SEARCH · Search NASA

Results for “parallel codes”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,387 records · Page 77

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation

We evaluate AI-assisted generative capabilities on fundamental numerical kernels in high-performance computing (HPC), including AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG. We test the generated kernel codes for a variety of language-supported programming models, including (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). We use the GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code as of April 2023 to generate a vast amount of implementations given simple + + prompt variants. To quantify and compare the results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. Results suggest that the OpenAI Codex outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general purpose Python can benefit from adding code keywords, while Julia prompts perform acceptably well for its mature programming models (e.g., Threads and CUDA.jl). We expect for these benchmarks to provide a point of reference for each programming model's community. Overall, understanding the convergence of large language models, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

Godoy, William↗

NASA NTRS1981

Capacity, cutoff rate, and coding for a direct-detection optical channel

It is shown that when Pierce's pulse-position modulation scheme with 2 to the L power positions (where L is some positive integer) is used on a self-noise-limited direct-detection optical communication channel, there results a (2 to the L power)-ary erasure channel that is equivalent to the parallel combination of L completely correlated binary erasure channels. The capacity of the full channel is the sum of the capacities of the component channels, but the cutoff rate of the full channel is shown to be much smaller than the sum of the cutoff rates. An interpretation of the cutoff rate is given that suggests a complexity advantage in coding separately on the component channels. It is shown that if short-constraint length convolutional codes with Viterbi decoders are used on the component channels, then the performance and complexity compare favorably with the Reed-Solomon coding system proposed by McEliece (1979) for the full channel. The reasons for this unexpectedly fine performance by the convolutional code system are explored in detail, as are various facets of the channel structure.

Massey, J. L.↗

DOE OSTI2023

Roadmap on electronic structure codes in the exascale era

Electronic structure calculations have been instrumental in providing many important insights into a range of physical and chemical properties of various molecular and solid-state systems. Their importance to various fields, including materials science, chemical sciences, computational chemistry and device physics, is underscored by the large fraction of available public supercomputing resources devoted to these calculations. As we enter the exascale era, exciting new opportunities to increase simulation numbers, sizes, and accuracies present themselves. In order to realize these promises, the community of electronic structure software developers will however first have to tackle a number of challenges pertaining to the efficient use of new architectures that will rely heavily on massive parallelism and hardware accelerators. This roadmap provides a broad overview of the state-of-the-art in electronic structure calculations and of the various new directions being pursued by the community. It covers 14 electronic structure codes, presenting their current status, their development priorities over the next five years, and their plans towards tackling the challenges and leveraging the opportunities presented by the advent of exascale computing.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Local time stepping for the shallow water equations in MPAS

In this work we assess the performance of a set of local time-stepping (LTS) schemes for the shallow water equations implemented in the Model for Prediction Across Scales (MPAS). The goal of LTS is to speed up the simulation by allowing different time-steps on different regions of the computational grid. The LTS schemes considered here were originally introduced by Hoang et al. (2019) [26], who laid out the mathematical foundation of the methods. Here, the authors take on the task of presenting a fast, efficient and scalable parallel implementation of these LTS methods on high performance computing machines, with the aim to provide a recipe for other climate modeling groups that may be interested in employing LTS algorithms in their codes. As a matter of fact, even if MPAS is our framework of choice, our approach is general enough and could be of interest to other groups beyond the MPAS community. Due to their nature, LTS methods possess an inherent load imbalance that needs to be carefully addressed in order to obtain efficient scalability. Even more important is the far from trivial task of computing the right-hand side terms only on specific LTS regions during the time-stepping procedure. An inefficient handling of this task causes a drastic decay of the CPU time performance, making the LTS algorithms practically of no use. The emphasis of the present work is therefore on the computational and parallel aspects of the LTS methods, whose proper treatment is crucial to make the methods run faster against existing strategies, such as for instance high-order explicit global time-stepping schemes. This is in fact the ultimate goal of using an LTS procedure and it is the one to which we direct all our optimization efforts.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

