Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory tool”

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 595 records · Page 33

Asynchronous Two-Level Checkpointing Scheme for Large-Scale Adjoints in the Spectral-Element Solver Nek5000

Adjoints are an important computational tool for large-scale sensitivity evaluation, uncertainty quantification, and derivative-based optimization. An essential component of their performance is the storage/recomputation balance in which efficient checkpointing methods play a key role. We introduce a novel asynchronous two-level adjoint checkpointing scheme for multistep numerical time discretizations targeted at large-scale numerical simulations. The checkpointing scheme combines bandwidth-limited disk checkpointing and binomial memory checkpointing. Based on assumptions about the target petascale systems, which we later demonstrate to be realistic on the IBM Blue Gene/Q system Mira, we create a model of the expected performance of our checkpointing approach and validate it using the highly scalable Navier-Stokes spectralelement solver Nek5000 on small to moderate subsystems of the Mira supercomputer. In turn, this allows us to predict optimal algorithmic choices when using all of Mira. We also demonstrate that two-level checkpointing is significantly superior to single-level checkpointing when adjoining a large number of time integration steps. To our knowledge, this is the first time two-level checkpointing had been designed, implemented, tuned, and demonstrated on fluid dynamics codes at large scale of 50k+ cores.

Adjoints↗

Generalized quantum master equations can improve the accuracy of semiclassical predictions of multitime correlation functions

Multitime quantum correlation functions are central objects in physical science, offering a direct link between the experimental observables and the dynamics of an underlying model. While experiments such as 2D spectroscopy and quantum control can now measure such quantities, the accurate simulation of such responses remains computationally expensive and sometimes impossible, depending on the system’s complexity. A natural tool to employ is the generalized quantum master equation (GQME), which can offer computational savings by extending reference dynamics at a comparatively trivial cost. However, dynamical methods that can tackle chemical systems with atomistic resolution, such as those in the semiclassical hierarchy, often suffer from poor accuracy, limiting the credence one might lend to their results. By combining work on the accuracy-boosting formulation of semiclassical memory kernels with recent work on the multitime GQME, here we show for the first time that one can exploit a multitime semiclassical GQME to dramatically improve both the accuracy of coarse mean-field Ehrenfest dynamics and obtain orders of magnitude efficiency gains.

Chemistry↗

Machine-learning based model reduction for partial differential equations

We develop a novel synergistic approach between model reduction and machine learning. The specific goal of this project is to aid in the construction of reduced order models for basis functions that are custom-made to represent the solution of partial differential equations. Partial differential equations (PDEs) are one of the main mathematical tools for describing physical phenomena. However, due to either efficiency or necessity, for many real-world problems, we are interested in constructing reduced order models (ROMs) which focus only on the explicit computation of subsets of the active spatio-temporal scales in the problem, while treating the interaction with the rest of the scales approximately. The task of accurate representation of such interactions (usually called memory terms) constitutes a vast area of research known as model reduction. PI Stinis has significant expertise in the construction of ROMs for complex systems. In addition, in recent work with the project key participant Qadeer, they have utilized machine learning to acquire custom-made basis functions (CBFs) to expand the solutions of PDEs. In the proposed work, we will merge the two concepts by constructing ROMs for subsets of the CBFs needed to represent the solution of a PDE. Specifically, we will use the Mori-Zwanzig model reduction formalism to construct ROMs for subsets of CBFs for nonlinear PDEs of various complexity, as well as investigate the usage of CBFs in the spectral vanishing viscosity method for problems that can form shocks in finite time. The outcome of the research is aimed to be proof-of-concept about a novel synergistic approach between model reduction and machine learning, thus advancing the field of scientific machine learning. Such a capability will benefit the efficient modeling of physical systems appearing in various areas of interest to the DOE.

97 MATHEMATICS AND COMPUTING↗

Enhancement and Extension of Porosity Model in the FDNS-500 Code to Provide Enhanced Simulations of Rocket Engine Components

