Search NASA⌕ Search

SEARCH · Search NASA

Results for “coding productivity”

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 73 records · Page 4

IMPROVEMENTS TO THE TIME STEPPING ALGORITHM OF RELAP5-3D

The RELAP5-3D time step method is used to perform thermo-hydraulic and neutronic simulations of nuclear reactors and other devices. It discretizes time and space by numerically solving several differential equations. Previously, time step size was controlled by halving or doubling the size of a previous time step. This process caused the code to run slower than it potentially could. In this research project, the RELAP5-3D time step method was modifi ed to allow a new method of changing time steps to improve execution speed and to control error. The new RELAP5-3D time step method being studied involves making the time step proportional to the material courant limit (MCL), while insuring that the time step does not increase by more than a factor of two between advancements. As before, if a step fails or mass error is excessive, the time step is cut in half. To examine performance of the new method, a measure of run time and a measure of error were plotted against a changing MCL proportionality constant (m) in seven test cases. The removal of the upper time step limit produced a small increase in error, but a large decrease in execution time. The best value of m was found to be 0.9. The new algorithm is capable of producing a signifi cant increase in execution speed, with a relatively small increase in mass error. The improvements made are now under consideration for inclusion as a special option in the RELAP5-3D production code.

Cumberland, R↗

Python-Based Scientific Analysis and Visualization of Precipitation Systems at NASA Marshall Space Flight Center

At NASA Marshall Space Flight Center (MSFC), Python is used several different ways to analyze and visualize precipitating weather systems. A number of different Python‐based software packages have been developed, which are available to the larger scientific community. The approach in all these packages is to utilize pre‐existing Python modules as well as to be object‐oriented and scalable. The first package that will be described and demonstrated is the Python Advanced Microwave Precipitation Radiometer (AMPR) Data Toolkit, or PyAMPR for short. PyAMPR reads geolocated brightness temperature data from any flight of the AMPR airborne instrument over its 25‐year history into a common data structure suitable for user‐defined analyses. It features rapid, simplified (i.e., one line of code) production of quick‐look imagery, including Google Earth overlays, swath plots of individual channels, and strip charts showing multiple channels at once. These plotting routines are also capable of significant customization for detailed, publication‐ready figures. Deconvolution of the polarization‐varying channels to static horizontally and vertically polarized scenes is also available. Examples will be given of PyAMPR's contribution toward real‐time AMPR data display during the Integrated Precipitation and Hydrology Experiment (IPHEx), which took place in the Carolinas during May‐June 2014. The second software package is the Marshall Multi‐Radar/Multi‐Sensor (MRMS) Mosaic Python Toolkit, or MMM‐Py for short. MMM‐Py was designed to read, analyze, and display three‐dimensional national mosaicked reflectivity data produced by the NOAA National Severe Storms Laboratory (NSSL). MMM‐Py can read MRMS mosaics from either their unique binary format or their converted NetCDF format. It can also read and properly interpret the current mosaic design (4 regional tiles) as well as mosaics produced prior to late July 2013 (8 tiles). MMM‐Py can easily stitch multiple tiles together to provide a larger regional or national picture of precipitating weather systems. Composites, horizontal and vertical crosssections, and combinations thereof are easily displayed using as little as one line of code. MMM‐Py can also write to the native MRMS binary format, and sub‐sectioning of tiles (or multiple stitched tiles) is anticipated to be in place by the time of this meeting. Thus, MMM‐Py also can be used to power the creation of custom mosaics for targeted regional studies. Overlays of other data (e.g., lightning observations) are easily accomplished. Demonstrations of MMM‐Py, including the creation of animations, will be shown. Finally, Marshall has done significant work to interface Python‐based analysis routines with the U.S. Department of Energy's Py‐ART software package for radar data ingest, processing, and analysis. One example of this is the Python Turbulence Detection Algorithm (PyTDA), an MSFC‐based implementation of the National Center for Atmospheric Research (NCAR) Turbulence Detection Algorithm (NTDA) for the purposes of convective‐scale analysis, situational awareness, and forensic meteorology. PyTDA exploits Py‐ART's radar data ingest routines and data model to rapidly produce aviation‐relevant turbulence estimates from Doppler radar data. Work toward processing speed optimization and better integration within the Py‐ART framework will be highlighted. Python‐based analysis within the Py‐ART framework is also being done for new research related to intercomparison of ground‐based radar data with satellite estimates of ocean winds, as well as research on the electrification of pyrocumulus clouds.

