Search NASA⌕ Search

SEARCH · Search NASA

Results for “computer system benchmarking”

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 1,747 records · Page 97

Acceleration of the IMplicit–EXplicit nonhydrostatic unified model of the atmosphere on manycore processors

We present the acceleration of an IMplicit-EXplicit (IMEX) nonhydrostatic atmospheric model on manycore processors such as graphic processing units (GPUs) and Intel's Many Integrated Core (MIC) architecture. IMEX time integration methods sidestep the constraint imposed by the Courant-Friedrichs-Lewy condition on explicit methods through corrective implicit solves within each time step. In this work, we implement and evaluate the performance of IMEX on manycore processors relative to explicit methods. Using 3D-IMEX at Courant number C = 15, we obtained a speedup of about 4x relative to an explicit time stepping method run with the maximum allowable C = 1. Moreover, the unconditional stability of IMEX with respect to the fast waves means the speedup can increase significantly with the Courant number as long as the accuracy of the resulting solution is acceptable. We show a speedup of 100x at C = 150 using 1D-IMEX to demonstrate this point. Several improvements on the IMEX procedure were necessary in order to outperform our results with explicit methods: (a) reducing the number of degrees of freedom of the IMEX formulation by forming the Schur complement, (b) formulating a horizontally explicit vertically implicit 1D-IMEX scheme that has a lower workload and better scalability than 3D-IMEX, (c) using high-order polynomial preconditioners to reduce the condition number of the resulting system, and (d) using a direct solver for the 1D-IMEX method by performing and storing LU factorizations once to obtain a constant cost for any Courant number. Without all of these improvements, explicit time integration methods turned out to be difficult to beat. We discuss in detail the IMEX infrastructure required for formulating and implementing efficient methods on manycore processors. Several parametric studies are conducted to demonstrate the gain from each of the abovementioned improvements. Lastly, we validate our results with standard benchmark problems in numerical weather prediction and evaluate the performance and scalability of the IMEX method using up to 4192 GPUs and 16 Knights Landing processors.

97 MATHEMATICS AND COMPUTING↗

Implementation and validation of a fully implicit accumulator model in RELAP-7

This paper presents the implementation and validation of an accumulator model in RELAP-7 under the framework of preconditioned Jacobian free Newton Krylov (JFNK) method, based on the similar model used in RELAP5. RELAP-7 is a new nuclear reactor system safety analysis code being developed at the Idaho National Laboratory (INL). RELAP-7 is a fully implicit system code. The JFNK and preconditioning methods used in RELAP-7 is briefly discussed. The slightly modified accumulator model is summarized for completeness. The implemented model was validated with LOFT L3-1 test and benchmarked with RELAP5 results. RELAP-7 and RELAP5 had almost identical results for the accumulator gas pressure and water level, although there were some minor difference in other parameters such as accumulator gas temperature and tank wall temperature. One advantage of the JFNK method is its easiness to maintain and modify models due to fully separation of numerical methods from physical models. It would be straightforward to extend the current RELAP-7 accumulator model to simulate the advanced accumulator design. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Toward an AI-Powered Software Pipeline for Real-Time Tracking and Analysis of Wildfire and Smoke

