Search NASA⌕ Search

SEARCH · Search NASA

Results for “computer code development”

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 559 records · Page 31

Application of performance portability solutions for GPUs and many-core CPUs to track reconstruction kernels

Next generation High-Energy Physics (HEP) experiments are presented with significant computational challenges, both in terms of data volume and processing power. Using compute accelerators, such as GPUs, is one of the promising ways to provide the necessary computational power to meet the challenge. The current programming models for compute accelerators often involve using architecture-specific programming languages promoted by the hardware vendors and hence limit the set of platforms that the code can run on. Developing software with platform restrictions is especially unfeasible for HEP communities as it takes significant effort to convert typical HEP algorithms into ones that are efficient for compute accelerators. Multiple performance portability solutions have recently emerged and provide an alternative path for using compute accelerators, which allow the code to be executed on hardware from different vendors. We apply several portability solutions, such as Kokkos, SYCL, C++17 std::execution::par and Alpaka, on two mini-apps extracted from the mkFit project: p2z and p2r. These apps include basic kernels for a Kalman filter track fit, such as propagation and update of track parameters, for detectors at a fixed z or fixed r position, respectively. The two mini-apps explore different memory layout formats. We report on the development experience with different portability solutions, as well as their performance on GPUs and many-core CPUs, measured as the throughput of the kernels from different GPU and CPU vendors such as NVIDIA, AMD and Intel.

Kwok, Ka Martin↗

Application of performance portability solutions for GPUs and many-core CPUs to track reconstruction kernels

Next generation High-Energy Physics (HEP) experiments are presented with significant computational challenges, both in terms of data volume and processing power. Using compute accelerators, such as GPUs, is one of the promising ways to provide the necessary computational power to meet the challenge. The current programming models for compute accelerators often involve using architecture-specific programming languages promoted by the hardware vendors and hence limit the set of platforms that the code can run on. Developing software with platform restrictions is especially unfeasible for HEP communities as it takes significant effort to convert typical HEP algorithms into ones that are efficient for compute accelerators. Multiple performance portability solutions have recently emerged and provide an alternative path for using compute accelerators, which allow the code to be executed on hardware from different vendors. We apply several portability solutions, such as Kokkos, SYCL, C++17 std::execution::par, Alpaka, and OpenMP/OpenACC, on two mini-apps extracted from the mkFit project: p2z and p2r. These apps include basic kernels for a Kalman filter track fit, such as propagation and update of track parameters, for detectors at a fixed z or fixed r position, respectively. The two mini-apps explore different memory layout formats. We report on the development experience with different portability solutions, as well as their performance on GPUs and many-core CPUs, measured as the throughput of the kernels from different GPU and CPU vendors such as NVIDIA, AMD and Intel.

Kwok, Ka Hei Martin↗

Development of a Reference Model for Molten-Salt-Cooled Pebble-Bed Reactor Using SAM

To support the development and utilization of the SAM code for fluoride-salt-cooled high-temperature pebble-bed reactor (PB-FHR) safety analysis and licensing, an effort was devoted to developing reference models for PB-FHR primary loop and the reactor cavity cooling system (RCCS). A reference standard problem of a prototypical reactor design is foundational to NRC and industry to verify the adequacy of computer codes and evaluation models for a specific reactor type. The SAM code was enhanced for the reference PB-FHR model development, including a 1D-3D flow coupling scheme and conjugate heat transfer between porous media and solid structures. The reference FHR primary loop model was developed based on the UC Berkeley Mk1 FHR design with additional design features from the Kairos Power’s KP-FHR core. The PB-FHR core is modeled by a two-dimensional porous medium while the rest of the primary loop is represented by a SAM one-dimensional model. A SAM one-dimensional primary loop model was also developed for comparison using a single channel approach for the reactor core. Furthermore, the water-based NSTF cavity was modeled using SAM multi-dimensional flow module, to assist in evaluating SAM capabilities of modeling the emergency heat removal systems relying on RCCS concepts.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Scientific Discovery through Advanced Computing

My work during the past year has involved application and development of the M3D code. M3D (Multi-level 3D) carries out simulation studies of plasmas using multiple levels of physics, geometry, and grid models. M3D combines a two dimensional unstructured mesh with finite element discretization in poloidal planes, with a pseudo spectral representation in the toroidal direction. Two critical MHD issues have emerged with the ITER effort: the suppression of edge localized modes (ELMs) by resonant magnetic perturbations (RMPs) and disruptions. Large ELMs can cause an unacceptable heat and particle flux to the wall and divertor. The application of RMPs to ITER is now being planned, although there are still some questions about how RMPs work. Disruptions can produce a much larger heat and particle than ELMs, and in addition can cause unacceptable mechanical stress on the wall and blanket. I have been carrying out extended MHD simulations which address these issues.

