Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computer software and hardware”

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 793 records · Page 44

High-Performance Design Patterns for Modern Fortran

This paper presents ideas for using coordinate-free numerics in modern Fortran to achieve code flexibility in the partial differential equation (PDE) domain. We also show how Fortran, over the last few decades, has changed to become a language well-suited for state-of-the-art software development. Fortran’s new coarray distributed data structure, the language’s class mechanism, and its side-effect-free, pure procedure capability provide the scaffolding on which we implement HPC software. These features empower compilers to organize parallel computations with efficient communication. We present some programming patterns that support asynchronous evaluation of expressions comprised of parallel operations on distributed data. We implemented these patterns using coarrays and the message passing interface (MPI). We compared the codes’ complexity and performance. The MPI code is much more complex and depends on external libraries. The MPI code on Cray hardware using the Cray compiler is 1.5–2 times faster than the coarray code on the same hardware. The Intel compiler implements coarrays atop Intel’s MPI library with the result apparently being 2–2.5 times slower than manually coded MPI despite exhibiting nearly linear scaling efficiency. As compilers mature and further improvements to coarrays comes in Fortran 2015, we expect this performance gap to narrow.

Haveraaen, Magne↗

Batched Sparse Linear Algebra (Final Report for Subcontract B648960)

This report finalizes design specifications for developing batched kernels for small tensor operations for unassembled matrix-free iterative solvers, batched solvers for partially assembled operators, and batched solvers with support for various sparse formats. The outcome of the project milestones is a set of interfaces to Batched Sparse LA solvers running on hardware accelerators for use in ECP Libraries and Applications. It is part of the development of sparse batched kernels, solvers/preconditioners as well as creating interoperability in xSDK libraries with sparse and dense batched functions to benefit ECP applications. The participants included representatives from ECP libraries (not limited to the xSDK project), applications, and vendors (AMD, Intel, and NVIDIA). Batched sparse linear algebra solvers form the new frontier for algorithmic development and performance engineering. Many applications (ECP and non-ECP alike) require simultaneous solutions of small linear systems of equations that are structurally sparse. To move towards high hardware utilization, it is important to provide these applications with appropriate interfaces to efficient batched sparse solvers running on modern hardware accelerators. We present interface designs in use by HPC software libraries supporting batched sparse linear algebra and the development of sparse batched kernel codes for solvers and preconditioners. We also address the potential interoperability opportunities to keep the software portable between the major hardware accelerators from AMD, Intel, and NVIDIA. The presented interface specifications includes batched band, sparse iterative, and sparse direct solvers. This report summarizes progress in Kokkos Kernels and the xSDK libraries MAGMA, Ginkgo, hypre, SUNDIALS, and SuperLU_dist.

97 MATHEMATICS AND COMPUTING↗

Performance study of atomic tally methods for GPU-accelerated Monte Carlo dose calculation - 25352

Over the past several years, the graphics processing unit (GPU) technology has rapidly gained ground in scientific computing due to its outstanding performance and programmability. GPU implementation of Monte Carlo radiation transport for dose calculations has been reported by many investigators. The majority of these studies adopted single-precision floating point format because of the higher peak floating point operations per second (FLOPS) the GPUs can deliver than double-precision. It has been known that calculation using single-precision is more prone to numerical round-off errors, especially when a single tally data is accumulated 'atomically' and repeatedly by thousands of GPU threads. To mitigate this problem, the least intrusive solution in theory is to replace the single-precision atomic-add tally function with a double-precision version. However, the complexity lies in the fact that some GPUs (Nvidia GPUs prior to the Pascal generation; all current AMD GPUs) do not readily offer such double-precision function at hardware level, and that software emulation is too slow to use if not optimized properly. This paper discusses several atomic-add tally methods with reduced numerical errors used throughout ARCHER development. The original software-based compare-and-swap method (CAS) was shown to be inefficient due to high intra-warp thread contention, whereas the improved software-based warp-aggregated method (WAG) and Kahan summation method (KAS) eliminated the thread contention and performed very well on Kepler and Maxwell GPUs, being more than 13 times faster than CAS in our tests. The hardware-based (HB) double-precision atomic-add feature available on Pascal and Volta GPUs exceeded software emulation and offered the best performance universally, so did WIB, a combination of WAG and HB methods. It was also shown that in a single-precision dose engine, KAS managed to maintain high reliability when the single-precision atomic-add tally underestimated the dose by 25%. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗

RAJA - LLNL HPC Architecture Portability Encapsulation Layer Version 1.0

RAJA is a collection of C++ software abstractions designed to make HPC applications portable across a range of hardware architectures and programming models. The main conceptual abstraction in FAJA is a loop. RAJA provides abstractions for types, loop execution and scheduling, and loop iteration space portioning and ordering cooperate to insulate algorithms in application code that domain experts write from implementations details of those algorithms that may need to depend on the underlying computer hardware for high performance.

ECP↗

RAJA - LLNL HPC Architecture Portability Encapsulation Layer Version 1.0

RAJA is a collection of C++ software abstractions designed to make HPC applications portable across a range of hardware architectures and programming models. The main conceptual abstraction in FAJA is a loop. RAJA provides abstractions for types, loop execution and scheduling, and loop iteration space portioning and ordering cooperate to insulate algorithms in application code that domain experts write from implementations details of those algorithms that may need to depend on the underlying computer hardware for high performance.

Hornung, Richard↗

Early Experiences Porting the NAMD and VMD Molecular Simulation and Analysis Software to GPU-Accelerated OpenPOWER Platforms, In: ISC High Performance 2016: High Performance Computing

All-atom molecular dynamics simulations of biomolecules provide a powerful tool for exploring the structure and dynamics of large protein complexes within realistic cellular environments. Unfortunately, such simulations are extremely demanding in terms of their computational requirements, and they present many challenges in terms of preparation, simulation methodology, and analysis and visualization of results. We describe our early experiences porting the popular molecular dynamics simulation program NAMD and the simulation preparation, analysis, and visualization tool VMD to GPU-accelerated OpenPOWER hardware platforms. We report our experiences with compiler-provided autovectorization and compare with hand-coded vector intrinsics for the POWER8 CPU. We explore the performance benefits obtained from unique POWER8 architectural features such as 8-way SMT and its value for particular molecular modeling tasks. Finally, we evaluate the performance of several GPU-accelerated molecular modeling kernels and relate them to other hardware platforms.

Computer Science↗

Efficiency and Scalability of Barrier Synchronization on NoC Based Many-core Architectures

Interconnects based on Networks-on-Chip are an appealing solution to address future microprocessor designs where, very likely, hundreds of cores will be connected on a single chip. A fundamental role in highly parallelized applications running on many-core architectures will be played by barrier primitives used to synchronize the execution of parallel processes. This paper focuses on the analysis of the efficiency and scalability of different barrier implementations in many-core architectures based on NoCs. Several message passing barrier implementations based on four algorithms (all-to-all, master-slave, butterfly and tree) have been implemented and evaluated for a single-chip target architecture composed of a variable number of cores (from 4 to 128) and different network topologies (mesh, torus, ring, clustered-ring and fat-tree). Using a cycle-accurate simulator, we show the scalability of each barrier for every NoC topology, analyzing and comparing theoretical with real behaviors. We observed that some barrier algorithms, when implemented in hardware or software, show a different scaling behavior with respect to those theoretically expected. We evaluate the efficiency of each combination topology-barrier, demonstrating that, in many cases, simple network topologies can be more efficient than complex and highly connected topologies.