Real-time tracking of wildfires and smoke is crucial for effective response, minimizing damage, protecting lives, and efficiently managing resources during fire emergencies. We develop a web-based AI-powered pipeline that detects wildfires in aerial video and estimates deployment-relevant behavior metrics, including cumulative burned area, burned-area growth rate, fire spread direction, and smoke dispersion. The system combines a YOLO-based detector with YCbCr-based fire segmentation, HSV-based smoke segmentation, Farneback optical flow, and centroid-based spatiotemporal tracking. Using ground sampling distance (GSD), pixel-level fire masks are converted to physical burned-area measurements by correlating fire pixel counts with camera altitude and tilt angle. We benchmark YOLO variants and non-YOLO baselines (GoogLeNet, CNN, DBN, Autoencoder, U-Net, and AlexNet) on the IEEE FLAME dataset and a newly created aerial frame dataset, Wildfire-DB. Cross-dataset evaluation uses a strict threshold-transfer protocol: decision thresholds are selected on FLAME validation and transferred unchanged to Wildfire-DB to quantify generalization under domain shift. YOLOv6 achieves the strongest cross-dataset frame-level fire detection on Wildfire-DB (ROC-AUC 0.8200, PR-AUC 0.8044, and transferred-threshold F1 0.7596). For tracking-oriented deployment requiring oriented localization, YOLO11-OBB provides the most reliable cross-dataset behavior among OBB-capable models while remaining computationally feasible. To analyze the feasibility of UAV deployment, we further measure inference efficiency using synchronized GPU and CPU power logs on a fixed workload of 1569 frames. YOLO-family models process the video in 5.73–12.47 seconds with net energy of 1247.28–1775.39 J, substantially lower latency and energy than heavier classification and reconstruction baselines. Overall, model optimality depends on operational objectives: YOLOv6 is best for cross-dataset detection robustness, whereas YOL...

Color segmentation↗

Code validation of SAM using natural-circulation experimental data from the compact integral effects test (CIET) facility

The primary objective of this study is to validate the system analysis code, SAM, using experimental data from the Compact Integral Effects Test (CIET) experimental loop. SAM is a modern system analysis code being developed at Argonne National Laboratory for safety analysis of designs for advanced non-light water reactors (non-LWRs), such as sodium-cooled fast reactors, high-temperature gas-cooled reactors, and fluoride salt-cooled high-temperature reactors (FHRs). To support SAM code development for the wide range of non-LWR applications, it is of paramount importance to validate the code against experiments highly relevant to these reactor concepts. Additionally, the CIET facility, which was designed to reproduce the thermal-hydraulics response of FHRs under both forced- and natural-circulation conditions, has been identified and selected as one of the benchmark test facilities for SAM code validation. In this study, two sets of available CIET tests were selected for SAM code validation purposes, namely, power step change transient tests and steady-state natural-circulation tests. For all selected tests, SAM-predicted results show very good agreement with experimental data. The successful validation of SAM against these selected CIET experiments demonstrates that the computer code is well suited for thermal-hydraulics analysis of FHR designs.

42 ENGINEERING↗

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters

In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer paral- lelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation.

