Search NASA⌕ Search

SEARCH · Search NASA

Results for “Performance Portability”

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 1,423 records · Page 79

Portable nitrous oxide sensor for understanding agricultural and soil emissions

Nitrous oxide (N2O) is the third most important greenhouse gas (GHG,) with an atmospheric lifetime of ~114 years and a global warming impact ~300 times greater than that of carbon dioxide. The main cause of nitrous oxide’s atmospheric increase is anthropogenic emissions, and over 80% of the current global anthropogenic flux is related to agriculture, including associated land-use change. An accurate assessment of N2O emissions from agriculture is vital not only for understanding the global N2O balance and its impact on climate but also for designing crop systems with lower GHG emissions. Such assessments are currently hampered by the lack of instrumentation and methodologies to measure ecosystem-level fluxes at appropriate spatial and temporal scales. Southwest Sciences and Princeton University are developing and testing new open-path eddy covariance instrumentation for continuous and fast (10 Hz) measurement of nitrous oxide emissions. An important advance, now being implemented, is the use of new mid-infrared laser sources that enable the development of exceptionally low power (<10 W) compact instrumentation that can be used even in remote sites lacking in power. The instrumentation will transform the ability to measure and understand ecosystem-level nitrous oxide fluxes. The Phase II results included successful extended field testing of prototype flux instruments, based on quantum cascade lasers, in collaboration with Michigan State University. Results of these tests demonstrated a flux detection limit of 5 µg m-2 s-1 and showed excellent agreement and correlation with measurements using chamber techniques. Initial tests of an instrument using an interband cascade laser (ICL) were performed, verifying that an order of magnitude reduction in instrument power requirements can be realized. These results point toward future improvements and testing leading to introduction of a commercial open path instrument for N2O flux measurements that is truly portable and cost-effective. The technology developed on this project is especially groundbreaking as it could be widely applied across FLUXNET and AmeriFlux sites (>1200 worldwide) for direct measurements of N2O exchange. The technology can be more broadly applied to gas monitoring requirements in industry, environmental monitoring, health and safety, etc.

47 OTHER INSTRUMENTATION↗

Performance of a Multifunctional Space Evaporator- Absorber-Radiator (SEAR)

The Space Evaporator-Absorber-Radiator (SEAR) is a nonventing thermal control subsystem that combines a Space Water Membrane Evaporator (SWME) with a Lithium Chloride Absorber Radiator (LCAR). The LCAR is a heat pump radiator that absorbs water vapor produced in the SWME. Because of the very low water vapor pressure at equilibrium with lithium chloride solution, the LCAR can absorb water vapor at a temperature considerably higher than the SWME, enabling heat rejection by thermal radiation from a relatively small area radiator. Prior SEAR prototypes used a flexible LCAR that was designed to be installed on the outer surface of a portable life support system (PLSS) backpack. This paper describes a SEAR subsystem that incorporates a very compact LCAR. The compact, multifunctional LCAR is built in the form of thin panels that can also serve as the PLSS structural shell. We designed and assembled a 2 sq ft prototype LCAR based on this design and measured its performance in thermal vacuum tests when supplied with water vapor by a SWME. These tests validated our models for SEAR performance and showed that there is enough area available on the PLSS backpack shell to enable heat rejection from the LCAR.

Izenson, Michael G.↗

Optimizing Blocking and Nonblocking Reduction Operations for Multicore Systems: Hierarchical Design and Implementation

Many scientific simulations, using the Message Passing Interface (MPI) programming model, are sensitive to the performance and scalability of reduction collective operations such as MPI Allreduce and MPI Reduce. These operations are the most widely used abstractions to perform mathematical operations over all processes that are part of the simulation. In this work, we propose a hierarchical design to implement the reduction operations on multicore systems. This design aims to improve the efficiency of reductions by 1) tailoring the algorithms and customizing the implementations for various communication mechanisms in the system 2) providing the ability to configure the depth of hierarchy to match the system architecture, and 3) providing the ability to independently progress each of this hierarchy. Using this design, we implement MPI Allreduce and MPI Reduce operations (and its nonblocking variants MPI Iallreduce and MPI Ireduce) for all message sizes, and evaluate on multiple architectures including InfiniBand and Cray XT5. We leverage and enhance our existing infrastructure, Cheetah, which is a framework for implementing hierarchical collective operations to implement these reductions. The experimental results show that the Cheetah reduction operations outperform the production-grade MPI implementations such as Open MPI default, Cray MPI, and MVAPICH2, demonstrating its efficiency, flexibility and portability. On Infini- Band systems, with a microbenchmark, a 512-process Cheetah nonblocking Allreduce and Reduce achieves a speedup of 23x and 10x, respectively, compared to the default Open MPI reductions. The blocking variants of the reduction operations also show similar performance benefits. A 512-process nonblocking Cheetah Allreduce achieves a speedup of 3x, compared to the default MVAPICH2 Allreduce implementation. On a Cray XT5 system, a 6144-process Cheetah Allreduce outperforms the Cray MPI by 145%. The evaluation with an application kernel, Conjugate Gradient solver, shows that the Cheetah reductions speeds up total time to solution by 195%, demonstrating the potential benefits for scientific simulations.