Lang, Timothy J.↗

NASA GPU Hackathon Yields Significant Code Improvements

The NASA GPU Hackathon 2020 brought together application developers and computer experts to help get important NASA applications running effectively on graphics processing unit (GPU) nodes. Nine teams of application developers participated in this virtual event, a major impetus for teams to modernize codes of interest for NASA missions to CPU nodes containing GPU accelerators, with a focus on hands-on problem solving. The photo in Figure1 shows 30 of the more than50 participants. The HECC project and NVIDIA jointly organized the event, and HECC provided five Pleiades nodes each with 4 V100 GPUs for teams to use. The virtual event, which took place over four days from September 28–October 7, 2020, used Microsoft Teams and Slack as collaboration tools. Each team consisted of three to six members from NASA Centers and supporting organizations. The teams were paired with one to two mentors from industry, government, and academia. The experience levels of the teams ranged from being GPU novices to advanced CUDA programming experts. OpenACC and the emerging Kokkos API were used in addition to CUDA for GPU programming. During the event, which focused on accelerating AeroSciences and CFD applications, most teams achieved considerable performance improvements on both GPUs and CPUs. For example, a team with no GPU experience completed a first port of a time-critical loop to a GPU. Another team of expert CUDA programmers were able to restructure their algorithm, yielding a factor of five speed-up. And another team sped up some of their CUDA kernels by a factor of 20, which directly translated into their production code. This article highlights some of the many successes resulting from the event.

HECC↗

MPI + OpenACC: Accelerating radiation transport mini-application, minisweep, on heterogeneous systems

According to the article, architectures are rapidly evolving, and exascale machines are expected to offer billion-way concurrency. We need to rethink algorithms, languages and programming models among other components in order to migrate large scale applications and explore parallelism on these machines. Although directive-based programming models allow programmers to worry less about programming and more about science, expressing complex parallel patterns in these models can be a daunting task especially when the goal is to match the performance that the hardware platforms can offer. One such pattern is wavefront. This paper extensively studies a wavefront-based miniapplication for Denovo, a production code for nuclear reactor modeling. We parallelize the Koch–Baker–Alcouffe (KBA) parallel-wavefront sweep algorithm in the main kernel of Minisweep (the miniapplication) using CUDA 9.0, OpenMP 4.0 (SIMD) and OpenACC 2.6. Our OpenACC implementation running on NVIDIA’s next-generation Volta GPU boasts an 85.06x speedup over serial code, which is larger than CUDA’s 83.72x speedup over the same serial implementation. We also explore the scalability of our solution using MPI to decompose our simulation domain, allowing us to run on many nodes and accelerators present in state-of-the-art HPC systems. Our parallelization effort across platforms also motivated us to define an abstract parallelism model that is architecture independent, with a goal of creating software abstractions that can be used by applications employing the wavefront sweep motif.

Computer Science↗

On the adequacy of lightweight thread approaches for high-level parallel programming models

High-level parallel programming models (PMs) are becoming crucial in order to extract the computational power of current on-node multi-threaded parallelism. The most popular PMs, such as OpenMP or OmpSs, are directive-based: the complexity of the hardware is hidden by the underlying runtime system, improving coding productivity. The implementations of OpenMP usually rely on POSIX threads (pthreads), offering excellent performance for coarse-grained parallelism and a perfect match with the current hardware. OmpSs is a task oriented PM based on an ad hoc runtime solution called Nanos++; it is the precursor of the tasking parallelism in the OpenMP tasking specification. A recent trend in runtimes and applications points to leveraging massive on-node parallelism in conjunction with fine-grained and dynamic scheduling paradigms. In this paper we analyze the behavior of the OpenMP and OmpSs PMs on top of the recently emerged Generic Lightweight Threads (GLT) API. GLT exposses a common API for lightweight thread (LWT) libraries that offers the possibility of running the same application over different native LWT solutions. We describe the design details of those high-level PMs implemented on top of GLT and analyze different scenarios in order to assess where the use of LWTs may benefit application performance. Our work reveals those scenarios where LWTs overperform pthread-based solutions and compares the performance between an ad hoc solution and a generic implementation.

