Search NASA⌕ Search

SEARCH · Search NASA

Results for “threads”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

TomocuPy – efficient GPU-based tomographic reconstruction with asynchronous data processing

Fast 3D data analysis and steering of a tomographic experiment by changing environmental conditions or acquisition parameters require fast, close to real-time, 3D reconstruction of large data volumes. Here a performance-optimized TomocuPy package is presented as a GPU alternative to the commonly used central processing unit (CPU) based TomoPy package for tomographic reconstruction. TomocuPy utilizes modern hardware capabilities to organize a 3D asynchronous reconstruction involving parallel read/write operations with storage drives, CPU–GPU data transfers, and GPU computations. In the asynchronous reconstruction, all the operations are timely overlapped to almost fully hide all data management time. Since most cameras work with less than 16-bit digital output, the memory usage and processing speed are furthermore optimized by using 16-bit floating-point arithmetic. As a result, 3D reconstruction with TomocuPy became 20–30 times faster than its multi-threaded CPU equivalent. Full reconstruction (including read/write operations and methods initialization) of a 2048 3 tomographic volume takes less than 7 s on a single Nvidia Tesla A100 and PCIe 4.0 NVMe SSD, and scales almost linearly increasing the data size. To simplify operation at synchrotron beamlines, TomocuPy provides an easy-to-use command-line interface. Efficacy of the package was demonstrated during a tomographic experiment on gas-hydrate formation in porous samples, where a steering option was implemented as a lens-changing mechanism for zooming to regions of interest.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

Real-time data processing for serial crystallography experiments

We report the use of streaming data interfaces to perform fully online data processing for serial crystallography experiments, without storing intermediate data on disk. The system produces Bragg reflection intensity measurements suitable for scaling and merging, with a latency of less than 1 s per frame. Our system uses the CrystFEL software in combination with the ASAP::O data framework. In a series of user experiments at PETRA III, frames from a 16 megapixel Dectris EIGER2 X detector were searched for peaks, indexed and integrated at the maximum full-frame readout speed of 133 frames per second. The computational resources required depend on various factors, most significantly the fraction of non-blank frames ('hits'). The average single-thread processing time per frame was 242 ms for blank frames and 455 ms for hits, meaning that a single 96-core computing node was sufficient to keep up with the data, with ample headroom for unexpected throughput reductions. Further significant improvements are expected, for example by binning pixel intensities together to reduce the pixel count. We discuss the implications of real-time data processing on the `data deluge' problem from recent and future photon-science experiments, in particular on calibration requirements, computing access patterns and the need for the preservation of raw data.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Addressing Load Imbalance in Bioinformatics and Biomedical Applications: Efficient Scheduling across Multiple GPUs

Computational bioinformatics and biomedical applications frequently contain heterogeneously sized units of work or tasks, for instance due to variability in the sizes of biological sequences and molecules. Variable-sized workloads lead to load imbalances in parallel implementations which detract from efficiency and performance. Many modern computing resources now have multiple graphics processing units(GPUs) per computer for acceleration. These multiple GPU resources need to be used efficiently through balancing of workloads across the GPUs. OpenMP is a portable directive-based parallel programming API used ubiquitously in bioscience applications to program CPUs; recently, the use of OpenMP directives for GPU acceleration has become possible. Here, motivated by experiences with imbalanced loads in GPU-accelerated bioinformatics applications, we address the load balancing problem using OpenMP task-to-GPU scheduling combined with OpenMP GPU offloading for multiply heterogeneous workloads – loads with both variable input sizes, and simultaneously, variable convergence rates for algorithms with a stochastic component – scheduled across multiple GPUs. We aim to develop strategies which are both easy to use and have lower overheads, and may be incorporated incrementally in existing programs which already make use of OpenMP for CPU-based threading in order to make use of multi-GPU computers. We test different combinations of input size variability and convergence rate variability, and characterize the effects of these different scenarios on the performance of scheduling strategies across multiple GPUs with OpenMP. We present several dynamic scheduling solutions for different parallel patterns, explore optimizations, and provide publicly available example computational kernels to make these strategies easy to use in programs. This work will enable application developers to efficiently and easily use multiple GPUs for imbalanced workloads found in bioinformatics and biomedical applications.

