Search NASA⌕ Search

SEARCH · Search NASA

Results for “Heterogeneous systems”

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 325 records · Page 18

Performance Assessment of OpenMP Compilers Targeting NVIDIA V100 GPUs

Heterogeneous systems are becoming increasingly prevalent. In order to exploit the rich compute resources of such systems, robust programming models are needed for application developers to seamlessly migrate legacy code from today’s systems to tomorrow’s. Over the past decade and more, directives have been established as one of the promising paths to tackle programmatic challenges on emerging systems. This work focuses on applying and demonstrating OpenMP offloading directives on five proxy applications. We observe that the performance varies widely from one compiler to the other; a crucial aspect of our work is reporting best practices to application developers who use OpenMP offloading compilers. While some issues can be worked around by the developer, there are other issues that must be reported to the compiler vendors. By restructuring OpenMP offloading directives, we gain an 18x speedup for the su3 proxy application on NERSC’s Cori system when using the Clang compiler, and a 15.7x speedup by switching max reductions to add reductions in the laplace mini-app when using the Cray-llvm compiler on Cori.

Davis, Josh↗

Present status of Stacy modification program and fundamental nuclear properties of experimental cores related to fuel debris criticality - 14264

A modification program of the Static Experiment Critical Facility, STACY is now undergoing in Japan Atomic Energy Agency, JAEA, in order to accumulate fundamental critical data relating the critical control technology for fuel debris treatment in the Fukushima Daiichi Nuclear Power Station, 1FNPS. In accordance with the new regulatory requirement for research reactors established by Nuclear Regulation Authority of Japan, NRA in December 2013, fundamental design policies and basic nuclear properties of STACY have been confirmed for the critical experiments which are oriented to research on criticality control in the 1FNPS. Reactivity control in the STACY experiments is made by adjusting the water level in a core tank. The moderating ratio of the heterogeneous system which determines neutron spectrum can be adjusted by changing lattice plates. Safety review by NRA for revised basic design started in March, 2015. This paper described main specifications of experimental cores for license procedure, the availability of re activity control system, and the range of nuclear characteristics such as reactivity control, reactivity coefficients and kinetic parameters, which dominate static and transient characteristics of the STACY cores. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Force-triggered, Bio-based, Sealants for Prefabricated Building Components: Towards Improved Efficiency, Performance and Sustainability

The prefabricated building construction industry has made extensive progress in expediting the manufacture of prefabricated components at offsite plants. However, this progress has not translated to the assembly of the prefabricated components at the construction site. Case in point, sealing the joints between components to prevent air leaks requires the manual application of tape, caulk, or spray foam at the jobsite, and performance is highly dependent on the skills of the installer. To reduce assembly time and improve assembly quality of prefabricated components, we developed a sealant that can be installed at the plant and triggered at the jobsite. Additionally, we used this opportunity to lower the use of fossil fuel derived feedstocks and introduced bio-based alternatives to decrease the embodied carbon of the new sealant. We evaluated a series of force-triggered, bio-based, high strength, and fast curing sealants, consisting of a one-part heterogeneous system. These sealants are derived from formulations with ≥80% of biogenic carbon, consisting of a cardanol derived diepoxy that is microencapsulated in a polymer shell and embedded in a cardanol derived amine curing agent. The microcapsule shell allows separation of the reactive species in the one part sealant allowing shelf stability to an otherwise fast curing system. When the microcapsules are broken and activated by force, the highly reactive species mix and cure, exhibiting peel strengths up to 143 ppi. The shelf stability of these sealants and the on-demand triggering of the curing reactions enable installation on prefabricated components and storage prior to delivery and assembly at a jobsite, which could result in consistent sealant application with lower installation time than tapes and caulks at the construction site.

Cortes Guzman, Karen [ORNL] (ORCID:000000028793468↗

A Comparison of Homogeneous and Heterogeneous Uranium Metal-Water Systems using Calculated and Experimental Critical Data