97 MATHEMATICS AND COMPUTING↗

Unlocking the potential of DNA-based tagging: current market solutions and expanding horizons

The commercialization of DNA tagging is a growing trend that demonstrates the increasing practicality of this novel approach. This interdisciplinary technology is based on the distinctive characteristics of DNA as a molecule that can remain stable in varying environmental conditions and store data following appropriate preparation. Moreover, newly developed technologies could simplify DNA synthesis and the encoding of data within DNA. The implementation of DNA tagging presents distinctive benefits in comparison to conventional labelling techniques, including universal product code (UPC) barcoding, radio-frequency identification (RFID), quick response (QR) codes, and Bluetooth technologies, by surmounting the limitations encountered by these systems. The discourse pertains to extant DNA-tagging mechanisms along with prospective implementations in a wide range of domains, including but not limited to art, the metaverse, forensics, wildlife monitoring, and the military. The potential of DNA labelling in various contexts underscores the importance of continued research and development in this rapidly evolving field.

59 BASIC BIOLOGICAL SCIENCES↗

NUCLEAR GAMMA-RAY DE-EXCITATION LINES AND CONTINUUM FROM ACCELERATED-PARTICLE INTERACTIONS IN SOLAR FLARES

Analyses of gamma-ray line emission in solar flares have provided information about conditions in flaring magnetic loops, the abundances of the chromosphere where the gamma rays are produced, and the composition and spectrum of the flare-accelerated ions. While laboratory measurements of the cross sections for production of the strongest lines seen in flare spectra are available, these measurements often only cover a limited range of projectile energies. In addition, the bulk of the gamma-ray emission arises from the numerous weaker lines for which there are no measurements. The gamma-ray de-excitation-line production code, developed originally by Ramaty, Kozlovsky, and Lingenfelter, has been and continues to be the primary theoretical tool used for analyses of solar-flare gamma-ray data. The code uses both measured cross sections and estimated cross sections where measurements are inadequate. We have improved the completeness and accuracy of this code in three ways. (1) We use recent cross section measurements to improve cross sections for those lines already explicitly included in the code and to provide cross sections for new explicit lines. (2) For the first time, we give a detailed evaluation of the unresolved-line 'continuum' (i.e., all line emission not accounted for by the explicit lines in the code). Because adequate laboratory measurements for this emission are not available, the primary tool for this evaluation was the theoretical nuclear program TALYS. We explore how this unresolved-line continuum depends on parameters relevant for solar flares. (3) We use TALYS to improve those line cross sections where available laboratory measurements are inadequate and to provide cross sections for new explicit lines for which no measurements exist. Numerical cross section values for all lines explicitly addressed by the code and for the unresolved-line continua are given in the Appendix.

79 ASTRONOMY AND ASTROPHYSICS↗

Abstractions and Directives for Adapting Wavefront Algorithms to Future Architectures

Architectures are rapidly evolving, and exascale machines are expected to offer billion-way concurrency. We need to rethink algorithms, languages and programming models among other components in order to migrate large scale applications and explore parallelism on these machines. Although directive-based programming models allow programmers to worry less about programming and more about science, expressing complex parallel patterns in these models can be a daunting task especially when the goal is to match the performance that the hardware platforms can offer. One such pattern is wavefront. This paper extensively studies a wavefront-based miniapplication for Denovo, a production code for nuclear reactor modeling. We parallelize the Koch-Baker-Alcouffe (KBA) parallel-wavefront sweep algorithm in the main kernel of Minisweep (the miniapplication) using CUDA, OpenMP and OpenACC. Our OpenACC implementation running on NVIDIA's next-generation Volta GPU boasts an 85.06x speedup over serial code, which is larger than CUDA's 83.72x speedup over the same serial implementation. Our experimental platform includes SummitDev, an ORNL representative architecture of the upcoming Summit supercomputer. Our parallelization effort across platforms also motivated us to define an abstract parallelism model that is architecture independent, with a goal of creating software abstractions that can be used by applications employing the wavefront sweep motif.

Searles, Robert↗

OpenMP 4.5 Validation and Verification Suite

OpenMP, a directive-based programming API, introduce directives for accelerator devices that programmers are starting to use more frequently in production codes. To make sure OpenMP directives work correctly across architectures, it is critical to have a mechanism that tests for an implementation's conformance to the OpenMP standard. This testing process can uncover ambiguities in the OpenMP specification, which helps compiler developers and users make a better use of the standard. We fill this gap through our validation and verification test suite that focuses on the offload directives available in OpenMP 4.5.

Pophale, SwaroopS↗

JPype

JPype is a Python module to provide full access to Java from within Python. It allows Python to make use of Java only libraries, exploring and visualization of Java structures, development and testing of Java libraries, scientific computing, and much more. By gaining the best of both worlds using Python for rapid prototyping and Java for strong typed production code, JPype provides a powerful environment for engineering and code development. This is achieved not through re-implementing Python, as Jython has done, but rather through interfacing at the native level in both virtual machines. This shared memory based approach achieves decent computing performance, while providing the access to the entirety of CPython and Java libraries.

