Search NASA⌕ Search

SEARCH · Search NASA

Results for “program architectures”

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 1,333 records · Page 74

Parallelization and checkpointing of GPU applications through program transformation

GPUs have emerged as a powerful tool for accelerating general-purpose applications. The availability of programming languages that makes writing general-purpose applications for running on GPUs tractable have consolidated GPUs as an alternative for accelerating general purpose applications. Among the areas that have benefited from GPU acceleration are: signal and image processing, computational fluid dynamics, quantum chemistry, and, in general, the High Performance Computing (HPC) Industry. In order to continue to exploit higher levels of parallelism with GPUs, multi-GPU systems are gaining popularity. In this context, single-GPU applications are parallelized for running in multi-GPU systems. Furthermore, multi-GPU systems help to solve the GPU memory limitation for applications with large application memory footprint. Parallelizing single-GPU applications has been approached by libraries that distribute the workload at runtime, however, they impose execution overhead and are not portable. On the other hand, on traditional CPU systems, parallelization has been approached through application transformation at pre-compile time, which enhances the application to distribute the workload at application level and does not have the issues of library-based approaches. Hence, a parallelization scheme for GPU systems based on application transformation is needed. Like any computing engine of today, reliability is also a concern in GPUs. GPUs are vulnerable to transient and permanent failures. Current checkpoint/restart techniques are not suitable for systems with GPUs. Checkpointing for GPU systems present new and interesting challenges, primarily due to the natural differences imposed by the hardware design, the memory subsystem architecture, the massive number of threads, and the limited amount of synchronization among threads. Therefore, a checkpoint/restart technique suitable for GPU systems is needed. The goal of this work is to exploit higher levels of parallelism and to develop support for application-level fault tolerance in applications using multiple GPUs. Our techniques reduce the burden of enhancing single-GPU applications to support these features. To achieve our goal, this work designs and implements a framework for enhancing a single-GPU OpenCL application through application transformation.

97 MATHEMATICS AND COMPUTING↗

Performance Portability in the Exascale Computing Project: Exploration Through a Panel Series

Performance portability is a critical issue for the Exascale Computing Project (ECP) because of nontrivial architectural differences between machines available today and those expected at exascale. Many ECP project teams are working toward performance portability, and would expect to benefit from sharing lessons learned, identifying gaps, and discovering opportunities for partnerships. To facilitate this communication, the IDEAS-ECP project partnered with the three focus areas of ECP (application development, software technology, and hardware and integration), and Department of Energy computing facilities, to lead a series of panel discussions on performance portability. The panels were organized around broadly common themes of algorithmic and data locality challenges. In this article, we describe the panel series, its objectives, and perspectives from the various areas of the project. Finally, we also discuss use cases that are distinctive, as well as conclusions drawn from the collective experience of the participants.

97 MATHEMATICS AND COMPUTING↗

Dark Matter and Track Triggering with the CMS Experiment (Final Report)

This report summarizes the progress from DOE Early Career Award entitled “Dark Matter and Track Triggering with the CMS Experiment”. The first major goal of the project was to establish a sensitive Dark Matter (DM) search program for the CMS experiment in Run-2 of the LHC. Two related strategies were developed to accomplish this goal. First, we designed and executed searches for DM produced in association with heavy flavor quark pairs, top/anti-top (ttbar) and bottom/anti-bottom (bbbar). In addition, we sought to maximize the power of Run-2 DM searches through the development of a statistical combination of all major search channels within a consistent theoretical framework. The results of these aspects of the project are detailed in Section 1. The second major goal of the project was to develop a real-time “Level-1” tracking trigger system for the high-luminosity LHC (HL-LHC) CMS upgrade. Charged particle tracking in the first stage of the CMS trigger will be crucial for surviving the high-pileup environment expected at the HL-LHC. The L1 tracking trigger must process all front-end hit data sent from the inner Tracker and will have just 4us to output track primitives to the downstream L1 trigger without data loss. Our development of the CMS tracking trigger is described in Section 2. The team supported by the award is given in Section 3. The project resulted in 10 peer reviewed publications, a graduate student thesis, and contributions to the CMS Phase-2 Tracker Technical Design Report, as is detailed in Section 4. Our development work for the CMS tracking trigger has been integrated in the backend system architecture for the Tracker upgrade.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