In the past, the design of rocket engines has primarily relied on the cold flow/hot fire test, and the empirical correlations developed based on the database from previous designs. However, it is very costly to fabricate and test various hardware designs during the design cycle, whereas the empirical model becomes unreliable in designing the advanced rocket engine where its operating conditions exceed the range of the database. The main goal of the 2nd Generation Reusable Launching Vehicle (GEN-II RLV) is to reduce the cost per payload and to extend the life of the hardware, which poses a great challenge to the rocket engine design. Hence, understanding the flow characteristics in each engine components is thus critical to the engine design. In the last few decades, the methodology of computational fluid dynamics (CFD) has been advanced to be a mature tool of analyzing various engine components. Therefore, it is important for the CFD design tool to be able to properly simulate the hot flow environment near the liquid injector, and thus to accurately predict the heat load to the injector faceplate. However, to date it is still not feasible to conduct CFD simulations of the detailed flowfield with very complicated geometries such as fluid flow and heat transfer in an injector assembly and through a porous plate, which requires gigantic computer memories and power to resolve the detailed geometry. The rigimesh (a sintered metal material), utilized to reduce the heat load to the faceplate, is one of the design concepts for the injector faceplate of the GEN-II RLV. In addition, the injector assembly is designed to distribute propellants into the combustion chamber of the liquid rocket engine. A porosity mode thus becomes a necessity for the CFD code in order to efficiently simulate the flow and heat transfer in these porous media, and maintain good accuracy in describing the flow fields. Currently, the FDNS (Finite Difference Navier-Stakes) code is one of the CFD codes which are most widely used by research engineers at NASA Marshall Space Flight Center (MSFC) to simulate various flow problems related to rocket engines. The objective of this research work during the 10-week summer faculty fellowship program was to 1) debug the framework of the porosity model in the current FDNS code, and 2) validate the porosity model by simulating flows through various porous media such as tube banks and porous plate.

Cheng, Gary↗

Validation of CFD/Heat Transfer Software for Turbine Blade Analysis

I am an intern in the Turbine Branch of the Turbomachinery and Propulsion Systems Division. The division is primarily concerned with experimental and computational methods of calculating heat transfer effects of turbine blades during operation in jet engines and land-based power systems. These include modeling flow in internal cooling passages and film cooling, as well as calculating heat flux and peak temperatures to ensure safe and efficient operation. The branch is research-oriented, emphasizing the development of tools that may be used by gas turbine designers in industry. The branch has been developing a computational fluid dynamics (CFD) and heat transfer code called GlennHT to achieve the computational end of this analysis. The code was originally written in FORTRAN 77 and run on Silicon Graphics machines. However the code has been rewritten and compiled in FORTRAN 90 to take advantage of more modem computer memory systems. In addition the branch has made a switch in system architectures from SGI's to Linux PC's. The newly modified code therefore needs to be tested and validated. This is the primary goal of my internship. To validate the GlennHT code, it must be run using benchmark fluid mechanics and heat transfer test cases, for which there are either analytical solutions or widely accepted experimental data. From the solutions generated by the code, comparisons can be made to the correct solutions to establish the accuracy of the code. To design and create these test cases, there are many steps and programs that must be used. Before a test case can be run, pre-processing steps must be accomplished. These include generating a grid to describe the geometry, using a software package called GridPro. Also various files required by the GlennHT code must be created including a boundary condition file, a file for multi-processor computing, and a file to describe problem and algorithm parameters. A good deal of this internship will be to become familiar with these programs and the structure of the GlennHT code. Additional information is included in the original extended abstract.

Kiefer, Walter D.↗

Numerical study for prediction of optimum operational parameters in laser welding of NiTi alloy

Laser welding of NiTi alloy is a challenging process since it strongly affects the functionality of the material in the heat affected and fusion zones. Furthermore, the inherent thermal process can remarkably change the transformation temperature of NiTi alloy in the welding zone because of variation in the material composition. Accordingly, the laser parameters such as laser power and velocity effectively determine the quality of the welded component. The functional and mechanical behavior of the resulting welded NiTi parts can also be effectively improved by controlling laser parameters, and consequently, improve the weldability quality. The purpose of the present study was to establish a reliable finite element model to predict the thermal behavior induced by the laser welding process. Here, a numerical model was employed to estimate the optimum laser parameters, which can reduce the heat affected and the fusion regions and thus result in a better weld. The results of the finite element model show good accuracy compared to the experimental results including the transient temperature and the dimension of the heat affected and fusion zones. In addition, an Artificial Neural Network (ANN) approach was applied, as a predictable tool, to perform a nonlinear mapping between inputs and outputs of the welding process in order to find the optimum laser parameters.

