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 847 records · Page 47

A Testbed of Parallel Kernels for Computer Science Research

For several decades, computer scientists have sought guidance on how to evolve architectures, languages, and programming models for optimal performance, efficiency, and productivity. Unfortunately, this guidance is most often taken from the existing software/hardware ecosystem. Architects attempt to provide micro-architectural solutions to improve performance on fixed binaries. Researchers tweak compilers to improve code generation for existing architectures and implementations, and they may invent new programming models for fixed processor and memory architectures and computational algorithms. In today's rapidly evolving world of on-chip parallelism, these isolated and iterative improvements to performance may miss superior solutions in the same way gradient descent optimization techniques may get stuck in local minima. In an initial study, we have developed an alternate approach that, rather than starting with an existing hardware/software solution laced with hidden assumptions, defines the computational problems of interest and invites architects, researchers and programmers to implement novel hardware/ software co-designed solutions. Our work builds on the previous ideas of computational dwarfs, motifs, and parallel patterns by selecting a representative set of essential problems for which we provide: An algorithmic description; scalable problem definition; illustrative reference implementations; verification schemes. For simplicity, we focus initially on the computational problems of interest to the scientific computing community but proclaim the methodology (and perhaps a subset of the problems) as applicable to other communities. We intend to broaden the coverage of this problem space through stronger community involvement. Previous work has established a broad categorization of numerical methods of interest to the scientific computing, in the spirit of the NAS Benchmarks, which pioneered the basic idea of a 'pencil and paper benchmark' in the 1990s. The initial result of the more modern study was the seven dwarfs, which was subsequently extended to 13 motifs. These motifs have already been useful in defining classes of applications for architecture-software studies. However, these broad-brush problem statements often miss the nuance seen in individual kernels. For example, the computational requirements of particle methods vary greatly between the naive (but more accurate) direct calculations and the particle-mesh and particle-tree codes. Thus we commenced our study with an enumeration of problems, but then proceeded by providing not only reference implementations for each problem, but more importantly a mathematical definition that allows one to escape iterative approaches to software/hardware optimization. To ensure long term value, we have augmented each of our reference implementations with both a scalable problem generator and a verification scheme. In a paper we have prepared that documents our efforts, we describe in detail this process of problem definition, scalable input creation, verification, and implementation of reference codes for the scientific computing domain. Table 1 enumerates and describes the level of support we've developed for each kernel. We group these important kernels using the Berkeley dwarfs/motifs taxonomy using a red box in the appropriate column. As kernels become progressively complex, they build upon other, simpler computational methods. We note this dependency via orange boxes. After enumeration of the important numerical problems, we created a domain-appropriate high-level definition of each problem. To ensure future endeavors are not tainted by existing implementations, we specified the problem definition to be independent of both computer architecture and existing programming languages, models, and data types. Then, to provide context as to how such kernels productively map to existing architectures, languages and programming models, we produced reference implementations for most of the kernel (see table). These sample codes should be viewed as 'hints,' designed to show how other designers have mapped a problem's operands and operators to existing hardware and software. Since we wanted such implementations to be illustrative, we tried to ensure they were the most straightforward implementation in the easiest to understand languages using familiar architectures. To that end, most of the linear algebra-oriented computations are written in MATLAB using array indexing to process matrices, rather than one-line library calls to compute the same kernel. This ensures that the kernel's computation is explicit and readable in the implementation and not hidden behind a library. For other problems, such as the Barnes-Hut n-Body solver, the implementations were written in pure C, without any supporting library computations. Along this line, we have also created a scalable problem generator to accompany each computation.

97 MATHEMATICS AND COMPUTING↗

Optimization of Material Recycling During the Decommissioning Process of Nuclear Power Plants - 16123

The German Government decided in 2011 to phase out nuclear power. Therefore, in the near future there will be several nuclear power plants queued up, in parallel, for dismantling. In nuclear decommissioning there is no standardized procedure available, so that a high level of optimization potential can be assumed. We present the results of a preliminary study, in which the optimization potential of metal recycling during the dismantling process should be estimated. The project can be roughly divided into four sections: - Determination of the metal inventory of an exemplarily selected plant; - Analysis of the recycling routes of scrap metal fractions and assessment of the potential for optimization of each process step during the dismantling; - Conduction of activation calculations to uncover the potential of interim storage allowing for radioactive decay; - In collaboration with the Institute of Process Metallurgy and Metal Recycling at the RWTH Aachen, appropriate process steps and process chains of an optimized metal recycling for each of the resulting scrap metal fractions are identified. The paper and the presentation summarize the status and the results of the project implementation and will address for the optimization potentials for decommissioning projects. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Parallel Algorithms for Computing the Tensor-Train Decomposition