MEPHESTO: Modeling Energy-Performance in Heterogeneous SoCs and Their Trade-Offs

Integrated shared memory heterogeneous architectures are pervasive because they satisfy the diverse needs of mobile, autonomous, and edge computing platforms. Although specialized processing units (PUs) that share a unified system memory improve performance and energy efficiency by reducing data movement, they also increase contention for this memory since the PUs interact with each other. Prior work has investigated performance degradation due to memory contention, but few have studied the relationship of power and energy to memory contention. Moreover, a comprehensive solution that models memory contention for kernel placement on contemporary heterogeneous systems on chip (SoCs) in response to energy and performance has been largely unaddressed.This paper presents MEPHESTO, a novel and holistic approach for managing this balance. The authors characterize applications and PUs in terms of two memory contention factors - time factors and power factors - to achieve the desired trade-off between energy and performance for collocated kernel execution on heterogeneous systems. The authors believe that this investigation is the first to combine all of these factors and present a simple knob-based approach that expresses the target trade-off. The approach is evaluated on a diverse integrated shared memory heterogeneous system with a CPU, GPU, and programmable vision accelerator. By using an empirical model for memory contention that provides up to 92% accuracy, the kernel collocation approach can provide a near-optimal ordering and placement based on the user-defined, energy-performance trade-off parameter. Moreover, the dynamic programming-based heuristics provide up to 30% better energy or 20% performance benefits when compared with the greedy approaches commonly employed by previous studies.

Alaul haque monil, Mohammad↗

CRADA Final Report: CRADA Number NFE-22-09330 with General Fusion

General Fusion is developing a magnetized target fusion (MTF) approach that involves compressing an initial magnetically confined plasma inside a cavity formed in liquid metal. This approach builds from concepts initially developed under the Linus program at the U.S. Naval Research Laboratory and combines it with advances from compact toroid experiment (CTX) and sustained spheromak plasma experiment (SSPX) in compact toroid plasmas and coaxial Marshall gun systems. Modeling the tokamak during compression is central to designing a successful MTF device. The plasma is formed by coaxial helicity injection in the General Fusion device. Immediately after formation, the plasma has a diverted tokamak configuration with a single null. As the wall moves inwards, the plasma is repelled from the conducting surface and driven inwards by currents induced by its magnetic field in the liquid metal wall. As the liquid metal closes (or bridges) the opening of the coaxial plasma injector, the magnetic field topology alters to remove the null. Due to this, the plasma moves from a diverted to a wall-limited configuration. The liquid metal liner continues to close in and change shape, reducing in radius by a factor of ten at the peak of plasma compression. A model of the MTF plasma must be able to handle this continually varying geometry, and to be predictive, it must faithfully include the real imperfections arising in the process. In this project, we pursued a Monte Carlo approach to closures for MHD by computing kinetic electron trajectories in an MHD plasma background from simulations of GF devices. This requires enhancing the capabilities of the KORC-T code for running large ensembles of kinetic trajectories by porting it to GPU architectures and enabling workflows for large ensembles on OLCF machines. With these capabilities, it is possible to produce a large library of kinetic calculations of electron orbits evolving in plasma configurations spanning the magnetic configurations and plasma density profiles, including non-axisymmetry, arising in the General Fusion’s existing PI3 spherical tokamak device. Using ensembles will capture particles passing a single point in space in a given magnetic configuration, and the entire dataset will cover a range of global magnetic field geometries. By sampling around many starting points, this dataset will capture the spatial dependence of the plasma parameters. From this large dataset, it is possible to produce a reduced model for the kinetic effects not captured in MHD.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Programming interfacial energetic offsets and charge transfer in β-Pb 0.33 V 2 O 5 /quantum-dot heterostructures: Tuning valence-band edges to overlap with midgap states

Here, semiconductor heterostructures for solar energy conversion interface light-harvesting semiconductor nanoparticles with wide-band-gap semiconductors that serve as charge acceptors. In such heterostructures, the kinetics of charge separation depend on the thermodynamic driving force, which is dictated by energetic offsets across the interface. A recently developed promising platform interfaces semiconductor quantum dots (QDs) with ternary vanadium oxides that have characteristic midgap states situated between the valence and conduction bands. In this work, we have prepared CdS/β-Pb 0.33 V 2 O 5 heterostructures by both linker-assisted assembly and surface precipitation and contrasted these materials with CdSe/β-Pb 0.33 V 2 O 5 heterostructures prepared by the same methods. Increased valence-band (VB) edge onsets in X-ray photoelectron spectra for CdS/β-Pb 0.33 V 2 O 5 heterostructures relative to CdSe/β-Pb 0.33 V 2 O 5 heterostructures suggest a positive shift in the VB edge potential and, therefore, an increased driving force for the photoinduced transfer of holes to the midgap state of β-Pb 0.33 V 2 O 5 . This approach facilitates a ca. 0.40 eV decrease in the thermodynamic barrier for hole injection from the VB edge of QDs suggesting an important design parameter. Transient absorption spectroscopy experiments provide direct evidence of hole transfer from photoexcited CdS QDs to the midgap states of β-Pb 0.33 V 2 O 5 NWs, along with electron transfer into the conduction band of the β-Pb 0.33 V 2 O 5 NWs. Hole transfer is substantially faster and occurs at <1-ps time scales, whereas completion of electron transfer requires 5—30 ps depending on the nature of the interface. The differentiated time scales of electron and hole transfer, which are furthermore tunable as a function of the mode of attachment of QDs to NWs, provide a vital design tool for designing architectures for solar energy conversion. More generally, the approach developed here suggests that interfacing semiconductor QDs with transition-metal oxide NWs exhibiting intercalative midgap states yields a versatile platform wherein the thermodynamics and kinetics of charge transfer can be systematically modulated to improve the efficiency of charge separation across interfaces.