Heterogeneous effects of fissile units latticed in water has been documented in several forms in commonly referenced handbooks and guides. Many of these documents provide guidance for when heterogeneous systems are more reactive than their homogenous counterparts if controlling fissile mass or volume. This information provides insight into when heterogeneity should be considered for conservatism, however this information is not always displayed in a manner that is comparable to commonly referenced data, such as critical curves based on spherical systems. This paper aims to provide a juxtaposition of homogenous and heterogeneous uranium metal-water systems using both experimental and calculated critical data displayed in the format of commonly referenced critical curves. This format allows for easy comparison between the two systems against parameters that are often considered for single unit analysis such as: uranium density, fissile mass, system volume, and total system mass (fissile mass plus moderator mass). Calculated critical spherical systems provide an equal comparison between latticed geometry types as the latticed array can be cut off or restricted in the same manner in each series of models, which is not true for experimental values. Additionally, enrichment of the latticed units can be made uniform in the calculated systems, which is also difficult to achieve when referencing experimental data of varying latticed geometries. A comparison of calculated critical values and available experimental values is provided to show how these parameters can impact the critical spherical system result.

36 MATERIALS SCIENCE↗

A Comparison of Homogeneous and Heterogeneous Uranium Metal-Water Systems using Calculated and Experimental Critical Data

Heterogeneous effects of fissile units latticed in water has been documented in several forms in commonly referenced handbooks and guides. Many of these documents provide guidance for when heterogeneous systems are more reactive than their homogenous counterparts if controlling fissile mass or volume. This information provides insight into when heterogeneity should be considered for conservatism, however this information is not always displayed in a manner that is comparable to commonly referenced data, such as critical curves based on spherical systems. This paper aims to provide a juxtaposition of homogenous and heterogeneous uranium metal-water systems using both experimental and calculated critical data displayed in the format of commonly referenced critical curves. This format allows for easy comparison between the two systems against parameters that are often considered for single unit analysis such as: uranium density, fissile mass, system volume, and total system mass (fissile mass plus moderator mass). Calculated critical spherical systems provide an equal comparison between latticed geometry types as the latticed array can be physically cut off or restricted in the same manner in each series of models, which is not true for experimental values. Additionally, enrichment of the latticed units can be made uniform in the calculated systems, which is difficult to achieve when referencing experimental data of varying latticed geometries. A comparison of calculated critical values and available experimental values is provided to show how these parameters can impact the critical spherical system result.

36 MATERIALS SCIENCE↗

Measuring the effects of heterogeneity on distributed systems

Distributed computer systems in daily use are becoming more and more heterogeneous. Currently, much of the design and analysis studies of such systems assume homogeneity. This assumption of homogeneity has been mainly driven by the resulting simplicity in modeling and analysis. A simulation study is presented which investigated the effects of heterogeneity on scheduling algorithms for hard real time distributed systems. In contrast to previous results which indicate that random scheduling may be as good as a more complex scheduler, this algorithm is shown to be consistently better than a random scheduler. This conclusion is more prevalent at high workloads as well as at high levels of heterogeneity.

El-Toweissy, Mohamed↗

A vector-product information retrieval system adapted to heterogeneous, distributed computing environments

Vector-product information retrieval (IR) systems produce retrieval results superior to all other searching methods but presently have no commercial implementations beyond the personal computer environment. The NASA Electronic Library Systems (NELS) provides a ranked list of the most likely relevant objects in collections in response to a natural language query. Additionally, the system is constructed using standards and tools (Unix, X-Windows, Notif, and TCP/IP) that permit its operation in organizations that possess many different hosts, workstations, and platforms. There are no known commercial equivalents to this product at this time. The product has applications in all corporate management environments, particularly those that are information intensive, such as finance, manufacturing, biotechnology, and research and development.

Rorvig, Mark E.↗

Parallel Monte Carlo Methods for Heterogeneous Hardware Computer Systems Using GPUs and Coprocessors: Recent Development of ARCHER Code - Paper 54

Traditional methods of accelerating Monte Carlo (MC) calculations typically use CPUs as the computing unit. The parallelism is based upon multithreading on a multi-core processor, and message passing interface (MPI) across many processors and nodes. In recent years, the hardware accelerators have been introduced by the high performance computing industry as an alternative approach to achieve massive parallelism. Hardware accelerators have the advantage of high Floating-point Operations Per Second (FLOPS) and high energy efficiency. Examples include graphics processing units (GPUs) and coprocessors. Compute-intensive programs can be off-loaded to them to be concurrently executed by hundreds or thousands of active threads. Existing production MC codes, however, cannot be directly compiled or executed on the new platforms. It is therefore necessary to rewrite or redevelop the code using the hardware accelerator specific programming models and APIs. Several studies have been conducted on using GPUs to accelerate MC calculations in reactor analysis and medical physics. In this paper, we present the recent progress at Rensselaer Polytechnic Institute (RPI) in developing a new parallel MC code called ARCHER (Accelerated Radiation-transport Computations in Heterogeneous Environments) for coupled photon-electron transport simulations. The code is designed as a test bed to evaluate the efficacy of heterogeneous computing systems for low-cost MC-based radiation dosimetric calculations. The code has three variants corresponding to three parallel hardware platforms: ARCHER-CPU (multi-core CPU), ARCHER-GPU (Nvidia GPU) and ARCHER-COP (Intel Xeon Phi coprocessor). The code has been used for several applications, including CT imaging dosimetry, radiotherapy dosimetry and radiation shielding design. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗

HetArch: Heterogeneous Microarchitectures for Superconducting Quantum Systems

Noisy Intermediate-Scale Quantum Computing (NISQ) has dominated headlines in recent years, with the longer-term vision of Fault-Tolerant Quantum Computation (FTQC) offering significant potential but at currently intractable resource costs and quantum error correction (QEC) overheads. For problems of interest, FTQC will require millions of physical qubits with long coherence times, high-fidelity gates, and compact sizes to surpass classical systems. Just as heterogeneous specialization has offered scaling benefits in classical computing, it is likewise gaining interest in FTQC. However, systematic use of heterogeneity in either hardware or software elements of FTQC systems remains a serious challenge due to the vast design space and the variable physical constraints. This paper meets the challenge of making heterogeneous FTQC design practical by introducing HetArch, a toolbox for designing heterogeneous quantum systems, and using it to explore heterogeneous design scenarios. Using a hierarchical approach, we successively break quantum algorithms into smaller operations (akin to classical application kernels), thus greatly simplifying the design space and resulting tradeoffs. Specializing to superconducting systems, we then design optimized heterogeneous hardware composed of varied superconducting devices, abstracting physical constraints into design rules that enable devices to be assembled into standard cells optimized for specific operations, which, in turn, form heterogeneous modules optimized for quantum subroutines. Finally, we provide a heterogeneous design space exploration framework which reduces the simulation burden by a factor of 10^4 or more and allows us to characterize optimal design points. We use these techniques to design superconducting quantum modules for entanglement distillation, error correction, and code teleportation, reducing error rates by 2.6×, 10.7×, and 3.4× compared to homogeneous systems.

Quantum Computing, Quantum Physics, Computer Archi↗

Quantifying biogeochemical heterogeneity in soil systems

Soils are increasingly perceived as complex systems with properties and biogeochemical functions that vary on millimeter scales. Quantitative information about the resulting biogeochemical heterogeneity is needed to improve process knowledge and to render biogeochemical models more mechanistic. Here in this work, we demonstrate how standardized arrays of Pt-electrodes can be used to quantify biogeochemical or ‘functional’ soil heterogeneity, defined as the extent to which the soil is subdivided into microenvironments. Our case study confirmed the validity of this approach for a soil sequence consisting of a well-drained, a moderately well drained and a poorly drained Mollisol. We found that (i) variations in soil moisture content are the immediate cause for variations in functional heterogeneity, with (ii) soil porosity influencing rates and the magnitude of change. We posit that the deployment of standardized arrays of Pt-electrodes will offer an affordable option to monitor the general metabolic state of the soil system and simultaneously quantify the functional heterogeneity of underlying processes at any point in time. Such information should be useful to improve quantitative estimates of processes as diverse as trace gas emissions, trace gas consumption, reductive dehalogenation and mobilization of metals in the subsurface biosphere. Lastly, we recommend that parameterization of functional soil heterogeneity be included in long-term soil monitoring programs such as Superfund Sites, Critical Zone Observatories, Long Term Ecological Research (LTER) and National Ecological Observatory Network (NEON) sites.

54 ENVIRONMENTAL SCIENCES↗

An Efficient Referencing And Sample Positioning System To Investigate Heterogeneous Substances With Combined Microfocused Synchrotron X-ray Techniques

A referencing and sample positioning system has been developed to transfer object positions measured with an offline microscope to a synchrotron experimental station. The accuracy should be sufficient to deal with heterogeneous samples on micrometer scale. Together with an online fluorescence mapping visualisation the optical alignment helps to optimize measuring procedures for combined microfocused X-ray techniques.