Wang, Tianqi↗

Towards a NEAMS-based high-fidelity model of the MARVEL reactor

This report outlines the progress of Idaho National Laboratory in developing a high-fidelity and high-resolution model of the Microreactor Applications Research Validation and Evaluation reactor. The model was developed under the Nuclear Energy Advanced Modeling and Simulation microreactor application driver at Idaho National Laboratory. The overarching objective of this activity is the development of a high-fidelity multiphysics MARVEL model using NEAMS tools, and to verify and validate NEAMS tools against MARVEL reference simulation and experimental data, respectively. This is a unique opportunity to conduct multiphysics analysis on a soon-to-be-deployed microreactor. This multiphysics model developed under the NEAMS-funded INL microreactor application driver leverages three single-physics models coupled via the MOOSE’s MultiApp and Transfer systems. The latter systems enable in-memory data transfer between MOOSE-based and MOOSE-wrapped applications. The first single-physics model, that functions as main application, leverages Griffin to model the neutron transport in the core through the discontinuous finite element (DFEM) discrete ordinates solver (SN). Several optimization flags that were developed by the Griffin developer team were beta-tested to enhance the solver’s performance. These include the combined use of using_average_xs and update_averaged_xs_on that enable to avoid expensive on-the-fly cross sections evaluations at each linear iterations in favor of evaluations of the macroscopic cross sections at each Picard iteration. The second single-physics model uses BISON to handle solid heat transfer and asymptotic hydrogen redistribution analysis in the fuel. While the model returns consistent results for the temperature and hydrogen distribution in the fuel, a mismatch was noticed in the calculated temperature in the reflector due to the value of the gap conductance used in our model. Ongoing investigations are being performed to assess the origin of this discrepancy. Finally, the System Analysis Module (SAM) was used to model the flow of the sodium-potassium eutectic in the primary loop. A first verification was also performed showing good agreement in terms of mass flow rate and inlet temperature. All mesh files were generated using the MOOSE Reactor module, removing the need for external meshing tools. Notably, this workscope represents one of the initial applications of the MOOSE Reactor module for modeling highly irregular geometries. The use of the reactor module significantly streamlined the mesh generation process. The full multiphysics mode, that combines all the single physics models, was leveraged to conduct initial steady-state multiphysics simulations to compute power, and temperature distribution in the reactor. Initial testing was performed for transient simulations as well. In this case, the new checkpoint restart capability for eigenvalue calculations was tested showing the capability for streamlined restart of transient calculations. Future work will focus on improving the fidelity of the model by performing comprehensive code-to-code comparisons. For instance, the full-core Griffin neutronics model will be benchmarked against MCNP reference results, that were provided by the MARVEL design team. Additionally, the SAM T/H model will be verified against reference RELAP-5 results for selected accident scenarios. Besides code-to-code verification exercises, the model fidelity will be improved by replacing the single-channel SAM model with a more complex SAM-Pronghorn coupled model, in which the sub-channel capability is deployed to obtain radial temperature resolution in the coolant. This model will be developed in synergy with the NEAMS thermal hydraulics team.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Application of a Density Law via Python for Aqueous Plutonium Nitrate

A predictive density tool has been developed in Python to reduce bias and uncertainty in nuclear criticality safety calculations for plutonium nitrate systems. The Pitzer Method and an empirical method were implemented into the tool, allowing for plutonium nitrate density calculations. Additionally, the Python tool can generate atom densities for a MCNP6.2 material card using the density from the selected method and directly the densities into a prepared MCNP6 input text file. The material card and density are calculated based on customizable user inputs of plutonium content, nitric acid content, temperature, plutonium isotope weight percentages and impurity concentrations. The Python tool has been validated and verified against the International Handbook of Evaluated Criticality Safety Benchmark Experiments to predict densities within a root mean square error of 1.0% for the Pitzer method and 1.8% for the empirical method. These errors in density were shown to lead to a ±0.5% error in MCNP6.2 calculated k effective for the Pitzer method and a ±1.7% error for the Empirical method. Simultaneous work is also being done at the University of New Mexico and Los Alamos National Laboratory to create a similar tool for plutonium chloride solutions, which aims to provide the accreditation of the chlorine absorption. These capabilities will not only provide more accurate models but also lead the way towards a better understanding of solution systems and potential relaxation in the conservatism of the current aqueous plutonium processing limits.

97 MATHEMATICS AND COMPUTING↗

Matrix approach to land carbon cycle modeling: A case study with the Community Land Model

The terrestrial carbon (C) cycle has been commonly represented by a series of C balance equations to track C influxes into and effluxes out of individual pools in earth system models (ESMs). This representation matches our understanding of C cycle processes well but makes it difficult to track model behaviors. It is also computationally expensive, limiting the ability to conduct comprehensive parametric sensitivity analyses. To overcome these challenges, we have developed a matrix approach, which reorganizes the C balance equations in the original ESM into one matrix equation without changing any modeled C cycle processes and mechanisms. We applied the matrix approach to the Community Land Model (CLM4.5) with vertically-resolved biogeochemistry. The matrix equation exactly reproduces litter and soil organic carbon (SOC) dynamics of the standard CLM4.5 across different spatial-temporal scales. The matrix approach enables effective diagnosis of system properties such as C residence time and attribution of global change impacts to relevant processes. We illustrated, for example, the impacts of CO 2 fertilization on litter and SOC dynamics can be easily decomposed into the relative contributions from C input, allocation of external C into different C pools, nitrogen regulation, altered soil environmental conditions, and vertical mixing along the soil profile. In addition, the matrix tool can accelerate model spin-up, permit thorough parametric sensitivity tests, enable pool-based data assimilation, and facilitate tracking and benchmarking of model behaviors. Altogether, the matrix approach can make a broad range of future modeling activities more efficient and effective.