36 MATERIALS SCIENCE↗

Mitigation for Removal of Building 01-202681 in the Main Storage Yard of the Area 1 Subdock, Nevada National Security Site, Nye County, Nevada

The Main Storage Yard was originally recorded as SHPO Resource No. S2772 in 2020 during an architectural survey of the Area 1 Subdock (Collins et al. 2022). It was recommended individually eligible for listing in the NRHP under Criteria A and C and as contributing to the significance of the potential Area 1 Subdock Historic District. The SHPO concurred with these determinations in a letter dated April 29, 2022 (Reed). The Main Storage Yard retains all seven aspects of integrity. The location, design, materials, workmanship, feeling, and association have not changed since the original construction. Since the purpose of the yard is to maintain storage equipment that is actively being used, the design and feeling will change each time equipment is moved. Such actions reinforce the integrity of design and feeling. Buildings 01-101 and 01-102 were removed (Collins and Menocal 2020), but the other buildings and storage yard remain. Therefore, the setting has been changed, but not to the degree that the Main Storage Yard no longer conveys its significance (see Figures 4 and 5 for comparison). The Main Storage Yard was designed to facilitate the relocation of the Area 3 Subdock to Area 1 in 1985. The design for the overall Subdock provided a centralized cluster of buildings surrounded by two large storage yards. While the North Storage Yard largely serves as overflow storage, the Main Storage Yard holds the majority of drill rigs and drilling equipment needed to support big hole drilling. The Main Storage Yard and its contents were essential elements of the nuclear testing drilling program on the NNSS thus making it eligible for the NRHP under Criterion A for its contribution to broad patterns of history by storing specially designed equipment for underground nuclear testing at the NNSS. It is also eligible under Criterion C as it is an engineered landscape that now serves as an open-air repository of drilling technology and nuclear testing. In addition to its individual significance, the Main Storage Yard also contributes to the significance of the Area 1 Subdock Historic District as it showcases a variety of big-hole drilling equipment, support facilities, and warehouses that were specially designed for nuclear testing at the NNSS. Despite the demolition of two contributing elements to date, the district still contains numerous examples of other facilities with the purpose of supporting big-hole drilling; therefore, the district still remains eligible under Criteria A and C.

54 ENVIRONMENTAL SCIENCES↗

An Integrated View of Hydraulic Induced Fracture Geometry in Hydraulic Fracture Test Site 2

