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 721 records · Page 40

The Linearly Scaling 3D Fragment Method for Large Scale Electronic Structure Calculations

The Linearly Scaling three-dimensional fragment (LS3DF) method is an O(N) ab initio electronic structure method for large-scale nano material simulations. It is a divide-and-conquer approach with a novel patching scheme that effectively cancels out the artificial boundary effects, which exist in all divide-and-conquer schemes. This method has made ab initio simulations of thousand-atom nanosystems feasible in a couple of hours, while retaining essentially the same accuracy as the direct calculation methods. The LS3DF method won the 2008 ACM Gordon Bell Prize for algorithm innovation. Our code has reached 442 Tflop/s running on 147,456 processors on the Cray XT5 (Jaguar) at OLCF, and has been run on 163,840 processors on the Blue Gene/P (Intrepid) at ALCF, and has been applied to a system containing 36,000 atoms. In this paper, we will present the recent parallel performance results of this code, and will apply the method to asymmetric CdSe/CdS core/shell nanorods, which have potential applications in electronic devices and solar cells.

97 MATHEMATICS AND COMPUTING↗

Solving large sparse eigenvalue problems on supercomputers

An important problem in scientific computing consists in finding a few eigenvalues and corresponding eigenvectors of a very large and sparse matrix. The most popular methods to solve these problems are based on projection techniques on appropriate subspaces. The main attraction of these methods is that they only require the use of the matrix in the form of matrix by vector multiplications. The implementations on supercomputers of two such methods for symmetric matrices, namely Lanczos' method and Davidson's method are compared. Since one of the most important operations in these two methods is the multiplication of vectors by the sparse matrix, methods of performing this operation efficiently are discussed. The advantages and the disadvantages of each method are compared and implementation aspects are discussed. Numerical experiments on a one processor CRAY 2 and CRAY X-MP are reported. Possible parallel implementations are also discussed.

Philippe, Bernard↗

Computer modeling of pulsed CO2 lasers for lidar applications

The experimental results will enable a comparison of the numerical code output with experimental data. This will ensure verification of the validity of the code. The measurements were made on a modified commercial CO2 laser. Results are listed as following. (1) The pulse shape and energy dependence on gas pressure were measured. (2) The intrapulse frequency chirp due to plasma and laser induced medium perturbation effects were determined. A simple numerical model showed quantitative agreement with these measurements. The pulse to pulse frequency stability was also determined. (3) The dependence was measured of the laser transverse mode stability on cavity length. A simple analysis of this dependence in terms of changes to the equivalent fresnel number and the cavity magnification was performed. (4) An analysis was made of the discharge pulse shape which enabled the low efficiency of the laser to be explained in terms of poor coupling of the electrical energy into the vibrational levels. And (5) the existing laser resonator code was changed to allow it to run on the Cray XMP under the new operating system.

Spiers, Gary D.↗

PAN AIR: A computer program for predicting subsonic or supersonic linear potential flows about arbitrary configurations using a higher order panel method. Volume 2: User's manual (version 3.0)

A comprehensive description of user problem definition for the PAN AIR (Panel Aerodynamics) system is given. PAN AIR solves the 3-D linear integral equations of subsonic and supersonic flow. Influence coefficient methods are used which employ source and doublet panels as boundary surfaces. Both analysis and design boundary conditions can be used. This User's Manual describes the information needed to use the PAN AIR system. The structure and organization of PAN AIR are described, including the job control and module execution control languages for execution of the program system. The engineering input data are described, including the mathematical and physical modeling requirements. Version 3.0 strictly applies only to PAN AIR version 3.0. The major revisions include: (1) inputs and guidelines for the new FDP module (which calculates streamlines and offbody points); (2) nine new class 1 and class 2 boundary conditions to cover commonly used modeling practices, in particular the vorticity matching Kutta condition; (3) use of the CRAY solid state Storage Device (SSD); and (4) incorporation of errata and typo's together with additional explanation and guidelines.