97 MATHEMATICS AND COMPUTING↗

Evaluation of CHO Benchmarks on the Arria 10 FPGA using Intel FPGA SDK for OpenCL

The OpenCL standard is an open programming model for accelerating algorithms on heterogeneous computing system. OpenCL extends the C-based programming language for developing portable codes on different platforms such as CPU, Graphics processing units (GPUs), Digital Signal Processors (DSPs) and Field Programmable Gate Arrays (FPGAs). The Intel FPGA SDK for OpenCL is a suite of tools that allows developers to abstract away the complex FPGA-based development flow for a high-level software development flow. Users can focus on the design of hardware-accelerated kernel functions in OpenCL and then direct the tools to generate the low-level FPGA implementations. The approach makes the FPGA-based development more accessible to software users as the needs for hybrid computing using CPUs and FPGAs are increasing. It can also significantly reduce the hardware development time as users can evaluate different ideas with high-level language without deep FPGA domain knowledge. Benchmarking of OpenCL-based framework is an effective way for analyzing the performance of system by studying the execution of the benchmark applications. CHO is a suite of benchmark applications that provides support for OpenCL [1]. The authors presented CHO as an OpenCL port of the CHStone benchmark. Using Altera OpenCL (AOCL) compiler to synthesize the benchmark applications, they listed the resource usage and performance of each kernel that can be successfully synthesized by the compiler. In this report, we evaluate the resource usage and performance of the CHO benchmark applications using the Intel FPGA SDK for OpenCL and Nallatech 385A FPGA board that features an Arria 10 FPGA device. The focus of the report is to have a better understanding of the resource usage and performance of the kernel implementations using Arria-10 FPGA devices compared to Stratix-5 FPGA devices. In addition, we also gain knowledge about the limitations of the current compiler when it fails to synthesize a benchmark application.

97 MATHEMATICS AND COMPUTING↗

Validation of radiative transfer computation with Monte Carlo method for ultra-relativistic background flow

We developed a three-dimensional radiative transfer code for an ultra-relativistic background flow-field by using the Monte Carlo (MC) method in the context of gamma-ray burst (GRB) emission. For obtaining reliable simulation results in the coupled computation of MC radiation transport with relativistic hydrodynamics which can reproduce GRB emission, we validated radiative transfer computation in the ultra-relativistic regime and assessed the appropriate simulation conditions. The radiative transfer code was validated through two test calculations: (1) computing in different inertial frames and (2) computing in flow-fields with discontinuous and smeared shock fronts. The simulation results of the angular distribution and spectrum were compared among three different inertial frames and in good agreement with each other. If the time duration for updating the flow-field was sufficiently small to resolve a mean free path of a photon into ten steps, the results were thoroughly converged. The spectrum computed in the flow-field with a discontinuous shock front obeyed a power-law in frequency whose index was positive in the range from 1 to 10 MeV. The number of photons in the high-energy side decreased with the smeared shock front because the photons were less scattered immediately behind the shock wave due to the small electron number density. The large optical depth near the shock front was needed for obtaining high-energy photons through bulk Compton scattering. Even one-dimensional structure of the shock wave could affect the results of radiation transport computation. Although we examined the effect of the shock structure on the emitted spectrum with a large number of cells, it is hard to employ so many computational cells per dimension in multi-dimensional simulations. Therefore, a further investigation with a smaller number of cells is required for obtaining realistic high-energy photons with multi-dimensional computations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

GPU COMPUTING FOR PARTICLE TRACKING

This is a feasibility study of using a modern Graphics Processing Unit (GPU) to parallelize the accelerator particle tracking code. To demonstrate the massive parallelization features provided by GPU computing, a simplified TracyGPU program is developed for dynamic aperture calculation. Performances, issues, and challenges from introducing GPU are also discussed. General purpose Computation on Graphics Processing Units (GPGPU) bring massive parallel computing capabilities to numerical calculation. However, the unique architecture of GPU requires a comprehensive understanding of the hardware and programming model to be able to well optimize existing applications. In the field of accelerator physics, the dynamic aperture calculation of a storage ring, which is often the most time consuming part of the accelerator modeling and simulation, can benefit from GPU due to its embarrassingly parallel feature, which fits well with the GPU programming model. In this paper, we use the Tesla C2050 GPU which consists of 14 multi-processois (MP) with 32 cores on each MP, therefore a total of 448 cores, to host thousands ot threads dynamically. Thread is a logical execution unit of the program on GPU. In the GPU programming model, threads are grouped into a collection of blocks Within each block, multiple threads share the same code, and up to 48 KB of shared memory. Multiple thread blocks form a grid, which is executed as a GPU kernel. A simplified code that is a subset of Tracy++ [2] is developed to demonstrate the possibility of using GPU to speed up the dynamic aperture calculation by having each thread track a particle.

