Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel processing”

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 883 records · Page 49

Grain structure and texture selection regimes in metal powder bed fusion

Additive manufacturing (AM) offers opportunities to produce complex part geometries not possible with conventional processing and in some cases even improve part performance. However, adoption has been slowed by difficulties assessing microstructure variability and there is no straightforward approach to relate processing to grain structure characteristics. In this study, datasets from AdditiveFOAM heat transport simulations of laser powder bed fusion (LPBF) are used to drive ExaCA simulations of grain structure. The GPU utilization of ExaCA and an algorithmic update for modeling melt pool overlap region solidification enabled rapid and parallel simulation across a wider range of process conditions than previously explored with cellular automata-based solidification models. A texture selection angle $θ_s$ is defined based on melt pool overlap geometry, and the range of $θ_s$ over which a commonly observed texture transition occurs in characterized AM builds was well-reproduced by ExaCA simulations over a wide range of melt pool shape, hatch spacing, and layer height. ExaCA simulations with 90 degree rotation of the scan direction on every other layer reproduced a number of trends from the AM literature including grain refinement, the dominance of layers with larger melt pools on the final grain structure, and the weakening or strengthening of texture depending on odd and even layer melt pool overlap geometry. EBSD data from a benchmark AM part is used to validate the simulated mechanism of a layer rotation-induced texture strengthening effect. Importantly, these results expand the understanding of the mechanisms for texture selection in alloys with cubic crystal symmetry and offer an approach to easily evaluate processing conditions. With this new understanding, these modeling tools will enable anticipation of previously unexpected variations in grain structure and target specific microstructures and properties.

36 MATERIALS SCIENCE↗

EMMA: an adaptive mesh refinement cosmological simulation code with radiative transfer

EMMA is a cosmological simulation code aimed at investigating the reionization epoch. It handles simultaneously collisionless and gas dynamics, as well as radiative transfer physics using a moment-based description with the M1 approximation. Field quantities are stored and computed on an adaptive three-dimensional mesh and the spatial resolution can be dynamically modified based on physically motivated criteria. Physical processes can be coupled at all spatial and temporal scales. We also introduce a new and optional approximation to handle radiation: the light is transported at the resolution of the non-refined grid and only once the dynamics has been fully updated, whereas thermo-chemical processes are still tracked on the refined elements. Such an approximation reduces the overheads induced by the treatment of radiation physics. A suite of standard tests are presented and passed by EMMA, providing a validation for its future use in studies of the reionization epoch. The code is parallel and is able to use graphics processing units (GPUs) to accelerate hydrodynamics and radiative transfer calculations. Depending on the optimizations and the compilers used to generate the CPU reference, global GPU acceleration factors between ×3.9 and ×16.9 can be obtained. As a result, vectorization and transfer operations currently prevent better GPU performance and we expect that future optimizations and hardware evolution will lead to greater accelerations.

79 ASTRONOMY AND ASTROPHYSICS↗

Compressed basis GMRES on high-performance graphics processing units

Krylov methods provide a fast and highly parallel numerical tool for the iterative solution of many large-scale sparse linear systems. To a large extent, the performance of practical realizations of these methods is constrained by the communication bandwidth in current computer architectures, motivating the investigation of sophisticated techniques to avoid, reduce, and/or hide the message-passing costs (in distributed platforms) and the memory accesses (in all architectures). This article leverages Ginkgo’s memory accessor in order to integrate a communication-reduction strategy into the (Krylov) GMRES solver that decouples the storage format (i.e., the data representation in memory) of the orthogonal basis from the arithmetic precision that is employed during the operations with that basis. Given that the execution time of the GMRES solver is largely determined by the memory accesses, the cost of the datatype transforms can be mostly hidden, resulting in the acceleration of the iterative step via a decrease in the volume of bits being retrieved from memory. Together with the special properties of the orthonormal basis (whose elements are all bounded by 1), this paves the road toward the aggressive customization of the storage format, which includes some floating-point as well as fixed-point formats with mild impact on the convergence of the iterative process. We develop a high-performance implementation of the “compressed basis GMRES” solver in the Ginkgo sparse linear algebra library using a large set of test problems from the SuiteSparse Matrix Collection. We demonstrate robustness and performance advantages on a modern NVIDIA V100 graphics processing unit (GPU) of up to 50% over the standard GMRES solver that stores all data in IEEE double-precision.