Nelson, KarlE.↗

Pressio

Reduced-order Models (ROMs). ROMs are "compressed" approximations of high-fidelity computational models. Implementing ROM methods in production codes is typically intrusive, i.e. the native codes must be adapted and modified, with individual ROM methods reimplemented in every application code. This clearly constitutes an obstacle to users who want to use ROMs. To address this, we have developed Pressio, which is a C++ header-only ROM library that can be used by an application code in a non-intrusive fashion. The main objectives behind the design of Pressio are: (a) support for general computational models (data structures, PDE types); (b) heterogeneous hardware (CPU, GPU); (c) performance; and (d) extensibility. Using metaprogramming techniques, Pressio detects and leverages the application?s native linear algebra data structures (e.g. vector and matrix) to run the ROM methods. The application only needs to expose the velocity vector and Jacobian matrix via an adapter class. Pressio checks at compile time that the target application meets the correct API. The library is structured in several modular packages including (a) non-linear least-square solvers (e.g. Gauss-Newton with and without line-search); (b) singular value decomposition (for the computation of the ROM generalized coordinates) and (c) algebraic hyper-reduction.SAND2019-5878 M

Blonigan, Patrick↗

Pressio v.1.0

Reduced-order Models (ROMs). ROMs are "compressed" approximations of high-fidelity computational models. Implementing ROM methods in production codes is typically intrusive, i.e. the native codes must be adapted and modified, with individual ROM methods reimplemented in every application code. This clearly constitutes an obstacle to users who want to use ROMs. To address this, we have developed Pressio, which is a C++ header-only ROM library that can be used by an application code in a non-intrusive fashion. The main objectives behind the design of Pressio are: (a) support for general computational models (data structures, PDE types); (b) heterogeneous hardware (CPU, GPU); (c) performance; and (d) extensibility. Using metaprogramming techniques, Pressio detects and leverages the application?s native linear algebra data structures (e.g. vector and matrix) to run the ROM methods. The application only needs to expose the velocity vector and Jacobian matrix via an adapter class. Pressio checks at compile time that the target application meets the correct API. The library is structured in several modular packages including (a) non-linear least-square solvers (e.g. Gauss-Newton with and without line-search); (b) singular value decomposition (for the computation of the ROM generalized coordinates) and (c) algebraic hyper-reduction.SAND2019-5878 M

Blonigan, Patrick↗

Validation of Two Hydrocodes with a Bi-Metallic Shaped Charge Experiment

Staggered grid (SGH) and cell-centered (CCH) Lagrangian Hydrodynamics are two approaches to modeling high explosives experiments. These experiments often involve complex flows with multiple materials with and without constitutive relationships. One example of complex flow phenomena is the discontinuous velocities along the tangential direction of a contact surface. Lagrangian methods combined with a contact surface algorithm are well-suited for these types of flows. In this work, the SGH and CCH schemes coupled with a contact surface algorithm are used to model a bi-metallic shaped charge experiment. The shaped charge experiment will be used to validate the contact surface methods, and is scheduled to be performed in the coming year at LANL. The experiment consists of a high explosive wrapped around a hemispherical shell of aluminum and an inner hemispherical shell of copper. The interface between the aluminum and copper shells is modeled both as a frictionless and “bonded” surface. The simulations are performed in a two-dimensional r-z coordinate system using the production code FLAG. A modified Gurney solution for an imploding sphere and Richardson extrapolation is used to evaluate the reasonableness of the results.

