Search NASA⌕ Search

SEARCH · Search NASA

Results for “graphic processing units”

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 793 records · Page 44

Accelerating Scientific Applications With SambaNova Reconfigurable Dataflow Architecture

Here, our exploratory work finds that the SambaNova Reconfigurable Dataflow Architecture (RDA) along with the SambaFlow software stack provides for an attractive system and solution to accelerate AI for science workloads. We have observed the efficacy of using the system with a diverse set of science applications and reasoned their suitability for performance gains over traditional hardware. As the Data-Scale system provides for a very large memory capacity, the system can be used to train models that typically do not fit in a GPU. The architecture also provides for deeper integration with upcoming supercomputers at the Argonne Leadership Computing Facility (ALCF), a US Department of Energy Office of Science user facility, to help advance science insights.

97 MATHEMATICS AND COMPUTING↗

Performance Portability in the Exascale Computing Project: Exploration Through a Panel Series

Performance portability is a critical issue for the Exascale Computing Project (ECP) because of nontrivial architectural differences between machines available today and those expected at exascale. Many ECP project teams are working toward performance portability, and would expect to benefit from sharing lessons learned, identifying gaps, and discovering opportunities for partnerships. To facilitate this communication, the IDEAS-ECP project partnered with the three focus areas of ECP (application development, software technology, and hardware and integration), and Department of Energy computing facilities, to lead a series of panel discussions on performance portability. The panels were organized around broadly common themes of algorithmic and data locality challenges. In this article, we describe the panel series, its objectives, and perspectives from the various areas of the project. Finally, we also discuss use cases that are distinctive, as well as conclusions drawn from the collective experience of the participants.

97 MATHEMATICS AND COMPUTING↗

Co-design for Particle Applications at Exascale

Co-design across the Exascale Computing Project (ECP) has been critical for both enabling science applications and bringing disparate communities together. Developing and porting applications to the various high-performance computing (HPC) architectures on pre-exascale and exascale computers has been quite challenging due to the diversity of hardware features and software stacks. The Co-design Center for Particle Applications (CoPA) has developed and enhanced the Cabana and PROGRESS/BML libraries to facilitate the creation of new particle applications, make existing particle applications exascale capable, and allow teams to explore new capabilities. Particle methods from atomistic, mesoscale, continuum, through cosmological scales have been built with Cabana, along with new possibilities for application coupling. Similarly, the PROGRESS/BML library has enabled quantum particle applications with linear algebra solvers to use advanced hardware. Across these CoPA-developed libraries, the co-design abstraction layer combines performance portability with math library support to facilitate separation of concerns and directly support science runs.

97 MATHEMATICS AND COMPUTING↗

Real-Time Interactive 4D-STEM Phase-Contrast Imaging From Electron Event Representation Data: Less computation with the right representation

The arrival of direct electron detectors (DED) with high frame-rates in the field of scanning transmission electron microscopy has enabled many experimental techniques that require collection of a full diffraction pattern at each scan position, a field which is subsumed under the name four dimensional-scanning transmission electron microscopy (4D-STEM). DED frame rates approaching 100 kHz require data transmission rates and data storage capabilities that exceed commonly available computing infrastructure. Current commercial DEDs allow the user to make compromises in pixel bit depth, detector binning or windowing to reduce the per-frame file size and allow higher frame rates. This change in detector specifications requires decisions to be made before data acquisition that may reduce or lose information that could have been advantageous during data analysis. The 4D Camera, a DED with 87 kHz frame-rate developed at Lawrence Berkeley National Laboratory, reduces the raw data to a linear-index encoded electron event representation (EER). Here we show with experimental data from the 4D Camera that linear-index encoded EER and its direct use in 4D-STEM phase contrast imaging methods enables real-time, interactive phase-contrast from large-area 4D-STEM datasets. Furthermore, we detail the computational complexity advantages of the EER and the necessary computational steps to achieve real-time interactive ptychography and center-of-mass differential phase contrast using commonly available hardware accelerators.