42 ENGINEERING↗

SSR APPLIED – Automated Power Plants: Intelligent, Efficient and Digitised (V.2)

This report describes work undertaken during the SSR APPLIED project. The focus of the project has been on the development of digital twins to de-risk licensing of improved operating and maintenance practices. The operation of a bespoke flowing separate effects molten salt loop at ANL, with realistic temperature gradients, will provide invaluable data for computer codes validation. Three digital twins of aspects of the SSR-W have been successfully developed using ANL expertise and software. These digital twins have demonstrated optimization of the fuel cycle, the ability to model transients using an integrated coupled neutronic – thermal-hydraulic model with a model of the fuel expansion feedback so important to the inherent safety of the SSR-W. Advanced machine learning techniques have been developed and demonstrated for optimization of heat exchanger operation and maintenance.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Co-Design: Fabrication of Unalloyed Plutonium

The successful induction casting of plutonium is a challenge which requires technical expertise in areas including physical metallurgy, surface and corrosion chemistry, materials science, electromagnetic engineering and a host of other technologies all which must be applied in concert. Here at LANL, we are employing a combined experimental and computational approach to design molds and develop process parameters needed to produce desired temperature profiles and improved castings. Computer simulations are performed using the commercial code FLOW-3D and the LANL ASC computer code TRUCHAS to reproduce the entire casting process starting with electromagnetic or radiative heating of the mold and metal and continuing through pouring with coupled fluid flow, heat transfer and non-isothermal solidification. This approach greatly reduces the time required to develop a new casting designs and also increases our understanding of the casting process, leading to a more homogeneous, consistent product and better process control. We will discuss recent casting development results in support of unalloyed plutonium rods for mechanical testing.

CASTING↗

HACC: Simulating sky surveys on state-of-the-art supercomputing architectures

Current and future surveys of large-scale cosmic structure are associated with a massive and complex datastream to study, characterize, and ultimately understand the physics behind the two major components of the ‘Dark Universe’, dark energy and dark matter. In addition, the surveys also probe primordial perturbations and carry out fundamental measurements, such as determining the sum of neutrino masses. Large-scale simulations of structure formation in the Universe play a critical role in the interpretation of the data and extraction of the physics of interest. Just as survey instruments continue to grow in size and complexity, so do the supercomputers that enable these simulations. In this paper, we report on HACC (Hardware/Hybrid Accelerated Cosmology Code), a recently developed and evolving cosmology N-body code framework, designed to run efficiently on diverse computing architectures and to scale to millions of cores and beyond. HACC can run on all current supercomputer architectures and supports a variety of programming models and algorithms. It has been demonstrated at scale on Cell- and GPU-accelerated systems, standard multi-core node clusters, and Blue Gene systems. HACC’s design allows for ease of portability, and at the same time, high levels of sustained performance on the fastest supercomputers available. We present a description of the design philosophy of HACC, the underlying algorithms and code structure, and outline implementation details for several specific architectures. We show selected accuracy and performance results from some of the largest high resolution cosmological simulations so far performed, including benchmarks evolving more than 3.6 trillion particles.

