Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Memory benchmark”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Verification and Validation of the ENDF/B-VII.1 v4.3m1 MPACT 51-Group Cross Section Library

The MPACT neutronics module of the Consortium for Advanced Simulation of Light Water Reactors (CASL) core simulator is a 3-D whole core transport code being developed for the Virtual Environment for Reactor Analysis (VERA) CASL toolset. Key characteristics of the MPACT code include (1) a subgroup method for resonance selfshielding and (2) a whole-core transport solver with a 2-D/1-D synthesis method. The MPACT code requires a cross section library to support all of its core simulation capabilities; a cross section library would be MPACT’s most influencing component for simulation accuracy. Due to the limitation of computing capacity even in high performance computing, the cross section library must be developed to enhance computational efficiency in memory and computing time without losing accuracy and generality. This requires a very coarse energy group structure with about 50 groups. Multigroup (MG) neutron cross section libraries for the CASL VERA-CS neutronics simulator MPACT have been created by using the AMPX/SCALE code package developed at Oak Ridge National Laboratory (ORNL). A new 51-group structure was developed for efficient simulation to be applicable for both pressurized water reactor (PWR) and boiling water reactor (BWR) simulations. New v4.3m1 MPACT 51-group library with the ENDF/B- VII.1 nuclear data were developed for MPACT. Since SCALE KENO has some issues in the probability table and has a low cutoff energy for the free gas model, this issue has been corrected. This study focused on the development of the ENDF/B-VII.1 v4.3m1 MPACT MG library, including verification and validation. This document includes the library generation methodology and procedure, the verification procedure, and benchmark results compared to continuous energy Monte Carlo results using newly developed cross section libraries.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
NASA NTRS2011

Interplanetary Overlay Network Bundle Protocol Implementation

The Interplanetary Overlay Network (ION) system's BP package, an implementation of the Delay-Tolerant Networking (DTN) Bundle Protocol (BP) and supporting services, has been specifically designed to be suitable for use on deep-space robotic vehicles. Although the ION BP implementation is unique in its use of zero-copy objects for high performance, and in its use of resource-sensitive rate control, it is fully interoperable with other implementations of the BP specification (Internet RFC 5050). The ION BP implementation is built using the same software infrastructure that underlies the implementation of the CCSDS (Consultative Committee for Space Data Systems) File Delivery Protocol (CFDP) built into the flight software of Deep Impact. It is designed to minimize resource consumption, while maximizing operational robustness. For example, no dynamic allocation of system memory is required. Like all the other ION packages, ION's BP implementation is designed to port readily between Linux and Solaris (for easy development and for ground system operations) and VxWorks (for flight systems operations). The exact same source code is exercised in both environments. Initially included in the ION BP implementations are the following: libraries of functions used in constructing bundle forwarders and convergence-layer (CL) input and output adapters; a simple prototype bundle forwarder and associated CL adapters designed to run over an IPbased local area network; administrative tools for managing a simple DTN infrastructure built from these components; a background daemon process that silently destroys bundles whose time-to-live intervals have expired; a library of functions exposed to applications, enabling them to issue and receive data encapsulated in DTN bundles; and some simple applications that can be used for system checkout and benchmarking.

Burleigh, Scott C.↗
DOE OSTI2024

Developing And Scaling an OpenFOAM Model to Study Turbulent Flow in a HFIR Coolant Channel