39↗

Development Plus Kinetic and Mechanistic Studies of a Prototype Supported-Nanoparticle Heterogeneous Catalyst Formation System in Contact with Solution: Ir(1,5-COD)Cl/ -Al2O3 and Its Reduction by H2 to Ir(0)n/γ-Al2O3

An important question and hence goal in catalysis is how best to transfer the synthetic and mechanistic insights gained from the modern revolution in nanoparticle synthesis, characterization, and catalysis to prepare the next generation of improved, supported-nanoparticle heterogeneous catalysts. It is precisely this question and to-date somewhat elusive goal which are addressed by the present work. More specifically, the global hypothesis investigated herein is that the use of speciation-controlled, well-characterized, solid oxide supported-organometallic precatalysts in contact with solution will lead to the next generation of better composition, size- and shape-controlled, as well as highly active and reproducible, supported-nanoparticle heterogeneous catalysts-ones that can also be understood kinetically and mechanistically. Developed herein are eight criteria defining a prototype system for supported-nanoparticle heterogeneous catalyst formation in contact with solution. The initial prototype system explored is the precatalyst, Ir(1,5-COD)Cl/{gamma}-Al{sub 2}O{sub 3} (characterized via ICP, CO adsorption, IR, and XAFS spectroscopies), and the well-defined product, Ir(0){sub n}/{gamma}-Al{sub 2}O{sub 3} (characterized by reaction stoichiometry, TEM, and XAFS). The Ir(0){sub n}/{gamma}-Al{sub 2}O{sub 3} system proved to be a highly active and long-lived catalyst in the simple test reaction of cyclohexene hydrogenation and in comparison to two literature Ir(0){sub n}/Al{sub 2}O{sub 3} heterogeneous catalysts examined under identical conditions. High activity (2.2-4.8-fold higher than that of the literature Ir(0){sub n}/Al{sub 2}O{sub 3} catalysts tested under the same conditions) and good lifetime ({ge} 220,000 total turnovers of cyclohexene hydrogenation) are observed, in part by design since only acetone solvent, cyclohexene, and H{sub 2} are possible ligands in the resultant 'weakly ligated/labile-ligand' supported nanoclusters. Significantly, the Ir(1,5-COD)Cl/{gamma}-Al{sub 2}O{sub 3} + H{sub 2} {yields} Ir(0){sub n}/{gamma}-Al{sub 2}O{sub 3} heterogeneous catalyst formation kinetics were also successfully monitored using the cyclohexene hydrogenation reporter reaction method previously developed and applied to solution-nanoparticle formation. The observed sigmoidal supported-nanoparticle heterogeneous catalyst formation kinetics, starting from the Ir(1,5-COD)Cl/{gamma}-Al{sub 2}O{sub 3} precatalyst, are closely fit by the two-step mechanism of slow continuous nucleation (A {yields} B, rate constant k{sub 1} = 1.5(1.1) x 10{sup -3} h{sup -1}) followed by fast autocatalytic surface growth (A + B {yields} 2B, rate constant k{sub 2} = 1.6(2) x 10{sup 4} h{sup -1} M{sup -1}), where A is the Ir(1,5-COD)Cl/{gamma}-Al{sub 2}O{sub 3} precatalyst and B is the resultant Ir(0){sub n}/{gamma}-Al{sub 2}O{sub 3} catalyst. The kinetics are significant in establishing the ability to monitor the formation of supported-nanoparticle heterogeneous catalysts in contact with solution. They also suggest that the nine synthetic and mechanistic insights from the two-step mechanism of nanoparticle formation in solution should now apply also to the formation of supported-nanoparticle heterogeneous catalysts in contact with solution. The results open the door for new syntheses of supported-nanoparticle heterogeneous catalysts under nontraditional, mild, and flexible conditions where supported organometallics and other precursors are in contact with solution, so that additional variables such as the solvent choice, added ligands, solution temperature, and so on can be used to control the catalyst formation steps and, ideally, the resultant supported-nanoparticle heterogeneous catalyst composition, size, and shape.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Modeling heterogeneous processor scheduling for real time systems

A new model is presented to describe dataflow algorithms implemented in a multiprocessing system. Called the resource/data flow graph (RDFG), the model explicitly represents cyclo-static processor schedules as circuits of processor arcs which reflect the order that processors execute graph nodes. The model also allows the guarantee of meeting hard real-time deadlines. When unfolded, the model identifies statically the processor schedule. The model therefore is useful for determining the throughput and latency of systems with heterogeneous processors. The applicability of the model is demonstrated using a space surveillance algorithm.