79 ASTRONOMY AND ASTROPHYSICS↗

Investigation on the Core Bypass Flow in a Very High Temperature Reactor

Uncertainties associated with the core bypass flow are some of the key issues that directly influence the coolant mass flow distribution and magnitude, and thus the operational core temperature profiles, in the very high-temperature reactor (VHTR). Designers will attempt to configure the core geometry so the core cooling flow rate magnitude and distribution conform to the design values. The objective of this project is to study the bypass flow both experimentally and computationally. Researchers will develop experimental data using state-of-the-art particle image velocimetry in a small test facility. The team will attempt to obtain full field temperature distribution using racks of thermocouples. The experimental data are intended to benchmark computational fluid dynamics (CFD) codes by providing detailed information. These experimental data are urgently needed for validation of the CFD codes. The following are the project tasks: (1) Construct a small-scale bench-top experiment to resemble the bypass flow between the graphite blocks, varying parameters to address their impact on bypass flow. Wall roughness of the graphite block walls, spacing between the blocks, and temperature of the blocks are some of the parameters to be tested. (2) Perform CFD to evaluate pre- and post-test calculations and turbulence models, including sensitivity studies to achieve high accuracy. (3) Develop the state-of-the art large eddy simulation (LES) using appropriate subgrid modeling. (4) Develop models to be used in systems thermal hydraulics codes to account and estimate the bypass flows. These computer programs include, among others, RELAP3D, MELCOR, GAMMA, and GAS-NET. Actual core bypass flow rate may vary considerably from the design value. Although the uncertainty of the bypass flow rate is not known, some sources have stated that the bypass flow rates in the Fort St. Vrain reactor were between 8 and 25 percent of the total reactor mass flow rate. If bypass flow rates are on the high side, the quantity of cooling flow through the core may be considerably less than the nominal design value, causing some regions of the core to operate at temperatures in excess of the design values. These effects are postulated to lead to localized hot regions in the core that must be considered when evaluating the VHTR operational and accident scenarios.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Uncertainty Quantification and Sensitivity Analysis for Coupled VERA-CS and FRAPCON

The current nuclear power plant fleet in the U.S. is facing numerous challenges economically ranging from low natural gas price to the rapidly growing renewable energy sources such as wind and solar power. In order for the nuclear industry to keep the viability of its operating fleet, new innovations have to be introduced to lower the costs to operate the fleet. One area that could contribute to the cost reduction is to lower the fuel cycle cost and improve the plant safety through initiatives such as higher burnup fuel and accident tolerant fuel. At the same time, the nuclear industry has to address future challenges on the horizon such as load following and other flexible operating strategies as well as those associated with new regulations such as 10 CFR 50.69 and 10 CFR50.46c etc. All these require coupled analysis of core neutronics, thermal hydraulics and fuel performance, which necessitates the development of a multi-physics toolkit. Since different models, assumptions, and fidelities have gone into various computer codes, how to consistently propagate uncertainties in a multi-physics environment warrants careful evaluation. The U.S. DOE's Light Water Reactor Sustainability (LWRS) Program initiated a project to develop analytical capabilities to support the industry to address these challenges. The general idea behind the initiative was the development of an integrated multiphysics evaluation model. This integrated evaluation model is called LOTUS which stands for LOCA Toolkit for the U.S. Light Water Reactors. The focus of LOTUS is to establish the automation of the interface between the five disciplines. LOTUS framework ensures that uncertainties can be easily propagated to solve the problems forward and backward (inverse) with large numbers of simulations. The objective of this work is to perform uncertainty quantification (UQ) and sensitivity analysis (SA) on a coupling of CASL's Virtual Environment for Reactor Applications-Core Simulator (VERA-CS) and NRC's fuel performance code FRAPCON. The work presented herein is a subset of the overall LOTUS framework. The figures of merit (FOM) selected for analysis are minimum departure from nucleate boiling ratio (MDNBR), maximum fuel centerline temperature (MFCT), and the gap conductance at peak power (GCPP). All FOM are obtained at the end of the of a depletion case for a half cycle lasting 263 days. The minimum is taken over all spatial location for each pin at the end of the half cycle. This value is calculated in VERACS alone and has been analyzed in previous work by Brown and Zhang. The MFCT is available in both VERA-CS and FRAPCON, but is calculated via different methods (see Model Inconsistencies section for more details). For this work, only the FRAPCON values are reported due to the code's maturity from extensive validation in fuel performance. Previous work includes SA on a standalone nuclear fuel performance code VTT-modified FRAPCON- 3.4 by Ikonen. The GCPP is the gap conductance at the location corresponding to maximum power in the fuel rod. This value is available in FRAPCON alone and highlights the capability of LOTUS to obtain unique fuel performance metrics for each pin in a core simulation.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Experimental validation of an integrated modelling approach to neutron emission studies at JET

