Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel optimization”

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 955 records · Page 53

Comparative Performance Analysis of Coarse Solvers for Algebraic Multigrid on Multicore and Manycore Architectures

In this paper, we study the performance of a two-level algebraic-multigrid algorithm, with a focus on the impact of the coarse-grid solver on performance. We consider two algorithms for solving the coarse-space systems: the preconditioned conjugate gradient method and a new robust HSS-embedded low-rank sparse-factorization algorithm. Our test data comes from the SPE Comparative Solution Project for oil-reservoir simulations. We contrast the performance of our code on one 12-core socket of a Cray XC30 machine with performance on a 60-core Intel Xeon Phi coprocessor. To obtain top performance, we optimized the code to take full advantage of fine-grained parallelism and made it thread-friendly for high thread count. We also developed a bounds-and-bottlenecks performance model of the solver which we used to guide us through the optimization effort, and also carried out performance tuning in the solver’s large parameter space. Finally, as a result, significant speedups were obtained on both machines.

97 MATHEMATICS AND COMPUTING↗

Parallel k-means Clustering of Geospatial Data Sets Using Manycore CPU Architectures

The increasing availability of high-resolution geospatiotemporal data sets from sources such as observatory networks, remote sensing platforms, and computational Earth system models has opened new possibilities for knowledge discovery and mining of weather, climate, ecological, and other geoscientific data sets fused from disparate sources. Many of the standard tools used on individual workstations are impractical for the analysis and synthesis of data sets of this size; however, new algorithmic approaches that can effectively utilize the complex memory hierarchies and the extremely high levels of parallelism available in state-of-the-art high-performance computing platforms can enable such analysis. Here, we describe pKluster, an open-source tool we have developed for accelerated k-means clustering of geospatial and geospatiotemporal data, and discuss algorithmic modifications and code optimizations we have made to enable it to effectively use parallel machines based on novel CPU architectures—such as the Intel “Knights Landing” Xeon Phi and Skylake Xeon processors—with many cores and hardware threads, and employing significant single instruction, multiple data (SIMD) parallelism. We outline some applications of the code in ecology and climate science contexts and present a detailed discussion of the performance of the code for one such application, LiDAR-derived vertical vegetation structure classification.

Mills, Richard T↗

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.↗

Exploring MPI Communication Models for Graph Applications Using Graph Matching as a Case Study

Traditional implementations of parallel graph operations on distributed memory platforms are written using Message Passing Interface (MPI) point to point communication primitives such as Send-Recv (blocking and nonblocking). Apart from this classical model, the MPI community has over the years added other communication models; however, their suitability for handling the irregular traffic workloads typical of graph operations remain comparatively less explored. Our aim in this paper is to study these relatively underutilized communication models of MPI for graph applications. More specifically, we evaluate MPI’s one-sided programming, or Remote Memory Access (RMA), and nearest neighborhood collectives using a process graph topology. There are features in these newer models that are intended to better map to irregular communication patterns, as exemplified in graph algorithms. As a concrete application for our case study, we use distributed memory implementations of a weighted graph matching algorithm to investigate performances of MPI-3 RMA and neighborhood collective operations compared to nonblocking Send- Recv. A matching in a graph is a subset of edges such that no two matched edges are incident on the same vertex. A maximum weight matching is a matching of maximum weight computed as the sum of the weights of matched edges. Algorithms for optimal matching have quadratic complexity and are difficult to parallelize. More importantly, execution of graph matching is dominated by high volume of irregular memory accesses, making it an ideal candidate for studying the effects of various MPI communication models on graph applications at scale. Our neighborhood collectives and RMA implementations yields up to 6× speedup over traditional optimized nonblocking Send-Recv implementations, on thousands of cores of the NERSC Cori supercomputer. We believe the lessons learned from this case study can be adopted to benefit a wider range of graph application codes.