DIF3D-VARIANT 12.0: Updates and New Features

The DIF3D code has been a workhorse of fast reactor analysis work at Argonne National Laboratory for over 40 years. In 1995, a transport option called VARIANT was added to DIF3D to improve the flux solutions for fast reactor problems which we term DIF3D-VARIANT today. DIF3D-VARIANT performs nodal neutron transport calculations using P N or SP N theory in Cartesian and hexagonal two- and three-dimensional geometries. The limited computing capabilities of the time restricted DIF3D-VARIANT to use at most a 6 th order spatial approximation combined with a P3 flux approximation and P1 scattering kernel for a 33 group structure on most studied reactor problems. Computer capabilities have increased steadily since 1995 and today much larger space-angle-energy approximations are possible. This manuscript serves as an update to the theory section of the original DIF3D-VARIANT manual and details more than twenty years of changes made to DIF3D to make version 12 which was released on November 1 st , 2024. The primary focus of the initial work was to extend the space-angle approximations available in DIF3D-VARIANT such that the error due to transport approximations could be better understood. This work was started and completed in 2002 and marked the official version 10. Unfortunately, those higher order approximations could not be used at that time due to the memory constraints of the BPOINTER part of DIF3D (limited to 2 GB). In version 11, completed in 2012, BPOINTER was circumvented in DIF3D-VARIANT for the largest arrays by introducing a Fortran 90 module called LMA (Large Memory Array). This seamlessly replaces all of the functionality of the BPOINTER concept, but it allows 64 bit addressing for every array such that they can be larger than 2 GB. It is now common for DIF3D-VARIANT jobs to consume 50 GB of memory on modern workstations when using high order space-angle approximations and a large number of groups. Many improvements were made to version 11 from 2012 to 2022 when work to create version 12 started. For version 12, several parts of DIF3D were updated to improve performance and thread parallelism was introduced to further reduce the runtime. Numerous minor bugs were discovered in DIF3D-VARIANT as part of the process of creating the perturbation and sensitivity code PERSENT. All of these algorithmic problems were identified in the transition from version 10 to version 11 which prevented DIF3D-VARIANT from running efficiently and reliably. Firstly, the coarse mesh rebalance scheme would routinely diverge and a study detailed in this report demonstrates how it was also typically not effective. This is not a failure of the coarse mesh rebalance methodology, but a failure of its implementation in DIF3D-VARIANT for hexagonal geometries. The fission source extrapolation algorithm was also found to be unreliable on larger group structure problems, leading to divergence in some cases and a negligible improvement in performance overall. Finally, the “Omega” acceleration applied to the partial current solver routine of DIF3D-VARIANT was found to cause DIF3D-VARIANT to converge to the wrong answer. To resolve these issues, both the coarse mesh rebalance and fission source extrapolation were permanently disabled in version 11. The Tchebychev acceleration was put in as a temporary reliable alternative but it is generally inferior to coarse mesh rebalance or coarse mesh finite difference. For the Omega acceleration, the factor was restricted to guarantee that it would not cause follow-on errors in PERSENT. Due to limited funding to support maintenance and development of DIF3D in the last 10 years, no effort was spent since to resolve the outer iteration acceleration. Except for the threading work, all of the changes discussed in this manuscript refer to changes made between version 10 and version 11. Performance comparisons are done to demonstrate the improvements from version 9 to version 12. As will be demonstrated, the updated versi

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2020

Quantum Dynamics at Scale: Ultrafast Control of Emergent Functional Materials

Confluence of extreme-scale quantum dynamics simulations (i.e. quantum@scale) and cutting-edge x-ray free-electron laser experiments are revolutionizing materials science. An archetypal example is the exciting concept of using picosecond light pulses to control emergent material properties on demand in atomically-thin layered materials. This paper describes efforts to scale our quantum molecular dynamics engine toward the United States' first exaflop/s computer, under an Aurora Early Science Program project named "Metascalable layered material genome". Key algorithmic and computing techniques incorporated are: (1) globally-scalable and locally-fast solvers within a linear-scaling divide-conquer-recombine algorithmic framework; (2) algebraic `BLASification' of computational kernels; and (3) data alignment and loop restructuring, along with register and cache blocking, for enhanced vectorization and efficient memory access. The resulting weak-scaling parallel efficiency was 0.93 on 131,072 Intel Xeon Phi cores for a 56.6 million atom (or 169 million valence-electron) system, whereas the various code transformations achieved 5-fold speedup. The optimized simulation engine allowed us for the first time to establish a significant effect of substrate on the dynamics of layered material upon electronic excitation.