97 MATHEMATICS AND COMPUTING↗

Modeling performance of data collection systems for high-energy physics

Exponential increases in scientific experimental data are outpacing silicon technology progress, necessitating heterogeneous computing systems—particularly those utilizing machine learning (ML)—to meet future scientific computing demands. The growing importance and complexity of heterogeneous computing systems require systematic modeling to understand and predict the effective roles for ML. We present a model that addresses this need by framing the key aspects of data collection pipelines and constraints and combining them with the important vectors of technology that shape alternatives, computing metrics that allow complex alternatives to be compared. For instance, a data collection pipeline may be characterized by parameters such as sensor sampling rates and the overall relevancy of retrieved samples. Alternatives to this pipeline are enabled by development vectors including ML, parallelization, advancing CMOS, and neuromorphic computing. By calculating metrics for each alternative such as overall F1 score, power, hardware cost, and energy expended per relevant sample, our model allows alternative data collection systems to be rigorously compared. We apply this model to the Compact Muon Solenoid experiment and its planned high luminosity-large hadron collider upgrade, evaluating novel technologies for the data acquisition system (DAQ), including ML-based filtering and parallelized software. The results demonstrate that improvements to early DAQ stages significantly reduce resources required later, with a power reduction of 60% and increased relevant data retrieval per unit power (from 0.065 to 0.31 samples/kJ). However, we predict that further advances will be required in order to meet overall power and cost constraints for the DAQ.

Olin-Ammentorp, Wilkie (ORCID:0000000224729862)↗

SDN solutions for switching dedicated long-haul connections: Measurements and comparative analysis

We consider a scenario of two sites connected over a dedicated, long-haul connection that must quickly fail-over in response to degradations in host-to-host application performance. The traditional layer-2/3 hot stand-by fail-over solutions do not adequately address the variety of application degradations, and more recent single controller Software Defined Networks (SDN) solutions are not effective for long-haul connections. We present two methods for such a path fail-over using OpenFlow enabled switches: (a) a light-weight method that utilizes host scripts to monitor application performance and dpctl API for switching, and (b) a generic method that uses two OpenDaylight (ODL) controllers and REST interfaces. For both methods, the restoration dynamics of applications contain significant statistical variations due to the complexities of controllers, north bound interfaces and switches; they, together with the wide variety of vendor implementations, complicate the choice among such solutions. We develop the impulse-response method based on regression functions of performance parameters to provide a rigorous and objective comparison of different solutions. We describe testing results of the two proposed methods, using TCP throughput and connection rtt as main parameters, over a testbed consisting of HP and Cisco switches connected over longhaul connections emulated in hardware by ANUE devices. Lastly, the combination of analytical and experimental results demonstrate that the dpctl method responds seconds faster than the ODL method on average, even though both methods eventually restore original TCP throughput.

97 MATHEMATICS AND COMPUTING↗

xesn: Echo state networks powered by Xarray and Dask

Xesn is a Python package that allows scientists to easily design Echo State Networks (ESNs) for forecasting problems. ESNs are a Recurrent Neural Network architecture introduced by Jaeger (2001) that are part of a class of techniques termed Reservoir Computing. One defining characteristic of these techniques is that all internal weights are determined by a handful of global, scalar parameters, thereby avoiding problems during backpropagation and reducing training time significantly. Because this architecture is conceptually simple, many scientists implement ESNs from scratch, leading to questions about computational performance. Xesn offers a straightforward, standard implementation of ESNs that operates efficiently on CPU and GPU hardware. The package leverages optimization tools to automate the parameter selection process, so that scientists can reduce the time finding a good architecture and focus on using ESNs for their domain application. Importantly, the package flexibly handles forecasting tasks for out-of-core, multi-dimensional datasets, eliminating the need to write parallel programming code. Xesn was initially developed to handle the problem of forecasting weather dynamics, and so it integrates naturally with Python packages that have become familiar to weather and climate scientists such as Xarray (Hoyer & Hamman, 2017). However, the software is ultimately general enough to be utilized in other domains where ESNs have been useful, such as in signal processing (Jaeger & Haas, 2004).