Ghosh, Sayan↗

Efficient Heterogeneous Execution on Large Multicore and Accelerator Platforms: Case Study Using a Block Tridiagonal Solver

The algorithmic and implementation principles are explored in gainfully exploiting GPU accelerators in conjunction with multicore processors on high-end systems with large numbers of compute nodes, and evaluated in an implementation of a scalable block tridiagonal solver. The accelerator of each compute node is exploited in combination with multicore processors of that node in performing block-level linear algebra operations in the overall, distributed solver algorithm. Optimizations incorporated include: (1) an efficient memory mapping and synchronization interface to minimize data movement, (2) multi-process sharing of the accelerator within a node to obtain balanced load with multicore processors, and (3) an automatic memory management system to efficiently utilize accelerator memory when sub-matrices spill over the limits of device memory. Results are reported from our novel implementation that uses MAGMA and CUBLAS accelerator software systems simultaneously with ACML for multithreaded execution on processors. Overall, using 940 nVidia Tesla X2090 accelerators and 15,040 cores, the best heterogeneous execution delivers a 10.9-fold reduction in run time relative to an already efficient parallel multicore-only baseline implementation that is highly optimized with intra-node and inter-node concurrency and computation-communication overlap. Detailed quantitative results are presented to explain all critical runtime components contributing to hybrid performance.

Park, Alfred J↗

Parallel computation of 3-D Navier-Stokes flowfields for supersonic vehicles

Multidisciplinary design optimization of aircraft will require unprecedented capabilities of both analysis software and computer hardware. The speed and accuracy of the analysis will depend heavily on the computational fluid dynamics (CFD) module which is used. A new CFD module has been developed to combine the robust accuracy of conventional codes with the ability to run on parallel architectures. This is achieved by parallelizing the ARC3D algorithm, a central-differenced Navier-Stokes method, on the Intel iPSC/860. The computed solutions are identical to those from conventional machines. Computational speed on 64 processors is comparable to the rate on one Cray Y-MP processor and will increase as new generations of parallel computers become available.

Ryan, James S.↗

Efficient Ensemble-Based Stochastic Gradient Methods for Optimization Under Geological Uncertainty

Ensemble-based stochastic gradient methods, such as the ensemble optimization (EnOpt) method, the simplex gradient (SG) method, and the stochastic simplex approximate gradient (StoSAG) method, approximate the gradient of an objective function using an ensemble of perturbed control vectors. These methods are increasingly used in solving reservoir optimization problems because they are not only easy to parallelize and couple with any simulator but also computationally more efficient than the conventional finite-difference method for gradient calculations. In this work, we show that EnOpt may fail to achieve sufficient improvement of the objective function when the differences between the objective function values of perturbed control variables and their ensemble mean are large. On the basis of the comparison of EnOpt and SG, we propose a hybrid gradient of EnOpt and SG to save on the computational cost of SG. We also suggest practical ways to reduce the computational cost of EnOpt and StoSAG by approximating the objective function values of unperturbed control variables using the values of perturbed ones. We first demonstrate the performance of our improved ensemble schemes using a benchmark problem. Results show that the proposed gradients saved about 30–50% of the computational cost of the same optimization by using EnOpt, SG, and StoSAG. As a real application, we consider pressure management in carbon storage reservoirs, for which brine extraction wells need to be optimally placed to reduce reservoir pressure buildup while maximizing the net present value. Results show that our improved schemes reduce the computational cost significantly.

58 GEOSCIENCES↗

Genetically Engineered Microelectronic Infrared Filters

A genetic algorithm is used for design of infrared filters and in the understanding of the material structure of a resonant tunneling diode. These two components are examples of microdevices and nanodevices that can be numerically simulated using fundamental mathematical and physical models. Because the number of parameters that can be used in the design of one of these devices is large, and because experimental exploration of the design space is unfeasible, reliable software models integrated with global optimization methods are examined The genetic algorithm and engineering design codes have been implemented on massively parallel computers to exploit their high performance. Design results are presented for the infrared filter showing new and optimized device design. Results for nanodevices are presented in a companion paper at this workshop.