59 BASIC BIOLOGICAL SCIENCES↗

SU-E-T-761: TOMOMC, A Monte Carlo-Based Planning VerificationTool for Helical Tomotherapy

Purpose: Present a new Monte Carlo code (TOMOMC) to calculate 3D dose distributions for patients undergoing helical tomotherapy treatments. TOMOMC performs CT-based dose calculations using the actual dynamic variables of the machine (couch motion, gantry rotation, and MLC sequences). Methods: TOMOMC is based on the GEPTS (Gama Electron and Positron Transport System) general-purpose Monte Carlo system (Chibani and Li, Med. Phys. 29, 2002, 835). First, beam models for the Hi-Art Tomotherpy machine were developed for the different beam widths (1, 2.5 and 5 cm). The beam model accounts for the exact geometry and composition of the different components of the linac head (target, primary collimator, jaws and MLCs). The beams models were benchmarked by comparing calculated Pdds and lateral/transversal dose profiles with ionization chamber measurements in water. See figures 1–3. The MLC model was tuned in such a way that tongue and groove effect, inter-leaf and intra-leaf transmission are modeled correctly. See figure 4. Results: By simulating the exact patient anatomy and the actual treatment delivery conditions (couch motion, gantry rotation and MLC sinogram), TOMOMC is able to calculate the 3D patient dose distribution which is in principal more accurate than the one from the treatment planning system (TPS) since it relies on the Monte Carlo method (gold standard). Dose volume parameters based on the Monte Carlo dose distribution can also be compared to those produced by the TPS. Attached figures show isodose lines for a H&N patient calculated by TOMOMC (transverse and sagittal views). Analysis of differences between TOMOMC and TPS is an ongoing work for different anatomic sites. Conclusion: A new Monte Carlo code (TOMOMC) was developed for Tomotherapy patient-specific QA. The next step in this project is implementing GPU computing to speed up Monte Carlo simulation and make Monte Carlo-based treatment verification a practical solution.

60 APPLIED LIFE SCIENCES↗

Learning in continuous action space for developing high dimensional potential energy models

Reinforcement learning (RL) approaches that combine a tree search with deep learning have found remarkable success in searching exorbitantly large, albeit discrete action spaces, as in chess, Shogi and Go. Many real-world materials discovery and design applications, however, involve multi-dimensional search problems and learning domains that have continuous action spaces. Exploring high-dimensional potential energy models of materials is an example. Traditionally, these searches are time consuming (often several years for a single bulk system) and driven by human intuition and/or expertise and more recently by global/local optimization searches that have issues with convergence and/or do not scale well with the search dimensionality. Here, in a departure from discrete action and other gradient-based approaches, we introduce a RL strategy based on decision trees that incorporates modified rewards for improved exploration, efficient sampling during playouts and a “window scaling scheme" for enhanced exploitation, to enable efficient and scalable search for continuous action space problems. Using high-dimensional artificial landscapes and control RL problems, we successfully benchmark our approach against popular global optimization schemes and state of the art policy gradient methods, respectively. We demonstrate its efficacy to parameterize potential models (physics based and high-dimensional neural networks) for 54 different elemental systems across the periodic table as well as alloys. We analyze error trends across different elements in the latent space and trace their origin to elemental structural diversity and the smoothness of the element energy surface. Broadly, our RL strategy will be applicable to many other physical science problems involving search over continuous action spaces.

