Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Stencil Computation”

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 37 records · Page 2

Using Verified Lifting to Optimize Legacy Stencil Codes (Final Project Report)

This project investigated new techniques for compiling stencil and stencil-like computations. Stencils computations are commonly found in applications such as image processing, physical simulations, image processing, and machine learning. In recent years, many high-performance domain-specific languages (DSLs) have been proposed to optimize stencil computations. To leverage such DSLs, however, existing codes often need to be rewritten. Such rewriting is manual, labor intensive, and error-prone. To alleviate such issues, this project investigated the application of program synthesis and artificial learning techniques to enable stencil computations to automatically leverage new high-performance DSLs. Rather than constructing syntax driven rules, verified lifting uses program synthesis to search for a target code fragment to compile the given input code into. In addition, it also searches for a proof that validates how the found target code fragment preserves the semantics of the original input. Thus, the target code fragment is guaranteed to be semantically equivalent to the input.

97 MATHEMATICS AND COMPUTING↗

Detecting Soft Errors in Stencil based Computations

Given the growing emphasis on system resilience, it is important to develop software-level error detectors that help trap hardware-level faults with reasonable accuracy while minimizing false alarms as well as the performance overhead introduced. We present a technique that approaches this idea by taking stencil computations as our target, and synthesizing detectors based on machine learning. In particular, we employ linear regression to generate computationally inexpensive models which form the basis for error detection. Our technique has been incorporated into a new open-source library called SORREL. In addition to reporting encouraging experimental results, we demonstrate techniques that help reduce the size of training data. We also discuss the efficacy of various detectors synthesized, as well as our future plans.

97 MATHEMATICS AND COMPUTING↗

FPDetect: Efficient Reasoning About Stencil Programs Using Selective Direct Evaluation

We present FPDetect, a low-overhead approach for detecting logical errors and soft errors affecting stencil computations without generating false positives. We develop an offline analysis that tightly estimates the number of floating-point bits preserved across stencil applications. This estimate rigorously bounds the values expected in the data space of the computation. Violations of this bound can be attributed with certainty to errors. FPDetect helps synthesize error detectors customized for user-specified levels of accuracy and coverage. FPDetect also enables overhead reduction techniques based on deploying these detectors coarsely in space and time. Experimental evaluations demonstrate the practicality of our approach.

97 MATHEMATICS AND COMPUTING↗

Hands-on Performance Tuning of 3D Finite Difference Earthquake Simulation on GPU Fermi Chipset

3D simulation of earthquake ground motion is one of the most challenging computational problems in science. The emergence of graphic processing units (GPU) as an effective alternative to traditional general purpose processors has become increasingly capable in terms of accelerating scientific computing research. In this paper, we describe our experiences in porting AWP-ODC, a 3D finite difference seismic wave propagation code, to the latest GPU Fermi chipset. We completely rewrote this Fortran-based 13-point asymmetric stencil computation code in C and MPI-CUDA in order to take advantage of the powerful GPU computing capabilities. Our new CUDA code implemented the asymmetric 3D stencil on Fermi to make the best use of GPU on-chip memory for an aggressive parallel efficiency. Benchmark on NVIDIA Tesla M2090 demonstrated 10x speedup versus the original fully optimized AWP-ODC FORTRAN MPI code running on a single Intel Nehalem 2.4 GHz CPU socket (4 cores/CPU), and 15x speedup versus the same MPI code running on a single AMD Istanbul 2.6 GHz CPU socket (6 cores/CPU). Sustained single-GPU performance of 143.8 GFLOPS in single precision is benchmarked for the testing case of 128x128x960 mesh size.

3D Stencil Computation↗

Snowflake: A Lightweight Portable Stencil DSL

Stencil computations are not well optimized by general-purpose production compilers and the increased use of multicore, manycore, and accelerator-based systems makes the optimization problem even more challenging. In this paper we present Snowflake, a Domain Specific Language (DSL) for stencils that uses a 'micro-compiler' approach, i.e., small, focused, domain-specific code generators. The approach is similar to that used in image processing stencils, but Snowflake handles the much more complex stencils that arise in scientific computing, including complex boundary conditions, higher-order operators (larger stencils), higher dimensions, variable coefficients, non-unit-stride iteration spaces, and multiple input or output meshes. Snowflake is embedded in the Python language, allowing it to interoperate with popular scientific tools like SciPy and iPython; it also takes advantage of built-in Python libraries for powerful dependence analysis as part of a just-in-time compiler. We demonstrate the power of the Snowflake language and the micro-compiler approach with a complex scientific benchmark, HPGMG, that exercises the generality of stencil support in Snowflake. By generating OpenMP comparable to, and OpenCL within a factor of 2x of hand-optimized HPGMG, Snowflake demonstrates that a micro-compiler can support diverse processor architectures and is performance-competitive whilst preserving a high-level Python implementation.