97 MATHEMATICS AND COMPUTING↗

Case Study of Using Kokkos and SYCLs Performance-Portable Frameworks for Milc-Dslash Benchmark on NVIDIA, AMD and Intel GPUs

Six of the top ten supercomputers in the TOP500 list from June 2021 rely on NVIDIA GPUs to achieve their peak compute bandwidth. With the announcement of Aurora, Frontier, and El Capitan, Intel and AMD have also entered the domain of providing GPUs for scientific computing. A consequence of the increased diversity in the GPU landscape is the emergence of portable programming models such as Kokkos, SYCL, OpenCL, and OpenMP, which allow application developers to maintain a single-source code across a diverse range of hardware architectures. While the portable frameworks try to optimize the compute resource usage on a given architecture, it is the programmers responsibility to expose parallelism in an application that can take advantage of thousands of processing elements available on GPUs. In this paper, we introduce a GPU-friendly parallel implementation of Milc-Dslash that exposes multiple hierarchies of parallelism in the algorithm. Milc-Dslash was designed to serve as a benchmark with highly optimized matrix-vector multiplications to measure the resource utilization on the GPU systems. The parallel hierarchies in the Milc-Dslash algorithm are mapped onto a target hardware using Kokkos and SYCL programming models. We present the performance achieved by Kokkos and SYCL implementations of Milc-Dslash on NVIDIA A100 GPU, AMD MI100 GPU, and Intel Gen9 GPU. Additionally, we compare the Kokkos and SYCL performances with those obtained from the versions written in CUDA and HIP programming models on NVIDIA A100 GPU and AMD MI100 GPU, respectively.

Dufek, Amanda S↗

Parallel Harness for Informatic Stream Hashing

PHISH is a lightweight framework which a set of independent processes can use to exchange data as they run on the same desktop machine, on processors of a parallel machine, or on different machines across a network. This enables them to work in a coordinated parallel fashion to perform computations on either streaming, archived, or self-generated data. The PHISH distribution includes a simple, portable library for performing data exchanges in useful patterns either via MPI message-passing or ZMQ sockets. PHISH input scripts are used to describe a data-processing algorithm, and additional tools provided in the PHISH distribution convert the script into a form that can be launched as a parallel job.

Plimpton, Steve↗

Parallel Harness for Informatic Stream Hashing

PHISH is a lightweight framework which a set of independent processes can use to exchange data as they run on the same desktop machine, on processors of a parallel machine, or on different machines across a network. This enables them to work in a coordinated parallel fashion to perform computations on either streaming, archived, or self-generated data. The PHISH distribution includes a simple, portable library for performing data exchanges in useful patterns either via MPI message-passing or ZMQ sockets. PHISH input scripts are used to describe a data-processing algorithm, and additional tools provided in the PHISH distribution convert the script into a form that can be launched as a parallel job.

Steve Plimpton, Tim Shead↗

GPU Acceleration of Volume Fraction and Centroid Computation from General Shapes on Unstructured Mesh

One important requirement for coupling multi-physics models is a means to remap fields between meshes in an accurate and conservative manner. Since the remapping algorithm is embarrassingly parallel, this motivates the use of Graphical Processing Units (GPU) for such routine. However, since our remapping code, portage, is fairly complex, we explore the use of GPUs through a simpler problem of generating material’s volume fraction and centroid inside each cell of the mesh. We use the same programming structure that is used in portage, namely, on-node parallelism via NVIDIA’s thrust library. Using a similar programming structure enables us to draw lessons from this study that can be applied to the more complex problem. We have found that while the speed-up is pronounced (10-100 times), significant effort is required to re-factor the code so that thrust can be used with a CUDA backend. Moreover, thrust takes away the fine grain control that vanilla CUDA programming gives us.