Gorentla Venkata, Manjunath↗

Performance of a Multifunctional Space Evaporator-Absorber-Radiator (SEAR)

The Space Evaporator-Absorber-Radiator (SEAR) is a nonventing thermal control subsystem that combines a Space Water Membrane Evaporator (SWME) with a Lithium Chloride Absorber Radiator (LCAR). The LCAR is a heat pump radiator that absorbs water vapor produced in the SWME. Because of the very low water vapor pressure at equilibrium with lithium chloride solution, the LCAR can absorb water vapor at a temperature considerably higher than the SWME, enabling heat rejection sufficient for most EVA activities by thermal radiation from a relatively small area radiator. Prior SEAR prototypes used a flexible LCAR that was designed to be installed on the outer surface of a portable life support system (PLSS) backpack. This paper describes a SEAR subsystem that incorporates a very compact LCAR. The compact, multifunctional LCAR is built in the form of thin panels that can also serve as the PLSS structural shell. We designed and assembled a 2 ft² prototype LCAR based on this design and measured its performance in thermal vacuum tests when supplied with water vapor by a SWME. These tests validated our models for SEAR performance and showed that there is enough area available on the PLSS backpack shell to enable rejection of metabolic heat from the LCAR. We used results of these tests to assess future performance potential and suggest approaches for integrating the SEAR system with future space suits.

Izenson, Michael G.↗

Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors

Abstract Efficient and accurate algorithms are necessary to reconstruct particles in the highly granular detectors anticipated at the High-Luminosity Large Hadron Collider and the Future Circular Collider. We study scalable machine learning models for event reconstruction in electron-positron collisions based on a full detector simulation. Particle-flow reconstruction can be formulated as a supervised learning task using tracks and calorimeter clusters. We compare a graph neural network and kernel-based transformer and demonstrate that we can avoid quadratic operations while achieving realistic reconstruction. We show that hyperparameter tuning significantly improves the performance of the models. The best graph neural network model shows improvement in the jet transverse momentum resolution by up to 50% compared to the rule-based algorithm. The resulting model is portable across Nvidia, AMD and Habana hardware. Accurate and fast machine-learning based reconstruction can significantly improve future measurements at colliders.

Physics↗

Revitalizing the Space Shuttle's Thermal Protection System with Reverse Engineering and 3D Vision Technology

The Space Shuttle is protected by a Thermal Protection System (TPS) made of tens of thousands of individually shaped heat protection tile. With every flight, tiles are damaged on take-off and return to earth. After each mission, the heat tiles must be fixed or replaced depending on the level of damage. As part of the return to flight mission, the TPS requirements are more stringent, leading to a significant increase in heat tile replacements. The replacement operation requires scanning tile cavities, and in some cases the actual tiles. The 3D scan data is used to reverse engineer each tile into a precise CAD model, which in turn, is exported to a CAM system for the manufacture of the heat protection tile. Scanning is performed while other activities are going on in the shuttle processing facility. Many technicians work simultaneously on the space shuttle structure, which results in structural movements and vibrations. This paper will cover a portable, ultra-fast data acquisition approach used to scan surfaces in this unstable environment.

Wilson, Brad↗

Revitalizing the Space Shuttle's Thermal Protection System with Reverse Engineering and 3D Vision Technology

The Space Shuttle is protected by a Thermal Protection System (TPS) made of tens of thousands of individually shaped heat protection tile. With every flight, tiles are damaged on take-off and return to earth. After each mission, the heat tiles must be fixed or replaced depending on the level of damage. As part of the return to flight mission, the TPS requirements are more stringent, leading to a significant increase in heat tile replacements. The replacement operation requires scanning tile cavities, and in some cases the actual tiles. The 3D scan data is used to reverse engineer each tile into a precise CAD model, which in turn, is exported to a CAM system for the manufacture of the heat protection tile. Scanning is performed while other activities are going on in the shuttle processing facility. Many technicians work simultaneously on the space shuttle structure, which results in structural movements and vibrations. This paper will cover a portable, ultra-fast data acquisition approach used to scan surfaces in this unstable environment.

Wilson, Brad↗

Experiences with High-Level Programming Directives for Porting Applications to GPUs. In: Facing the Multicore--Challenge II, Lecture Notes in Computer Science.