Engineering(42)↗

SciDAC Center for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas

During the first year of the SciDAC gyrokinetic particle simulation (GPS) project, the GPS team (Zhihong Lin, Liu Chen, Yasutaro Nishimura, and Igor Holod) at the University of California, Irvine (UCI) studied the tokamak electron transport driven by electron temperature gradient (ETG) turbulence, and by trapped electron mode (TEM) turbulence and ion temperature gradient (ITG) turbulence with kinetic electron effects, extended our studies of ITG turbulence spreading to core-edge coupling. We have developed and optimized an elliptic solver using finite element method (FEM), which enables the implementation of advanced kinetic electron models (split-weight scheme and hybrid model) in the SciDAC GPS production code GTC. The GTC code has been ported and optimized on both scalar and vector parallel computer architectures, and is being transformed into objected-oriented style to facilitate collaborative code development. During this period, the UCI team members presented 11 invited talks at major national and international conferences, published 22 papers in peer-reviewed journals and 10 papers in conference proceedings. The UCI hosted the annual SciDAC Workshop on Plasma Turbulence sponsored by the GPS Center, 2005-2007. The workshop was attended by about fifties US and foreign researchers and financially sponsored several gradual students from MIT, Princeton University, Germany, Switzerland, and Finland. A new SciDAC postdoc, Igor Holod, has arrived at UCI to initiate global particle simulation of magnetohydrodynamics turbulence driven by energetic particle modes. The PI, Z. Lin, has been promoted to the Associate Professor with tenure at UCI.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Determination of the Spectral Index in the Fission Spectrum Energy Regime

Neutron reaction cross sections play a vital role in tracking the production and destruction of isotopes exposed to neutron fluence. They are central to the process of reconciling the initial and final atom inventories. Measurements of irradiated samples by radiochemical methods in tangent with an algorithm are used to evaluate the fluence a sample is exposed to over the course of the irradiation. This algorithm is the Isotope Production Code (IPC) created and used by the radiochemistry data assessment team at Los Alamos National Laboratory (LANL). An integral result is calculated by varying the total neutron fluence seen by a sample. A sample, irradiated in a critical assembly, will be exposed to a unique neutron flux defined by the neutron source and distance of the sample from the source. Neutron cross sections utilized are a function of the hardness of the neutron spectrum at the location of irradiation. A spectral index is used an indicator of the hardness of the neutron spectrum. Cross sections fit forms applied in IPC are collapsed from a LANL 30-group energy structure. Several decades of research and development have been performed to formalize the current IPC cross section library. Basis of the current fission spectrum neutron reaction cross section library is rooted in critical assembly experiments performed from the 1950’s through the early 1970’s at LANL. The focus of this report is development of the spectral index used an indicator of the hardness of the neutron spectrum in the fission spectrum energy regime.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

New Tools to Prepare ACE Cross-section Files for MCNP Analytic Test Problems

Monte Carlo calculations using one-group cross sections, multigroup cross sections, or simple continuous energy cross sections are often used to: (1) verify production codes against known analytical solutions, (2) verify new methods and algorithms that do not involve detailed collision physics, (3) compare Monte Carlo calculation methods with deterministic methods, and (4) teach fundamentals to students. In this work we describe 2 new tools for preparing the ACE cross-section files to be used by MCNP ® for these analytic test problems, simple_ace.pl and simple_ace_mg.pl.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Challenges of Monte Carlo Transport

These are slides from a presentation for Parallel Summer School at Los Alamos National Laboratory. Solving discretized partial differential equations (PDEs) of interest can require a large number of computations. We can identify concurrency to allow parallel solution of discrete PDEs. Simulated particles histories can be used to solve the Boltzmann transport equation. Particle histories are independent in neutral particle transport, making them amenable to parallel computation. Physical parameters and method type determine the data dependencies of particle histories. Data requirements shape parallel algorithms for Monte Carlo. Then, Parallel Computational Physics and Parallel Monte Carlo are discussed and, finally, the results are given. The mesh passing method greatly simplifies the IMC implementation and allows simple load-balancing. Using MPI windows and passive, one-sided RMA further simplifies the implementation by removing target synchronization. The author is very interested in implementations of PGAS that may allow further optimization for one-sided, read-only memory access (e.g. Open SHMEM). The MPICH_RMA_OVER_DMAPP option and library is required to make one-sided messaging scale on Trinitite - Moonlight scales poorly. Interconnect specific libraries or functions are likely necessary to ensure performance. BRANSON has been used to directly compare the current standard method to a proposed method on idealized problems. The mesh passing algorithm performs well on problems that are designed to show the scalability of the particle passing method. BRANSON can now run load-imbalanced, dynamic problems. Potential avenues of improvement in the mesh passing algorithm will be implemented and explored. A suite of test problems that stress DD methods will elucidate a possible path forward for production codes.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

ECP STPR04 Milestone 5 Report

This report documents the completion of milestone STPRO4-5 Kokkos interoperability with general SIMD types to force vectorization on ATS-1. The Kokkos team worked with application developers to enable the utilization of SIMD intrinsics, which allowed up to 3.7x improvement of the affected kernels on ATS-1 in a proxy application. SIMD types are now deployed in the production code base.

97 MATHEMATICS AND COMPUTING↗