Sidwell, Kenneth W.↗

The 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 in order to accelerate the parallel communication 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 effect of the various optimizations are demonstrated, and we show that the combined effect of these optimizations leads to roughly a factor of three performance improvement. The overall solution efficiency is compared with that obtained on the CRAY-YMP vector supercomputer.

Das, R.↗

Managing a Cray supercomputer as a git branch

Summary Modern software engineering/DevOps techniques applied to Cray XC Series systems management enable higher fidelity translation from test to production environments, reduce administration costs by avoiding duplicate efforts, and increase reliability. This can be done by using a git repository to track and manage all system configurations on the SMW(s) (System Management Workstation) and then adapt a gitflow‐like development methodology. Using git improves change management with peer review of changes, identification of who made a change, knowing why a change was made, facilitating easier reversion of bad changes, and enables a workflow using the ideas from gitflow with individual branches for preparing, maintaining, and recording releases. Using branches enables multiple contributors to work on different types of changes without getting unexpected changes from another feature area. We will describe a process similar to that used at NERSC (National Energy Research Scientific Computing Center) to extract/abstract configuration data, manage it using git, and then re‐apply changes to the SMW(s).

Jacobsen, Douglas M.↗

Transonic Navier-Stokes wing solution using a zonal approach. Part 1: Solution methodology and code validation

A fast diagonalized Beam-Warming algorithm is coupled with a zonal approach to solve the three-dimensional Euler/Navier-Stokes equations. The computer code, called Transonic Navier-Stokes (TNS), uses a total of four zones for wing configurations (or can be extended to complete aircraft configurations by adding zones). In the inner blocks near the wing surface, the thin-layer Navier-Stokes equations are solved, while in the outer two blocks the Euler equations are solved. The diagonal algorithm yields a speedup of as much as a factor of 40 over the original algorithm/zonal method code. The TNS code, in addition, has the capability to model wind tunnel walls. Transonic viscous solutions are obtained on a 150,000-point mesh for a NACA 0012 wing. A three-order-of-magnitude drop in the L2-norm of the residual requires approximately 500 iterations, which takes about 45 min of CPU time on a Cray-XMP processor. Simulations are also conducted for a different geometrical wing called WING C. All cases show good agreement with experimental data.

Flores, J.↗

Transonic Navier-Stokes wing solution using a zonal approach. Part 1: Solution methodology and code validation

A fast diagonalized Beam-Warming algorithm is coupled with a zonal approach to solve the three dimensional Euler/Navier-Stokes equations. The computer code, called Transonic Navier-Stokes (TNS), uses a total of four zones for wing configurations (or can be extended to complete aircraft configurations by adding zones). In the inner blocks near the wing surface, the thin-layer Navier-Stokes equations are solved, while in the outer two blocks the Euler equations are solved. The diagonal algorithm yields a speedup of as much as a factor of 40 over the original algorithm/zonal method code. The TNS code, in addition, has the capability to model wind tunnel walls. Transonic viscous solutions are obtained on a 150,000-point mesh for a NACA 0012 wing. A three-order-of-magnitude drop in the L2-norm of the residual requires approximately 500 iterations, which takes about 45 min of CPU time on a Cray-XMP processor. Simulations are also conducted for a different geometrical wing called WING C. All cases show good agreement with experimental data.

Flores, J.↗

Reaching bandwidth saturation using transparent injection parallelization

Although logically available, applications may not exploit enough instantaneous communication concurrency to maximize network utilization on HPC systems. This is exacerbated in hybrid programming models that combine single program multiple data with OpenMP or CUDA. We present the design of a “multi-threaded” runtime able to transparently increase the instantaneous network concurrency and to provide near saturation bandwidth, independent of the application configuration and dynamic behavior. The runtime offloads communication requests from application level tasks to multiple communication servers. The servers use system specific performance models to attain network saturation. Our techniques alleviate the need for spatial and temporal application level message concurrency optimizations. Experimental results show improved message throughput and bandwidth by as much as 150% for 4 KB messages on InfiniBand and by as much as 120% for 4 KB messages on Cray Aries. For more complex operations such as all-to-all collectives, we observe as much as 30% speedup. This translates into 23% speedup on 12,288 cores for a NAS FT implemented using FFTW. We observe as much as 76% speedup on 1500 cores for an already optimized UPC+OpenMP geometric multigrid application using hybrid parallelism. For the geometric multigrid GPU implementation, we observe as much as 44% speedup on 512 GPUs.