36 MATERIALS SCIENCE↗

Data-driven recovery of hidden physics in reduced order modeling of fluid flows

In this article, we introduce a modular hybrid analysis and modeling (HAM) approach to account for hidden physics in reduced order modeling (ROM) of parameterized systems relevant to fluid dynamics. The hybrid ROM framework is based on using first principles to model the known physics in conjunction with utilizing the data-driven machine learning tools to model the remaining residual that is hidden in data. This framework employs proper orthogonal decomposition as a compression tool to construct orthonormal bases and Galerkin projection (GP) as a model to build the dynamical core of the system. Our proposed methodology hence compensates structural or epistemic uncertainties in models and utilizes the observed data snapshots to compute true modal coefficients spanned by these bases. The GP model is then corrected at every time step with a data-driven rectification using a long short-term memory (LSTM) neural network architecture to incorporate hidden physics. A Grassmannian manifold approach is also adopted for interpolating basis functions to unseen parametric conditions. The control parameter governing the system's behavior is thus implicitly considered through true modal coefficients as input features to the LSTM network. The effectiveness of the HAM approach is then discussed through illustrative examples that are generated synthetically to take hidden physics into account. Furthermore, our approach thus provides insights addressing a fundamental limitation of the physics-based models when the governing equations are incomplete to represent underlying physical processes.

42 ENGINEERING↗

Cholla-MHD: An Exascale-capable Magnetohydrodynamic Extension to the Cholla Astrophysical Simulation Code

Abstract We present an extension of the massively parallel, GPU native, astrophysical hydrodynamics code Cholla to magnetohydrodynamics (MHD). Cholla solves the ideal MHD equations in their Eulerian form on a static Cartesian mesh utilizing the Van Leer + constrained transport integrator, the HLLD Riemann solver, and reconstruction methods at second and third order. Cholla’s MHD module can perform ≈260 million cell updates per GPU-second on an NVIDIA A100 while using the HLLD Riemann solver and second order reconstruction. The inherently parallel nature of GPUs combined with increased memory in new hardware allows Cholla’s MHD module to perform simulations with resolutions ∼500 3 cells on a single high-end GPU (e.g., an NVIDIA A100 with 80 GB of memory). We employ GPU direct Message Passing Interface to attain excellent weak scaling on the exascale supercomputer Frontier, while using 74,088 GPUs and simulating a total grid size of over 7.2 trillion cells. A suite of test problems highlights the accuracy of Cholla’s MHD module and demonstrates that zero magnetic divergence in solutions is maintained to round off error. We also present new testing and CI tools using GoogleTest, GitHub Actions, and Jenkins that have made development more robust and accurate and ensure reliability in the future.

Astronomy & Astrophysics↗

NAS - Supercomputing master tool for aeronautics

Features, performance objectives and applications planned for the NASA National Aerodynamics Simulator (NAS) are outlined. NAS was conceived in the 1970s as a means to performing numerical aerodynamic simulations beyond the scope of wind tunnel testing for high-speed flight. Present supercomputers cannot deal with problems exhibiting strongly coupled viscous effects, which are being increasingly more accurately represented by approximations to the full Navier-Stokes equations. Located at the NASA-Ames Center, the NAS will by 1990 comprise a distributed computer network capable of a 4 Gflop computing rate and have a memory capacity of 1 billion 64-bit words. Remote access to the system through UNIX-based microcomputers will be available through land lines and satellite links. New supercomputers will be tested on the system without disturbing ongoing work. The core machine will be a Cray-2 with a 2 Gflop rate.

Bailey, F. R.↗

Expressing Parallelism with ROOT

The need for processing the ever-increasing amount of data generated by the LHC experiments in a more efficient way has motivated ROOT to further develop its support for parallelism. Such support is being tackled both for shared-memory and distributed-memory environments. The incarnations of the aforementioned parallelism are multi-threading, multi-processing and cluster-wide executions. In the area of multi-threading, we discuss the new implicit parallelism and related interfaces, as well as the new building blocks to safely operate with ROOT objects in a multi-threaded environment. Regarding multi-processing, we review the new MultiProc framework, comparing it with similar tools (e.g. multiprocessing module in Python). Finally, as an alternative to PROOF for cluster-wide executions, we introduce the efforts on integrating ROOT with state-of-the-art distributed data processing technologies like Spark, both in terms of programming model and runtime design (with EOS as one of the main components). For all the levels of parallelism, we discuss, based on real-life examples and measurements, how our proposals can increase the productivity of scientists.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Emergence of microbial networks as response to hostile environments