Algebraic BLASification↗

DOE OSTI2018

Parallel Fenics Implementation of Block Solvers (pFibs)

This software is a Python package designed to act as an interface between FEniCS and PETSc to facilitate the construction and application of parallel block solvers/preconditioners. The original intent of this software was to help enable Battery and Wind Farm simulations for use on high performance computing systems. The code is written in Python and uses the petsc4py module to access the more advance features of the PETSc Krylov Solver. In essence, pFibs is an interface to make accessing these features more streamlined. Additionally, pFibs also provides a template for building custom Python based preconditioning algorithms.

Allen, Jeffery↗

DOE OSTI2023

PNNL-CompBio/BoltzmannMFX

BoltzmannMFX is a biological simulation code that solves chemical reaction networks using maximum entropy methods. It uses modules from MFiX-Exa and is based on the AMReX framework for massively parallel block-structured adaptive mesh applications.

Palmer, Bruce↗

DOE OSTI2023

ERF: Energy Research and Forecasting

The Energy Research and Forecasting (ERF) code is a new model that simulates the mesoscale and microscale dynamics of the atmosphere using the latest high-performance computing architectures. It employs hierarchical parallelism using an MPI+X model, where X may be OpenMP on multicore CPU-only systems, or CUDA, HIP, or SYCL on GPU-accelerated systems. ERF is built on AMReX (Zhang et al., 2019, 2021), a block-structured adaptive mesh refinement (AMR) software framework that provides the underlying performance-portable software infrastructure for block-structured mesh operations. The "energy" aspect of ERF indicates that the software has been developed with renewable energy applications in mind. In addition to being a numerical weather prediction model, ERF is designed to provide a flexible computational framework for the exploration and investigation of different physics parameterizations and numerical strategies, and to characterize the flow field that impacts the ability of wind turbines to extract wind energy. The ERF development is part of a broader effort led by the US Department of Energy's Wind Energy Technologies Office.

17 WIND ENERGY↗

NASA NTRS2000

A Simple Tool for the Design and Analysis of Multiple-Reflector Antennas in a Multi-Disciplinary Environment

The process of designing and analyzing a multiple-reflector system has traditionally been time-intensive, requiring large amounts of both computational and human time. At many frequencies, a discrete approximation of the radiation integral may be used to model the system. The code which implements this physical optics (PO) algorithm was developed at the Jet Propulsion Laboratory. It analyzes systems of antennas in pairs, and for each pair, the analysis can be computationally time-consuming. Additionally, the antennas must be described using a local coordinate system for each antenna, which makes it difficult to integrate the design into a multi-disciplinary framework in which there is traditionally one global coordinate system, even before considering deforming the antenna as prescribed by external structural and/or thermal factors. Finally, setting up the code to correctly analyze all the antenna pairs in the system can take a fair amount of time, and introduces possible human error. The use of parallel computing to reduce the computational time required for the analysis of a given pair of antennas has been previously discussed. This paper focuses on the other problems mentioned above. It will present a methodology and examples of use of an automated tool that performs the analysis of a complete multiple-reflector system in an integrated multi-disciplinary environment (including CAD modeling, and structural and thermal analysis) at the click of a button. This tool, named MOD Tool (Millimeter-wave Optics Design Tool), has been designed and implemented as a distributed tool, with a client that runs almost identically on Unix, Mac, and Windows platforms, and a server that runs primarily on a Unix workstation and can interact with parallel supercomputers with simple instruction from the user interacting with the client.