Improving the understanding of how computational fluid dynamics (CFD) direct numerical simulations (DNS) of flows in the High Flux Isotope Reactor (HFIR) perform when run in parallel using the high performance computing (HPC) platform Summit at the Oak Ridge Leadership Computing Facility (OLCF) is of particular importance to boost the computational tools used to support HFIR conversion to low enriched fuel (LEU). Evaluation of scaling performance was driven by the increasing importance of graphics processing unit (GPU) usage in HPC, which is becoming the standard for modern supercomputers such as Summit. The desired results are to obtain a strong positive correlation between the computational resources dedicated to a problem and the relative speed-up of the simulation in comparison to a benchmark. This capability will allow substantially improvement in HFIR flow analytical capabilities, specifically when predicting turbulence properties at high Reynolds numbers. The study leverages previous simulation results performed with code PHASTA (finite element) on HPC platforms Cori (NERSC) and Theta (ALCF) [1] with computing options provided in the computing platform OpenFOAM (finite volume) at OLCF. Transitioning from PHASTA to OpenFOAM will (1) eliminate dependence on third-party software for mesh generation and manipulation, (2) reduce resource needs by employing modern architectures, and (3) build expertise for future modeling of HFIR-specific problems like heat transfer in involute geometry, entrance effects, flow structure in channel corners, and so on—all important issues when defining the available thermal margins in the transition to LEU. CPUs and GPUs differ significantly in their architecture and utilization, as discussed in the literature [2]. The most important differences are in the approach to computations and their memory. A single GPU contains a large quantity of cores, enabling it to perform with a much higher throughput than a CPU, but execution requires a different approach. GPU codes execute instructions using the Single-Instruction Multiple-Thread (SIMT) approach in which a single instruction is used for groups of threads called warps. A warp typically consists of 32 threads which must execute the same set of instructions, although on separate threads. Alternately, a CPU has far fewer cores that are much more flexible in their operation, excelling at quickly performing more complex serial computations. This is why GPUs have greater throughput when properly utilized. The second important difference is seen when comparing their memory spaces. Limited memory allocations and CPU–GPU communications cause a significant bottleneck in GPU-accelerated programs. Further study was required to properly take advantage of GPU resources. A comprehensive analysis of code performance and the model-specific features of turbulence constitutes the core of this work. In this study, a DNS simulation of HFIR channel turbulence was performed with the finite volume CFD code OpenFOAM v2112 and CUDA v11.0 on Red Hat Enterprise Linux v8.2. The OpenFOAM installation had AMGx integrated to enable GPU acceleration and utilizes the PETSc4FOAM library. The computational resources and the problem size were scaled on CPU and CPU + GPU architectures to gain a better understanding of the performance of a DNS problem on modern computing hardware. The study aimed to analyze the scaling of the code exclusively on CPUs and then to examine the scaling of the codes with GPU acceleration enabled. Scaling studies included CPU and GPU acceleration on a mesh of varying resolution to analyze the impact of problem size relative to computational resources. In the course of preparing the GPU configuration on Summit, mainly using the AMGX solvers, difficulties were encountered stemming from constant changes resulting from extensive ongoing development activities and the changing environment. This resulted in the inability to complete the GPU portion of the work. The code was compiled and tested, but production runs to assess acceleration were not performed because the used discretional compute time allocation expired as year-end approached. The Summit HPC platform is scheduled for decommissioning in 2024, making it unattractive for future use with Nvidia-based GPUs. Therefore, the work will be moved onto NERSC machines in FY24. An application was prepared and submitted, and sufficient node-hours were awarded to continue the research in the next calendar year. This report summarizes work performed thus far, which mostly focused on CPU OpenFOAM computing.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2018

Reduced scaling CASPT2 using supporting subspaces and tensor hyper-contraction

Here, we present a reduced scaling formulation of the state specific complete active space second-order perturbation method (CASPT2) requiring O( N 4 ) operations and O( N 2 ) memory for a fixed active space, where N is proportional to system size. Motivated by the properties of the Kronecker sum, we introduce the supporting subspace technique (SST), which decomposes the CASPT2 linear equations into two parts: a single-reference MP2 energy term using dressed orbitals, plus a reduced linear system with dimension scaling as O( N 2 ). Together with Laplace quadrature, the SST allows us to reformulate CASPT2 using a MP2 energy computation and Fock builds. By further applying the tensor hyper-contraction (THC) approximation, the MP2-like term can be computed with O( N 4 ) operations, and the remainder can be solved with O( N 3 ) operations using the preconditioned conjugate gradient method. This is the first application of THC in the context of multi-reference methods. We also developed an efficient implementation of the method by utilizing graphical processing units and exploiting spatial sparsity in tensor operations. We benchmark the accuracy of the new method against conventional CASPT2 for reactions in the gas phase. We apply the new method to Menshutkin S N 2 reactions in carbon nanotubes, demonstrating the feasibility of CASPT2 calculations with O(100) atoms.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2019