The majority of microorganisms live in complex communities under varying conditions. One pivotal question in evolutionary biology is the emergence of cooperative traits and their sustainment in altered environments or in the presence of free-riders. Co-occurrence patterns in the spatial distribution of biofilms can help define species’ identities, and systems biology tools are revealing networks of interacting microorganisms. However, networks of inter-dependencies involving micro-organisms in the planktonic phase may be just as important, with the added complexity that they are not bounded in space. An integrated approach linking imaging, “Omics” and modeling has the potential to enable new hypothesis and working models. In order to understand how cooperation can emerge and be maintained without abilities like memory or recognition we use evolutionary game theory as the natural framework to model cell-cell interactions arising from evolutive decisions. We consider a finite population distributed in a spatial domain (biofilm), and divided into two interacting classes with different traits. This interaction can be weighted by distance, and produces physical connections between two elements allowing them to exchange finite amounts of energy and matter. Available strategies to each individual of one class in the population are the propensities or “willingness” to connect any individual of the other class. Following evolutionary game theory, we propose a mathematical model which explains the patterns of connections which emerge when individuals are able to find connection strategies that asymptotically optimize their fitness. The process explains the formation of a network for efficiently exchanging energy and matter among individuals and thus ensuring their survival in hostile environments.

59 BASIC BIOLOGICAL SCIENCES↗

Preparing an Incompressible-Flow Fluid Dynamics Code for Exascale-Class Wind Energy Simulations: Preprint

The US Department of Energy has identified Exascale-Class wind farm simulation tools as critical to wind energy scientific discovery. A primary objective of the Exawind project is to build high-performance, predictive Computational Fluid Dynamics tools that satisfy these modeling needs. GPU accelerators will serve as the computational thoroughbreds of next generation, Exascale-Class, platforms. Here, we report on our efforts for preparing the Exawind unstructured mesh solver, Nalu-Wind, for Exascale-Class machines. For computing at this scale, a simple port of the incompressible-flow algorithms to GPUs is not sufficient. One needs novel algorithms that are application aware, memory efficient, and optimized for latest generation GPU devices to get high-performance. The result of our efforts are unstructured mesh simulations of wind turbines that use 1/6 the compute resources of Summit supercomputer at Oak Ridge National Lab. In particular, we demonstrate a first-of-its-kind, simulation using Algebraic Multigrid solvers on over 4000 GPUs.

algebraic multigrid↗

Tracking Files Using the Kepler Provenance Framework

Workflow Management Systems (WFMS), such as Kepler, are proving to be an important tool in scientific problem solving. They can automate and manage complex processes and huge amounts of data produced by petascale simulations. Typically, the produced data need to be properly visualized and analyzed by scientists in order to achieve the desired scientific goals. Both run-time and post analysis may benefit from, even require, additional meta-data - provenance information. One of the challenges in this context is the tracking of the data files that can be produced in very large numbers during stages of the workflow, such as visualizations. The Kepler provenance framework collects all or part of the raw information flowing through the workflow graph. This information then needs to be further parsed to extract meta-data of interest. This can be done through add-on tools and algorithms. We show how to automate tracking specific information such as data files locations.

97 MATHEMATICS AND COMPUTING↗

DESTINY

DESTINY is a comprehensive tool for modeling 3D and 2D cache designs using SRAM,embedded DRAM (eDRAM), spin transfer torque RAM (STT-RAM), resistive RAM (ReRAM), and phase change RAM (PCN). In its purpose, it is similar to CACTI, CACTI-3DD or NVSim. DESTINY is very useful for performing design-space exploration across several dimensions, such as optimizing for a target (e.g. latency, area or energy-delay product) for agiven memory technology, choosing the suitable memory technology or fabrication method (i.e. 2D v/s 3D) for a given optimization target, etc. DESTINY has been validated against several cache prototypes. DESTINY is expected to boost studies of next-generation memory architectures used in systems ranging from mobile devices to extreme-scale supercomputers.

Source record↗

Development of the tangent linear and adjoint models of the global online chemical transport model MPAS-CO 2 v7.3