4D-STEM↗

A performance model for GPUs with caches

To exploit the abundant computational power of the world's fastest supercomputers, an even workload distribution to the typically heterogeneous compute devices is necessary. While relatively accurate performance models exist for conventional CPUs, accurate performance estimation models for modern GPUs do not exist. This paper presents two accurate models for modern GPUs: a sampling-based linear model, and a model based on machine-learning (ML) techniques which improves the accuracy of the linear model and is applicable to modern GPUs with and without caches. We first construct the sampling-based linear model to predict the runtime of an arbitrary OpenCL kernel. Based on an analysis of NVIDIA GPUs' scheduling policies we determine the earliest sampling points that allow an accurate estimation. The linear model cannot capture well the significant effects that memory coalescing or caching as implemented in modern GPUs have on performance. We therefore propose a model based on ML techniques that takes several compiler-generated statistics about the kernel as well as the GPU's hardware performance counters as additional inputs to obtain a more accurate runtime performance estimation for modern GPUs. We demonstrate the effectiveness and broad applicability of the model by applying it to three different NVIDIA GPU architectures and one AMD GPU architecture. On an extensive set of OpenCL benchmarks, on average, the proposed model estimates the runtime performance with less than 7 percent error for a second-generation GTX 280 with no on-chip caches and less than 5 percent for the Fermi-based GTX 580 with hardware caches. On the Kepler-based GTX 680, the linear model has an error of less than 10 percent. On an AMD GPU architecture, Radeon HD 6970, the model estimates with 8 percent of error rates. As a result, the proposed technique outperforms existing models by a factor of 5 to 6 in terms of accuracy.

97 MATHEMATICS AND COMPUTING↗

IRIS: A Performance-Portable Framework for Cross-Platform Heterogeneous Computing

From edge to exascale, computer architectures are becoming more heterogeneous and complex. The systems typically have fat nodes, with multicore CPUs and multiple hardware accelerators such as GPUs, FPGAs, and DSPs. This complexity is causing a crisis in programming systems and performance portability. Several programming systems are working to address these challenges, but the increasing architectural diversity is forcing software stacks and applications to be specialized for each architecture. As we show, all of these approaches critically depend on their software framework for discovery, execution, scheduling, and data orchestration. To address this challenge, we believe that a more agile and proactive software framework is essential to increase performance portability and improve user productivity. To this end, we have designed and implemented IRIS: a performance-portable framework for cross-platform heterogeneous computing. IRIS can discover available resources, manage multiple diverse programming platforms (e.g., CUDA, Hexagon, HIP, Level Zero, OpenCL, OpenMP) simultaneously in the same execution, respect data dependencies, orchestrate data movement proactively, and provide for user-configurable scheduling. To simplify data movement, IRIS introduces a shared virtual device memory with relaxed consistency among different heterogeneous devices. IRIS also adds an automatic kernel workload partitioning technique using the polyhedral model so that it can resize kernels for a wide range of devices. Our evaluation on three architectures, ranging from Qualcomm Snapdragon to a Summit supercomputer node, shows that IRIS improves portability across a wide range of diverse heterogeneous architectures with negligible overhead.

97 MATHEMATICS AND COMPUTING↗

Simulation of Hurricane Harvey flood event through coupled hydrologic-hydraulic models: Challenges and next steps

Using the 2017 Hurricane Harvey flood event as a test case, this study set up a series of sensitivity analyses to highlight three challenges associated with large-scale flood inundation modeling, including (a) model parameterization, (b) errors in digital elevation models, and (c) effects of reservoir retention. Driven by radar-based hourly rainfall data, a series of hydrologic-hydraulic models including the VIC hydrologic model, RAPID routing model, and Flood2D-GPU hydrodynamic model are set up over Harris County, Texas, to simulate flood inundation and hazards. The results demonstrate the importance of hydrologic parameters in improving flood modeling. For a large flood event such as Hurricane Harvey, the effect of the initial water depths is insignificant. The Manning's n values may increase the peak water depth by ~1%, the flood extents by 65km 2 , and the high danger zone by ~6%. On the contrary, the bathymetry correction factors may reduce the flood extent by ~1.4% and the high-danger zone by ~4%. Reducing the reservoir storage capacity to 1% may increase the flood extent by ~4% and the high-danger zone by ~17%. This study may provide supporting information to guide and prioritize the development of future high-performance computing hydrodynamic large-scale flood simulations.