RoCE: Promising Technology for Ethernet as a High Performance Networking Fabric

Remote Direct Memory Access (RDMA) over Converged Ethernet (RoCE) has the potential to provide performance that rivals traditional high performance fabrics. If this potential proves out, significant impacts on system procurement decisions could follow. This work provides a series of small scale performance results which are used to compare and contrast the performance of RoCE-enabled Ethernet with TCP-based Ethernet and an HPC network. Additionally, a discussion of the maturity of RoCE firmware/software stacks and documentation is provided along with useful approaches for probing performance. A detailed description of two experimental setups known to have good RoCE performance is given, including step-by-step configuration and the exact hardware and software revisions employed. At small scales, RoCE is found to have significant performance advantages over "out-of-the-box" TCP protocols and is competitive with state-of-the-art high performance networks. Further examination of RoCE using a wider array of benchmarks and at greater scale is warranted.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

A Privacy Preserving Model-Free Optimization and Control Framework for Demand Response from Residential Thermal Loads

We consider the problem of optimizing the cost of procuring electricity for a large collection of homes managed by a load serving entity, by pre-cooling or pre-heating the thermal inertial loads in the homes to avoid procuring power during periods of peak electricity pricing. We would like to accomplish this objective in a completely privacy-preserving and model-free manner, that is, without direct access to the state variables (temperatures or power consumption) or the dynamical models (thermal characteristics) of individual homes, while guaranteeing personal comfort constraints of the consumers. We propose a two-stage optimization and control framework to address this problem. In the first stage, we use a long short-term memory (LSTM) network to predict hourly electricity prices, based on historical pricing data and weather forecasts. Given the hourly price forecast and thermal models of the homes, the problem of designing an optimal power consumption trajectory that minimizes the total electricity procurement cost for the collection of thermal loads can be formulated as a large-scale integer program (with millions of variables) due to the on-off cyclical dynamics of such loads. We provide a simple heuristic relaxation to make this large-scale optimization problem model-free and computationally tractable. In the second stage, we translate the results of this optimization problem into distributed open-loop control laws that can be implemented at individual homes without measuring or estimating their state variables, while simultaneously ensuring consumer comfort constraints. We demonstrate the performance of this approach on a large-scale test case comprising of 500 homes in the Houston area and benchmark its performance against a direct model-based optimization and control solution.

Sivaranjani, S.↗
DOE OSTI2023

XploreNAS : Explore Adversarially Robust and Hardware-efficient Neural Architectures for Non-ideal Xbars

Compute In-Memory platforms such as memristive crossbars are gaining focus as they facilitate acceleration of Deep Neural Networks (DNNs) with high area and compute efficiencies. However, the intrinsic non-idealities associated with the analog nature of computing in crossbars limits the performance of the deployed DNNs. Furthermore, DNNs are shown to be vulnerable to adversarial attacks leading to severe security threats in their large-scale deployment. Thus, finding adversarially robust DNN architectures for non-ideal crossbars is critical to the safe and secure deployment of DNNs on the edge. This work proposes a two-phase algorithm-hardware co-optimization approach called XploreNAS that searches for hardware efficient and adversarially robust neural architectures for non-ideal crossbar platforms. We use the one-shot Neural Architecture Search approach to train a large Supernet with crossbar-awareness and sample adversarially robust Subnets therefrom, maintaining competitive hardware efficiency. Our experiments on crossbars with benchmark datasets (SVHN, CIFAR10, CIFAR100) show up to ~8–16% improvement in the adversarial robustness of the searched Subnets against a baseline ResNet-18 model subjected to crossbar-aware adversarial training. We benchmark our robust Subnets for Energy-Delay-Area-Products (EDAPs) using the Neurosim tool and find that with additional hardware efficiency–driven optimizations, the Subnets attain ~1.5–1.6× lower EDAPs than ResNet-18 baseline.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1994