97 MATHEMATICS AND COMPUTING↗

Multi-GPU Implementation of a 3D Finite Difference Time Domain Earthquake Code on Heterogeneous Supercomputers

We have developed a highly scalable 3D Finite Difference GPU code for use in earthquake engineering and disaster management through regional petascale earthquake simulations. This MPI-CUDA code is based on a widely-used wave propagation code called AWP-ODC and restructured for high throughput and efficiency on a heterogeneous computing architecture. We present an effective communication reduction technique for leveraging GPUs with minimal PCI-e overhead, and a novel overlapping method to fully hide data communication latency between GPUs. The optimization concept used in this work can be extended to general stencil computing on a structured grid. The benchmarks demonstrated sustained 100 TFlops in single precision for 49 billion mesh points using 952 GPUs on the NCCS Titan Phase 5 system, which is a 77-fold speedup compared to the CPU version of the code. This multi-GPU implementation has been validated and used for a large-scale verification wave propagation simulation of Mw5.4 Chino Hills earthquake using 128 GPUs.

58 GEOSCIENCES↗

Locality Aware Concurrent Start for Stencil Applications

Stencil computations are at the heart of many physical simulations used in scientific codes. Thus, there exists a plethora of optimization efforts for this family of computations. Among these techniques, tiling techniques that allow concurrent start have proven to be very efficient in providing better performance for these critical kernels. Nevertheless, with many core designs being the norm, these optimization techniques might not be able to fully exploit locality (both spatial and temporal) on multiple levels of the memory hierarchy without compromising parallelism. It is no longer true that the machine can be seen as a homogeneous collection of nodes with caches, main memory and an interconnect network. New architectural designs exhibit complex grouping of nodes, cores, threads, caches and memory connected by an ever evolving network-on-chip design. These new designs may benefit greatly from carefully crafted schedules and groupings that encourage parallel actors (i.e. threads, cores or nodes) to be aware of the computational history of other actors in close proximity. In this paper, we provide an efficient tiling technique that allows hierarchical concurrent start for memory hierarchy aware tile groups. Each execution schedule and tile shape exploit the available parallelism, load balance and locality present in the given applications. We demonstrate our technique on the Intel Xeon Phi architecture with selected and representative stencil kernels. We show improvement ranging from 5.58% to 31.17% over existing state-of-the-art techniques.

Locality Aware execution, jagged tiling↗

CFD validation in OECD/NEA t-junction benchmark.

When streams of rapidly moving flow merge in a T-junction, the potential arises for large oscillations at the scale of the diameter, D, with a period scaling as O(D/U), where U is the characteristic flow velocity. If the streams are of different temperatures, the oscillations result in experimental fluctuations (thermal striping) at the pipe wall in the outlet branch that can accelerate thermal-mechanical fatigue and ultimately cause pipe failure. The importance of this phenomenon has prompted the nuclear energy modeling and simulation community to establish a benchmark to test the ability of computational fluid dynamics (CFD) codes to predict thermal striping. The benchmark is based on thermal and velocity data measured in an experiment designed specifically for this purpose. Thermal striping is intrinsically unsteady and hence not accessible to steady state simulation approaches such as steady state Reynolds-averaged Navier-Stokes (RANS) models.1 Consequently, one must consider either unsteady RANS or large eddy simulation (LES). This report compares the results for three LES codes: Nek5000, developed at Argonne National Laboratory (USA), and Cabaret and Conv3D, developed at the Moscow Institute of Nuclear Energy Safety at (IBRAE) in Russia. Nek5000 is based on the spectral element method (SEM), which is a high-order weighted residual technique that combines the geometric flexibility of the finite element method (FEM) with the tensor-product efficiencies of spectral methods. Cabaret is a 'compact accurately boundary-adjusting high-resolution technique' for fluid dynamics simulation. The method is second-order accurate on nonuniform grids in space and time, and has a small dispersion error and computational stencil defined within one space-time cell. The scheme is equipped with a conservative nonlinear correction procedure based on the maximum principle. CONV3D is based on the immersed boundary method and is validated on a wide set of the experimental and benchmark data. The numerical scheme has a very small scheme diffusion and is the second and the first order accurate in space and time, correspondingly. We compare and contrast simulation results for three computational fluid dynamics codes CABARET, Conv3D, and Nek5000 for the T-junction thermal striping problem that was the focus of a recent OECD/NEA blind benchmark. The corresponding codes utilize finite-difference implicit large eddy simulation (ILES), finite-volume LES on fully staggered grids, and an LES spectral element method (SEM), respectively. The simulations results are in a good agreement with experimenatl data. We present results from a study of sensitivity to computational mesh and time integration interval, and discuss the next steps in the simulation of this problem.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