54 ENVIRONMENTAL SCIENCES↗

Measurement with microscopic MRI and simulation of flow in different aneurysm models

Purpose: The impact and the development of aneurysms depend to a significant degree on the exchange of liquid between the regular vessel and the pathological extension. A better understanding of this process will lead to improved prediction capabilities. The aim of the current study was to investigate fluid-exchange in aneurysm models of different complexities by combining microscopic magnetic resonance measurements with numerical simulations. In order to evaluate the accuracy and applicability of these methods, the fluid-exchange process between the unaltered vessel lumen and the aneurysm phantoms was analyzed quantitatively using high spatial resolution. Methods: Magnetic resonance flow imaging was used to visualize fluid-exchange in two different models produced with a 3D printer. One model of an aneurysm was based on histological findings. The flow distribution in the different models was measured on a microscopic scale using time of flight magnetic resonance imaging. The whole experiment was simulated using fast graphics processing unit-based numerical simulations. The obtained simulation results were compared qualitatively and quantitatively with the magnetic resonance imaging measurements, taking into account flow and spin–lattice relaxation. Results: The results of both presented methods compared well for the used aneurysm models and the chosen flow distributions. The results from the fluid-exchange analysis showed comparable characteristics concerning measurement and simulation. Similar symmetry behavior was observed. Based on these results, the amount of fluid-exchange was calculated. Depending on the geometry of the models, 7% to 45% of the liquid was exchanged per second. Conclusions: The result of the numerical simulations coincides well with the experimentally determined velocity field. The rate of fluid-exchange between vessel and aneurysm was well-predicted. Hence, the results obtained by simulation could be validated by the experiment. The observed deviations can be caused by the noise in the measurement and by the limited resolution of the simulation. The resulting differences are small enough to allow reliable predictions of the flow distribution in vessels with stents and for pulsed blood flow.

60 APPLIED LIFE SCIENCES↗

A Survey of Methods for Analyzing and Improving GPU Energy Efficiency

Recent years have witnessed a phenomenal growth in the computational capabilities and applications of GPUs. However, this trend has also led to dramatic increase in their power consumption. This paper surveys research works on analyzing and improving energy efficiency of GPUs. It also provides a classification of these techniques on the basis of their main research idea. Further, it attempts to synthesize research works which compare energy efficiency of GPUs with other computing systems, e.g. FPGAs and CPUs. The aim of this survey is to provide researchers with knowledge of state-of-the-art in GPU power management and motivate them to architect highly energy-efficient GPUs of tomorrow.

architecture techniques↗

Porting a 3D seismic modeling code (SW4) to CORAL machines

Seismic waves fourth order (SW4) solves the seismic wave equations on Cartesian and curvilinear grids using large compute clusters with O (100,000) cores. In this article we discuss the porting of SW4 to run on the CORAL architecture using the RAJA performance portability abstraction layer. The performances of key kernels using RAJA and CUDA are compared to estimate the performance penalty of using the portability abstraction layer. Code changes required for efficiency on GPUs and minimizing time spent in Message Passing Interface (MPI) are discussed. This article describes a path for efficiently porting large code bases to GPU-based machines while avoiding the pitfalls of a new architecture in the early stages of its deployment. Current bottlenecks in the code are discussed along with possible architectural or software mitigations. SW4 runs 28× faster on one 4-GPU CORAL node than on a CTS-1 node (Dual Intel Xeon E5-2695 v4). SW4 is now in routine use on problems of unprecedented resolution (203 billion grid points) and scale on 1,200 nodes of Summit.

97 MATHEMATICS AND COMPUTING↗

Multiphysics coupling in the Exascale computing project

Multiphysics coupling presents a significant challenge in terms of both computational accuracy and performance. Achieving high performance on coupled simulations can be particularly challenging in a high-performance computing context. The US Department of Energy Exascale Computing Project has the mission to prepare mission-relevant applications for the delivery of the exascale computers starting in 2023. Many of these applications require multiphysics coupling, and the implementations must be performant on exascale hardware. In this special issue we feature six articles performing advanced multiphysics coupling that span the computational science domains in the Exascale Computing Project.

