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 1,135 records · Page 63

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↗

Parallel algorithms for mapping pipelined and parallel computations

Many computational problems in image processing, signal processing, and scientific computing are naturally structured for either pipelined or parallel computation. When mapping such problems onto a parallel architecture it is often necessary to aggregate an obvious problem decomposition. Even in this context the general mapping problem is known to be computationally intractable, but recent advances have been made in identifying classes of problems and architectures for which optimal solutions can be found in polynomial time. Among these, the mapping of pipelined or parallel computations onto linear array, shared memory, and host-satellite systems figures prominently. This paper extends that work first by showing how to improve existing serial mapping algorithms. These improvements have significantly lower time and space complexities: in one case a published O(nm sup 3) time algorithm for mapping m modules onto n processors is reduced to an O(nm log m) time complexity, and its space requirements reduced from O(nm sup 2) to O(m). Run time complexity is further reduced with parallel mapping algorithms based on these improvements, which run on the architecture for which they create the mappings.

Nicol, David M.↗

Multiphase complete exchange on Paragon, SP2 and CS-2

The overhead of interprocessor communication is a major factor in limiting the performance of parallel computer systems. The complete exchange is the severest communication pattern in that it requires each processor to send a distinct message to every other processor. This pattern is at the heart of many important parallel applications. On hypercubes, multiphase complete exchange has been developed and shown to provide optimal performance over varying message sizes. Most commercial multicomputer systems do not have a hypercube interconnect. However, they use special purpose hardware and dedicated communication processors to achieve very high performance communication and can be made to emulate the hypercube quite well. Multiphase complete exchange has been implemented on three contemporary parallel architectures: the Intel Paragon, IBM SP2 and Meiko CS-2. The essential features of these machines are described and their basic interprocessor communication overheads are discussed. The performance of multiphase complete exchange is evaluated on each machine. It is shown that the theoretical ideas developed for hypercubes are also applicable in practice to these machines and that multiphase complete exchange can lead to major savings in execution time over traditional solutions.

Bokhari, Shahid H.↗

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↗

Enhancing Terminal Deoxynucleotidyl Transferase Activity on Substrates with 3′ Terminal Structures for Enzymatic De Novo DNA Synthesis

Enzymatic oligonucleotide synthesis methods based on the template-independent polymerase terminal deoxynucleotidyl transferase (TdT) promise to enable the de novo synthesis of long oligonucleotides under mild, aqueous conditions. Intermediates with a 3′ terminal structure (hairpins) will inevitably arise during synthesis, but TdT has poor activity on these structured substrates, limiting its usefulness for oligonucleotide synthesis. Here, we described two parallel efforts to improve the activity of TdT on hairpins: (1) optimization of the concentrations of the divalent cation cofactors and (2) engineering TdT for enhanced thermostability, enabling reactions at elevated temperatures. By combining both of these improvements, we obtained a ~10-fold increase in the elongation rate of a guanine-cytosine hairpin.

59 BASIC BIOLOGICAL SCIENCES↗

BM3DORNL

BM3DORNL is a high-performance, open-source library for removing streak and ring artifacts from computed-tomography (CT) data, developed for neutron imaging at Oak Ridge National Laboratory's Spallation Neutron Source (VENUS beamline) and applicable to X-ray CT as well. Ring artifacts — concentric rings in reconstructed slices caused by detector pixel-to-pixel response non-uniformities — appear as vertical streaks in the sinogram and degrade both image quality and quantitative analysis. BM3DORNL operates in the sinogram domain using an adaptation of the BM3D (block-matching and 3D collaborative filtering) algorithm (Dabov et al., 2007). It provides a dedicated streak-removal mode, a true multi-scale BM3D variant (after Mäkinen et al., 2021) that suppresses wide streaks single-scale methods miss, and an alternative Fourier–SVD method (~2.6× faster) combining FFT-based energy detection with rank-1 SVD. The computationally intensive core is implemented in Rust with parallel (Rayon) block matching, integral-image pre-screening, and optimized transforms, and is exposed through a simple Python API (with an optional GUI) so it integrates directly into existing tomography reconstruction pipelines. It processes both 2D sinograms and 3D sinogram stacks, is pip-installable for Linux and macOS, and is documented at https://bm3dornl.readthedocs.io.

Zhang, Chen [Oak Ridge National Laboratory (ORNL),↗

Method of constructing dished ion thruster grids to provide hole array spacing compensation

The center-to-center spacings of a photoresist pattern for an array of holes applied to a thin metal sheet are increased by uniformly stretching the thin metal sheet in all directions along the plane of the sheet. The uniform stretching is provided by securely clamping the periphery of the sheet and applying an annular force against the face of the sheet, within the periphery of the sheet and around the photoresist pattern. The technique is used in the construction of ion thruster grid units where the outer or downstream grid is subjected to uniform stretching prior to convex molding. The technique provides alignment of the holes of grid pairs so as to direct the ion beamlets in a direction parallel to the axis of the grid unit and thereby provide optimization of the available thrust.

Banks, B. A.↗

Regenerative fuel cell energy storage system for a low earth orbit space station

A study was conducted to define characteristics of a Regenerative Fuel Cell System (RFCS) for low earth orbit Space Station missions. The RFCS's were defined and characterized based on both an alkaline electrolyte fuel cell integrated with an alkaline electrolyte water electrolyzer and an alkaline electrolyte fuel cell integrated with an acid solid polymer electrolyte (SPE) water electrolyzer. The study defined the operating characteristics of the systems including system weight, volume, and efficiency. A maintenance philosophy was defined and the implications of system reliability requirements and modularization were determined. Finally, an Engineering Model System was defined and a program to develop and demonstrate the EMS and pacing technology items that should be developed in parallel with the EMS were identified. The specific weight of an optimized RFCS operating at 140 F was defined as a function of system efficiency for a range of module sizes. An EMS operating at a nominal temperature of 180 F and capable of delivery of 10 kW at an overall efficiency of 55.4 percent is described. A program to develop the EMS is described including a technology development effort for pacing technology items.

Martin, R. E.↗

Single-agent parallel window search

Parallel window search is applied to single-agent problems by having different processes simultaneously perform iterations of Iterative-Deepening-A(asterisk) (IDA-asterisk) on the same problem but with different cost thresholds. This approach is limited by the time to perform the goal iteration. To overcome this disadvantage, the authors consider node ordering. They discuss how global node ordering by minimum h among nodes with equal f = g + h values can reduce the time complexity of serial IDA-asterisk by reducing the time to perform the iterations prior to the goal iteration. Finally, the two ideas of parallel window search and node ordering are combined to eliminate the weaknesses of each approach while retaining the strengths. The resulting approach, called simply parallel window search, can be used to find a near-optimal solution quickly, improve the solution until it is optimal, and then finally guarantee optimality, depending on the amount of time available.

Powley, Curt↗