Cwik, Tom↗

A second-order distributed memory parallel fast sweeping method for the Eikonal equation

The Eikonal equation is used to calculate wave propagation and distance fields, and due to its complexity requires numerical treatment for its solution. In this work, we present a second-order distributed memory parallel fast sweeping method. The second-order solution switches on a two-point stencil when two upwind points are available, and reverts to first-order otherwise. In all examples, the second-order method improves the solution over the first-order, allowing for significant savings in memory while achieving the same accuracy. Parallelization over distributed memory saw good weak scaling with optimal convergence. The computational time for second-order was approximately 2.5 times slower than first-order, where the largest amount of mesh points ran on 144 cores (512 GB) was ≈20 billion. The savings in memory from the second-order method combined with the distributed memory algorithm result in the ability to solve problems much larger than are possible with the serial first-order method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

MOCFE-Bone: The 3D-MOC Mini-Application for Exascale Research

MOCFE-Bone is a mini-application that simulates the main procedures in a 3D method of characteristics (MOC) code for numerical solution of the steady state neutron transport equation. 3D MOC was chosen as a specific methodology of interest in exascale computing for nuclear reactor applications because of its heterogeneous geometry capability, high degree of accuracy, and potential for scalability. In developing the mini-app, we focused on emulating the behavior of a production 3D MOC tool without requiring the input overhead associated with such a code. The MOCFE code at Argonne National Laboratory was used to investigate and characterize the behavior of the mini-app; the results of are presented here. Note that the existing MOCFE code resulted from research forays into the potential of 3D-MOC for large scale parallelism and is not a production level tool nor is it optimally implemented. Parts of the mini-app therefore reflect lessons learned and represent how a production-level tool would be written from this point forward rather than simply duplicating MOCFE, which has known scalability issues (i.e. parallelization in energy).

Wolters, E. R.↗

Spacial and objective decompositions for very large SCAPs

This paper considers the single commodity allocation problem (SCAP) for disaster recovery, a fundamental problem faced by all populated areas. SCAPs are complex stochastic optimization problems that combine resource allocation, warehouse routing, and parallel fleet routing. Moreover, these problems must be solved under tight run-time constraints to be practical in real-world disaster situations. This paper revisits the SCAP algorithm proposed in and proposes new storage allocation models that are necessary to enable the algorithm to scale to problem sizes of three orders of magnitude greater (250, 500, 1000 storage locations). The new algorithms are validated on large-scale hurricane disaster scenarios generated by Los Alamos National Laboratory using state-of-the-art disaster simulation tools.

97 MATHEMATICS AND COMPUTING↗

Memory-efficient optimization of Gyrokinetic particle-to-grid interpolation for multicore processors

We present multicore parallelization strategies for the particle-to-grid interpolation step in the Gyrokinetic Toroidal Code (GTC), a 3D particle-in-cell (PIC) application to study turbulent transport in magnetic-confinement fusion devices. Particle-grid interpolation is a known performance bottleneck in several PIC applications. In GTC, this step involves particles depositing charges to a 3D toroidal mesh, and multiple particles may contribute to the charge at a grid point. We design new parallel algorithms for the GTC charge deposition kernel, and analyze their performance on three leading multicore platforms. We implement thirteen different variants for this kernel and identify the best-performing ones given typical PIC parameters such as the grid size, number of particles per cell, and the GTC-specific particle Larmor radius variation. We find that our best strategies can be 2x faster than the reference optimized MPI implementation, and our analysis provides insight into desirable architectural features for high-performance PIC simulation codes.

97 MATHEMATICS AND COMPUTING↗

ParaDyn Implementation in the US Navy's DYSMAS Simulation System: FY08 Progress Report

The goal of this project is to increase the computational efficiency and capacity of the Navy's DYSMAS simulation system for full ship shock response to underwater explosion. Specifically, this project initiates migration to a parallel processing capability for the structural portion of the overall fluid-structure interaction model. The capstone objective for the first phase is to demonstrate operation of the DYSMAS simulation engine with a production model on a Naval Surface Warfare Center (IHD) parallel platform using the ParaDyn code for parallel processing of the structural dynamics. This year saw a successful launch to integrate ParaDyn, the high-parallel structural dynamics code from Lawrence Livermore National Laboratory (LLNL), into the DYSMAS system for simulating the response of ship structures to underwater explosion (UNDEX). The current LLNL version of DYNA3D, representing ten years of general development beyond the source branch used to initiate DYNA-N customization for DYSMAS, was first connected to the GEMINI flow code through DYSMAS Standard Coupler Interface (SCI). This permitted an early 'sanity check' by Naval Surface Warfare Center, Indian Head Division (NSWC-IHD) personnel that equivalent results were generated for their standard UNDEX test problems, thus ensuring the Verification & Validation pedigree they have developed remains intact. The ParaDyn code was then joined to the SCI in a manner requiring no changes to GEMINI. Three NSWC-IHD engineers were twice hosted at LLNL to become familiar with LLNL computer systems, the execution of the prototype software system, and to begin assessment of its accuracy and performance. Scaling data for the flow solver GEMINI was attained up to a one billion cell, 1000 processor run. The NSWC-IHD engineers were granted privileges to continue their evaluations through remote connections to LLNL's Open Computing Facility. Finally, the prototype changes were integrated into the mainline ParaDyn source repository and issued as part of its Version 8.1 beta release. This source was transmitted to NSWC-IHD and in collaboration with LLNL personnel the entire ParaDyn software suite successfully installed and demonstrated on its new SGI Altix machine. The ability of even minor numbers of processors for the structural dynamics to impact overall time-to-solution for DYSMAS has been demonstrated. Assessments of combined parallel efficiencies are beginning to highlight areas for further DYSMAS optimizations.