Until relatively recently, most of our understanding about the geometry of hydraulically induced fractures in unconventional reservoirs has been inferred by patterns observed via microseismic monitoring. Important information, such as fracture-azimuth, fracture-length, height-growth and other geometric data has been determined from microseismic “event clouds”, which in turn has been used to interpret a stimulated reservoir volume (SRV). It is important to note that relatively limited microseismic results have been acquired in conjunction with other diagnostics and validated in a consistent manner. The Hydraulic Fracture Test Site 2 (HFTS2) in the Permian Delaware Basin provides a unique opportunity to compare the frac geometry interpretations derived from multiple frac diagnostic tools and at multiple scales. The integrated view that emerges from all the frac diagnostic tools is that in HFTS2 the geometries of hydraulically induced fractures are not random and with a highly complex branching architecture. In fact, the fracs are mostly vertical, parallel plana domains, and both vertically and horizontally asymmetrical. The hydraulically induced fractures have a very consistent azimuth with a strike that matches SHmax. At the distance corresponding to the spacing between nearby wells in HFTS2, ~ 660 ft, the pattern of strain interceptions observed from Low Frequency Distributed Acoustic Sensing (LF-DAS) shows far-field dimensions that are consistent with the stage length dimensions at the stimulated well. In general, larger stages with higher number of clusters create larger number of interceptions and wider stimulated intervals than that of shorter stages with the same cluster to cluster spacing and fewer clusters. The hydraulically induced fractures also show a clear tendency to preferentially grow upwards as shown by the microseismic data, by the relative lower number of LF-DAS interceptions in nearby deeper wells and finally by the observed LF-DAS strain patterns in the vertical observation well. In the near field, the geometries of the fracture domains are also consistent. As shown by the distributed strain measurements obtained during production via the monitoring of Rayleigh Frequency Shift (RFS), each cluster has a separate, non-overlapping, frac-zone-domain that are generally centered around the locations of each perforation cluster. Overall, the hydraulically induced fractures in HFTS2 are interpreted as occurring in swarms associated with individual clusters, each with its own unique geometry but with similar predictable geometric and propagation tendencies. The comprehensive frac diagnostic program in HFTS2, the well-pad layout that permits the investigation of the Downloaded from http://onepetro.org/URTECONF/proceedings-pdf/21URTC/1-21URTC/D011S018R003/2477511/urtec-2021-5396-ms.pdf/1 by Carol Worster on 28 February 2022 URTeC 5396 2 impact that nearby producing wells has on frac geometry, together with an innovative Design of Experiment (DofE) that includes sequential-fracing, consistent cluster-to-cluster distances and few single-perforation cluster stages, has allowed us to gain a unique perspective about the geometry of the induced hydraulic fractures on this pad. Finally, the HFTS2 dataset has also provided us with a better understanding of the applicability and limitations of the different diagnostic tools.

58 GEOSCIENCES↗

Advanced Composite Wind Turbine Blade Design Based on Durability and Damage Tolerance

The objective of the program was to demonstrate and verify Certification-by-Analysis (CBA) capability for wind turbine blades made from advanced lightweight composite materials. The approach integrated durability and damage tolerance analysis with robust design and virtual testing capabilities to deliver superior, durable, low weight, low cost, long life, and reliable wind blade design. The GENOA durability and life prediction software suite was be used as the primary simulation tool. First, a micromechanics-based computational approach was used to assess the durability of composite laminates with ply drop features commonly used in wind turbine applications. Ply drops occur in composite joints and closures of wind turbine blades to reduce skin thicknesses along the blade span. They increase localized stress concentration, which may cause premature delamination failure in composite and reduced fatigue service life. Durability and damage tolerance (D&DT) were evaluated utilizing a multi-scale micro-macro progressive failure analysis (PFA) technique. PFA is finite element based and is capable of detecting all stages of material damage including initiation and propagation of delamination. It assesses multiple failure criteria and includes the effects of manufacturing anomalies (i.e., void, fiber waviness). Two different approaches have been used within PFA. The first approach is Virtual Crack Closure Technique (VCCT) PFA while the second one is strength-based. Constituent stiffness and strength properties for glass and carbon based material systems were reverse engineered for use in D&DT evaluation of coupons with ply drops under static loading. Lamina and laminate properties calculated using manufacturing and composite architecture details matched closely published test data. Similarly, resin properties were determined for fatigue life calculation. The simulation not only reproduced static strength and fatigue life as observed in the test, it also showed composite damage and fracture modes that resemble those reported in the tests. The results show that computational simulation can be relied on to enhance the design of tapered composite structures such as the ones used in turbine wind blades. A computational simulation for durability, damage tolerance (D&DT) and reliability of composite wind turbine blade structures in presence of uncertainties in material properties was performed. A composite turbine blade was first assessed with finite element based multi-scale progressive failure analysis to determine failure modes and locations as well as the fracture load. D&DT analyses were then validated with static test performed at Sandia National Laboratories. The work was followed by detailed weight analysis to identify contribution of various materials to the overall weight of the blade. The methodology ensured that certain types of failure modes, such as delamination progression, are contained to reduce risk to the structure. Probabilistic analysis indicated that composite shear strength has a great influence on the blade ultimate load under static loading. Weight was reduced by 12% with robust design without loss in reliability or D&DT. Structural benefits obtained with the use of enhanced matrix properties through nanoparticles infusion were also assessed. Thin unidirectional fiberglass layers enriched with silica nanoparticles were applied to the outer surfaces of a wind blade to improve its overall structural performance and durability. The wind blade was a 9-meter prototype structure manufactured and tested subject to three saddle static loading at Sandia National Laboratory (SNL). The blade manufacturing did not include the use of any nano-material. With silica nanoparticles in glass composite applied to the exterior surfaces of the blade, the durability and damage tolerance (D&DT) results from multi-scale PFA showed an increase in ultimate load of the blade by 9.2% as compared to baseline structural performance (without nano). The use of nanoparticles lead to a delay in the onset of delamination. Load-displacement relationships obtained from testing of the blade with baseline neat material were compared to the ones from analytical simulation using neat resin and using silica nanoparticles in the resin. Multi-scale PFA results for the neat material construction matched closely those from test for both load displacement and location and type of damage and failure. AlphaSTAR demonstrated that wind blade structures made from advanced composite materials can be certified with multi-scale progressive failure analysis by following building block verification approach.