36 MATERIALS SCIENCE↗

The Effects of Different Lattice Codes on Results of Sensitivity and Uncertainty Analysis

According to the UAM ('Uncertainty Analysis in Modeling') benchmark, uncertainties in the LWR system calculations at all stages should be determined and quantified. As the neutronics calculations are prerequisite for the predictions of the reactor system, and the uncertainties introduced by the neutronics calculations would be propagated to the subsequent calculations, hence uncertainty analysis has been firstly focused on the neutronics phase to quantify the uncertainties of the reactor-physics predictions in UAM. For the lattice physics, the objective of uncertainty analysis is focused on uncertainty quantifications of the few-group constants; for the core physics, uncertainties of the core steady-state stand-alone neutronics calculations are focused on. Based on the previous researches, the nuclear-data uncertainty has been treated as one of the most significant source of uncertainty and received the most focus. In the previous works, the domestic code UNICORN has the capability of performing sensitivity analysis and uncertainty analysis using the direct numerical perturbation (DNP) method and statistical sampling (SS) method. In this paper, the capability of the UNICORN code has been improved. The domestic lattice code NECP-CACTI has been added in UNICORN to perform the lattice calculations, with DRAGON5.0 and NECP-CACTI available for lattice calculations. For DRAGON5.0 and NECP-CACTI, all the methods and technologies are shared in UNICORN. Therefore, the effects of different lattice codes on the results of sensitivity and uncertainty analysis have been researched and determined in this paper. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Geospatial mapping of distribution grid with machine learning and publicly-accessible multi-modal data

Abstract Detailed and location-aware distribution grid information is a prerequisite for various power system applications such as renewable energy integration, wildfire risk assessment, and infrastructure planning. However, a generalizable and scalable approach to obtain such information is still lacking. In this work, we develop a machine-learning-based framework to map both overhead and underground distribution grids using widely-available multi-modal data including street view images, road networks, and building maps. Benchmarked against the utility-owned distribution grid map in California, our framework achieves > 80% precision and recall on average in the geospatial mapping of grids. The framework developed with the California data can be transferred to Sub-Saharan Africa and maintain the same level of precision without fine-tuning, demonstrating its generalizability. Furthermore, our framework achieves a R 2 of 0.63 in measuring the fraction of underground power lines at the aggregate level for estimating grid exposure to wildfires. We offer the framework as an open tool for mapping and analyzing distribution grids solely based on publicly-accessible data to support the construction and maintenance of reliable and clean energy systems around the world.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Support CEED-enabled ECP applications in their preparation for Aurora/Frontier

The goal of this milestone was to help CEED-enabled ECP applications (particularly ExaSMR, MARBL, ExaAM, ExaWind and E3SM) in their preparations for the Aurora and Frontier architectures. This work included collaboration with ECP vendors and porting and optimization of CEED’s benchmarks and miniapps to early access hardware. As part of this milestone, we also made the best bake-off problems and bake-off kernel implementation from Nek, MFEM, libParanumal and the external community available in the latest libCEED release, libCEED-0.7. During the milestone period we also organized, in virtual form, the fourth CEED Annual meeting (CEED4AM) which included representatives from ECP applications, vendors and software technology projects. The specific tasks addressed in this milestone were to: (1) Work with vendors to port and run CEED benchmarks on early access systems for Aurora and Frontier; (2) Make the best BP/BK implementations from Nek, MFEM, libParanumal and external community available in libCEED; (3) Organize the next CEED Annual meeting (CEED4AM); and (4) Optimize CEED applications and miniapps for Aurora and Frontier architectures. The artifacts delivered include the next libCEED release, libCEED-0.7, and a number of developments integrated within applications to improve their GPU performance and capabilities. See the CEED website, http://ceed.exascaleproject.org and the CEED GitHub organization, http://github.com/ceed for more details.