42 ENGINEERING↗

A Method for Optimizing Non-Axisymmetric Liners for Multimodal Sound Sources

Central processor unit times and memory requirements for a commonly used solver are compared to that of a state-of-the-art, parallel, sparse solver. The sparse solver is then used in conjunction with three constrained optimization methodologies to assess the relative merits of non-axisymmetric versus axisymmetric liner concepts for improving liner acoustic suppression. This assessment is performed with a multimodal noise source (with equal mode amplitudes and phases) in a finite-length rectangular duct without flow. The sparse solver is found to reduce memory requirements by a factor of five and central processing time by a factor of eleven when compared with the commonly used solver. Results show that the optimum impedance of the uniform liner is dominated by the least attenuated mode, whose attenuation is maximized by the Cremer optimum impedance. An optimized, four-segmented liner with impedance segments in a checkerboard arrangement is found to be inferior to an optimized spanwise segmented liner. This optimized spanwise segmented liner is shown to attenuate substantially more sound than the optimized uniform liner and tends to be more effective at the higher frequencies. The most important result of this study is the discovery that when optimized, a spanwise segmented liner with two segments gives attenuations equal to or substantially greater than an optimized axially segmented liner with the same number of segments.

Watson, W. R.↗

Vertex Reordering for Real-world Graphs and Applications: An Empirical Evaluation

Vertex reordering is a way to improve locality in graph computations. Given an input (or ``natural'') order, reordering aims to compute an alternate permutation of the vertices that is aimed at maximizing a locality-based objective. Given decades of research on this topic, there are tens of graph reordering schemes, and there are also several linear arrangement ``gap'' measures for treatment as objectives. However, a comprehensive empirical analysis of the efficacy of the ordering schemes against the different gap measures, and against real-world applications is currently lacking. In this study, we present an extensive empirical evaluation of up to 11 ordering schemes, taken from different classes of approaches, on a set of 34 real-world graphs emerging from different application domains. Our study is presented in two parts: a) a thorough comparative evaluation of the different ordering schemes on their effectiveness to optimize different linear arrangement gap measures, relevant to preserving locality; and b) extensive evaluation of the impact of the ordering schemes on two real-world, parallel graph applications, namely, community detection and influence maximization. Our studies show a significant divergence among the ordering schemes (up to $40\times$ between the best and the poor) in their effectiveness to reduce the gap measures; and a wide ranging impact of the ordering schemes on various aspects including application runtime (up to $4\times$), memory and cache use, load balancing, and parallel work and efficiency. The comparative study also help reveal the nuances of a parallel environment (compared to serial) on the ordering schemes and their role in optimizing applications.