17 WIND ENERGY↗

Architecture and Methods for Substation SCADA Cybersecurity: Best Practices

There are over 3000 electricity providers in the United States, encompassing investor and publicly owned utilities as well as electric cooperatives. There has been ongoing trends to increasingly automate and provide remote control and monitoring of electric energy delivery systems. The deployment of computer network technologies has increased the efficiency and reliability of electric power infrastructure. However, the increased use of digital communications has also increased the vulnerability to malicious cyber attacks [1]. In 2004 the National Research Councils (National Academies) formed a committee of specialists to address these vulnerabilities and propose possible solutions with an objective to prioritize the R&D needs for developing countermeasures. The committee addressed many potential concerns in the electric power delivery system and classified them based upon different criteria and presented recommendations to minimize the gap between the academic research directions and the needs of the electric utility industry. The complexity and diversity of the electric power delivery system in the U.S. has opened many ports for attackers and intruders [1]. This complexity and diversity is attributed to the fact that power delivery system is a network of substations, transmission and distribution lines, sub-networks of controlling, sensing and monitoring units, and human operator involvement for running the system [1]. Accordingly, any incident such as the occurrence of a fault or disturbance in this complex network cannot be deferred and should be resolved within an order of milliseconds, otherwise there is risk of large-scale outages similar to the occurrences in India and the U.S. in 2003 [2]. There are three main vulnerabilities in supervisory control and data acquisition (SCADA) systems commonly identified—physical vulnerability, cyber vulnerability and personal vulnerability [1]. In terms of cyber threats, SCADA systems are the most critical elements in the electric power grid in the U.S. Unauthorized access to a SCADA system could enable/disable unexpected equipment (such as disable the protection system or a circuit breaker) which could cause large scale disruptions of electric power delivery. This paper provides an overview of power system SCADA technologies in transmission substations (Section 2) and summarizes the best practices for implementing a cyber security program. After introducing SCADA system operations in Section 2, a description of the security challenges for SCADA systems is presented in Section 3. In Section 4, NECRC Critical Infrastructure Protection standards CIP-002 through CIP-009 are summarized. An overview of industry best practices is presented in Section 5.

97 MATHEMATICS AND COMPUTING↗

COMFEN 3.0 - Evolution of an Early Design Tool for Commercial Facades and Fenestration Systems

Achieving a net-zero energy building cannot be done solely by improving the efficiency of the engineering systems. It also requires consideration of the essential nature of the building including factors such as architectural form, massing, orientation and enclosure. Making informed decisions about the fundamental character of a building requires assessment of the effects of the complex interaction of these factors on the resulting performance of the building. The complexity of these interactions necessitates the use of modeling and simulation tools to dynamically analyze the effects of the relationships, yet decisions about the building fundamentals are often made in the earliest stages of design, before a `building? exists to model. To address these issues, Lawrence Berkeley National Laboratory (LBNL) has developed an early-design energy modeling tool (COMFEN) specifically to help make informed decisions about building facade fundamentals by considering the design of the building envelope, orientation and massing on building performance. COMFEN focuses on the concept of a ?space? or ?room? and uses the EnergyPlus, and RadianceTM engines and a simple, graphic user interface to allow the user to explore the effects of changing key early-design input variables on energy consumption, peak energy demand, and thermal and visual comfort. Comparative results are rapidly presented in a variety of graphic and tabular formats to help users move toward optimal facade and fenestration design choices.While COMFEN 1.0 utilized an ExcelTM-based user interface, COMFEN 3.0 has been reworked to include a simple, more intuitive, yet powerful Graphic User Interface (GUI), a broader range of libraries for associated system and component choices and deliver a wider range of graphic outputs and options. This paper (and presentation) outlines the objectives in developing and further refining COMFEN, the mechanics of the program, and plans for future development.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Machine Learning-enabled Scalable Performance Prediction of Scientific Codes

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. Here, we present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. PPT-AMMP uses machine learning and regression techniques to build the prediction models based on small instances of the input code, then integrates into a higher-order discrete-event simulation model of PPT running on Simian PDES engine. We validate PPT-AMMP on four standard computational physics benchmarks and present a use case of hardware parameter sensitivity analysis to identify bottleneck hardware resources on different code inputs. We further extend PPT-AMMP to predict the performance of a scientific application code, namely, the radiation transport mini-app SNAP. To this end, we analyze multi-variate regression models that accurately predict the reuse profiles and the basic block counts. We validate predicted SNAP runtimes against actual measured times.