97 MATHEMATICS AND COMPUTING↗

Dense LU Factorization on Multicore Supercomputer Nodes

Dense LU factorization is a prominent benchmark used to rank the performance of supercomputers. Many implementations, including the reference code HPL, use block-cyclic distributions of matrix blocks onto a two-dimensional process grid. The process grid dimensions drive a trade-off between communication and computation and are architecture- and implementation-sensitive. We show how the critical panel factorization steps can be made less communication-bound by overlapping asynchronous collectives for pivot identification and exchange with the computation of rank-k updates. By shifting this trade-off, a modified block-cyclic distribution can beneficially exploit more available parallelism on the critical path, and reduce panel factorization's memory hierarchy contention on now-ubiquitous multi-core architectures. The missed parallelism in traditional block-cyclic distributions arises because active panel factorization, triangular solves, and subsequent broadcasts are spread over single process columns or rows (respectively) of the process grid. Increasing one dimension of the process grid decreases the number of distinct processes in the other dimension. To increase parallelism in both dimensions, periodic 'rotation' is applied to the process grid to recover the row-parallelism lost by a tall process grid. During active panel factorization, rank-1 updates stream through memory with minimal reuse. In a column-major process grid, the performance of this access pattern degrades as too many streaming processors contend for access to memory. A block-cyclic mapping in the more popular row-major order does not encounter this problem, but consequently sacrifices node and network locality in the critical pivoting steps. We introduce 'striding' to vary between the two extremes of row- and column-major process grids. As a test-bed for further mapping experiments, we describe a dense LU implementation that allows a block distribution to be defined as a general function of block to processor. Other mappings can be tested with only small, local changes to the code.

99 GENERAL AND MISCELLANEOUS↗

A Parallel Ghosting Algorithm for The Flexible Distributed Mesh Database

Critical to the scalability of parallel adaptive simulations are parallel control functions including load balancing, reduced inter-process communication and optimal data decomposition. In distributed meshes, many mesh-based applications frequently access neighborhood information for computational purposes which must be transmitted efficiently to avoid parallel performance degradation when the neighbors are on different processors. This article presents a parallel algorithm of creating and deleting data copies, referred to as ghost copies, which localize neighborhood data for computation purposes while minimizing inter-process communication. The key characteristics of the algorithm are: (1) It can create ghost copies of any permissible topological order in a 1D, 2D or 3D mesh based on selected adjacencies. (2) It exploits neighborhood communication patterns during the ghost creation process thus eliminating all-to-all communication. (3) For applications that need neighbors of neighbors, the algorithm can create n number of ghost layers up to a point where the whole partitioned mesh can be ghosted. Strong and weak scaling results are presented for the IBM BG/P and Cray XE6 architectures up to a core count of 32,768 processors. The algorithm also leads to scalable results when used in a parallel super-convergent patch recovery error estimator, an application that frequently accesses neighborhood data to carry out computation.

Mubarak, Misbah↗

Serial2Parallel

In the era of machine learning, we often need to run the same code/script many times with little or no variations (e.g., performance evaluation, data preprocessing, data generation, hyperparameter tuning, etc.). It is not a problem when you just need to do that a few times, but when the number of repetitions becomes very large, it can be a daunting task. The code “Serial2Parallel” provides an easy way for users to be able to run many numbers of any serial code/scripts in a parallel manner across multiple nodes in an message passing interface (MPI) cluster. The code includes the server program that deals with task pool management and client program that processes task. The server gets the tasks ready and waits for clients' connections. The client code pulls tasks from the server and processes them. The client code will run in parallel.

Sangkeun, MattLee↗

Collective network for computer structures

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices ate included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network and class structures. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to needs of a processing algorithm.

97 MATHEMATICS AND COMPUTING↗

Collective network for computer structures

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices are included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network and class structures. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to needs of a processing algorithm.

Blumrich, Matthias A.↗

Collective network for computer structures

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices are included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to the needs of a processing algorithm.

97 MATHEMATICS AND COMPUTING↗

Ensemble Simulation Techniques and Fast Randomized Algorithms

The major goals of the project were to develop and analyze new ensemble simulation techniques, including trajectory stratification and preconditioned MCMC techniques, as well as develop fast numerical linear algebra techniques closely related to ensemble simulation ideas. The trajectory stratification techniques involve simulating in parallel short trajectory fragments of a Markov process confined to a specific region of space‐time and then patching together the statistics gathered to assemble estimates of very general dynamical properties. We have also developed this approach for rare event simulation and extended the techniques to applications requiring a more general framework (such as electronic structure calculations). The preconditioned MCMC techniques involve simulating multiple Markov chains in parallel and then using information from the ensemble to speed the mixing of each individual chain. The fast randomized linear algebra methods are motivated by the diffusion Monte Carlo technique, but are applicable to finding the dominant eigenvalue of (almost) general matrices. For most non‐negative matrices, the schemes result in an error (compared to the power method) that is constant in the dimension of the problem. For more general matrices, we see a very clear sublinear cost trend in computational tests.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Singlet fission for quantum information and quantum computing: the parallel JDE model