The tensor-train (TT) decomposition expresses a tensor in a data-sparse format used in molecular simulations, high-order correlation functions, and optimization. In this paper, we propose four parallelizable algorithms that compute the TT format from various tensor inputs: (1) Parallel-TTSVD for traditional format, (2) PSTT and its variants for streaming data, (3) Tucker2TT for Tucker format, and (4) TT-fADI for solutions of Sylvester tensor equations. We provide theoretical guarantees of accuracy, parallelization methods, scaling analysis, and numerical results. For example, for a d-dimension tensor in $\mathbb{R}$ $n\times∙∙∙$$\times$$n$ a two-sided sketching algorithm PSTT2 is shown to have a memory complexity of $O(n^{[d/2]})$, improving upon $O(n^{d—1})$ from previous algorithms.

97 MATHEMATICS AND COMPUTING↗

Layout-aware I/O Scheduling for terabits data movement

Many science facilities, such as the Department of Energy's Leadership Computing Facilities and experimental facilities including the Spallation Neutron Source, Stanford Linear Accelerator Center, and Advanced Photon Source, produce massive amounts of experimental and simulation data. These data are often shared among the facilities and with collaborating institutions. Moving large datasets over the wide-area network (WAN) is a major problem inhibiting collaboration. Next-generation, terabit-networks will help alleviate the problem, however, the parallel storage systems on the endsystem hosts at these institutions can become a bottleneck for terabit data movement. The parallel storage system (PFS) is shared by simulation systems, experimental systems, analysis and visualization clusters, in addition to wide-area data movers. These competing uses often induce temporary, but significant, I/O load imbalances on the storage system, which impact the performance of all the users. The problem is a serious concern because some resources are more expensive (e.g. super computers) or have time-critical deadlines (e.g. experimental data from a light source), but parallel file systems handle all requests fairly even if some storage servers are under heavy load. This paper investigates the problem of competing workloads accessing the parallel file system and how the performance of wide-area data movement can be improved in these environments. First, we study the I/O load imbalance problems using actual I/O performance data collected from the Spider storage system at the Oak Ridge Leadership Computing Facility. Second, we present I/O optimization solutions with layout-awareness on end-system hosts for bulk data movement. With our evaluation, we show that our I/O optimization techniques can avoid the I/O congested disk groups, improving storage I/O times on parallel storage systems for terabit data movement.

Kim, Youngjae↗

Layout-Aware I/O Scheduling for Terabits Data Movement

Many science facilities, such as the Department of Energy s Leadership Computing Facilities and experimental facilities including the Spallation Neutron Source, Stanford Linear Accelerator Center, and Advanced Photon Source, produce massive amounts of experimental and simulation data. These data are often shared among the facilities and with collaborating institutions. Moving large datasets over the wide- area network (WAN) is a major problem inhibiting collaboration. Next- generation, terabit-networks will help alleviate the problem, however, the parallel storage systems on the end-system hosts at these institutions can become a bottleneck for terabit data movement. The parallel storage system (PFS) is shared by simulation systems, experimental systems, analysis and visualization clusters, in addition to wide-area data movers. These competing uses often induce temporary, but significant, I/O load imbalances on the storage system, which impact the performance of all the users. The problem is a serious concern because some resources are more expensive (e.g. super computers) or have time-critical deadlines (e.g. experimental data from a light source), but parallel file systems handle all requests fairly even if some storage servers are under heavy load. This paper investigates the problem of competing workloads accessing the parallel file system and how the performance of wide-area data movement can be improved in these environments. First, we study the I/O load imbalance problems using actual I/O performance data collected from the Spider storage system at the Oak Ridge Leadership Computing Facility. Second, we present I/O optimization solutions with layout-awareness on end-system hosts for bulk data movement. With our evaluation, we show that our I/O optimization techniques can avoid the I/O congested disk groups, improving storage I/O times on parallel storage systems for terabit data movement.