97 MATHEMATICS AND COMPUTING↗

SwitchX : Gmin-Gmax Switching for Energy-efficient and Robust Implementation of Binarized Neural Networks on ReRAM Xbars

Memristive crossbars can efficiently implement Binarized Neural Networks (BNNs) wherein the weights are stored in high-resistance states (HRS) and low-resistance states (LRS) of the synapses. We propose SwitchX mapping of BNN weights onto ReRAM crossbars such that the impact of crossbar non-idealities, that lead to degradation in computational accuracy, are minimized. Essentially, SwitchX maps the binary weights in such a manner that a crossbar instance comprises of more HRS than LRS synapses. We find BNNs mapped onto crossbars with SwitchX to exhibit better robustness against adversarial attacks than the standard crossbar mapped BNNs, the baseline. Finally, we combine SwitchX with state-aware training (that further increases the feasibility of HRS states during weight mapping) to boost the robustness of a BNN on hardware. We find that this approach yields stronger defense against adversarial attacks than adversarial training, a state-of the-art software defense. We perform experiments on a VGG16 BNN with benchmark datasets (CIFAR-10, CIFAR-100 and TinyImagenet) and use Fast Gradient Sign Method (ϵ = 0.05 to 0.3) and Projected Gradient Descent (ϵ = $\frac{2}{255}$ to $\frac{32}{255}$, α = $\frac{2}{255}$) adversarial attacks. We show that SwitchX combined with state-aware training can yield upto ~35% improvements in clean accuracy and ~6–16% in adversarial accuracies against conventional BNNs. Furthermore, an important by-product of SwitchX mapping is increased crossbar power savings, owing to an increased proportion of HRS synapses, which is furthered with state-aware training. We obtain upto ~21–22% savings in crossbar power consumption for state-aware trained BNN mapped via SwitchX on 16 × 16 and 32 × 32 crossbars using the CIFAR-10 and CIFAR-100 datasets.

97 MATHEMATICS AND COMPUTING↗

Key Residential Building Equipment Technologies for Control and Grid Support PART I (Residential)

Electrical energy consumption of the residential sector is a crucial area of research that has in the past primarily focused on increasing the efficiency of household devices such as water heaters, dishwashers, air conditioners, and clothes washer and dryer units. However, the focus of this research is shifting as objectives such as developing the smart grid and ensuring that the power system remains reliable come to the fore, along with the increasing need to reduce energy use and costs. Load research has started to focus on mechanisms to support the power system through demand reduction and/or reliability services. The power system relies on matching generation and load, and day-ahead and real-time energy markets capture most of this need. However, a separate set of grid services exist to address the discrepancies in load and generation arising from contingencies and operational mismatches, and to ensure that the transmission system is available for delivery of power from generation to load. Currently, these grid services are mostly provided by generation resources. The addition of renewable resources with their inherent variability can complicate the issue of power system reliability and lead to the increased need for grid services. Using load as a resource, through demand response programs, can fill the additional need for flexible resources and even reduce costly energy peaks. Loads have been shown to have response that is equal to or better than generation in some cases. Furthermore, price-incentivized demand response programs have been shown to reduce the peak energy requirements, thereby affecting the wholesale market efficiency and overall energy prices. The residential sector is not only the largest consumer of electrical energy in the United States, but also has the highest potential to provide demand reduction and power system support, as technological advancements in load control, sensor technologies, and communication are made. The prevailing loads based on the largest electrical energy consumers in the residential sector are space heating and cooling, washer and dryer, water heating, lighting, computers and electronics, dishwasher and range, and refrigeration. As the largest loads, these loads provide the highest potential for delivering demand response and reliability services. Many residential loads have inherent flexibility that is related to the purpose of the load. Depending on the load type, electric power consumption levels can either be ramped, changed in a step-change fashion, or completely removed. Loads with only on-off capability (such as clothes washers and dryers) provide less flexibility than resources that can be ramped or step-changed. Add-on devices may be able to provide extra demand response capabilities. Still, operating residential loads effectively requires awareness of the delicate balance of occupants health and comfort and electrical energy consumption. This report is Phase I of a series of reports aimed at identifying gaps in automated home energy management systems for incorporation of building appliances, vehicles, and renewable adoption into a smart grid, specifically with the intent of examining demand response and load factor control for power system support. The objective is to capture existing gaps in load control, energy management systems, and sensor technology with consideration of PHEV and renewable technologies to establish areas of research for the Department of Energy. In this report, (1) data is collected and examined from state of the art homes to characterize the primary residential loads as well as PHEVs and photovoltaic for potential adoption into energy management control strategies; and (2) demand response rules and requirements across the various demand response programs are examined for potential participation of residential loads. This report will be followed by a Phase II report aimed at identifying the current state of technology of energy management systems, sensors, and communication technologies for demand response and load factor control applications for the residential sector. The purpose is to cover the gaps that exist in the information captured by the sensors for energy management system to be able to provide demand response and load factor control. The vision is the development of an energy management system or other controlling enterprise hardware and software that is not only able to control loads, PHEVs, and renewable generation for demand response and load factor control, but also to do so with consumer comforts in mind and in an optimal fashion.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Implementing High Performance Remote Method Invocation in CCA