Katz, Daniel S.↗

NASA NTRS2003

Monte Carlo Methodology Serves Up a Software Success

Widely used for the modeling of gas flows through the computation of the motion and collisions of representative molecules, the Direct Simulation Monte Carlo method has become the gold standard for producing research and engineering predictions in the field of rarefied gas dynamics. Direct Simulation Monte Carlo was first introduced in the early 1960s by Dr. Graeme Bird, a professor at the University of Sydney, Australia. It has since proved to be a valuable tool to the aerospace and defense industries in providing design and operational support data, as well as flight data analysis. In 2002, NASA brought to the forefront a software product that maintains the same basic physics formulation of Dr. Bird's method, but provides effective modeling of complex, three-dimensional, real vehicle simulations and parallel processing capabilities to handle additional computational requirements, especially in areas where computational fluid dynamics (CFD) is not applicable. NASA's Direct Simulation Monte Carlo Analysis Code (DAC) software package is now considered the Agency s premier high-fidelity simulation tool for predicting vehicle aerodynamics and aerothermodynamic environments in rarified, or low-density, gas flows.

Source record↗

DOE OSTI2019

Increasing Software Testing Coverage and Portability with Spack

Adequate testing coverage is critical for successful scientific software development. For numerically intensive codes, the test matrix should cover a variety of machines, compilers, third-party library dependencies, as well as possible other features such as memory testing, parallelization paradigms, and application options that may be enabled or disabled, as some examples. Such coverage can be a major burden on developers without powerful methods for managing the matrix. Spack is a great tool developed by Lawrence Livermore National Lab for managing software on a Unix-based system and in addition to this, we are leveraging Spack to simplify application testing development and management. Here we demonstrate exploiting many of Spack's features to orchestrate the test coverage for the Nalu-Wind application we are developing under the Exascale Computing Project. By using Spack underneath our testing infrastructure, we have increased our testing coverage, portability, robustness, and software quality. While we use our Nalu-Wind application as an example, the benefits of exploiting Spack for application testing can be had for other applications as well.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

Targeting GPUs with OpenMP directives on Summit: A simple and effective Fortran experience

We use OpenMP to target hardware accelerators (GPUs) on Summit, a newly deployed supercomputer at the Oak Ridge Leadership Computing Facility (OLCF), demonstrating simplified access to GPU devices for users of our astrophysics code GenASiS and useful speedup on a sample fluid dynamics problem. We modify our workhorse class for data storage to include members and methods that significantly streamline the persistent allocation of and association to GPU memory. Users offload computational kernels with OpenMP target directives that are rather similar to constructs already familiar from multi-core parallelization. In this initial example we ask, “With a given number of Summit nodes, how fast can we compute with and without GPUs?”, and find total wall time speedups of ~ 12X. We also find reasonable weak scaling up to 8000 GPUs (1334 Summit nodes). We make available the source code from this work at https://github.com/GenASiS/GenASiS_Basics.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2004