I/O and Storage↗

On Data Transfers Over Wide-Area Dedicated Connections

Dedicated wide-area network connections are employed in big data and high-performance computing scenarios, since the absence of cross-traffic promises to make it easier to analyze and optimize data transfers over them. However, nonlinear transport dynamics and end-system complexity due to multi-core hosts and distributed file systems make these tasks surprisingly challenging. We present an overview of methods to analyze memory and disk file transfers using extensive measurements over 10 Gbps physical and emulated connections with 0–366 ms round trip times (RTTs). For memory transfers, we derive performance profiles of TCP and UDT throughput as a function of RTT, which show concave regions in contrast to entirely convex regions predicted by previous models. These highly desirable concave regions can be expanded by utilizing large buffers and more parallel flows. We also present Poincar´e maps and Lyapunov exponents of TCP and UDT throughputtraces that indicate complex throughput dynamics. For disk file transfers, we show that throughput can be optimized using a combination of parallel I/O and network threads under direct I/O mode. Our initial throughput measurements of Lustre filesystems mounted over long-haul connections using LNet routers show convex profiles indicative of I/O limits.

Rao, Nageswara S.↗

Data-Driven Compositional Optimization in Misspecified Regimes

With a manifold growth in the scale and intricacy of systems, the challenges of parametric misspecification become pronounced. These concerns are further exacerbated in compositional settings, which emerge in problems complicated by modeling risk and robustness. In “Data-Driven Compositional Optimization in Misspecified Regimes,” the authors consider the resolution of compositional stochastic optimization problems, plagued by parametric misspecification. In considering settings where such misspecification may be resolved via a parallel learning process, the authors develop schemes that can contend with diverse forms of risk, dynamics, and nonconvexity. They provide asymptotic and rate guarantees for unaccelerated and accelerated schemes for convex, strongly convex, and nonconvex problems in a two-level regime with extensions to the multilevel setting. Surprisingly, the nonasymptotic rate guarantees show no degradation from the rate statements obtained in a correctly specified regime and the schemes achieve optimal (or near-optimal) sample complexities for general T-level strongly convex and nonconvex compositional problems.

Business & Economics↗

Livermore Big Artificial Neural Network Toolkit

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

Essen, BrianVan↗

Livermore Big Artificial Neural Network Toolkit

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

Essen, Brian Van↗

A Case Study of LLVM-Based Analysis for Optimizing SIMD Code Generation

This paper presents a methodology for using LLVM-based tools to tune the DCA++ (dynamical cluster approximation) application that targets the new ARM A64FX processor. The goal is to describe the changes required for the new architecture and generate efficient single instruction/multiple data (SIMD) instructions that target the new Scalable Vector Extension instruction set. During manual tuning, the authors used the LLVM tools to improve code parallelization by using OpenMP SIMD, refactored the code and applied transformation that enabled SIMD optimizations, and ensured that the correct libraries were used to achieve optimal performance. By applying these code changes, code speed was increased by 1.98× and 78 GFlops were achieved on the A64FX processor. The authors aim to automatize parts of the efforts in the OpenMP Advisor tool, which is built on top of existing and newly introduced LLVM tooling.

Huber, Joseph↗

DaCe - Data Centric Parallel Programming

DaCe is a parallel programming framework that takes code in Python/NumPy and other programming languages, and maps it to high-performance CPU, GPU, and FPGA programs, which can be optimized to achieve state-of-the-art. Internally, DaCe uses the Stateful DataFlow multiGraph (SDFG) data-centric intermediate representation: A transformable, interactive representation of code based on data movement. Since the input code and the SDFG are separate, it is possible to optimize a program without changing its source, so that it stays readable. On the other hand, transformations are customizable and user-extensible, so they can be written once and reused in many applications. With data-centric parallel programming, we enable direct knowledge transfer of performance optimization, regardless of the application or the target processor.