We report our effort in engineering a high performance remote method invocation (RMI) mechanism for the Common Component Architecture (CCA). This mechanism provides a highly efficient and easy-to-use mechanism for distributed computing in CCA, enabling CCA applications to effectively leverage parallel systems to accelerate computations. This work is built on the previous work of Babel RMI. Babel is a high performance language interoperability tool that is used in CCA for scientific application writers to share, reuse, and compose applications from software components written in different programming languages. Babel provides a transparent and flexible RMI framework for distributed computing. However, the existing Babel RMI implementation is built on top of TCP and does not provide the level of performance required to distribute fine-grained tasks. We observed that the main reason the TCP based RMI does not perform well is because it does not utilize the high performance interconnect hardware on a cluster efficiently. We have implemented a high performance RMI protocol, HPCRMI. HPCRMI achieves low latency by building on top of a low-level portable communication library, Aggregated Remote Message Copy Interface (ARMCI), and minimizing communication for each RMI call. Our design allows a RMI operation to be completed by only two RDMA operations. We also aggressively optimize our system to reduce copying. In this paper, we discuss the design and our experimental evaluation of this protocol. Our experimental results show that our protocol can improve RMI performance by an order of magnitude.

99 GENERAL AND MISCELLANEOUS↗

Radioactive Decay Chain Truncation Rules for Emergency Response Radiological Assessments

A set of radionuclide - decay chain truncation rules have been developed for use in the Turbo FRMAC and Specialized Hazard Assessment Response Capability (SHARC) software programs used to support radiological emergency response activities . Following the proposed rules, the software will truncate a decay chain after it encounters a progeny radionuclide with a half - life greater than 5,000 years. An analysis of the projected dose from many parent and progeny radionuclides over a 50 - year time period yielded that a radionuclide half - life cutoff of 5,000 years will exclude a negligible dose. Implementing the truncation rules will reduce the time required for assessments and minimize computer hardware requ irements without having a significant detrimental effect on dose projections and emergency response decisions. It is noted that the truncation rules may not be suited for long - term ( greater than 50 year) environmental assessments.