Leathrum, J. F.↗

Graph Partitioning for Parallel Applications in Heterogeneous Grid Environments

The problem of partitioning irregular graphs and meshes for parallel computations on homogeneous systems has been extensively studied. However, these partitioning schemes fail when the target system architecture exhibits heterogeneity in resource characteristics. With the emergence of technologies such as the Grid, it is imperative to study the partitioning problem taking into consideration the differing capabilities of such distributed heterogeneous systems. In our model, the heterogeneous system consists of processors with varying processing power and an underlying non-uniform communication network. We present in this paper a novel multilevel partitioning scheme for irregular graphs and meshes, that takes into account issues pertinent to Grid computing environments. Our partitioning algorithm, called MiniMax, generates and maps partitions onto a heterogeneous system with the objective of minimizing the maximum execution time of the parallel distributed application. For experimental performance study, we have considered both a realistic mesh problem from NASA as well as synthetic workloads. Simulation results demonstrate that MiniMax generates high quality partitions for various classes of applications targeted for parallel execution in a distributed heterogeneous environment.

Bisws, Rupak↗

Systems, methods, and software for determining spatially variable distributions of the dielectric properties of a heterogeneous material

Systems, methods, and software for measuring the spatially variable relative dielectric permittivity of materials along a linear or otherwise configured sensor element, and more specifically the spatial variability of soil moisture in one dimension as inferred from the dielectric profile of the soil matrix surrounding a linear sensor element. Various methods provided herein combine advances in the processing of time domain reflectometry data with innovations in physical sensing apparatuses. These advancements enable high temporal (and thus spatial) resolution of electrical reflectance continuously along an insulated waveguide that is permanently emplaced in contact with adjacent soils. The spatially resolved reflectance is directly related to impedance changes along the waveguide that are dominated by electrical permittivity contrast due to variations in soil moisture. Various methods described herein are thus able to monitor soil moisture in profile with high spatial resolution.

36 MATERIALS SCIENCE↗

HIPLZ: Enabling performance portability for exascale systems

While heterogeneous computing has emerged as a dominant trend in current and future High-Performance Computing (HPC) systems, it is also widely recognized that this shift has led to increased software complexity due to a proliferation of programming systems for different heterogeneous processors. One such example is the Heterogeneous-Compute Interface for Portability from AMD (HIP ), which is composed of a C Runtime API and C++ Kernel Language. Many HPC applications will likely use HIP on future exascale systems (e.g., Frontier and El Capitan), but HIP currently only targets AMD and NVIDIA processors. This limitation creates challenges for users who would also like to run their applications on exascale systems based on other architectures (e.g., Aurora, which is based on Intel hardware) that are currently not targeted by HIP . In this paper, we introduce the design and implementation of HIPLZ , a compiler and runtime system that uses the Intel Level Zero API to support HIP on Intel GPU architectures. We discuss the design of HIPLZ , derived from HIPCL (an implementation of HIP on top of OpenCL ), and portability issues that occur from using the Level Zero runtime as a backend. We evaluate our implementation by running several performance benchmarks and mini-apps written in HIP on Intel architectures using HIPLZ . Our results show that this approach provides competitive performance relative to Intel's OpenCL implementations on Intel Gen9 and UHD Graphics 770 GPUs, while providing good coverage of features needed by HPC applications. Overall, this approach is a promising demonstration of enabling performance portability for exascale systems.

97 MATHEMATICS AND COMPUTING↗

Efficient Sparse Matrix-Matrix Multiplication on Heterogeneous High Performance Systems

The efficient implementation of sparse matrix-matrix multiplications on high performance parallel machines poses several challenges: large size of input matrices, compressed representation, density of the output matrices, partitioning and load balancing of matrices that present parts with large differences in density and, thus, in computation times. In this paper we show how, starting from the requirements of such application, we developed a framework that allows its efficient implementation on heterogeneous clusters. We introduce a task based programming model and a runtime supported execution model which provides dynamic load balancing on clusters composed by CPUs and GPUs, allowing better utilization of the system while easing the handling of sparse matrices. Our results show that our solution, which co-designs the application together with the programming model and the runtime system, is able to obtain significant speed-ups due to a virtually perfect load balancing with respect to other programming approaches.

97 MATHEMATICS AND COMPUTING↗