97 MATHEMATICS AND COMPUTING↗

Automatic Generation of High-Performance Convolution Kernels on ARM CPUs for Deep Learning

In this work, we present FastConv, a template-based code auto-generation open source library that can automatically generate high-performance deep learning convolution kernels of arbitrary matrices/tensors shapes. FastConv is based on the Winograd algorithm, which is reportedly the highest performing algorithm for the time-consuming convolution layers of convolutional neural networks. ARM CPUs cover a wide range designs and specifications, from embedded devices to HPC-grade CPUs. The leads to the dilemma of how to consistently optimize Winograd-based convolution solvers for convolution layers of different shapes. FastConv addresses this problem by using templates to auto-generate multiple shapes of tuned kernels variants suitable for skinny tall matrices. As a performance portable library, FastConv transparently searches for the best combination of kernel shapes, cache tiles, scheduling of loop orders, packing strategies, access patterns, and online/offline computations. Auto-tuning is used to search the parameter configuration space for the best performance for a given target architecture and problem size. The experiments with layer-wise evaluation on the VGG--16 model confirms a 1.25x performance gains is got by tuning the Winograd library. Integrated comparison results shows 1.02x to 1.40x, 1.14x to 2.17x, and 1.22x and 2.48x speedup is achieved over NNPACK, Arm NN, and FeatherCNN on the Kunpeng 920 beside few cases. Furthermore, problem size performance portability experiments with various convolution shapes shows that FastConv achieves 1.2x to 1.7x speedup and 2x to 22x speedup over NNPACK and ARM NN inference engine using Winograd on Kunpeng 920 . CPU performance portability evaluation on the VGG--16 show an average speedup over NNPACK of 1.42x, 1.21x, 1.26x, 1.37x, 2.26x, and 11.02x is observed on Kunpeng 920, Snapdragon 835, 855, 888, Apple M1, and AWS Graviton2, respectively.

97 MATHEMATICS AND COMPUTING↗

Sandia Cloud Forensics and Incident Response Platform v 1.0

As systems and devices become virtualized and deployed in the cloud, the hypervisor becomes an increasingly appropriate place to collect performance data, system state, system landscape, function calls, transaction traces, and other characteristics. We developed a method by which an introspection application may be coupled with a hypervisor to “reach into” the VM with minimal intrusiveness to collect data critical to the reconstruction of events, files, and operations. Such a capability is required to take advantage of the hypervisor as an instrumentation platform and to integrate that data with more traditional collection mechanisms. The concept of a VM serviced by a lightweight hypervisor is a relatively new paradigm for forensic practitioners. Traditional forensic techniques, based on assumptions that the filesystem was directly interacting with the hardware through an abstraction, afforded the forensic practitioner the assumption that there was nothing controlling the application below the filesystem. This is not the case when using virtualized technologies. Hypervisors can covertly monitor, introspect and interact with the guest in a transparent fashion. The problems of storage and collection of actionable data are exhausting. The current challenge is most hypervisors do not expose a useful application programming interface (API) at a sufficient level to do transparent, fine-grained and customizable introspection. Scalable VM instrumentation and introspection at an in-depth level requires fast handling of events, as well as direct access to VM state. Furthermore, deep introspection benefits greatly from the ability to gather data from the hardware during the VM’s exit to the hypervisor. All of this requires identical access to the system as the hypervisor itself; improper use of this ability could easily cause system instability. It is for this reason we believe that the hypervisor developers have been hesitant to grant this much control through their APIs. However, our approach leverages other means to collect and monitor the guests in a targeted fashion. Virtual machine introspection (VMI) is a technique used to monitor the runtime state of a system-level virtual machine. The runtime state can be may include processor registers, memory, disk, network, and any other hardware-level events A review of research literature and current VMI technologies exposed several limitations and tradeoffs in VMI approaches, including: the use of in-guest agents; kernel to user space transitions (dramatically slowing down processing); VMI tool pre-configuration requirements; hypervisor version lock-in or source code patching; reliance on operating system symbols; limited processor features due to hypervisor (even if the hardware could do more). To address these constraints, a VMI tool was envisioned to provide the cloud forensic capabilities while having as few of these limitations as possible. The Kernel-based Virtual Machine Introspection (KVMi) tool was developed for hypervisors on Intel’s x86-64 architecture. To meet performance, scoping and use-case demands, the follow criteria were applied to KVMi to support live, forensic data collection: • Shall not require in-guest agents. • Shall work with any recent version of modern hypervisors. • Shall introspect upon any guest (VM) running modern versions of Windows, Linux and OS X. • Shall have the ability to find and track operating system artifacts • Shall not require operating system symbol files. • Shall be able to fully handle VM-exits, bypassing execution of the hypervisor if necessary, to facilitate new features the hypervisor may not support. • Shall be compilable/loadable on a running system with standard build tools.