SOMA: Observability, monitoring, and in situ analytics for exascale applications

With the rise of exascale systems and large, data-centric workflows, the need to observe and analyze high performance computing (HPC) applications during their execution is becoming increasingly important. HPC applications are typically not designed with online monitoring in mind, therefore, the observability challenge lies in being able to access and analyze interesting events with low overhead while seamlessly integrating such capabilities into existing and new applications. We explore how our service-based observation, monitoring, and analytics (SOMA) approach to collecting and aggregating both application-specific diagnostic data and performance data addresses these needs. Furthermore, we present our SOMA framework and demonstrate its viability with LULESH, a hydrodynamics proxy application. Then we focus on Astaroth, a multi-GPU library for stencil computations, highlighting the integration of the TAU and APEX performance tools and SOMA for application and performance data monitoring.

97 MATHEMATICS AND COMPUTING↗

A discontinuous Galerkin conservative level set scheme for interface capturing in multiphase flows

The accurate conservative level set (ACLS) method of Desjardins et al. [O. Desjardins, V. Moureau, H. Pitsch, An accurate conservative level set/ghost fluid method for simulating turbulent atomization, J. Comput. Phys. 227 (18) (2008) 8395–8416] is extended by using a discontinuous Galerkin (DG) discretization. DG allows for the scheme to have an arbitrarily high order of accuracy with the smallest possible computational stencil resulting in an accurate method with good parallel scaling. This work includes a DG implementation of the level set transport equation, which moves the level set with the flow field velocity, and a DG implementation of the reinitialization equation, which is used to maintain the shape of the level set profile to promote good mass conservation. A near second order converging interface curvature is obtained by following a height function methodology (common amongst volume of fluid schemes) in the context of the conservative level set. Various numerical experiments are conducted to test the properties of the method and show excellent results, even on coarse meshes. The tests include Zalesak’s disk, two-dimensional deformation of a circle, time evolution of a standing wave, and a study of the Kelvin–Helmholtz instability. Finally, this novel methodology is employed to simulate the break-up of a turbulent liquid jet.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Compact finite difference schemes with spectral-like resolution

The present finite-difference schemes for the evaluation of first-order, second-order, and higher-order derivatives yield improved representation of a range of scales and may be used on nonuniform meshes. Various boundary conditions may be invoked, and both accurate interpolation and spectral-like filtering can be accomplished by means of schemes for derivatives at mid-cell locations. This family of schemes reduces to the Pade schemes when the maximal formal accuracy constraint is imposed with a specific computational stencil. Attention is given to illustrative applications of these schemes in fluid dynamics.

Lele, Sanjiva K.↗

An Immersed Boundary Method for Solving the Compressible Navier-Stokes Equations with Fluid Structure Interaction

An immersed boundary method for the compressible Navier-Stokes equation and the additional infrastructure that is needed to solve moving boundary problems and fully coupled fluid-structure interaction is described. All the methods described in this paper were implemented in NASA's LAVA solver framework. The underlying immersed boundary method is based on the locally stabilized immersed boundary method that was previously introduced by the authors. In the present paper this method is extended to account for all aspects that are involved for fluid structure interaction simulations, such as fast geometry queries and stencil computations, the treatment of freshly cleared cells, and the coupling of the computational fluid dynamics solver with a linear structural finite element method. The current approach is validated for moving boundary problems with prescribed body motion and fully coupled fluid structure interaction problems in 2D and 3D. As part of the validation procedure, results from the second AIAA aeroelastic prediction workshop are also presented. The current paper is regarded as a proof of concept study, while more advanced methods for fluid structure interaction are currently being investigated, such as geometric and material nonlinearities, and advanced coupling approaches.

Equations↗

Auto-Tuning the 27-point Stencil for Multicore

This study focuses on the key numerical technique of stencil computations, used in many different scientific disciplines, and illustrates how auto-tuning can be used to produce very efficient implementations across a diverse set of current multicore architectures.