Ben-Nun, Tal↗

Gd 5 (Si,Ge) 4 thin film displaying large magnetocaloric and strain effects due to magnetostructural transition

Magnetic refrigeration based on the magnetocaloric effect is one of the best alternatives to compete with vapor-compression technology. Despite being already in its technology transfer stage, there is still room for optimization, namely, on the magnetic responses of the magnetocaloric material. In parallel, the demand for different magnetostrictive materials has been greatly enhanced due to the wide and innovative range of technologies that emerged in the last years (from structural evaluation to straintronics fields). In particular, the Gd 5 (Si x Ge 1–x ) 4 compounds are a family of well-known alloys that present both giant magnetocaloric and colossal magnetostriction effects. Despite their remarkable properties, very few reports have been dedicated to the nanostructuring of these materials: here, we report a ~800 nm Gd 5 Si 2.7 Ge 1.3 thin film. The magnetic and structural investigation revealed that the film undergoes a first order magnetostructural transition and as a consequence exhibits large magnetocaloric effect (–ΔS mMAX ~8.83 J kg –1 K –1 , ΔH = 5T) and giant thermal expansion (12000 p.p.m). The thin film presents a broader magnetic response in comparison with the bulk compound, which results in a beneficial magnetic hysteresis reduction. The ΔS mMAX exhibited by the Gd 5 (Si,Ge) 4 thin film makes it a promising candidate for micro/nano magnetic refrigeration area.

36 MATERIALS SCIENCE↗

The Persistent Challenge of Data Locality in the Post-Exascale Era

The era of exascale computing, exemplified by systems like Frontier achieving exaflop-level performance, marks a milestone. However, the quest for sheer compute power leads to strong imbalance in system design. Hence, scaling advancements in memory, network bandwidth, and storage are also necessary and pose challenges, with a crucial need to address data locality issues. This article underscores the fundamental importance of data locality as a key abstraction for optimizing application performance. Despite notable software solutions, the growing complexity of parallelism and memory hierarchy demands performance-portable data locality solutions across diverse computing platforms. Additionally, the article revisits data locality aspects, covering hardware considerations, application perspectives, software stack abstractions, and tool support. It concludes with insights into data locality challenges and opportunities, emphasizing the ongoing significance of collaborative research for progress in this critical issue.

Unat, Didem [Koc University, Istanbul (Turkey)] (O↗

Rethinking Visual Analytics for Streaming Data Applications

In the age of data science, the use of interactive information visualization techniques has become increasingly ubiquitous. From online scientific journals to the New York Times graphics desk, the utility of interactive visualization for both storytelling and analysis has become ever more apparent. As these techniques have become more readily accessible, the appeal of combining interactive visualization with computational analysis continues to grow. Arising out of a need for scalable, human-driven analysis, primary objective of visual analytics systems is to capitalize on the complementary strengths of human and machine analysis, using interactive visualization as a medium for communication between the two. These systems leverage developments from the fields of information visualization, computer graphics, machine learning, and human-computer interaction to support insight generation in areas where purely computational analyses fall short. Over the past decade, visual analytics systems have generated remarkable advances in many historically challenging analytical contexts. These include areas such as modeling political systems [Crouser et al. 2012], detecting financial fraud [Chang et al. 2008], and cybersecurity [Harrison et al. 2012]. In each of these contexts, domain expertise and human intuition is a necessary component of the analysis. This intuition is essential to building trust in the analytical products, as well as supporting the translation of evidence into actionable insight. In addition, each of these examples also highlights the need for scalable analysis. In each case, it is infeasible for a human analyst to manually assess the raw information unaided, and the communication overhead to divide the task between a large number of analysts makes simple parallelism intractable. Regardless of the domain, visual analytics tools strive to optimize the allocation of human analytical resources, and to streamline the sensemaking process on data that is massive, complex, incomplete, and uncertain in scenarios requiring human judgment.

97 MATHEMATICS AND COMPUTING↗

SU-C-BRA-03: An Automated and Quick Contour Errordetection for Auto Segmentation in Online Adaptive Radiotherapy