HPC systems now exploit GPUs within their compute nodes to accelerate program performance. As a result, high-end application development has become extremely complex at the node level. In addition to restructuring the node code to exploit the cores and specialized devices, the programmer may need to choose a programming model such as OpenMP or CPU threads in conjunction with an accelerator programming model to share and manage the different node resources. This comes at a time when programmer productivity and the ability to produce portable code has been recognized as a major concern. In order to offset the high development cost of creating CUDA or OpenCL kernels, directives have been proposed for programming accelerator devices, but their implications are not well known. In this paper, we evaluate the state of the art accelerator directives to program several applications kernels, explore transformations to achieve good performance, and examine the expressivity and performance penalty of using high-level directives versus CUDA. We also compare our results to OpenMP implementations to understand the benefits of running the kernels in the accelerator versus CPU cores.

CUDA Implementation↗

Experiences with High-Level Programming Directives for Porting Applications to GPUs

HPC systems now exploit GPUs within their compute nodes to accelerate program performance. As a result, high-end application development has become extremely complex at the node level. In addition to restructuring the node code to exploit the cores and specialized devices, the programmer may need to choose a programming model such as OpenMP or CPU threads in conjunction with an accelerator programming model to share and manage the difference node resources. This comes at a time when programmer productivity and the ability to produce portable code has been recognized as a major concern. In order to offset the high development cost of creating CUDA or OpenCL kernels, directives have been proposed for programming accelerator devices, but their implications are not well known. In this paper, we evaluate the state of the art accelerator directives to program several applications kernels, explore transformations to achieve good performance, and examine the expressiveness and performance penalty of using high-level directives versus CUDA. We also compare our results to OpenMP implementations to understand the benefits of running the kernels in the accelerator versus CPU cores.

43 PARTICLE ACCELERATORS↗

Ultralightweight Power System for Human-Portable Linac-Based X-Ray Sources

Industrial human-portable X-ray sources are widely used by security, nuclear safeguard, and defense agencies. However, the employed sources have significant energy, dose, size, weight, and power (SWaP) limitations, greatly affecting their practical application. RF linear accelerators (linacs) can serve as a flexible, reliable, and robust type of X-ray source if they can match the size, weight, cost, and imaging performance requirements of conventional ones. One of the most critical elements affecting these parameters is the high-voltage pulsed power supply system or modulator, which can make the largest contribution to the total weight and dimensions of the accelerator. Here, in this article, we present the design and demonstration results of a novel ultra lightweight power system based on a 24-kV solid-state Marx modulator for a hand-portable 0.15–2.0-MeV Ku -band linac-based X-ray source.

47 OTHER INSTRUMENTATION↗

Optimizing blocking and nonblocking reduction operations for multicore systems: Hierarchical design and implementation

Many scientific simulations, using the Message Passing Interface (MPI) programming model, are sensitive to the performance and scalability of reduction collective operations such as MPI_Allreduce and MPI_Reduce. These operations are the most widely used abstractions to perform mathematical operations over all processes that are part of the simulation. In this work, we propose a hierarchical design to implement the reduction operations on multicore systems. This design aims to improve the efficiency of reductions by 1) tailoring the algorithms and customizing the implementations for various communication mechanisms in the system 2) providing the ability to configure the depth of hierarchy to match the system architecture, and 3) providing the ability to independently progress each of this hierarchy. Using this design, we implement MPI_Allreduce and MPI_Reduce operations (and its nonblocking variants MPI_Iallreduce and MPI_Ireduce) for all message sizes, and evaluate on multiple architectures including InfiniBand and Cray XT5. We leverage and enhance our existing infrastructure, Cheetah, which is a framework for implementing hierarchical collective operations to implement these reductions. The experimental results show that the Cheetah reduction operations outperform the production-grade MPI implementations such as Open MPI default, Cray MPI, and MVAPICH2, demonstrating its efficiency, flexibility and portability. On Infini-Band systems, with a microbenchmark, a 512-process Cheetah nonblocking Allreduce and Reduce achieves a speedup of 23x and 10x, respectively, compared to the default Open MPI reductions. The blocking variants of the reduction operations also show similar performance benefits. A 512-process nonblocking Cheetah Allreduce achieves a speedup of 3x, compared to the default MVAPICH2 Allreduce implementation. On a Cray XT5 system, a 6144-process Cheetah Allreduce outperforms the Cray MPI by 145%. The evaluation with an application kernel, Conjugate Gradient solver, shows that the Cheetah reductions speeds up total time to solution by 195%, demonstrating the potential benefits for scientific simulations.