Barik, Reet↗

An optimized FM-index library for nucleotide and amino acid search

Abstract Background Pattern matching is a key step in a variety of biological sequence analysis pipelines. The FM-index is a compressed data structure for pattern matching, with search run time that is independent of the length of the database text. Implementation of the FM-index is reasonably complicated, so that increased adoption will be aided by the availability of a fast and flexible FM-index library. Results We present AvxWindowedFMindex (AWFM-index), a lightweight, open-source, thread-parallel FM-index library written in C that is optimized for indexing nucleotide and amino acid sequences. AWFM-index introduces a new approach to storing FM-index data in a strided bit-vector format that enables extremely efficient computation of the FM-index occurrence function via AVX2 bitwise instructions, and combines this with optional on-disk storage of the index’s suffix array and a cache-efficient lookup table for partial k-mer searches. The AWFM-index performs exact match count and locate queries faster than SeqAn3’s FM-index implementation across a range of comparable memory footprints. When optimized for speed, AWFM-index is $$\sim $$ ∼ 2–4x faster than SeqAn3 for nucleotide search, and $$\sim $$ ∼ 2–6x faster for amino acid search; it is also $$\sim $$ ∼ 4x faster with similar memory footprint when storing the suffix array in on-disk SSD storage. Conclusions AWFM-index is easy to incorporate into bioinformatics software, offers run-time performance parameterization, and provides clients with FM-index functionality at both a high-level (count or locate all instances of a query string) and low-level (step-wise control of the FM-index backward-search process). The open-source library is available for download at https://github.com/TravisWheelerLab/AvxWindowFmIndex.

59 BASIC BIOLOGICAL SCIENCES↗

The Inspectability Metric: A Formalized System Of Measurement Enabling The Design For Inspection Framework

Nondestructive evaluation (NDE) engineers are often confronted with structural design choices that present challenges to meeting inspection requirements. These challenges, at best, increase the resources needed to design an inspection solution and, at worst, require resource intensive redesign of the structure. If the inspectability of the structure can be determined early in the design cycle, these challenging inspection scenarios can be avoided. The emergence of additive manufacturing has further compounded this problem by enabling the creation of highly optimized structures with no regard to inspection constraints. Design for inspection (DFI) offers a framework to integrate nondestructive evaluation (NDE) into the design process to alleviate the mechanisms that produce uninspectable designs. DFI is the concept of including inspectability in a multi-objective optimization framework so that it can be considered in parallel to other metrics such as mass and manufacturability. This allows rapid evaluation of the trade-off between design metrics to find solutions that meet the inspection needs of a particular material system, structural concept, or vehicle program. To enable DFI, there must be a system by which the inspectability of a structure can be measured. This system must be agile to produce results quickly, it must be versatile to work with the type of incomplete information one would encounter early in the design process (such as lack of inspection requirements), and it must be delivered in a form that is easily understood by designers. To meet this need, this presentation introduces the novel inspectability metric as a system to measure inspectability. The inspectability metric is a standardized, automation friendly procedure that uses simulations to determine inspectability. Along with guidelines to properly process designs and integrate with existing workflows, the inspectability metric provides a suite of simulation tests to interrogate the ability to find defects and the sensitivity to variability. The testing rubric is designed to maximize the coverage of the parameter space while minimizing the number of simulations needed. The inspectability metric has been in development in collaboration with industry partners to ensure compatibility with modern simulation tools and aerospace design workflows. In this study, we will demonstrate how the inspectability metric is able to determine the inspectability of multiple types of structures, including aerospace composites and additively manufactured parts. We will then show how the inspectability score can be plugged into existing design optimization tasks, such as structural sizing algorithms or design for manufacturing (DFM) frameworks.

Design for inspection↗

Reductive Analysis with Compiler-Guided Large Language Models for Input-Centric Code Optimizations

Input-centric program optimization aims to optimize code by considering the relations between program inputs and program behaviors. Despite its promise, a long-standing barrier for its adoption is the difficulty of automatically identifying critical features of complex inputs. This paper introduces a novel technique, reductive analysis through compiler-guided Large Language Models (LLMs), to solve the problem through a synergy between compilers and LLMs. It uses a reductive approach to overcome the scalability and other limitations of LLMs in program code analysis. The solution, for the first time, automates the identification of critical input features without heavy instrumentation or profiling, cutting the time needed for input identification by 44× (or 450× for local LLMs), reduced from 9.6 hours to 13 minutes (with remote LLMs) or 77 seconds (with local LLMs) on average, making input characterization possible to be integrated into the workflow of program compilations. Optimizations on those identified input features show similar or even better results than those identified by previous profiling-based methods, leading to optimizations that yield 92.6% accuracy in selecting the appropriate adaptive OpenMP parallelization decisions, and 20-30% performance improvement of serverless computing while reducing resource usage by 50-60%.

Input-Centric Optimization↗