Stout, WilliamM.S.↗

Optimal Renewable Resource Allocation and Load Scheduling of Resilient Communities

This paper presents a methodology for enhancing community resilience through optimal renewable resource allocation and load scheduling in order to minimize unserved load and thermal discomfort. The proposed control architecture distributes the computational effort and is easier to be scaled up than traditional centralized control. The decentralized control architecture consists of two layers: The community operator layer (COL) allocates the limited amount of renewable energy resource according to the power flexibility of each building. The building agent layer (BAL) addresses the optimal load scheduling problem for each building with the allowable load determined by the COL. Both layers are formulated as a model predictive control (MPC) based optimization. Simulation scenarios are designed to compare different combinations of building weighting methods and objective functions to provide guidance for real-world deployment by community and microgrid operators. The results indicate that the impact of power flexibility is more prominent than the weighting factor to the resource allocation process. Allocation based purely on occupancy status could lead to an increase of PV curtailment. Further, it is necessary for the building agent to have multi-objective optimization to minimize unserved load ratio and maximize comfort simultaneously.

model predictive control↗

Overview of System Integration Analysis Activities for Integrated Waste Management

Spent nuclear fuel (SNF) generated by the current fleet of commercial nuclear reactors is being stored at the reactor sites in spent fuel pools (SFPs) and in dry independent spent fuel storage installations (ISFSIs). The US Department of Energy Office of Nuclear Energy (DOE-NE) is developing an Integrated Waste Management Program (IWMP) comprising a suite of options and supporting analyses to enable future informed choices. The IWMP is organized into the following five major areas: 1) Consent-Based Siting, 2) IWM Facilities and Equipment Concepts and Development, 3) Transportation Capability Analysis and Support, 4) Information Technology Solutions and Support, and 5) System Integration Analysis and Support. This paper discusses the activities ongoing in the IWMP System Integration Analysis and Support area. Two main areas of research in system integration are data and tools development, as well as system analysis assessments. One of the tools being developed in the system integration area is the Used Nuclear Fuel-Storage, Transportation & Disposal Analysis Resource and Data System (UNF-ST&DARDS) tool. It is being developed as a foundational resource for DOE-NE to manage SNF data, along with several compatible analysis tools for time-dependent characterization of SNF and related systems. UNF-ST&DARDS has the unparalleled ability to track SNF through the entire back end of the fuel cycle—from the time the fuel is discharged from a reactor through its disposal in a geological repository. UNF ST&DARDS interfaces with the SCALE code system for nuclear analysis and COBRA-SFS for thermal analysis. Another main tool being developed is the Next Generation System Analysis Model (NGSAM). NGSAM is an agent-based simulation software tool expressly designed to be capable of modeling the waste management system. NGSAM has been developed to enable informed decision-making by providing the capability of analyzing various potential system options for the management of SNF and HLW. Using NGSAM, system architecture analyses are being conducted to support the future deployment of a comprehensive nuclear waste management system that considers all major back-end aspects of the nuclear fuel cycle (i.e., transportation, storage, and disposal). System analysis assessments may investigate the implications of various strategies such as different acceptance rates, acceptance queues, facility capacities and options, standardized canisters, and different assumed system operation start dates. Recently, some system analysis effort has begun to look at how the waste management system might operate for advanced reactor fuel cycles.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

FUSRAP Case Study - Benefits and Lessons Learned from Implementation of a Modern Data Solution at Maywood - 18399