97 MATHEMATICS AND COMPUTING↗

RAG for FLAG: AI Assistance for a Physics Code

Artificial intelligence (AI) has quickly become an important tool in scientific research, where significant efforts are underway to develop tools that will expedite the research process. One area of particular impact is scientific software, which can be particularly complex, and therefore time consuming to learn and use effectively. AI assistants are increasingly helping to streamline the process by performing tasks such as interactively answering user questions or suggesting solutions. Los Alamos National Laboratory (LANL) develops several advanced scientific codes, such as FLAG, which can be used to run multiphysics simulations. With this study, our goal was to develop an AI assistant for FLAG that could help make the process of understanding the software and running physics simulations more efficient. To develop an AI assistant for FLAG, we used a method called retrieval-augmented generation (RAG), which is a technique that uses information from relevant data sources to enhance the accuracy of large language models (LLMs). We used the FLAG user manual and other FLAG documentation as the knowledge base for the RAG system. When a user provides a query, RAG retrieves relevant sections from the knowledge base in response, then uses those excerpts to generate grounded and contextually rich answers. We found that our AI assistant was able to provide context aware answers and source references to user queries. To evaluate performance, we developed a set of 40 benchmark questions and compared the accuracy of the responses to those of two standard LLMs without retrieval. Our AI assistant significantly outperformed the standard LLMs at answering FLAG-related questions, with an 82.5% accuracy rate, compared to 47.5% for both of the standard LLMs. This has the potential to make the process of learning and using FLAG much easier, especially for new users. Ultimately, it supports LANL’s broader mission by empowering scientists and engineers to focus more on discovery and analysis rather than on navigating complex software systems.

97 MATHEMATICS AND COMPUTING↗

A tweezer array with 6,100 highly coherent atomic qubits

Optical tweezer arrays have transformed atomic and molecular physics, now forming the backbone for a range of leading experiments in quantum computing, simulation and metrology. Typical experiments trap tens to hundreds of atomic qubits and, recently, systems with around 1,000 atoms were realized without defining qubits or demonstrating coherent control. However, scaling to thousands of atomic qubits with long coherence times and low-loss and high-fidelity imaging is an outstanding challenge and critical for progress in quantum science, particularly towards quantum error correction (QEC). Here we experimentally realize an array of optical tweezers trapping more than 6,100 neutral atoms in around 12,000 sites, simultaneously surpassing state-of-the-art performance for several metrics that underpin the success of the platform. Specifically, while scaling to such a large number of atoms, we demonstrate a coherence time of 12.6(1) s, a record for hyperfine qubits in an optical tweezer array. We show room-temperature trapping lifetimes of about 23 min, enabling record-high imaging survival of 99.98952(1)% with an imaging fidelity of more than 99.99%. We present a plan for zone-based quantum computing and demonstrate necessary coherence-preserving qubit transport and pick-up/drop-off operations on large spatial scales, characterized through interleaved randomized benchmarking. Our results, along with recent developments, indicate that universal quantum computing and QEC with thousands to tens of thousands of physical qubits could be a near-term prospect.

atomic and molecular physics↗

iez: Resource Contention Aware Load Balancing for Large-Scale Parallel File Systems

Parallel I/O performance is crucial to sustaining scientific applications on large-scale High-Performance Computing (HPC) systems. However, I/O load imbalance in the underlying distributed and shared storage systems can significantly reduce overall application performance. There are two conflicting challenges to mitigate this load imbalance: (i) optimizing systemwide data placement to maximize the bandwidth advantages of distributed storage servers, i.e., allocating I/O resources efficiently across applications and job runs; and (ii) optimizing client-centric data movement to minimize I/O load request latency between clients and servers, i.e., allocating I/O resources efficiently in service to a single application and job run. Moreover, existing approaches that require application changes limit wide-spread adoption in commercial or proprietary deployments. We propose iez, an “end-to-end control plane” where clients transparently and adaptively write to a set of selected I/O servers to achieve balanced data placement. Our control plane leverages realtime load information for distributed storage server global data placement while our design model leverages trace-based optimization techniques to minimize I/O load request latency between clients and servers. We evaluate our proposed system on an experimental cluster for two common use cases: synthetic I/O benchmark IOR for large sequential writes and a scientific application I/O kernel, HACC-I/O. Results show read and write performance improvements of up to 34% and 32%, respectively, compared to the state of the art.