Thavappiragasam, Mathialakan↗
DOE OSTI2023

Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools

Methods for model explainability have become increasingly critical for testing the fairness and soundness of deep learning. Concept-based interpretability techniques, which use a small set of human-interpretable concept exemplars in order to measure the influence of a concept on a model's internal representation of input, are an important thread in this line of research. In this work we show that these explainability methods can suffer the same vulnerability to adversarial attacks as the models they are meant to analyze. We demonstrate this phenomenon on two well-known concept-based interpretability methods: TCAV and faceted feature visualization. We show that by leveraging the geometry of the problem and carefully perturbing the examples of the concept that is being investigated, we can radically change the output of the interpretability method. The attacks that we propose can either induce positive interpretations (polka dots are an important concept for a model when classifying zebras) or negative interpretations (stripes are not an important factor in identifying images of a zebra). Our work highlights the fact that in safety-critical applications, there is need for security around not only the machine learning pipeline but also the model interpretation process.

Brown, Davis R.↗
DOE OSTI2021

Educating HPC Users in the use of advanced computing technology

We examine a multi-modal approach to educating and training users of an advanced computing technology testbed at the Institute for Advanced Computational Science at Stony Brook University. Ookami provides researchers worldwide with access to 176 Fujitsu A64FX compute nodes, this being the same processor technology powering the Japanese Fugaku supercomputer, the fastest computer in the world since June 2020. However, achieving high-performance on this Arm-based, leadership computing technology requires that users be familiar with details of computer architecture, performance analysis and modeling, and high-performance programming models that are commonly omitted in introductory programming courses. Indeed, regardless of their seniority, many of the testbed users are surprisingly unfamiliar with basic concepts such as vectorization, pipelining, latency/bandwidth, roofline models, computing energy/power, threads, and non-uniform memory access. These same concepts also pervade mainstream x86 technologies, so this is of widespread concern. Due to the national/global nature of our user community that is also very diverse in both discipline and experience, the inability to offer formal classes, and our experience that most people do not tend to read online documentation or training materials in sufficient depth, we have consciously employed multiple approaches that heavily emphasize (online) personal interactions and transfer of skills. Online documentation has been organized around best-practices and FAQs; twice-weekly hackathons and office hours via Zoom enable deep dives by both the team and the user community with multiple broad benefits; a Slack channel provides both real time and archived answers and discussions; and workshops, training and webinars target community needs as they arise. Furthermore, the perspective that these tools are being used in an educational setting rather than just for project communication makes them more effective and contributes to community success.

A64FX↗
DOE OSTI2022

A High-Performance Design for Hierarchical Parallelism in the QMCPACK Monte Carlo code

We introduce a new high-performance design for parallelism within the Quantum Monte Carlo code QMCPACK. We demonstrate that the new design is better able to exploit the hierarchical parallelism of heterogeneous architectures compared to the previous GPU implementation. The new version is able to achieve higher GPU occupancy via the new concept of crowds of Monte Carlo walkers, and by enabling more host CPU threads to effectively offload to the GPU. The higher performance is expected to be achieved independent of the underlying hardware, significantly improving developer productivity and reducing code maintenance costs. Scientific productivity is also improved with full support for fallback to CPU execution when GPU implementations are not available or CPU execution is more optimal.

Luo, Ye↗
DOE OSTI2019

Runtime Concurrency Control and Operation Scheduling for High Performance Neural Network Training

In this paper, we extend an existing runtime system (the TensorFlow runtime) to enable automatic concurrency control and scheduling of operations. We explore performance modeling to predict the performance of operations with various thread- level parallelism. Our performance model is highly accurate and lightweight. Leveraging the performance model, our runtime system employs a set of scheduling strategies that co-run opera- tions to improve hardware utilization and system throughput. Our runtime system demonstrates a significant performance benefit. Comparing with using the recommended configurations for concurrency control and operation scheduling in TensorFlow, our approach achieves 36% performance (execution time) im- provement on average (up to 49%) for four neural network models, and achieves high performance close to the optimal one manually obtained by the user.