This paper focuses on data production and management practices dating back to 1999 that continue to evolve to support the project today. In 2000, the FUSRAP Maywood Project began using a software environmental data management system and laboratory information management system, developed by a single database administrator (DA) and authored in Microsoft Access{sup TM} (MS Access). The original databases included basic functionality including sample number assignment and label generation, tracking of LIMS gamma spec QC and assignment of basic qualifiers and basic database queries. The DA continued over the next fifteen years to refine the EDMS/LIMS by integrating project-specific data evaluation guidance document processes and Quality Assurance/Quality Control (QA/QC) charting and excursion warning tools. With the retirement of the original DA, the U.S. Army Corps of Engineers (USACE)-Cabrera Team procured and implemented a commercial-leaning solution using modern database tools and an established EDMS vendor. For the database transition process, the project team established and configured the new EDMS/LIMS with basic architecture and accessibility; evaluated existing workflows; established/revised LIMS and EDMS-related documentation (manuals and procedures); and conducted dry runs and validation testing. The overall team coordinated closely to facilitate a seamless transition from initial assessment and authoring, to data migration, and finally to resumption of normal ongoing operations. Key features of the new EDMS Subcontractor's software included lookup tables, an import wizard, data checking options and unique indexes. Since the database systems became operational, the technical staff gathered useful feedback from end users (e.g., lab staff, field engineers, task managers, and the third-party data validator) to refine the EDMS/LIMS operation. This feedback triggered improvements in the performance of onsite laboratory qualification forms, promoted consistency in sample ID numbers between the database sample planning screens and field chain-of-custodies, corrected bugs in the LIMS Duplicate Evaluation Report, eliminated data import issues such as blank, inconsistent or missing data from key fields. One of the advantages of the commercial database solution was that it allowed the project to cut cost over time due to the lower cost of database maintenance provided by the commercial database vendor versus the cost of an on-staff DA. Cost savings are estimated at $40,000 per year. There were also indirect cost savings resulting from implementation of the new database since it allowed better integration of the LIMS and EDMS. While there will always be challenges associated with long term records/data management for any old remediation site, the Maywood Team's approach to an upgraded EDMS/LIMS implementation serves as one element of the overall effort to enhance the integrity and reproducibility of critical data that supports the remediation program while at the same time, more effectively using available resources. These lessons-learned will enhance implementation of cost-effective solutions for similar environmental remediation sites. (authors)

97 MATHEMATICS AND COMPUTING↗

Efficient Aho-Corasick String Matching on Emerging Multicore Architectures

String matching algorithms are critical to several scientific fields. Beside text processing and databases, emerging applications such as DNA protein sequence analysis, data mining, information security software, antivirus, ma- chine learning, all exploit string matching algorithms [3]. All these applica- tions usually process large quantity of textual data, require high performance and/or predictable execution times. Among all the string matching algorithms, one of the most studied, especially for text processing and security applica- tions, is the Aho-Corasick algorithm. 1 2 Book title goes here Aho-Corasick is an exact, multi-pattern string matching algorithm which performs the search in a time linearly proportional to the length of the input text independently from pattern set size. However, depending on the imple- mentation, when the number of patterns increase, the memory occupation may raise drastically. In turn, this can lead to significant variability in the performance, due to the memory access times and the caching effects. This is a significant concern for many mission critical applications and modern high performance architectures. For example, security applications such as Network Intrusion Detection Systems (NIDS), must be able to scan network traffic against very large dictionaries in real time. Modern Ethernet links reach up to 10 Gbps, and malicious threats are already well over 1 million, and expo- nentially growing [28]. When performing the search, a NIDS should not slow down the network, or let network packets pass unchecked. Nevertheless, on the current state-of-the-art cache based processors, there may be a large per- formance variability when dealing with big dictionaries and inputs that have different frequencies of matching patterns. In particular, when few patterns are matched and they are all in the cache, the procedure is fast. Instead, when they are not in the cache, often because many patterns are matched and the caches are continuously thrashed, they should be retrieved from the system memory and the procedure is slowed down by the increased latency. Efficient implementations of string matching algorithms have been the fo- cus of several works, targeting Field Programmable Gate Arrays [4, 25, 15, 5], highly multi-threaded solutions like the Cray XMT [34], multicore proces- sors [19] or heterogeneous processors like the Cell Broadband Engine [35, 22]. Recently, several researchers have also started to investigate the use Graphic Processing Units (GPUs) for string matching algorithms in security applica- tions [20, 10, 32, 33]. Most of these approaches mainly focus on reaching high peak performance, or try to optimize the memory occupation, rather than looking at performance stability. However, hardware solutions supports only small dictionary sizes due to lack of memory and are difficult to customize, while platforms such as the Cell/B.E. are very complex to program.

Tumeo, Antonino↗