Chaimov, Nicholas↗

Parallelized reliability estimation of reconfigurable computer networks

A parallelized system, ASSURE, for computing the reliability of embedded avionics flight control systems which are able to reconfigure themselves in the event of failure is described. ASSURE accepts a grammar that describes a reliability semi-Markov state-space. From this it creates a parallel program that simultaneously generates and analyzes the state-space, placing upper and lower bounds on the probability of system failure. ASSURE is implemented on a 32-node Intel iPSC/860, and has achieved high processor efficiencies on real problems. Through a combination of improved algorithms, exploitation of parallelism, and use of an advanced microprocessor architecture, ASSURE has reduced the execution time on substantial problems by a factor of one thousand over previous workstation implementations. Furthermore, ASSURE's parallel execution rate on the iPSC/860 is an order of magnitude faster than its serial execution rate on a Cray-2 supercomputer. While dynamic load balancing is necessary for ASSURE's good performance, it is needed only infrequently; the particular method of load balancing used does not substantially affect performance.

Nicol, David M.↗

Network issues for large mass storage requirements

File Servers and Supercomputing environments need high performance networks to balance the I/O requirements seen in today's demanding computing scenarios. UltraNet is one solution which permits both high aggregate transfer rates and high task-to-task transfer rates as demonstrated in actual tests. UltraNet provides this capability as both a Server-to-Server and Server-to-Client access network giving the supercomputing center the following advantages highest performance Transport Level connections (to 40 MBytes/sec effective rates); matches the throughput of the emerging high performance disk technologies, such as RAID, parallel head transfer devices and software striping; supports standard network and file system applications using SOCKET's based application program interface such as FTP, rcp, rdump, etc.; supports access to the Network File System (NFS) and LARGE aggregate bandwidth for large NFS usage; provides access to a distributed, hierarchical data server capability using DISCOS UniTree product; supports file server solutions available from multiple vendors, including Cray, Convex, Alliant, FPS, IBM, and others.

Perdue, James↗

GPU acceleration and performance of the particle-beam-dynamics code Elegant

Elegant is an accelerator physics and particle-beam dynamics code widely used for modeling and design of a variety of high-energy particle accelerators and accelerator-based systems. We discuss a recently developed version of the code that can take advantage of CUDA-enabled graphics processing units (GPUs) to achieve significantly improved performance for a large class of simulations that are important in practice. The GPU version is largely defined by a framework that simplifies implementations of the fundamental kernel types that are used by Elegant: particle operations, reductions, particle loss, histograms, array convolutions and random number generation. Accelerated performance on the Titan Cray XK-7 supercomputer is approximately 6–10 times better with the GPU than all the CPU cores associated with the same node count. In addition to performance, the maintainability of the GPU-accelerated version of the code was considered a key design objective. Accuracy with respect to the CPU implementation is also a core consideration. Finally, four different methods are used to ensure that the accelerated code faithfully reproduces the CPU results.