Liu, Jiawen↗
DOE OSTI2020

LOGAN: High-Performance GPU-Based X-Drop Long-Read Alignment

Pairwise sequence alignment is one of the most computationally intensive kernels in genomic data analysis, accounting for more than 90% of the runtime for key bioinformatics applications. This method is particularly expensive for third-generation sequences due to the high computational cost of analyzing sequences of length between 1Kb and 1Mb. Given the quadratic overhead of exact pairwise algorithms for long alignments, the community primarily relies on approximate algorithms that search only for high-quality alignments and stop early when one is not found. In this work, we present the first GPU optimization of the popular X-drop alignment algorithm, that we named LOGAN. Results show that our high-performance multi-GPU implementation achieves up to 181.6 GCUPS and speed-ups up to 6.6× and 30.7× using 1 and 6 NVIDIA Tesla V100, respectively, over the state-of-the-art software running on two IBM Power9 processors using 168 CPU threads, with equivalent accuracy. We also demonstrate a 2.3× LOGAN speed-up versus ksw2, a state-of-art vectorized algorithm for sequence alignment implemented in minimap2, a long-read mapping software. Furthermore, to highlight the impact of our work on a real-world application, we couple LOGAN with a many-to-many long-read alignment software called BELLA, and demonstrate that our implementation improves the overall BELLA runtime by up to 10.6×. Finally, we adapt the Roofline model for LOGAN and demonstrate that our implementation is near optimal on the NVIDIA Tesla V100s.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Communication-Avoiding and Memory-Constrained Sparse Matrix-Matrix Multiplication at Extreme Scale

Sparse matrix-matrix multiplication (SpGEMM) is a widely used kernel in various graph, scientific computing and machine learning algorithms. In this paper, we consider SpGEMMs performed on hundreds of thousands of processors generating trillions of nonzeros in the output matrix. Distributed SpGEMM at this extreme scale faces two key challenges: (1) high communication cost and (2) inadequate memory to generate the output. Furthermore, we address these challenges with an integrated communication-avoiding and memory-constrained SpGEMM algorithm that scales to 262,144 cores (more than 1 million hardware threads) and can multiply sparse matrices of any size as long as inputs and a fraction of output fit in the aggregated memory. As we go from 16,384 cores to 262,144 cores on a Cray XC40 supercomputer, the new SpGEMM algorithm runs 10x faster when multiplying large-scale protein-similarity matrices.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Investigation of Rear-Emitter GaAs 0.75 P 0.25 Top Cells for Application to III–V/Si Tandem Photovoltaics

A rear-emitter (rear-junction) n-on-p+ device design was investigated for use in metamorphic monolithic III-V/Si tandem solar cells as an alternative to the traditional front-emitter (front-junction) n+-on-p design for potentially greater resistance to threading dislocation-induced performance degradation. A comparison of MOCVD-grown rearversus front-emitter 1.7-eV bandgap GaAs 0.75 P 0.25 top cell isotypes demonstrated as 30-mV advantage in WOC for the rear-emitter design. Here, this reduction in WOC was determined to be nearly equally caused by a reduction in junction recombination current as well as reduced reverse saturation current from improved quasi-neutral region transport. These results suggest that the rear-emitter design may indeed be a promising pathway for application to metamorphic cells, including III-V/Si tandems, where achieving maximum voltage output is often hindered by elevated dislocation densities. However, further optimization of short-circuit current collection is needed to overcome suboptimal collection probability profiles that could limit the efficacy of such structures.

14 SOLAR ENERGY↗
DOE OSTI2019

Accelerating DCA++ (Dynamical Cluster Approximation) Scientific Application on the Summit supercomputer

Optimizing scientific applications on today’s accelerator-based high performance computing systems can be challenging, especially when multiple GPUs and CPUs with heterogeneous memories and persistent non-volatile memories are present. An example is Summit, an accelerator-based system at the Oak Ridge Leadership Computing Facility (OLCF) that is rated as the world’s fastest supercomputer to-date. New strategies are thus needed to expose the parallelism in legacy applications, while being amenable to efficient mapping to the underlying architecture.In this paper we discuss our experiences and strategies to port a scientific application, DCA++, to Summit. DCA++ is a highperformance research application that solves quantum manybody problems with a cutting edge quantum cluster algorithm, the dynamical cluster approximation.Our strategies aim to synergize the strengths of the different programming models in the code. These include: (a) streamlining the interactions between the CPU threads and the GPUs, (b) implementing computing kernels on the GPUs and decreasing CPU-GPU memory transfers, (c) allowing asynchronous GPU communications, and (d) increasing compute intensity by combining linear algebraic operations.Full-scale production runs using all 4600 Summit nodes attained a peak performance of 73.5 PFLOPS with a mixed precision implementation.We observed a perfect strong and weak scaling for the quantum Monte Carlo solver in DCA++, while encountering about 2× input/output (I/O) and MPI communication overhead on the time-to-solution for the full machine run. Our hardware agnostic optimizations are designed to alleviate the communication and I/O challenges observed, while improving the compute intensity and obtaining optimal performance on a complex, hybrid architecture like Summit.