Automated Instrumentation, Monitoring and Visualization of PVM Programs Using AIMS

We present views and analysis of the execution of several PVM (Parallel Virtual Machine) codes for Computational Fluid Dynamics on a networks of Sparcstations, including: (1) NAS Parallel Benchmarks CG and MG; (2) a multi-partitioning algorithm for NAS Parallel Benchmark SP; and (3) an overset grid flowsolver. These views and analysis were obtained using our Automated Instrumentation and Monitoring System (AIMS) version 3.0, a toolkit for debugging the performance of PVM programs. We will describe the architecture, operation and application of AIMS. The AIMS toolkit contains: (1) Xinstrument, which can automatically instrument various computational and communication constructs in message-passing parallel programs; (2) Monitor, a library of runtime trace-collection routines; (3) VK (Visual Kernel), an execution-animation tool with source-code clickback; and (4) Tally, a tool for statistical analysis of execution profiles. Currently, Xinstrument can handle C and Fortran 77 programs using PVM 3.2.x; Monitor has been implemented and tested on Sun 4 systems running SunOS 4.1.2; and VK uses XIIR5 and Motif 1.2. Data and views obtained using AIMS clearly illustrate several characteristic features of executing parallel programs on networked workstations: (1) the impact of long message latencies; (2) the impact of multiprogramming overheads and associated load imbalance; (3) cache and virtual-memory effects; and (4) significant skews between workstation clocks. Interestingly, AIMS can compensate for constant skew (zero drift) by calibrating the skew between a parent and its spawned children. In addition, AIMS' skew-compensation algorithm can adjust timestamps in a way that eliminates physically impossible communications (e.g., messages going backwards in time). Our current efforts are directed toward creating new views to explain the observed performance of PVM programs. Some of the features planned for the near future include: (1) ConfigView, showing the physical topology of the virtual machine, inferred using specially formatted IP (Internet Protocol) packets: and (2) LoadView, synchronous animation of PVM-program execution and resource-utilization patterns.

Mehra, Pankaj↗
NASA NTRS1994

Automated Instrumentation, Monitoring and Visualization of PVM Programs Using AIMS

We present views and analysis of the execution of several PVM codes for Computational Fluid Dynamics on a network of Sparcstations, including (a) NAS Parallel benchmarks CG and MG (White, Alund and Sunderam 1993); (b) a multi-partitioning algorithm for NAS Parallel Benchmark SP (Wijngaart 1993); and (c) an overset grid flowsolver (Smith 1993). These views and analysis were obtained using our Automated Instrumentation and Monitoring System (AIMS) version 3.0, a toolkit for debugging the performance of PVM programs. We will describe the architecture, operation and application of AIMS. The AIMS toolkit contains (a) Xinstrument, which can automatically instrument various computational and communication constructs in message-passing parallel programs; (b) Monitor, a library of run-time trace-collection routines; (c) VK (Visual Kernel), an execution-animation tool with source-code clickback; and (d) Tally, a tool for statistical analysis of execution profiles. Currently, Xinstrument can handle C and Fortran77 programs using PVM 3.2.x; Monitor has been implemented and tested on Sun 4 systems running SunOS 4.1.2; and VK uses X11R5 and Motif 1.2. Data and views obtained using AIMS clearly illustrate several characteristic features of executing parallel programs on networked workstations: (a) the impact of long message latencies; (b) the impact of multiprogramming overheads and associated load imbalance; (c) cache and virtual-memory effects; and (4significant skews between workstation clocks. Interestingly, AIMS can compensate for constant skew (zero drift) by calibrating the skew between a parent and its spawned children. In addition, AIMS' skew-compensation algorithm can adjust timestamps in a way that eliminates physically impossible communications (e.g., messages going backwards in time). Our current efforts are directed toward creating new views to explain the observed performance of PVM programs. Some of the features planned for the near future include: (a) ConfigView, showing the physical topology of the virtual machine, inferred using specially formatted IP (Internet Protocol) packets; and (b) LoadView, synchronous animation of PVM-program execution and resource-utilization patterns.

