the Global Arrays interface, and adds new capabilities to create versions, name versions, and compute on version data. Applications can focus versioning where and when it is most productive, and customize for each application structure independently. This control is portable, and its embedding in application source makes it natural to express and easy to maintain. The ability to name multiple versions and “partially materialize” them efficiently makes ambitious forward-recovery based on “data slices” across versions or data structures both easy to express and efficient. Using several large applications (OpenMC, preconditioned conjugate gradient (PCG) solver, ddcMD, and Chombo), we evaluate the programming effort to add resilience. The required changes are small (< 2% lines of code (LOC)), localized and machine-independent, and perhaps most important, require no software architecture changes. We also measure the overhead of adding GVR versioning and show that overheads < 2% are generally achieved. This overhead suggests that GVR can be implemented in large-scale codes and support portable error recovery with modest investment and runtime impact. Our results are drawn from both IBM BG/Q and Cray XC30 experiments, demonstrating portability. We also present two case studies of flexible error recovery, illustrating how GVR can be used for multi-version rollback recovery, and several different forward-recovery schemes. GVR’s multi-version enables applications to survive latent errors (silent data corruption) with significant detection latency, and forward recovery can make that recovery extremely efficient. Lastly, our results suggest that GVR is scalable, portable, and efficient. GVR interfaces are flexible, supporting a variety of recovery schemes, and altogether GVR embodies a gentle-slope path to tolerate growing error rates in future extreme-scale systems.

97 MATHEMATICS AND COMPUTING↗

Methodology for analysis and simulation of large multidisciplinary problems

The Integrated Structural Modeling (ISM) program is being developed for the Air Force Weapons Laboratory and will be available for Air Force work. Its goal is to provide a design, analysis, and simulation tool intended primarily for directed energy weapons (DEW), kinetic energy weapons (KEW), and surveillance applications. The code is designed to run on DEC (VMS and UNIX), IRIS, Alliant, and Cray hosts. Several technical disciplines are included in ISM, namely structures, controls, optics, thermal, and dynamics. Four topics from the broad ISM goal are discussed. The first is project configuration management and includes two major areas: the software and database arrangement and the system model control. The second is interdisciplinary data transfer and refers to exchange of data between various disciplines such as structures and thermal. Third is a discussion of the integration of component models into one system model, i.e., multiple discipline model synthesis. Last is a presentation of work on a distributed processing computing environment.

Russell, William C.↗

Accelerating virtual high-throughput ligand docking: current technology and case study on a petascale supercomputer

In this paper, we give the current state of high-throughput virtual screening. We describe a case study of using a task-parallel Message Passing Interface version of AutoDock4 to run a virtual high-throughput screen of one million compounds on the Jaguar Cray XK6 Supercomputer at Oak Ridge National Laboratory. We include a description of scripts developed to increase the efficiency of the predocking file preparation and postdocking analysis. A detailed tutorial, scripts, and source code for this Message Passing Interface version of AutoDock4 are available online at http://www.bio.utk.edu/baudrylab/autodockmpi.htm.

97 MATHEMATICS AND COMPUTING↗

Swarm Verification

Reportedly, supercomputer designer Seymour Cray once said that he would sooner use two strong oxen to plow a field than a thousand chickens. Although this is undoubtedly wise when it comes to plowing a field, it is not so clear for other types of tasks. Model checking problems are of the proverbial "search the needle in a haystack" type. Such problems can often be parallelized easily. Alas, none of the usual divide and conquer methods can be used to parallelize the working of a model checker. Given that it has become easier than ever to gain access to large numbers of computers to perform even routine tasks it is becoming more and more attractive to find alternate ways to use these resources to speed up model checking tasks. This paper describes one such method, called swarm verification.

grid computing↗

Data Transfer Study HPSS Archiving

The movement of the large amounts of data produced by codes run in a High Performance Computing (HPC) environment can be a bottleneck for project workflows. To balance filesystem capacity and performance requirements, HPC centers enforce data management policies to purge old files to make room for new computation and analysis results. Users at Oak Ridge Leadership Computing Facility (OLCF) and many other HPC user facilities must archive data to avoid data loss during purges, therefore the time associated with data movement for archiving is something that all users must consider. This study observed the difference in transfer speed from the originating location on the Lustre filesystem to the more permanent High Performance Storage System (HPSS). The tests were done with a number of different transfer methods for files that spanned a variety of sizes and compositions that reflect OLCF user data. This data will be used to help users of Titan and other Cray supercomputers plan their workflow and data transfers so that they are most efficient for their project. We will also discuss best practice for maintaining data at shared user facilities.