We describe the development of the tangent linear (TL) and adjoint models of the Model for Prediction Across Scales (MPAS)-CO 2 transport model, which is a global online chemical transport model developed upon the non-hydrostatic Model for Prediction Across Scales – Atmosphere (MPAS-A). The primary goal is to make the model system a valuable research tool for investigating atmospheric carbon transport and inverse modeling. First, we develop the TL code, encompassing all CO 2 transport processes within the MPAS-CO 2 forward model. Then, we construct the adjoint model using a combined strategy involving re-calculation and storage of the essential meteorological variables needed for CO 2 transport. This strategy allows the adjoint model to undertake a long-period integration with moderate memory demands. To ensure accuracy, the TL and adjoint models undergo vigorous verifications through a series of standard tests. The adjoint model, through backward-in-time integration, calculates the sensitivity of atmospheric CO 2 observations to surface CO 2 fluxes and the initial atmospheric CO 2 mixing ratio. To demonstrate the utility of the newly developed adjoint model, we conduct simulations for two types of atmospheric CO 2 observations, namely the tower-based in situ CO 2 mixing ratio and satellite-derived column-averaged CO 2 mixing ratio (X CO 2 ). A comparison between the sensitivity to surface flux calculated by the MPAS-CO 2 adjoint model with its counterpart from CarbonTracker–Lagrange (CT-L) reveals a spatial agreement but notable magnitude differences. These differences, particularly evident for X CO 2 , might be attributed to the two model systems' differences in the simulation configuration, spatial resolution, and treatment of vertical mixing processes. Moreover, this comparison highlights the substantial loss of information in the atmospheric CO 2 observations due to CT-L's spatial domain limitation. Furthermore, the adjoint sensitivity analysis demonstrates that the sensitivities to both surface flux and initial CO 2 conditions spread out throughout the entire Northern Hemisphere within a month. MPAS-CO 2 forward, TL, and adjoint models stand out for their calculation efficiency and variable-resolution capability, making them competitive in computational cost. In conclusion, the successful development of the MPAS-CO 2 TL and adjoint models, and their integration into the MPAS-CO 2 system, establish the possibility of using MPAS's unique features in atmospheric CO 2 transport sensitivity studies and in inverse modeling with advanced methods such as variational data assimilation.

54 ENVIRONMENTAL SCIENCES↗

Recent BOLT Discrete-Roughness Trip Results from the 20-Inch Mach 6 Tunnel

- Air Force Office of Scientific Research (AFOSR) primary sponsor of BOLT (for Boundary Layer Transition) sounding rocket flight project as continuation of previous HIFiRE flights (1 & 5) - Sounding rockets provide cost-effective flight research tool - Study hypersonic BoLT on increasingly complex geometries - BOLT shape includes concave surfaces and swept leading edges - Two missions, two flights: - BOLT mission at Esrange, Sweden - Johns Hopkins University Applied Physics Laboratory as lead - Focus on transition onset measurements - Flew June 2021 (staging anomaly) - BOLT II mission at Wallops Flight Facility, Virginia - Texas A&M and CUBRC provide primary leadership - Focus on turbulence measurements - Flew March 2022 - Flight named in memory of Mike Holden - NASA’s support to both BOLT missions provided through the Hypersonic Technologies Project (HTP)

Hypersonic↗

DESTINY

DESTINY is a comprehensive tool for modeling 3D and 2D cache designs using SRAM,embedded DRAM (eDRAM), spin transfer torque RAM (STT-RAM), resistive RAM (ReRAM), and phase change RAM (PCN). In its purpose, it is similar to CACTI, CACTI-3DD or NVSim. DESTINY is very useful for performing design-space exploration across several dimensions, such as optimizing for a target (e.g. latency, area or energy-delay product) for agiven memory technology, choosing the suitable memory technology or fabrication method (i.e. 2D v/s 3D) for a given optimization target, etc. DESTINY has been validated against several cache prototypes. DESTINY is expected to boost studies of next-generation memory architectures used in systems ranging from mobile devices to extreme-scale supercomputers.

Source record↗

DTLMod: A simulation framework for in situ workflow optimization

In situ processing workflows have become essential for coping with the explosion in data volume and velocity in large-scale scientific computing, providing domain scientists with early insights at runtime. Multiple frameworks implement this paradigm through a data transport layer (DTL), offering different data access modes and deployment schemes, but researchers currently lack the appropriate tools to assess design and deployment options before committing to costly real experiments. We introduce DTLMod, an open-source simulated DTL that enables performance evaluation of in situ workflow configurations at scale. Built on SimGrid, it links into any SimGrid-based simulator and is available in C++ and Python. We evaluate DTLMod along four axes: scalability (tens of thousands of simulated processes across interconnected clusters in seconds, with linear memory scaling), versatility (three implementation variants trading fidelity for speed), accuracy (simulated times faithfully reflecting real behavior), and practical utility (two use cases demonstrating evidence-based workflow design decisions).

Suter, Fred [ORNL] (ORCID:0000000319021955)↗