Mehra, Pankaj↗
DOE OSTI2018

SharP Data Constructs: Data Constructs to Enable Data-Centric Computing

Extreme-scale applications (i.e., Big-Compute) are becoming increasingly data-intensive, i.e., producing and consuming increasingly large amounts of data. The HPC systems traditionally used for these applications are now used for Big-Data applications such as data analytics, social network analysis, machine learning, and genomics. As a consequence of these trends, the system architecture should be flexible and data-centric. This can already be witnessed in the pre-exascale systems with TBs of on-node hierarchical and heterogeneous memories, PBs of system memory, low-latency, high-throughput networks, and many threaded cores. As such, the pre-exascale systems suit the needs of both Big-Compute and Big-Data applications. Though the system architecture is flexible enough to support both Big-Compute and Big-Data, we argue there is a software gap. Particularly, we need data-centric abstractions to leverage the full potential of the system, i.e., there is a need for native support for data resilience, the ability to express data locality and affinity, mechanisms to reduce data movement, the ability to share data, and abstractions to express User's data usage and data access patterns. In this paper, we (i) show the need for taking a holistic approach towards data-centric abstractions, (ii) show how these approaches were realized in the SHARed data-structure centric Programming abstraction (SharP) library, a data-structure centric programming abstraction, and (iii) apply these approaches to a variety of applications that demonstrate its usefulness. Particularly, we apply these approaches to QMCPack and the Graph500 benchmark and demonstrate the advantages of this approach on extreme-scale systems.

Aderholdt, William Ferrol↗
NASA NTRS2001

Development of a Hybrid RANS/LES Method for Turbulent Mixing Layers

Significant research has been underway for several years in NASA Glenn Research Center's nozzle branch to develop advanced computational methods for simulating turbulent flows in exhaust nozzles. The primary efforts of this research have concentrated on improving our ability to calculate the turbulent mixing layers that dominate flows both in the exhaust systems of modern-day aircraft and in those of hypersonic vehicles under development. As part of these efforts, a hybrid numerical method was recently developed to simulate such turbulent mixing layers. The method developed here is intended for configurations in which a dominant structural feature provides an unsteady mechanism to drive the turbulent development in the mixing layer. Interest in Large Eddy Simulation (LES) methods have increased in recent years, but applying an LES method to calculate the wide range of turbulent scales from small eddies in the wall-bounded regions to large eddies in the mixing region is not yet possible with current computers. As a result, the hybrid method developed here uses a Reynolds-averaged Navier-Stokes (RANS) procedure to calculate wall-bounded regions entering a mixing section and uses a LES procedure to calculate the mixing-dominated regions. A numerical technique was developed to enable the use of the hybrid RANS-LES method on stretched, non-Cartesian grids. With this technique, closure for the RANS equations is obtained by using the Cebeci-Smith algebraic turbulence model in conjunction with the wall-function approach of Ota and Goldberg. The LES equations are closed using the Smagorinsky subgrid scale model. Although the function of the Cebeci-Smith model to replace all of the turbulent stresses is quite different from that of the Smagorinsky subgrid model, which only replaces the small subgrid turbulent stresses, both are eddy viscosity models and both are derived at least in part from mixing-length theory. The similar formulation of these two models enables the RANS and LES equations to be solved with a single solution scheme and computational grid. The hybrid RANS-LES method has been applied to a benchmark compressible mixing layer experiment in which two isolated supersonic streams, separated by a splitter plate, provide the flows to a constant-area mixing section. Although the configuration is largely two dimensional in nature, three-dimensional calculations were found to be necessary to enable disturbances to develop in three spatial directions and to transition to turbulence. The flow in the initial part of the mixing section consists of a periodic vortex shedding downstream of the splitter plate trailing edge. This organized vortex shedding then rapidly transitions to a turbulent structure, which is very similar to the flow development observed in the experiments. Although the qualitative nature of the large-scale turbulent development in the entire mixing section is captured well by the LES part of the current hybrid method, further efforts are planned to directly calculate a greater portion of the turbulence spectrum and to limit the subgrid scale modeling to only the very small scales. This will be accomplished by the use of higher accuracy solution schemes and more powerful computers, measured both in speed and memory capabilities.