97 MATHEMATICS AND COMPUTING↗

PeleC: An adaptive mesh refinement solver for compressible reacting flows

Reacting flow simulations for combustion applications require extensive computing capabilities. Leveraging the AMReX library, the Pele suite of combustion simulation tools targets the largest supercomputers available and future exascale machines. We introduce PeleC, the compressible solver in the Pele suite, and detail its capabilities, including complex geometry representation, chemistry integration, and discretization. We present a comparison of development efforts using both OpenACC and AMReX’s C++ performance portability framework for execution on multiple GPU architectures. We discuss relevant details that have allowed PeleC to achieve high performance and scalability. PeleC’s performance characteristics are measured through relevant simulations on multiple supercomputers. The success of PeleC’s design for exascale is exhibited through demonstration of a 160 billion cell simulation and weak scaling onto 100% of Summit, an NVIDIA-based GPU supercomputer at Oak Ridge National Laboratory. Our results provide confidence that PeleC will enable future combustion science simulations with unprecedented fidelity.

97 MATHEMATICS AND COMPUTING↗

Elviz – exploration of metagenome assemblies with an interactive visualization tool

Metagenomics, the sequencing of DNA collected from an entire microbial community, enables the study of natural microbial consortia in their native habitats. Metagenomics studies produce huge volumes of data, including both the sequences themselves and metadata describing their abundance, assembly, predicted functional characteristics and environmental parameters. The ability to explore these data visually is critically important to meaningful biological interpretation. Current genomics applications cannot effectively integrate sequence data, assembly metadata, and annotation to support both genome and community-level inquiry. Elviz (Environmental Laboratory Visualization) is an interactive web-based tool for the visual exploration of assembled metagenomes and their complex metadata. Elviz allows scientists to navigate metagenome assemblies across multiple dimensions and scales, plotting parameters such as GC content, relative abundance, phylogenetic affiliation and assembled contig length. Furthermore Elviz enables interactive exploration using real-time plot navigation, search, filters, axis selection, and the ability to drill from a whole-community profile down to individual gene annotations. Thus scientists engage in a rapid feedback loop of visual pattern identification, hypothesis generation, and hypothesis testing. Compared to the current alternative of generating a succession of static figures, Elviz can greatly accelerate the speed of metagenome analysis. Elviz can be used to explore both user-submitted datasets and numerous metagenome studies publicly available at the Joint Genome Institute (JGI). Elviz is freely available at http://genome.jgi.doe.gov/viz and runs on most current web-browsers.

59 BASIC BIOLOGICAL SCIENCES↗

Matrix Product (GEMM) Performance Data from GPUs

Timing data for mixed precision GEMM matrix product operations on several GPU models, including NVIDIA V100 and A100, AMD MI100 and Intel P580. Also data from machine learning model training on this data using Scikit-learn.

97 MATHEMATICS AND COMPUTING↗

TxDOT Road Elevation Model Dataset

This dataset provides three formats of Road Elevation Model (REM) data: 3D road line/polygon GeoPackage (GPKG), road lidar LAZ and COPC LAZ, and road digital surface model (DSM) GeoTIFF. Data are produced from the ~50TB TxGIO (formerly TNRIS) state lidar collections. This dataset is currently organized by maintenance section in each TxDOT district. Computation is done on GPU computing resources at Oak Ridge National Laboratory (ORNL), through a Strategic Partnership Project with UT Austin and an NSF ACCESS computing allocation award that enables fast massive data movement between TACC Corral and ORNL CADES/OLCF using Globus. In addition to this release from ORNL, a copy of this dataset can also be downloaded at https://web.corral.tacc.utexas.edu/nfiedata/road3d/.