07 ISOTOPE AND RADIATION SOURCES↗

LEED: A Lightwave Energy-Efficient Datacenter

The Lightwave Energy-Efficient Datacenter (LEED) program is a disruptive “green-field” approach that provides a quantum leap in the energy efficiency of datacenters. LEED’s fundamental value proposition is that a novel and re-architected optical network—RotorNet— can deliver “more bandwidth per buck” as well as unique system-level attributes that significantly improve overall datacenter energy efficiency and performance. LEED has developed three system-level testbeds. The first testbed uses calibrated hardware and software power measurements to determine server energy efficiency as a function of network bandwidth and workload. These measurements have shown that increasing network communications bandwidth dramatically increases server energy efficiency providing a realistic path to the overall ENLITENED program goal of doubling the number of transactions per joule. The second testbed demonstrates key hardware: a prototype low-loss, high-port count optical “selector switch”. This switch was fabricated, racked, and tested. Measured switch characteristics include loss, bandwidth, crosstalk, switch time, system-level switch time (including the transceivers), and bit error rate. The third testbed demonstrates a fully working and manufactured pinwheel design which dramatically lowers the cost of design, while delivering high switch radix and low reconfiguration times. The LEED project has tied these three novel photonic switch prototypes together with production servers and software through the development of a novel FPGA-based NIC platform called Corundum. Corundum ensures that the packet-switched protocols supported by commodity operating systems and devices can interface with the Rotor switch design. The LEED group has used this combined hardware and software prototype to characterize applications running at a commercially relevant scale. The project has used a combination of enhanced optical modulation amplitude (OMA) modulators, broadband multiplexers and demultiplexers, avalanche photodiodes, and a novel burst-mode receivers to enable the insertion of LEED-developed optical switches without the need for expensive optical amplification. Our modeling has shown that measured LEED-developed device characteristics can achieve link characteristics of 2 pJ/bit including both transceivers and the Rotor switch. In summary, the LEED program has demonstrated a credible and practical path, through novel hardware and software, to realize the program objectives of ENLITENED. The net result will ensure that the United States maintains its strength in the crucial sector of Information Technology, which is vital to both our economic security and our national security.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Improving performance via mini-applications.

Application performance is determined by a combination of many choices: hardware platform, runtime environment, languages and compilers used, algorithm choice and implementation, and more. In this complicated environment, we find that the use of mini-applications - small self-contained proxies for real applications - is an excellent approach for rapidly exploring the parameter space of all these choices. Furthermore, use of mini-applications enriches the interaction between application, library and computer system developers by providing explicit functioning software and concrete performance results that lead to detailed, focused discussions of design trade-offs, algorithm choices and runtime performance issues. In this paper we discuss a collection of mini-applications and demonstrate how we use them to analyze and improve application performance on new and future computer platforms.

97 MATHEMATICS AND COMPUTING↗

Towards a theory of economic value for modeling and simulation: incremental cost of parallel simulation (wip)

A useful perspective on the economic value of simulation in engineering comes from considering the role simulation plays in constructing a system. We propose a conceptual model that combines an embryonic concept of the value of an information bit with cost estimation tools used in software engineering. The model provides an economic justification for the common conception that models should be built to address specific questions rather than to comprehensively represent a referent system. Extending these ideas, we offer a model for the incremental value of parallel execution to explain why simulation applications that take advantage of sophisticated parallel discrete event simulation tools form a relatively narrow niche despite the ubiquity of parallel computing hardware. The proposed model enables us to bring value of information criteria into model development and to make predictions about the future of parallel simulation applications.

Nutaro, James J↗

SymPLe 1131: A novel architectural solution for the realization of verifiable digital I and C systems and embedded digital devices - 387

One of the main reasons for the increasing popularity of FPGAs in embedded systems and digital I and C systems is that they provide many of the advantages from both hardware and software components. FPGAs provide configurability approaching that of SW, while at the same time delivering deterministic behavior of pure hardware solutions. However, with regard to Software Common Cause Failures (CCF), the use of FPGAs in digital I and C platforms should not be seen as plug-in remedy for reduction or elimination of CCF. To address CCF, we argue that it is not enough to manage the complexity of an I and C device or system, but we must also have the ability to constrain complexity (as needed) and rigorously reason about execution and device functionality. This paper presents the work done regarding an FPGA overlay architecture called SymPLe. SymPLe is designed to reduce the gap between software and hardware approaches for digital I and C systems and increases deterministic behavior and verifiability of the application, architecture and safety-critical system while reasoning about CCF. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