Georgiadis, Nicholas J.↗
DOE OSTI2025

Direct numerical simulations for hybrid rocket boundary layers: Performance modeling and scaling

This paper presents a comprehensive performance and scaling analysis of direct numerical simulations for reacting boundary layers, focusing on slab burner configurations. Using a PETSc-based finite volume CFD framework, the study evaluates the scalability and computational cost of flow, chemistry, and radiation evaluations across 2D and 3D simulations. Polymethyl methacrylate (PMMA) is the fuel with pure O 2 as the oxidizer, modeled using a detailed chemical kinetics mechanism with 113 species and 660 reactions. A ray-tracing-based radiation solver, designed for distributed memory applications, is implemented to model radiation heat transfer. Parallel scalability is analyzed for the coupled flow, chemistry, and radiation heat transfer processes. Weak and strong scaling studies are conducted on up to 15,000 computational ranks, revealing robust performance when flow cells exceed 200 per rank. Chemistry evaluations dominate the computational cost in large 3D simulations, accounting for approximately 40% of the total runtime, while flow processes contribute around 35%, and radiation solver contributions remain below 10% due to reduced evaluation frequencies. GPU accelerated chemistry evaluation, implemented with Zero-RK, demonstrates significant promise, achieving up to a 4x speedup for workloads exceeding 30,000 cells per GPU. However, diminishing returns are observed for smaller workloads due to CPU-GPU communication overhead. This study identifies key challenges, including memory bottlenecks and the effects of domain partitioning on flow scalability, while highlighting the potential of GPU-accelerated chemistry to reduce computational costs. In conclusion, these findings provide realizable run configurations for 2D, 3D, and GPU-accelerated cases, offering insights for optimizing reactive flow solvers.

CFD Scalability↗
DOE OSTI2025

Experiences with SYCL on AMD GPUs with Kokkos

With the recent diversification of the hardware landscape in the high-performance computing (HPC) community, performance-portability solutions are becoming more and more important. One of the most popular choices is Kokkos, which recently became a Linux Foundation project. Most of its development is supported by the US Department of Energy and the French Alternative Energies and Atomic Energy Commission. Kokkos is implemented as a C++ library with multiple backends to support CPUs as well as various GPU architectures. These backends include OpenMP, CUDA, HIP, and also SCYL. This approach enables users to leverage the preferred vendor toolchain for the respective platform (e.g. CUDA, ROCm, OneAPI). The SYCL backend is used to target Intel GPUs, in particular to support the Aurora exascale supercomputer. However, SYCL itself also offers a large degree of portability, and in fact Kokkos’ CI for SYCL has been running on NVIDIA hardware due to a lack of access to Intel GPUs. In this report, we describe our experience with using Kokkos SYCL backend on AMD GPUs targeting the Frontier supercomputer at Oak Ridge National Laboratory. The two major SYCL implementations are DPC++ and AdaptiveCpp. While the Kokkos SYCL backend has been implemented using the former, the latter was the first implementation to target AMD GPUs. We will discuss the experience with both of these SYCL implementations in terms of functionality and performance. Using Kokkos to evaluate SYCL toolchains has a number of benefits. Kokkos’ use of SYCL is fairly complex, exercising features such as graphs, relocatable device functions, atomics – including for non-arithmetic types, as well as pinned and page migratable memory allocations. Kokkos also needs to implement capabilities such as Kokkos’ hierarchical parallelism that are not a straight-forward mapping to SYCL capabilities. Furthermore, a large number of libraries and applications that represent diverse use cases are implemented in Kokkos, providing readily available test cases for a toolchain evaluation. Preliminary results show that support for AMD GPUs in DPC++ is much less mature than for NVIDIA GPUs or Intel GPUs. While the situation has improved significantly over the last year, we still encounter many runtime failures, dispatching problems, and code generation issues. With AdaptiveCpp the challenges arise even earlier in the evaluation process. Since Kokkos’ SYCL implementation is largely focused on supporting Intel GPUs, we opted to leverage SYCL extensions which are available in DPC++ but not in AdaptiveCpp. Furthermore, AdaptiveCpp appears to be less conformant with the SYCL2020 standard which Kokkos relies on. In some cases, we are able to work around the lack of feature support, in other cases we have to disable certain Kokkos capabilities to evaluate the toolchain. Our evaluation will leverage Kokkos’ unit tests to establish basic functionality and feature completeness. We then use simple benchmarks for components of a CG implementation as a measure of usability and performance of the SYCL toolchains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Performance improvements of the windowed multipole formalism using a rational fraction approximation of the Faddeeva function