Abstract Singlet fission is a photoconversion process that generates a doubly excited, maximally spin entangled pair state. This state has applications to quantum information and computing that are only beginning to be realized. In this article, we construct and analyze a spin-exciton hamiltonian to describe the dynamics of the two-triplet state. We find the selection rules that connect the doubly excited, spin-singlet state to the manifold of quintet states and comment on the mechanism and conditions for the transition into formally independent triplets. For adjacent dimers that are oriented and immobilized in an inert host, singlet fission can be strongly state-selective. We make predictions for electron paramagnetic resonance experiments and analyze experimental data from recent literature. Our results give conditions for which magnetic resonance pulses can drive transitions between optically polarized magnetic sublevels of the two-exciton states, making it possible to realize quantum gates at room temperature in these systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Improved bacterial recombineering by parallelized protein discovery

Exploiting bacteriophage-derived homologous recombination processes has offered precise, multiplex editing of microbial genomes and the construction of billions of customized genetic variants in a single day. The techniques that enable this, multiplex automated genome engineering (MAGE) and directed evolution with random genomic mutations (DIvERGE), are however, currently limited to a handful of microorganisms for which single-stranded DNA-annealing proteins (SSAPs) that promote efficient recombineering have been identified. Thus, to enable genome-scale engineering in new hosts, efficient SSAPs must first be found. Here we present a high-throughput method for SSAP discovery that we call “serial enrichment for efficient recombineering” (SEER). By performing SEER in Escherichia coli to screen hundreds of putative SSAPs, we identify highly active variants PapRecT and CspRecT. CspRecT increases the efficiency of single-locus editing to as high as 50% and improves multiplex editing by 5- to 10-fold in E. coli , while PapRecT enables efficient recombineering in Pseudomonas aeruginosa , a concerning human pathogen. CspRecT and PapRecT are also active in other, clinically and biotechnologically relevant enterobacteria. We envision that the deployment of SEER in new species will pave the way toward pooled interrogation of genotype-to-phenotype relationships in previously intractable bacteria.

60 APPLIED LIFE SCIENCES↗

HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization

We present a new software, HYPPO, that enables the automatic tuning of hyperparameters of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) methods, HYPPO uses adaptive surrogate models and directly accounts for uncertainty in model predictions to find accurate and reliable models that make robust predictions. Using asynchronous nested parallelism, we are able to significantly alleviate the computational burden of training complex architectures and quantifying the uncertainty. HYPPO is implemented in Python and can be used with both TensorFlow and PyTorch libraries. We demonstrate various software features on time-series prediction and image classification problems as well as a scientific application in computed tomography image reconstruction. Finally, we show that (1) we can reduce by an order of magnitude the number of evaluations necessary to find the most optimal region in the hyperparameter space and (2) we can reduce by two orders of magnitude the throughput for such HPO process to complete.

adaptation models↗

Asi Nuclear Energy Sensors Data Portal Chatbot And Data Structuring Tool

The Idaho National Laboratory (INL) is advancing the development of an AI-powered chatbot and data structuring tool specifically designed to accelerate data mining processes for sensor-related information and seamlessly integrate the results into the ASI Sensors Data Portal (https://nes.energy.gov/). By doing so, the software aims to enhance the accessibility, usability, and organization of sensor data for nuclear energy applications. The software initial phase focuses on retrieving comprehensive datasets, prioritizing the past five years of publicly available information from the Office of Scientific and Technical Information (OSTI). These datasets will be meticulously processed to ensure compatibility, employing cleaning and preprocessing steps to eliminate irrelevant, incomplete, or corrupted information, thus establishing a robust foundation for subsequent AI use. The data will serve as the backbone for training an AI model and chatbot, which will act as an interactive tool enabling users to ask complex, context-specific questions and receive accurate, validated answers derived from constrained literature. In parallel, the project incorporates a data structuring process supported by AI to organize sensor information from multiple sources into a standardized format. This structured data will include detailed sensor specifications, such as measurement range, applications, accuracy, and operating conditions, generated and documented with AI. These specifications will be systematically integrated into the sensor portal. To maintain the highest levels of accuracy and relevance, all AI-generated outputs will be reviewed and validated by subject matter experts (SMEs), with additional fields or parameters added as needed. Future stages of the project aim to expand the dataset beyond OSTI to include other sources and potentially incorporate unclassified controlled information (UCI) with restricted access protocols to address security and confidentiality requirements.

Mapes, NormanJ. [Idaho National Laboratory (INL), ↗