43 PARTICLE ACCELERATORS↗

Lightweight and Statistical Techniques for Petascale Debugging: Correctness on Petascale Systems (CoPS) Preliminry Report

Petascale platforms with O(10{sup 5}) and O(10{sup 6}) processing cores are driving advancements in a wide range of scientific disciplines. These large systems create unprecedented application development challenges. Scalable correctness tools are critical to shorten the time-to-solution on these systems. Currently, many DOE application developers use primitive manual debugging based on printf or traditional debuggers such as TotalView or DDT. This paradigm breaks down beyond a few thousand cores, yet bugs often arise above that scale. Programmers must reproduce problems in smaller runs to analyze them with traditional tools, or else perform repeated runs at scale using only primitive techniques. Even when traditional tools run at scale, the approach wastes substantial effort and computation cycles. Continued scientific progress demands new paradigms for debugging large-scale applications. The Correctness on Petascale Systems (CoPS) project is developing a revolutionary debugging scheme that will reduce the debugging problem to a scale that human developers can comprehend. The scheme can provide precise diagnoses of the root causes of failure, including suggestions of the location and the type of errors down to the level of code regions or even a single execution point. Our fundamentally new strategy combines and expands three relatively new complementary debugging approaches. The Stack Trace Analysis Tool (STAT), a 2011 R&D 100 Award Winner, identifies behavior equivalence classes in MPI jobs and highlights behavior when elements of the class demonstrate divergent behavior, often the first indicator of an error. The Cooperative Bug Isolation (CBI) project has developed statistical techniques for isolating programming errors in widely deployed code that we will adapt to large-scale parallel applications. Finally, we are developing a new approach to parallelizing expensive correctness analyses, such as analysis of memory usage in the Memgrind tool. In the first two years of the project, we have successfully extended STAT to determine the relative progress of different MPI processes. We have shown that the STAT, which is now included in the debugging tools distributed by Cray with their large-scale systems, substantially reduces the scale at which traditional debugging techniques are applied. We have extended CBI to large-scale systems and developed new compiler based analyses that reduce its instrumentation overhead. Our results demonstrate that CBI can identify the source of errors in large-scale applications. Finally, we have developed MPIecho, a new technique that will reduce the time required to perform key correctness analyses, such as the detection of writes to unallocated memory. Overall, our research results are the foundations for new debugging paradigms that will improve application scientist productivity by reducing the time to determine which package or module contains the root cause of a problem that arises at all scales of our high end systems. While we have made substantial progress in the first two years of CoPS research, significant work remains. While STAT provides scalable debugging assistance for incorrect application runs, we could apply its techniques to assertions in order to observe deviations from expected behavior. Further, we must continue to refine STAT's techniques to represent behavioral equivalence classes efficiently as we expect systems with millions of threads in the next year. We are exploring new CBI techniques that can assess the likelihood that execution deviations from past behavior are the source of erroneous execution. Finally, we must develop usable correctness analyses that apply the MPIecho parallelization strategy in order to locate coding errors. We expect to make substantial progress on these directions in the next year but anticipate that significant work will remain to provide usable, scalable debugging paradigms.

97 MATHEMATICS AND COMPUTING↗

Inlet Spillage Drag Predictions Using the AIRPLANE Code

AIRPLANE (Jameson/Baker) is a steady inviscid unstructured Euler flow solver. It has been validated on many HSR geometries. It is implemented as MESHPLANE, an unstructured mesh generator, and FLOPLANE, an iterative flow solver. The surface description from an Intergraph CAD system goes into MESHPLANE as collections of polygonal curves to generate the 3D mesh. The flow solver uses a multistage time stepping scheme with residual averaging to approach steady state, but R is not time accurate. The flow solver was ported from Cray to IBM SP2 by Wu-Sun Cheng (IBM); it could only be run on 4 CPUs at a time because of memory limitations. Meshes for the four cases had about 655,000 points in the flow field, about 3.9 million tetrahedra, about 77,500 points on the surface. The flow solver took about 23 wall seconds per iteration when using 4 CPUs. It took about eight and a half wall hours to run 1,300 iterations at a time (the queue limit is 10 hours). A revised version of FLOPLANE (Thomas) was used on up to 64 CPUs to finish up some calculations at the end. We had to turn on more communication when using more processors to eliminate noise that was contaminating the flow field; this added about 50% to the elapsed wall time per iteration when using 64 CPUs. This study involved computing lift and drag for a wing/body/nacelle configuration at Mach 0.9 and 4 degrees pitch. Four cases were considered, corresponding to four nacelle mass flow conditions.