The windowed multipole (WMP) formalism was introduced as a way to calculate Doppler broadened cross sections on the fly during Monte Carlo simulations. While more arithmetic is needed compared to point-wise cross section look-ups, performance remained competitive from the large memory reductions and sequential data access. The single most expensive function call in a depleted fuel assembly problem using WMP comes from the evaluation of the Faddeeva function, which previously relied on a highly accurate, highly-branching algorithm. This paper explores the use of rational fraction approximations tailored to the domain interest of reactor physics applications and the development of lower accuracy approximations sufficient for our application. The rational approximations were implemented and tested in OpenMC on an infinite medium problem to stress the cross section calculation routine and a PWR assembly problem. In both cases, the rational approximation nearly eliminated the ∼ 20% penalty previously observed when comparing to point-wise libraries. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

A graphics processing unit accelerated sparse direct solver and preconditioner with block low rank compression

We present the GPU implementation efforts and challenges of the sparse solver package STRUMPACK. The code is made publicly available on github with a permissive BSD license. STRUMPACK implements an approximate multifrontal solver, a sparse LU factorization which makes use of compression methods to accelerate time to solution and reduce memory usage. Multiple compression schemes based on rank-structured and hierarchical matrix approximations are supported, including hierarchically semi-separable, hierarchically off-diagonal butterfly, and block low rank. Here, in this paper, we present the GPU implementation of the block low rank (BLR) compression method within a multifrontal solver. Our GPU implementation relies on highly optimized vendor libraries such as cuBLAS and cuSOLVER for NVIDIA GPUs, rocBLAS and rocSOLVER for AMD GPUs and the Intel oneAPI Math Kernel Library (oneMKL) for Intel GPUs. Additionally, we rely on external open source libraries such as SLATE (Software for Linear Algebra Targeting Exascale), MAGMA (Matrix Algebra on GPU and Multi-core Architectures), and KBLAS (KAUST BLAS). SLATE is used as a GPU-capable ScaLAPACK replacement. From MAGMA we use variable sized batched dense linear algebra operations such as GEMM, TRSM and LU with partial pivoting. KBLAS provides efficient (batched) low rank matrix compression for NVIDIA GPUs using an adaptive randomized sampling scheme. The resulting sparse solver and preconditioner runs on NVIDIA, AMD and Intel GPUs. Interfaces are available from PETSc, Trilinos and MFEM, or the solver can be used directly in user code. We report results for a range of benchmark applications, using the Perlmutter system from NERSC, Frontier from ORNL, and Aurora from ALCF. For a high frequency wave equation on a regular mesh, using 32 Perlmutter compute nodes, the factorization phase of the exact GPU solver is about 6.5× faster compared to the CPU-only solver. The BLR-enabled GPU solver is about 13.8× faster than the CPU exact solver. For a collection of SuiteSparse matrices, the STRUMPACK exact factorization on a single GPU is on average 1.9× faster than NVIDIA’s cuDSS solver.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

An investigation on machine learning predictive accuracy improvement and uncertainty reduction using VAE-based data augmentation

The confluence of ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and the availability of large datasets place multiple engineering fields at the threshold of dramatic progress. However, a unique challenge in nuclear engineering is data scarcity because experimentation on nuclear systems is usually more expensive and time-consuming than most other disciplines. One potential way to resolve the data scarcity issue is deep generative learning, which uses certain ML models to learn the underlying distribution of existing data and generate synthetic samples that resemble the real data. In this way, one can significantly expand the dataset to train more accurate predictive ML models. In this study, our objective is to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. We investigated whether the data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, the DNN prediction uncertainties are quantified using Bayesian Neural Networks (BNN) and conformal prediction (CP) to assess the impact on predictive uncertainty reduction. To test the proposed methodology, we used TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. Here, we found that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved the prediction confidence intervals, and reduced the prediction uncertainties.