An integrated modelling methodology for the calculation of realistic plasma neutron sources for the JET tokamak has been developed. The computational chain comprises TRANSP plasma transport and DRESS neutron spectrum calculations, and their coupling to the MCNP neutron transport code, bridging plasma physics and neutronics. Here, we apply the developed methodology to the analysis of neutron emission properties of deuterium and helium plasmas at JET, and validate individual modelling steps against neutron diagnostic measurements. Two types of JET discharges are modelled—baseline-like and three-ion radio-frequency scenarios—due to their diversity in plasma heating, characteristics of the induced fast ion population, and the imprint of these on neutron emission properties. The neutron emission modelling results are quantitatively compared to the total neutron yield from fission chambers, neutron emissivity profiles from the neutron camera, neutron spectra from the time-of-flight spectrometer, and neutron activation measurements. The agreement between measured and calculated quantities is found to be satisfactory for all four diagnostic systems within the estimated experimental and computational uncertainties. Additionally, the effect of neutrons not originating from the dominating D(D, n) 3 He reactions is studied through modelling of triton burnup DT neutrons, and, in mixed D- 3 He plasmas, neutrons produced in the 9 Be(D, nγ) 10 B reaction on impurities. It is found that these reactions can contribute up to several percent to the total neutron yield and dominate the neutron activation of samples. Finally, the effect of MeV-range fast ions on the neutron activation of 115 In and 27 Al samples is measured and computationally validated.

integrated modelling↗

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↗

Development and performance of a HemeLB GPU code for human-scale blood flow simulation

In recent years, it has become increasingly common for high performance computers (HPC) to possess some level of heterogeneous architecture - typically in the form of GPU accelerators. In some machines these are isolated within a dedicated partition, whilst in others they are integral to all compute nodes - often with multiple GPUs per node - and provide the majority of a machine's compute performance. In light of this trend, it is becoming essential that codes deployed on HPC are updated to execute on accelerator hardware. Here, in this paper, we introduce a GPU implementation of the 3D blood flow simulation code HemeLB that has been developed using CUDA C++. We demonstrate how taking advantage of NVIDIA GPU hardware can achieve significant performance improvements compared to the equivalent CPU only code on which it has been built whilst retaining the excellent strong scaling characteristics that have been repeatedly demonstrated by the CPU version. With HPC positioned on the brink of the exascale era, we use HemeLB as a motivation to provide a discussion on some of the challenges that many users will face when deploying their own applications on upcoming exascale machines.

59 BASIC BIOLOGICAL SCIENCES↗

Preface to the Proceedings of the 23rd Topical Conference on High-Temperature Plasma Diagnostics

Measurements of phenomena advance our understanding of the physical universe. As our understanding grows, more precise measurements are required, as are measurements of new quantities. Diagnosis of a plasma requires developing new instruments, also called diagnostics, as well as new ways to analyze, interpret, synthesize, and correlate their measurements. Further, as computing power increases and multi-physics codes improve their accuracy, more precise measurements are needed to guide future code developments and to validate predictions of these simulation codes. The Topical Conference on High-Temperature Plasma Diagnostics is focused on presenting and documenting the most recent advances in these instrumentation areas for plasmas. The 23rd occurrence of this biennial conference took place on December 14–17, 2020, and was hosted by Los Alamos National Laboratory. Originally scheduled for June 2020 in Santa Fe, New Mexico, the conference was postponed and then held virtually due to the global COVID-19 pandemic. Conference times were adjusted and presentations were scheduled to meet the needs of attendees in Europe, the USA, and Asia.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Collaborative Research: Improved Efficiency and Coupling of the Radiation Code in the ACME Earth System Model. Final Report

This final report details all work performed on the project by both project partners. This project provided support to properly couple RTE+RRTMGP, a high-performance broadband radiation code, within DOE’s Energy Exascale Earth System Model (E3SM). RTE+RRTMGP is a successor to the RRTMG radiation code, which has been widely accepted for its speed and accuracy by the global modeling community, and has been in use in the NCAR CESM for many years and was implemented in the initial version of E3SM. However, the computational cost of RRTMG remains high relative to other components in part due to its complexity and to its inefficient use of modern optimization strategies, issues that were rectified by the development of RTE+RRTMGP. Many of the accomplishment in this project necessitated significant collaboration with the E3SM development team. One focus of the project was to enhance the code’s optimization on the limited number of emerging computing systems on which the model is expected be used, including Many Integrated Core (MIC) architectures and Graphics Processing Unit (GPU) hardware. We also developed additional capabilities for RTE+RRTMGP that E3SM scientists identified as important for the planned applications of the model. The result of our project was optimization of a key physical component (radiative transfer calculations) of E3SM, directly supporting E3SM’s overarching global modeling objectives. More broadly, this project provided overall advancements in the use of radiative transfer calculations in atmospheric modeling and simulation, particularly for climate.

54 ENVIRONMENTAL SCIENCES↗