Thomas, Scott D.↗

An efficient nonlinear relaxation technique for the three-dimensional, Reynolds-averaged Navier-Stokes equations

An efficient implicit method for the computation of steady, three-dimensional, compressible Navier-Stokes flowfields is presented. A nonlinear iteration strategy based on planar Gauss-Seidel sweeps is used to drive the solution toward a steady state, with approximate factorization errors within a crossflow plane reduced by the application of a quasi-Newton technique. A hybrid discretization approach is employed, with flux-vector splitting utilized in the streamwise direction and central differences with artificial dissipation used for the transverse fluxes. Convergence histories and comparisons with experimental data are presented for several 3-D shock-boundary layer interactions. Both laminar and turbulent cases are considered, with turbulent closure provided by a modification of the Baldwin-Barth one-equation model. For the problems considered (175,000-325,000 mesh points), the algorithm provides steady-state convergence in 900-2000 CPU seconds on a single processor of a Cray Y-MP.

Edwards, Jack R.↗

surf3d: A 3-D finite-element program for the analysis of surface and corner cracks in solids subjected to mode-1 loadings

A computer program, surf3d, that uses the 3D finite-element method to calculate the stress-intensity factors for surface, corner, and embedded cracks in finite-thickness plates with and without circular holes, was developed. The cracks are assumed to be either elliptic or part eliptic in shape. The computer program uses eight-noded hexahedral elements to model the solid. The program uses a skyline storage and solver. The stress-intensity factors are evaluated using the force method, the crack-opening displacement method, and the 3-D virtual crack closure methods. In the manual the input to and the output of the surf3d program are described. This manual also demonstrates the use of the program and describes the calculation of the stress-intensity factors. Several examples with sample data files are included with the manual. To facilitate modeling of the user's crack configuration and loading, a companion program (a preprocessor program) that generates the data for the surf3d called gensurf was also developed. The gensurf program is a three dimensional mesh generator program that requires minimal input and that builds a complete data file for surf3d. The program surf3d is operational on Unix machines such as CRAY Y-MP, CRAY-2, and Convex C-220.

Raju, I. S.↗

Deploying Server-side File System Monitoring at NERSC

The Franklin Cray XT4 at the NERSC center was equipped with the server-side I/O monitoring infrastructure Cerebro/LMT, which is described here in detail. Insights gained from the data produced include a better understanding of instantaneous data rates during file system testing, file system behavior during regular production time, and long-term average behaviors. Information and insights gleaned from this monitoring support efforts to proactively manage the I/O infrastructure on Franklin. A simple model for I/O transactions is introduced and compared with the 250 million observations sent to the LMT database from August 2008 to February 2009.

97 MATHEMATICS AND COMPUTING↗

DSMC calculations for the delta wing

Results are reported from three-dimensional direct simulation Monte Carlo (DSMC) computations, using a variable-hard-sphere molecular model, of hypersonic flow on a delta wing. The body-fitted grid is made up of deformed hexahedral cells divided into six tetrahedral subcells with well defined triangular faces; the simulation is carried out for 9000 time steps using 150,000 molecules. The uniform freestream conditions include M = 20.2, T = 13.32 K, rho = 0.00001729 kg/cu m, and T(wall) = 620 K, corresponding to lambda = 0.00153 m and Re = 14,000. The results are presented in graphs and briefly discussed. It is found that, as the flow expands supersonically around the leading edge, an attached leeside flow develops around the wing, and the near-surface density distribution has a maximum downstream from the stagnation point. Coefficients calculated include C(H) = 0.067, C(DP) = 0.178, C(DF) = 0.110, C(L) = 0.714, and C(D) = 1.089. The calculations required 56 h of CPU time on the NASA Langley Voyager CRAY-2 supercomputer.

Celenligil, M. Cevdet↗