Bayesian neural network↗
DOE OSTI2018

A Weighted Least-Squares Transport Equation Compatible with Source Iteration and Voids

We present that second-order forms of the transport equation allow the use of continuous finite elements (CFEMs). This can be desired in multiphysics calculations where other physics require CFEM discretizations. Second-order transport operators are generally self-adjoint, yielding symmetric positive-definite (SPD) matrices, which allow the use of efficient linear algebra solvers with an enormous advantage in memory usage. Least-squares (LS) forms of the transport equation can circumvent the void problems of other second-order forms but are almost always nonconservative. Additionally, the standard LS form is not compatible with discrete ordinates method (SN) iterative solution techniques such as source iteration. A new form of the LS transport equation has recently been developed that is compatible with voids and standard SN iterative solution techniques. Performing nonlinear diffusion acceleration (NDA) using an independently differenced low-order equation enforces conservation for the whole system and makes this equation suitable for reactor physics calculations. In this context, “independent” means that both the transport and low-order solutions converge to the same scalar flux and current as the spatial mesh is refined, but for a given mesh, the solutions are not necessarily equal. In this paper we show that introducing a weight function into this LS equation improves issues with causality and can render our equation equal to the self-adjoint angular flux (SAAF) equation. Causality is a principle of the transport equation that states that information travels only downstream along characteristics. This principle can be violated numerically. We show how to limit the weight function in voids and demonstrate the effect of this limit on accuracy. Using the C5G7 benchmark, we compare our method to the SAAF formulation with a void treatment (SAAFτ) that is not self-adjoint and has a nonsymmetric coefficient matrix. Finallyl, we show that the weighted LS equation with NDA gives acceptable accuracy relative to the SAAFτ equation while maintaining a SPD system matrix.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Thermally generated magnonic spin currents in a polycrystalline gadolinium iron garnet thin film with perpendicular magnetic anisotropy

Rare-earth iron garnets (REIGs) are the benchmark systems for magnonics, including the longitudinal spin Seebeck effect (LSSE). While most research has focused on single-crystalline REIGs on complimentary garnet substrates, moving to more, cost-effective complementary metal-oxide semiconductor (CMOS)-compatible substrates is important to integrate REIG thin films with existing technology. In this regard, we grow a 130 nm-thick polycrystalline gadolinium iron garnet (GdIG) film on the Si/SiO2 substrate and investigate the temperature-dependent LSSE. Interestingly, the polycrystalline GdIG film exhibits perpendicular magnetic anisotropy (PMA) at room temperature which is induced by tensile in-plane (IP)-strain originating from the thermal-expansion mismatch between the GdIG film and the substrate during rapid thermal annealing. Further, a spin-reorientation transition from the out-of-plane IP direction below TS = 180 K is observed. Additionally, the film reveals a magnetic compensation temperature, TComp, of ≈240 K. The LSSE voltage not only demonstrates a sign-inversion around TComp, but also shows noticeable changes around TS. As compared to a single-crystalline GdIG film, the lower LSSE voltage for the polycrystalline GdIG is attributed to the higher effective magnetic anisotropy and enhanced magnon scattering at the grain boundaries. Our study not only paves the way for the cost-effective growth of CMOS-compatible REIG-based systems with PMA for magnonic memory and information processing applications, but also highlights the fact that the spincaloritronic and spin-insulatronic properties of the polycrystalline REIGs follow those of their single-crystalline counterparts with reduced spin-to-charge conversion efficiency through LSSE which can be tuned further by controlling the average gran size and interface engineering.

Physics↗