Big Data↗

Scalable Algorithms for Distributed-Memory Adaptive Mesh Refinement

This paper presents scalable algorithms and data structures for adaptive mesh refinement computations. We describe a novel mesh restructuring algorithm for adaptive mesh refinement computations that uses a constant number of collectives regardless of the refinement depth. To further increase scalability, we describe a localized hierarchical coordinate-based block indexing scheme in contrast to traditional linear numbering schemes, which incur unnecessary synchronization. In contrast to the existing approaches which take O(P) time and storage per process, our approach takes only constant time and has very small memory footprint. With these optimizations as well as an efficient mapping scheme, our algorithm is scalable and suitable for large, highly-refined meshes. We present strong-scaling experiments up to 2k ranks on Cray XK6, and 32k ranks on IBM Blue Gene/Q.

Langer, Akhil↗

Design and Performance Analysis of a Massively Parallel Atmospheric General Circulation Model

In the 1990's computer manufacturers are increasingly turning to the development of parallel processor machines to meet the high performance needs of their customers. Simultaneously, atmospheric scientists study weather and climate phenomena ranging from hurricanes to El Nino to global warming that require increasingly fine resolution models. Here, implementation of a parallel atmospheric general circulation model (GCM) which exploits the power of massively parallel machines is described. Using the horizontal data domain decomposition methodology, this FORTRAN 90 model is able to integrate a 0.6 deg. longitude by 0.5 deg. latitude problem at a rate of 19 Gigaflops on 512 processors of a Cray T3E 600; corresponding to 280 seconds of wall-clock time per simulated model day. At this resolution, the model has 64 times as many degrees of freedom and performs 400 times as many floating point operations per simulated day as the model it replaces.

Schaffer, Daniel S.↗

Multithreaded Algorithms for Graph Coloring

Graph algorithms are challenging to parallelize when high performance and scalability are primary goals. Low concurrency, poor data locality, irregular access pattern, and high data access to computation ratio are among the chief reasons for the challenge. The performance implication of these features is exasperated on distributed memory machines. More success is being achieved on shared-memory, multi-core architectures supporting multithreading. We consider a prototypical graph problem, coloring, and show how a greedy algorithm for solving it can be e*ectively parallelized on multithreaded architectures. We present in particular two di*erent parallel algorithms. The first relies on speculation and iteration, and is suitable for any shared-memory, multithreaded system. The second uses data ow principles and is targeted at the massively multithreaded Cray XMT system. We benchmark the algorithms on three di*erent platforms and demonstrate scalable runtime performance. In terms of quality of solution, both algorithms use nearly the same number of colors as the serial algorithm.

Catalyurek, Umit V↗

XGC1: Performance on the 8-core and 12-core Cray XT5 systems at ORNL

The XGC1 code is used to model multiscale tokamak plasma turbulence dynamics in realistic diverted magnetic field geometry. In June 2009, XGC1 demonstrated nearly linear weak and strong scaling out to 150,000 cores on a Cray XT5 with 8-core nodes when solving problems of relevance to running experiments on the ITER tokamak. Here we compare performance, and discuss further performance optimizations, when running XGC1 on an XT5 with 12-core nodes on up to 224,000 cores.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Effects of Ordering Strategies and Programming Paradigms on Sparse Matrix Computations

The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. For systems that are ill-conditioned, it is often necessary to use a preconditioning technique. In this paper, we investigate the effects of various ordering and partitioning strategies on the performance of parallel CG and ILU(O) preconditioned CG (PCG) using different programming paradigms and architectures. Results show that for this class of applications: ordering significantly improves overall performance on both distributed and distributed shared-memory systems, that cache reuse may be more important than reducing communication, that it is possible to achieve message-passing performance using shared-memory constructs through careful data ordering and distribution, and that a hybrid MPI+OpenMP paradigm increases programming complexity with little performance gains. A implementation of CG on the Cray MTA does not require special ordering or partitioning to obtain high efficiency and scalability, giving it a distinct advantage for adaptive applications; however, it shows limited scalability for PCG due to a lack of thread level parallelism.

Oliker, Leonid↗

OpenMP Parallelization and Optimization of Graph-Based Machine Learning Algorithms

In this paper, we investigate the OpenMP parallelization and optimization of two novel data classification algorithms. The new algorithms are based on graph and PDE solution techniques and provide significant accuracy and performance advantages over traditional data classification algorithms in serial mode. The methods leverage the Nystrom extension to calculate eigenvalue/eigenvectors of the graph Laplacian and this is a self-contained module that can be used in conjunction with other graph-Laplacian based methods such as spectral clustering. We use performance tools to collect the hotspots and memory access of the serial codes and use OpenMP as the parallelization language to parallelize the most time-consuming parts. Where possible, we also use library routines. We then optimize the OpenMP implementations and detail the performance on traditional supercomputer nodes (in our case a Cray XC30), and test the optimization steps on emerging testbed systems based on Intel’s Knights Corner and Landing processors. We show both performance improvement and strong scaling behavior. Finally, a large number of optimization techniques and analyses are necessary before the algorithm reaches almost ideal scaling.

97 MATHEMATICS AND COMPUTING↗