Wadhwa, Bharti↗

Postseismic Deformation after the 1964 Great Alaskan Earthquake: Collaborative Research with Goddard Space Flight Center

The purpose of this project was to carry out GPS observations on the Kenai Peninsula, southern Alaska, in order to study the postseismic and contemporary deformation following the 1964 Alaska earthquake. All of the research supported in this grant was carried out in collaboration with Dr. Steven Cohen of Goddard Space Flight Center. The research funding from this grant primarily supported GPS fieldwork, along with the acquisition of computer equipment to allow analysis and modeling of the GPS data. A minor amount of salary support was provided by the PI, but the great majority of the salary support was provided by the Geophysical Institute. After the expiration of this grant, additional funding was obtained from the National Science Foundation to continue the work. This grant supported GPS field campaigns in August 1995, June 1996, May-June and September 1997, and May-June 1998. We initially began the work by surveying leveling benchmarks on the Kenai peninsula that had been surveyed after the 1964 earthquake. Changes in height from the 1964 leveling data to the 1995+ GPS data, corrected for the geoid-ellipsoid separation, give the total elevation change since the earthquake. Beginning in 1995, we also identified or established sites that were suitable for long-term surveying using GPS. In the subsequent annual GPS campaigns, we made regular measurements at these GPS marks, and steadily enhanced our set of points for which cumulative postseismic uplift data were available. From 4 years of Global Positioning System (GPS) measurements, we find significant spatial variations in present-day deformation between the eastern and western Kenai peninsula, Alaska. Sites in the eastern Kenai peninsula and Prince William Sound move to the NNW relative to North America, in the direction of Pacific-North America relative plate motion. Velocities decrease in magnitude from nearly the full plate rate in southern Prince William Sound to about 30 mm/yr at Seward and to about 5 mm/yr near Anchorage. In contrast, sites in the western Kenai peninsula move to the SW, in a nearly trenchward direction, with a velocity of about 20 mm/yr. The data are consistent with the shallow plate interface offshore and beneath the eastern Kenai and Prince William Sound being completely locked or nearly so, with elastic strain accumulation resulting in rapid motion in the direction of relative plate motion of sites in the overriding plate. The velocities of sites in the western Kenai, along strike to the southwest, are opposite in sign with those predicted from elastic strain accumulation. These data are incompatible with a significant locked region in this segment of the plate boundary. Trenchward velocities are found also for some sites in the Anchorage area. We interpret the trenchward velocities as being caused by a continuing postseismic transient from the 1964 great Alaska earthquake.

Freymueller, Jeffrey T.↗

Spatial Support Vector Regression to Detect Silent Errors in the Exascale Era

As the exascale era approaches, the increasing capacity of high-performance computing (HPC) systems with targeted power and energy budget goals introduces significant challenges in reliability. Silent data corruptions (SDCs) or silent errors are one of the major sources that corrupt the executionresults of HPC applications without being detected. In this work, we explore a low-memory-overhead SDC detector, by leveraging epsilon-insensitive support vector machine regression, to detect SDCs that occur in HPC applications that can be characterized by an impact error bound. The key contributions are three fold. (1) Our design takes spatialfeatures (i.e., neighbouring data values for each data point in a snapshot) into training data, such that little memory overhead (less than 1%) is introduced. (2) We provide an in-depth study on the detection ability and performance with different parameters, and we optimize the detection range carefully. (3) Experiments with eight real-world HPC applications show thatour detector can achieve the detection sensitivity (i.e., recall) up to 99% yet suffer a less than 1% of false positive rate for most cases. Our detector incurs low performance overhead, 5% on average, for all benchmarks studied in the paper. Compared with other state-of-the-art techniques, our detector exhibits the best tradeoff considering the detection ability and overheads.

Subasi, Omer↗