13 HYDRO ENERGY↗

Quantum Monte Carlo Endstation for Petascale Computing

The major achievements enabled by QMC Endstation grant include * Performance improvement on clusters of x86 multi-core systems, especially on Cray XT systems * New and improved methods for the wavefunction optimizations * New forms of trial wavefunctions * Implementation of the full application on NVIDIA GPUs using CUDA The scaling studies of QMCPACK on large-scale systems show excellent parallel efficiency up to 216K cores on Jaguarpf (Cray XT5). The GPU implementation shows speedups of 10-15x over the CPU implementation on older generation of x86. We have implemented hybrid OpenMP/MPI scheme in QMC to take advantage of multi-core shared memory processors of petascale systems. Our hybrid scheme has several advantages over the standard MPI-only scheme. * Memory optimized: large read-only data to store one-body orbitals and other shared properties to represent the trial wave function and many-body Hamiltonian can be shared among threads, which reduces the memory footprint of a large-scale problem. * Cache optimized: the data associated with an active Walker are in cache during the compute-intensive drift-diffusion process and the operations on an Walker are optimized for cache reuse. Thread-local objects are used to ensure the data affinity to a thread. * Load balanced: Walkers in an ensemble are evenly distributed among threads and MPI tasks. The two-level parallelism reduces the population imbalance among MPI tasks and reduces the number of point-to-point communications of large messages (serialized objects) for the Walker exchange. * Communication optimized: the communication overhead, especially for the collective operations necessary to determine ET and measure the properties of an ensemble, is significantly lowered by using less MPI tasks. The multiple forms of parallelism afforded by QMC algorithms make them ideal candidates for acceleration in the many-core paradigm. We presented the results of our effort to port the QMCPACK simulation code to the NVIDIA CUDA GPU platform. We restructured the CPU algorithms to express additional parallelism, minimize GPU-CPU communication, and efficiently utilize the GPU memory hierarchy. Using mixed precision on GT200 GPUs and MPI for intercommunication and load balancing, we observe typical full-application speedups of approximately 10x to 15x relative to quad-core Xeon CPUs alone, while reproducing the double-precision CPU results within statistical error. We developed an all-electron quantum Monte Carlo (QMC) method for solids that does not rely on pseudopotentials, and used it to construct a primary ultra-high-pressure calibration based on the equation of state of cubic boron nitride. We computed the static contribution to the free energy with the QMC method and obtained the phonon contribution from density functional theory, yielding a high-accuracy calibration up to 900 GPa usable directly in experiment. We computed the anharmonic Raman frequency shift with QMC simulations as a function of pressure and temperature, allowing optical pressure calibration. In contrast to present experimental approaches, small systematic errors in the theoretical EOS do not increase with pressure, and no extrapolation is needed. This all-electron method is applicable to first-row solids, providing a new reference for ab initio calculations of solids and benchmarks for pseudopotential accuracy. We compared experimental and theoretical results on the momentum distribution and the quasiparticle renormalization factor in sodium. From an x-ray Compton-profile measurement of the valence-electron momentum density, we derived its discontinuity at the Fermi wavevector finding an accurate measure of the renormalization factor that we compared with quantum-Monte-Carlo and G0W0 calculations performed both on crystalline sodium and on the homogeneous electron gas. Our calculated results are in good agreement with the experiment. We have been studying the heat of formation for various Kubas complexes of molecular hydrogen on Ti(1,2)ethylene-nH2 using Diffusion Monte Carlo. This work has been started and is ongoing. We are studying systems involving 1 and 2 Ti bonding sites with up to 10 hydrogen molecules in numerous configurations. This work will establish a benchmark that will test the accuracy of density functional calculations and establish the feasibility of our methods for similar systems.

97 MATHEMATICS AND COMPUTING↗

A Multireference Approach to Electron and Electron–Nuclear Dynamics in Nanomaterials (Final Report)

Many important chemical and physical phenomena involve dynamics on large number of electronic states. Thus, there is a critical need to develop methods to simulate dynamics in dense manifolds of states. Towards this end, we have: a) developed the multiple cloning in dense manifolds of states (MCDMS) method, which is capable of accurately modeling the quantum mechanical coherence between populations on a large number of electronic states, b) implemented MCDMS into the free, open-source PySpawn software package, c) developed graphics processing unit-accelerated algorithms modeling electron dynamics in light fields via Floquet time-dependent configuration interaction (F-TDCI), and d) critically compared different orbital bases in order to achieve an accurate and efficient F-TDCI expansion. This grant ended in August 2020, when our group moved to from Michigan State University to Stony Brook University, where this project continues under grant number DE-SC0021643.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Large Terrain Modeling and Visualization for Planets

Physics-based simulations are actively used in the design, testing, and operations phases of surface and near-surface planetary space missions. One of the challenges in realtime simulations is the ability to handle large multi-resolution terrain data sets within models as well as for visualization. In this paper, we describe special techniques that we have developed for visualization, paging, and data storage for dealing with these large data sets. The visualization technique uses a real-time GPU-based continuous level-of-detail technique that delivers multiple frames a second performance even for planetary scale terrain model sizes.

digital elevation map↗