NASA Multidimensional Stirling Convertor Code Developed

A high-efficiency Stirling Radioisotope Generator (SRG) for use on potential NASA Space Science missions is being developed by the Department of Energy, Lockheed Martin, Stirling Technology Company, and the NASA Glenn Research Center. These missions may include providing spacecraft onboard electric power for deep space missions or power for unmanned Mars rovers. Glenn is also developing advanced technology for Stirling convertors, aimed at substantially improving the specific power and efficiency of the convertor and the overall power system. Performance and mass improvement goals have been established for second- and third-generation Stirling radioisotope power systems. Multiple efforts are underway to achieve these goals, both in house at Glenn and under various grants and contracts. These efforts include the development of a multidimensional Stirling computational fluid dynamics code, high-temperature materials, advanced controllers, an end-to-end system dynamics model, low-vibration techniques, advanced regenerators, and a lightweight convertor. Under a NASA grant, Cleveland State University (CSU) and its subcontractors, the University of Minnesota (UMN) and Gedeon Associates, have developed a twodimensional computer simulation of a CSUmod Stirling convertor. The CFD-ACE commercial software developed by CFD Research Corp. of Huntsville, Alabama, is being used. The CSUmod is a scaled version of the Stirling Technology Demonstrator Convertor (TDC), which was designed and fabricated by the Stirling Technology Company and is being tested by NASA. The schematic illustrates the structure of this model. Modeled are the fluid-flow and heat-transfer phenomena that occur in the expansion space, the heater, the regenerator, the cooler, the compression space, the surrounding walls, and the moving piston and displacer. In addition, the overall heat transfer, the indicated power, and the efficiency can be calculated. The CSUmod model is being converted to a two-dimensional model of the TDC at NASA Glenn. Validation of the multidimensional Stirling code is an important part of the grant effort. UMN has been generating data in an oscillating-flow test facility using two different test sections: a 90 turn and a cooler/regenerator/heater test section. CSU has created computational fluid dynamics models of both these test sections and has been making comparisons with the data, then improving their models to improve the agreement with the test data. CSU has also been using data available in the literature for code validation. UMN is now preparing to begin fabrication of a new 180 turn test section that will be more representative of certain portions of the Stirling engine geometry. Simulations to almost periodic steady state with the two-dimensional CSUmod model indicate that, to reach periodic steady state on a single 2-GHz desktop computer, 75 to 100 complete simulation cycles would be required and between 1 and 2 months of computer time. Therefore, Glenn has purchased the first 8 computers, of a 64-computer cluster, to be run in parallel to accelerate the simulation. On the basis of CFD Research Corp.'s experience with running the parallelized version of CFD-ACE on their clusters, we estimate that the complete 64-computer cluster will reduce simulation computing time by a factor of about 40. Plans are to continue development of these multidimensional Stirling codes and to use them to study the fluid-flow and heat-transfer phenomena that occur inside Stirling convertors. This is expected to lead to improved thermodynamic loss understanding, onedimensional design and performance codes, and engine performance.

Tew, Roy C.↗

DOE OSTI2024

A Generalized Nuclear Code of Accounts for Cost Estimation Standardization

This is a joint INL-EPRI study. Link to corresponding page at the Electric Power Research Institute (EPRI): https://www.epri.com/research/products/000000003002028937 Recent Advanced Reactor (AR) designs typically offer features and attributes that depart from traditional water-cooled reactors in terms of fuel forms, coolants, structural materials, size, safety margins, and other important design and operational aspects. These departures, relative to the industry experience, will likely present a challenge for potential owner-operators when evaluating one or more AR designs for commercial deployment on a like-for-like basis. This is further exacerbated with new classes of reactors gaining prominence (e.g., microreactors) and new emerging applications (e.g., floating barge reactors or space propulsion reactors). The differences in design-specific technologies are compounded by the differences in approach to cost estimation. The lack of consistency in build up toward cost estimates creates a challenge when comparing competing concepts and evaluating their associated cost drivers. The outcome of a 2019 Scoping Study conducted by the Electric Power Research Institute (EPRI) indicated the need for a cost modeling guide (CMG), which would be underpinned by a technology-neutral and inclusive Generalized Nuclear Code of Accounts (GN-COA). A code of accounts (COA) is a tool by which costs are identified in even more specific categories, providing clarity on what specific costs are included in an estimate. A parallel independent effort was meanwhile taking place at Idaho National Laboratory via funding by the Systems Analysis Integration (SA&I) campaign of the Office of Nuclear Energy under the U.S. Department of Energy (U.S. DOE-NE) to also update the COA structure to enable more flexibility and encompass a wider variety of reactor technologies. After being made aware of these synergistic efforts, the two parties decided to combine efforts and develop a joint new standard format for nuclear cost estimation that builds on previous structures. This document describes the development of this joint GN-COA and provides guidance on the implementation of the tool, which is provided as the associated GN-COA Excel document. The main attributes of this novel COA format are that all items are functionally defined (in order to be technology and application agnostic) and grouped into logical arrangements that facilitate the tabulation of costs for reactor constructions under consideration. The intent is for the GN-COA to form a standard that is endorsed by future vendors and customers.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2020