97 MATHEMATICS AND COMPUTING↗

Modeling and Simulating Multiple Failure Masking enabled by Local Recovery for Stencil-based Applications at Extreme Scales

By obtaining multi-process hard failure resilience at the application level is a key challenge that must be overcome before the promise of exascale can be fully realized. Some previous work has shown that online global recovery can dramatically reduce the overhead of failures when compared to the more traditional approach of terminating the job and restarting it from the last stored checkpoint. If online recovery is performed in a local manner further scalability is enabled, not only due to the intrinsic lower costs of recovering locally, but also due to derived effects when using some application types. In this paper we model one such effect, namely multiple failure masking, that manifests when running Stencil parallel computations on an environment when failures are recovered locally. First, the delay propagation shape of one or multiple failures recovered locally is modeled to enable several analyses of the probability of different levels of failure masking under certain Stencil application behaviors. These results indicate that failure masking is an extremely desirable effect at scale which manifestation is more evident and beneficial as the machine size or the failure rate increase.

97 MATHEMATICS AND COMPUTING↗

A design methodology for domain-optimized power-efficient supercomputing

As power has become the pre-eminent design constraint for future HPC systems, computational efficiency is being emphasized over simply peak performance. Recently, static benchmark codes have been used to find a power efficient architecture. Unfortunately, because compilers generate sub-optimal code, benchmark performance can be a poor indicator of the performance potential of architecture design points. Therefore, we present hardware/software cotuning as a novel approach for system design, in which traditional architecture space exploration is tightly coupled with software auto-tuning for delivering substantial improvements in area and power efficiency. We demonstrate the proposed methodology by exploring the parameter space of a Tensilica-based multi-processor running three of the most heavily used kernels in scientific computing, each with widely varying micro-architectural requirements: sparse matrix vector multiplication, stencil-based computations, and general matrix-matrix multiplication. Results demonstrate that co-tuning significantly improves hardware area and energy efficiency - a key driver for next generation of HPC system design.

97 MATHEMATICS AND COMPUTING↗

High-Order Methods for Computational Fluid Dynamics: A Brief Review of Compact Differential Formulations on Unstructured Grids

Popular high-order schemes with compact stencils for Computational Fluid Dynamics (CFD) include Discontinuous Galerkin (DG), Spectral Difference (SD), and Spectral Volume (SV) methods. The recently proposed Flux Reconstruction (FR) approach or Correction Procedure using Reconstruction (CPR) is based on a differential formulation and provides a unifying framework for these high-order schemes. Here we present a brief review of recent developments for the FR/CPR schemes as well as some pacing items.

Huynh, H. T.↗

Charon Message-Passing Toolkit for Scientific Computations

The Charon toolkit for piecemeal development of high-efficiency parallel programs for scientific computing is described. The portable toolkit, callable from C and Fortran, provides flexible domain decompositions and high-level distributed constructs for easy translation of serial legacy code or design to distributed environments. Gradual tuning can subsequently be applied to obtain high performance, possibly by using explicit message passing. Charon also features general structured communications that support stencil-based computations with complex recurrences. Through the separation of partitioning and distribution, the toolkit can also be used for blocking of uni-processor code, and for debugging of parallel algorithms on serial machines. An elaborate review of recent parallelization aids is presented to highlight the need for a toolkit like Charon. Some performance results of parallelizing the NAS Parallel Benchmark SP program using Charon are given, showing good scalability.

VanderWijngaart, Rob F.↗

Charon Message-Passing Toolkit for Scientific Computations

The Charon toolkit for piecemeal development of high-efficiency parallel programs for scientific computing is described. The portable toolkit, callable from C and Fortran, provides flexible domain decompositions and high-level distributed constructs for easy translation of serial legacy code or design to distributed environments. Gradual tuning can subsequently be applied to obtain high performance, possibly by using explicit message passing. Charon also features general structured communications that support stencil-based computations with complex recurrences. Through the separation of partitioning and distribution, the toolkit can also be used for blocking of uni-processor code, and for debugging of parallel algorithms on serial machines. An elaborate review of recent parallelization aids is presented to highlight the need for a toolkit like Charon. Some performance results of parallelizing the NAS Parallel Benchmark SP program using Charon are given, showing good scalability. Some performance results of parallelizing the NAS Parallel Benchmark SP program using Charon are given, showing good scalability.

VanderWijngarrt, Rob F.↗