Balduzzi, Giovanni↗
DOE OSTI2023

AMG Preconditioners based on parallel hybrid coarsening and multi-objective graph matching

We describe preliminary results from a multi-objective graph matching algorithm, in the coarsening step of an aggregation-based Algebraic MultiGrid (AMG) preconditioner, for solving large and sparse linear systems of equations on high-end parallel computers. We have two objectives. First, we wish to improve the convergence behavior of the AMG method when applied to highly anisotropic problems. Second, we wish to extend the parallel package \texttt{PSCToolkit} to exploit multi-threaded parallelism at the node level on multi-core processors. Our matching proposal balances the need to simultaneously compute high weights and large cardinalities by a new formulation of the weighted matching problem combining both these objectives using a parameter $\lambda$. We compute the matching by a parallel $2/3-\varepsilon$-approximation algorithm for maximum weight matchings. Results with the new matching algorithm show that for a suitable choice of the parameter $\lambda$ we compute effective preconditioners in the presence of anisotropy, i.e., smaller solve times, setup times, iterations counts, and operator complexity.

D'Ambra, Pasqua↗
DOE OSTI2021

Towards a III-V Solar Cell with a Metamorphic Graded Buffer Directly Grown on V-Groove Si Substrates

V-groove Si substrates offer a promising route for the direct growth of III-V solar cells on low-cost, photovoltaic-grade Si. In this work, we develop a method for coalescing GaP nucleated on V-groove substrates into thin films suitable for the growth of III-V solar cells. We demonstrate the ability to suppress nucleation-related defects by modifying the V-groove substrate to cover the (0 0 1)-oriented Si V-groove tops with SiN x . A threading dislocation density (TDD) of 5 × 10 7 cm -2 was measured with electron channeling contrast imaging. Continuing work will focus on further reducing the TDD and the growth of a GaAs solar cell on a GaP on V-groove Si template.

41 EE - Solar Energy Technologies Office (EE-4S)↗
DOE OSTI2024

1.1 eV GaInAs Cell Development for Dual-Use Solar and 1070 nm Laser Power Converters

Dual-use power converter cells can receive solar and laser power simultaneously to generate current, an application relevant to space and terrestrial industries. This study investigates two concepts of solar cells optimized for dual-use 1070 nm laser and solar power conversion, a single-junction and triple-junction cell. Because it is bandgap-tuned for a 1070 nm laser, the 1.1 eV junction is incorporated into each of the two designs, making its development key to the success of both concepts. Efficiency data for a one junction GaInAs cell demonstrates a laser conversion efficiency of 38% at 1070nm wavelength without an anti-reflection coating. However, the single-junction device requires optimization to reduce short wavelength absorption of the broad solar spectrum. In both devices, the graded buffer layers in the GaInAs cell affects the cell's performance by reducing threading dislocations in the active junction. However, the buffer in the three-junction device also acts as a lateral transport layer and so affects the fill factor depending on its sheet resistance. By varying the buffer thickness, we demonstrate a direct relationship between buffer thickness and sheet resistance reduction, while considering implications to open-circuit voltages. We also performed resistance modeling to determine the optimal grid spacing and thickness of the grid fingers to minimize losses due to sheet resistance and grid shading.

junctions↗
DOE OSTI2022

GSoFa: Scalable Sparse Symbolic LU Factorization on GPUs

Decomposing a matrix $\mathbf {A}$ into a lower matrix $\mathbf {L}$ and an upper matrix $\mathbf {U}$, which is also known as LU decomposition, is an essential operation in numerical linear algebra. For a sparse matrix, LU decomposition often introduces more nonzero entries in the $\mathbf {L}$ and $\mathbf {U}$ factors than in the original matrix. A symbolic factorization step is needed to identify the nonzero structures of $\mathbf {L}$ and $\mathbf {U}$ matrices. Attracted by the enormous potentials of the Graphics Processing Units (GPUs), an array of efforts have surged to deploy various LU factorization steps except for the symbolic factorization, to the best of our knowledge, on GPUs. This article introduces gSoFa, the first GPU-based symbolic factorization design with the following three optimizations to enable scalable LU symbolic factorization for nonsymmetric pattern sparse matrices on GPUs. First, here we introduce a novel fine-grained parallel symbolic factorization algorithm that is well suited for the Single Instruction Multiple Thread (SIMT) architecture of GPUs. Second, we tailor supernode detection into a SIMT friendly process and strive to balance the workload, minimize the communication and saturate the GPU computing resources during supernode detection. Third, we introduce a three-pronged optimization to reduce the excessive space consumption problem faced by multi-source concurrent symbolic factorization. Taken together, gSoFa achieves up to 31× speedup from 1 to 44 Summit nodes (6 to 264 GPUs) and outperforms the state-of-the-art CPU project, on average, by 5×. Notably, gSoFa also achieves up to 47 percent of the peak memory throughput of a V100 GPU in the Summit Supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