MBMS1.0: An Open-Source Code for Modeling and Simulation of Membrane-Based Dehumidification and Energy Recovery

Membrane-based dehumidification is currently being considered as a promising solution for the building application due to its low cost and very limited energy consumption. Developing a simple and efficient open-source code simulation tool is important for boosting the optimization and evaluation of such device in HVAC community. This paper reports a first-order physics based model which accounts for the fundamental heat and mass transfer of humid-air vapor at feed side to flow stream at permeate side. The current model comprises two membrane mass transfer submodels (i.e. microstructure model and performance map model); and it adopts a segment-by-segment methodology for discretizing heat and mass transfer governing equations. The model is capable of simulating both dehumidifiers and energy recovery ventilators with parallel-flow cross-flow, and counter-flow configurations. The model was validated with the measurements at appropriate device. The practices in dehumidification and energy recovery exchangers are also discussed. The model and open-source codes are expected to become a solid fundament for developing a more comprehensive and accurate membrane-based dehumidification in the future.

Gao, Zhiming↗

DOE OSTI2018

Parallelizable adjoint stencil computations using transposed forward-mode algorithmic differentiation

Algorithmic differentiation (AD) is a tool for generating discrete adjoint solvers, which efficiently compute gradients of functions with many inputs, for example for use in gradient-based optimization. AD is often applied to large computations such as stencil operators, which are an important part of most structured-mesh PDE solvers. Stencil computations are often parallelized, for example by using OpenMP, and optimized by using techniques such as cache-blocking and tiling to fully utilize multicore CPUs and many-core accelerators and GPUs. Differentiating these codes with conventional reverse-mode AD results in adjoint codes that cannot be expressed as stencil operations and may not be easily parallelizable. They thus leave most of the compute power of modern architectures unused. We present a method that combines forward-mode AD and loop transformation to generate adjoint solvers that use the same memory access pattern as the original computation that they are derived from and can benefit from the same optimization techniques. The effectiveness of this method is demonstrated by generating a scalable adjoint CFD solver for multicore CPUs and Xeon Phi accelerators.

algorithmic differentiation↗

NASA NTRS1994

Applications Performance Under MPL and MPI on NAS IBM SP2

On July 5, 1994, an IBM Scalable POWER parallel System (IBM SP2) with 64 nodes, was installed at the Numerical Aerodynamic Simulation (NAS) Facility Each node of NAS IBM SP2 is a "wide node" consisting of a RISC 6000/590 workstation module with a clock of 66.5 MHz which can perform four floating point operations per clock with a peak performance of 266 Mflop/s. By the end of 1994, 64 nodes of IBM SP2 will be upgraded to 160 nodes with a peak performance of 42.5 Gflop/s. An overview of the IBM SP2 hardware is presented. The basic understanding of architectural details of RS 6000/590 will help application scientists the porting, optimizing, and tuning of codes from other machines such as the CRAY C90 and the Paragon to the NAS SP2. Optimization techniques such as quad-word loading, effective utilization of two floating point units, and data cache optimization of RS 6000/590 is illustrated, with examples giving performance gains at each optimization step. The conversion of codes using Intel's message passing library NX to codes using native Message Passing Library (MPL) and the Message Passing Interface (NMI) library available on the IBM SP2 is illustrated. In particular, we will present the performance of Fast Fourier Transform (FFT) kernel from NAS Parallel Benchmarks (NPB) under MPL and MPI. We have also optimized some of Fortran BLAS 2 and BLAS 3 routines, e.g., the optimized Fortran DAXPY runs at 175 Mflop/s and optimized Fortran DGEMM runs at 230 Mflop/s per node. The performance of the NPB (Class B) on the IBM SP2 is compared with the CRAY C90, Intel Paragon, TMC CM-5E, and the CRAY T3D.

Saini, Subhash↗