Purpose: To develop a tool that can quickly and automatically assess contour quality generated from auto segmentation during online adaptive replanning. Methods: Due to the strict time requirement of online replanning and lack of ‘ground truth’ contours in daily images, our method starts with assessing image registration accuracy focusing on the surface of the organ in question. Several metrics tightly related to registration accuracy including Jacobian maps, contours shell deformation, and voxel-based root mean square (RMS) analysis were computed. To identify correct contours, additional metrics and an adaptive decision tree are introduced. To approve in principle, tests were performed with CT sets, planned and daily CTs acquired using a CT-on-rails during routine CT-guided RT delivery for 20 prostate cancer patients. The contours generated on daily CTs using an auto-segmentation tool (ADMIRE, Elekta, MIM) based on deformable image registration of the planning CT and daily CT were tested. Results: The deformed contours of 20 patients with total of 60 structures were manually checked as baselines. The incorrect rate of total contours is 49%. To evaluate the quality of local deformation, the Jacobian determinant (1.047±0.045) on contours has been analyzed. In an analysis of rectum contour shell deformed, the higher rate (0.41) of error contours detection was obtained compared to 0.32 with manual check. All automated detections took less than 5 seconds. Conclusion: The proposed method can effectively detect contour errors in micro and macro scope by evaluating multiple deformable registration metrics in a parallel computing process. Future work will focus on improving practicability and optimizing calculation algorithms and metric selection.

60 APPLIED LIFE SCIENCES↗

Measurements and analytics of wide-area file transfers over dedicated connections

Distributed scientific and big-data computations are becoming increasingly dependent on access to remote files. Wide-area file transfers are supported by two basic schemes: (i) application-level tools, such as GridFTP, that provide transport services between file systems housed at geographically separated sites, and (ii) file systems mounted over wide-area networks, using mechanisms such as LNet routers that make them transparently available. In both cases, the file transfer performance critically depends on the configuration consisting of host, file, IO, and disk subsystems, which are complex by themselves, as well as on their complex compositions implemented using buffers and IO-network data transitions. We present extensive file transfer rate measurements collected over dedicated 10 Gbps connections with 0-366 ms round-trip times, using GridFTP and XDD file transfer tools, and Lustre file system extended over wide-area networks using LNet routers. Our test configurations are composed of: three types of host systems; XFS, Lustre, and ext3 file systems; and Ethernet and SONET wide-area connections. We present analytics based on the convexity-concavity of throughput profiles which provide insights into throughput and its superior or inferior trend compared to linear interpolations. We propose the utilization-concavity coefficient, a scalar metric that characterizes the overall performance of any file transfer method consisting of specific configuration and scheme. Our results enable performance optimizations by highlighting the significant roles of (i) buffer sizes and parallelism in GridFTP and XDD, and (ii) buffer utilization and credit mechanism in LNet routers.

Rao, Nageswara↗

Large-scale 3D geoelectromagnetic modeling using parallel adaptive high-order finite element method

Here, we have investigated the use of the adaptive high-order finite-element method (FEM) for geoelectromagnetic modeling. Because high-order FEM is challenging from the numerical and computational points of view, most published finite-element studies in geoelectromagnetics use the lowest order formulation. Solution of the resulting large system of linear equations poses the main practical challenge. We have developed a fully parallel and distributed robust and scalable linear solver based on the optimal block-diagonal and auxiliary space preconditioners. The solver was found to be efficient for high finite element orders, unstructured and nonconforming locally refined meshes, a wide range of frequencies, large conductivity contrasts, and number of degrees of freedom (DoFs). Furthermore, the presented linear solver is in essence algebraic; i.e., it acts on the matrix-vector level and thus requires no information about the discretization, boundary conditions, or physical source used, making it readily efficient for a wide range of electromagnetic modeling problems. To get accurate solutions at reduced computational cost, we have also implemented goal-oriented adaptive mesh refinement. The numerical tests indicated that if highly accurate modeling results were required, the high-order FEM in combination with the goal-oriented local mesh refinement required less computational time and DoFs than the lowest order adaptive FEM.

58 GEOSCIENCES↗

Tough Errors are no Match (TEAM): Optimizing the Quantum Compiler for Noise Resilience

This project builds toward a comprehensive error-mitigating toolkit that makes quantum programming more robust and adaptive to the noisy, resource-limited nature of today’s quantum hardware. To that end, it integrates established error-mitigation methods — such as zero-noise extrapolation and dynamical decoupling — directly into compiler infrastructures. These techniques will be packaged as modules that can automatically adjust and combine based on performance analysis, enabling compilers to explore large design spaces and produce optimized, low-noise quantum programs with minimal manual intervention. In parallel, this project also explores new approaches to analog quantum programming or quantum simulation, and has developed the programming language SimuQ which treats quantum Hamiltonian evolution as the central object.

97 MATHEMATICS AND COMPUTING↗