STEPS: A Portable Numerical Simulation Toolkit for Electrical Power System Dynamic Studies

Numerical simulation is the key technique for large scale power system analysis. Redistribution of global renewable power via international interconnections requires new simulation tools to study the interconnected systems with different nominal frequencies as a whole. In this paper we introduce an open source simulation toolkit for electrical power systems (STEPS) which is hosted at Github. Its kernel is coded in C++ with major functions of power flow and electro-mechanical dynamic simulation. Flexible options are provided and configurable to improve power flow solution and dynamic simulation. Common devices and models are supported in STEPS for AC/DC hybrid system studies. Studies of interconnected systems with different nominal frequencies is supported in STEPS for research of international interconnection. Application program interfaces are provided and wrapped with Python to enable high-level interfaces for general applications. STEPS is thread safe and parallel computation is supported in both kernel and script levels to accelerate simulation. It is portable and works on Windows and GNU/Linux platforms. Cases from small to large scale systems are thoroughly tested to validate the toolkit with commercial packages as benchmarks.

42 ENGINEERING↗
DOE OSTI2022

A structural description of the evolution of stakeholders and risk communication in the Department of Energy's defense nuclear facilities: Historical perspective, major stakeholders, and external events

Regulators and policymakers are routinely challenged with explaining complex concepts concerning risk. Part of the challenge is helping external and internal stakeholders to understand the context behind risk-related information and decisions. Here, this paper will describe the historical evolution of the safety and regulatory framework for an important category in the nuclear industry—defense nuclear facilities owned and operated by the US Department of Energy. In parallel with describing this evolution, three major events which occurred external to the complex of defense nuclear facilities will be summarized, and their impact on the maturation of the Department's safety and regulatory framework will be discussed. Finally, integrated with these two threads of discussion will be a chronicle of the changing set of involved organizations and the expanding set of external stakeholders involved in risk decisions—and therefore, the risk communications ecosystem surrounding defense nuclear facilities. It will be noted that this system was once describable as a classic “iron triangle,” but now has progressed to a complex network of federal and state organizations, numerous congressional committees, and expanding sets of external stakeholders. It is hoped that a comprehensive discussion of the context of risk assessment in the defense nuclear facilities complex—addressing historical insights, organizational evolution, and the maturing structure of regulation—will provide enhanced opportunities for building trust and understanding in this complex environment.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2025

1.1 eV GaInAs Cell Development for Dual-Use Solar and 1070 nm Laser Power Converters

Dual-use photovoltaic cells can receive solar and laser power simultaneously to generate current, an application relevant to space and terrestrial industries. This study investigates two concepts of solar cells optimized for dual-use 1070 nm laser and solar power conversion, a single-junction and triple-junction cell. The cell designs are based upon the 3- junction inverted metamorphic solar cell, previously shown highly efficient for solar conversion. Because it is closely bandgap-tuned for a 1070 nm laser, the 1 eV bottom junction is incorporated into each of the two designs, making its development key to the success of both concepts. However, each design requires some modification for efficient dual use. The single-junction device requires optimization to reduce short wavelength absorption of the broad solar spectrum. In both devices, the graded buffer layers in the GaInAs cell affect the cell's performance by reducing threading dislocations in the active junction. However, the buffer in the three-junction device also acts as a lateral transport layer and so affects the fill factor depending on its sheet resistance. By varying the buffer thickness, we demonstrate a direct relationship between buffer thickness and sheet resistance reduction, while considering implications to open-circuit voltages. We also performed resistance modeling to determine the optimal grid spacing and thickness of the grid fingers to minimize losses due to sheet resistance and grid shading. Efficiency data for a one junction GaInAs cell demonstrates a laser conversion efficiency of 38% at 1070 nm wavelength without an anti-reflection coating.

dual-use↗