Venkata, Manjunath Gorentla↗

MFIX-Exa: Performance prediction of multiphase energy conversion devices

MFIX-Exa targets the high-fidelity CFD-DEM model in which particles are unresolved by the fluid grid (typically using a fluid mesh approximately twice the particle diameter) but discrete particle dynamics including collisions are resolved with a simple linear-spring dashpot model. The fluid field is solved with a modern low Mach number formation of a cell-centered, nodal-pressure approximate projection method using a Godunov scheme . Physics capabilities include: complex geometries via embedded boundaries (EBs), open and closed system ideal gas equations of state, species transport and heterogeneous chemi- cal reactions. MFIX-Exa is built on the AMReX software framework, the ECP Block-Structured Adaptive Mesh Refinement (AMR) Co-Design Center, which allows the code to be portable and performant.Further integration into the ECP ecosystem includes HYPRE linear solvers and Ascent for in situ visualization. Current project efforts focus on scaling up realistic simulations to the KPP of the challenge problem: NETs 50kW chemical looping reactor, shakedown and scaling on JSLE and OLCF TDS systems and reaching for any remaining performance improvements.

Musser, Jordan↗

Recent Advances in Rechargeable Aluminum-Ion Batteries and Considerations for Their Future Progress

Owing to their high theoretical capacity and reliable operational safety, nonaqueous rechargeable aluminum batteries (RABs) have emerged as a promising class of battery materials and been intensively studied in recent years; however, a lack of suitable, high-performing positive electrode materials, along with the need for air-sensitive and expensive ionic liquid electrolytes, has significantly hindered the practical use of RABs in large-scale applications. Therefore, we sought to carefully analyze positive electrode materials and the associated electrolytes that have been reported in these battery systems in order to stimulate the design of the next generation of high-performance and low-cost RABs. In this review, we have summarized the electrode materials that have been used in both nonaqueous and aqueous RAB systems and provided a rational classification based on the types of materials used and their respective structures. Additionally, we have reviewed electrolytes employed in RABs and have categorized them according to two main types of applications, either for fixed battery systems or for use in portable devices. Here, a systematic account of recent developments on RABs, with a focus on electrode materials, innovative perspectives, and impending research efforts on future RABs, has been included. Finally, a proposed liquid RAB system is discussed with the aim of solving issues regarding fast-charging and long operational lifetimes, followed by insights into solid RABs for use in both portable and multistructural RAB systems.

25 ENERGY STORAGE↗

Ion beam analysis in cultural heritage studies: Milestones and perspectives

For three decades, ion beam analysis (IBA) in external mode was considered as the best choice for the characterisation of cultural heritage materials, as it combines excellent analytical performance and non-invasive character. However, in recent years, other analytical techniques arose as serious competitors, such as those based on synchrotron radiation (X-ray absorption, fluorescence or diffraction) or those using portable instruments (XRF, micro-Raman). It is shown that nevertheless IBA remains unmatched thanks to two unique features, namely the analysis of light elements and the high-resolution 3D chemical imaging.

36 MATERIALS SCIENCE↗

Surface inspection using FTIR spectroscopy

The use of reflectance Fourier transform infrared (FTIR) spectroscopy as a tool for surface inspection is described. Laboratory instruments and portable instruments can support remote sensing probes that can map chemical contaminants on surfaces with detection limits under the best of conditions in the sub-nanometer range, i.e.. near absolute cleanliness, excellent performance in the sub-micrometer range, and useful performance for films tens of microns thick. Examples of discovering and quantifying contamination such as mineral oils and greases, vegetable oils, and silicone oils on aluminum foil, galvanized sheet steel, smooth aluminum tubing, and sandblasted 7075 aluminum alloy and D6AC steel. The ability to map in time and space the distribution of oil stains on metals is demonstrated. Techniques associated with quantitatively applying oils to metals, subsequently verifying the application, and non-linear relationships between reflectance and the quantity oil are described.

Powell, G. L.↗

An interactive parallel programming environment applied in atmospheric science

This article introduces an interactive parallel programming environment (IPPE) that simplifies the generation and execution of parallel programs. One of the tasks of the environment is to generate message-passing parallel programs for homogeneous and heterogeneous computing platforms. The parallel programs are represented by using visual objects. This is accomplished with the help of a graphical programming editor that is implemented in Java and enables portability to a wide variety of computer platforms. In contrast to other graphical programming systems, reusable parts of the programs can be stored in a program library to support rapid prototyping. In addition, runtime performance data on different computing platforms is collected in a database. A selection process determines dynamically the software and the hardware platform to be used to solve the problem in minimal wall-clock time. The environment is currently being tested on a Grand Challenge problem, the NASA four-dimensional data assimilation system.

Interactive Display Devices↗

Ultrawideband Electromagnetic Interference to Aircraft Radios: Results of Limited Functional Testing With United Airlines and Eagles Wings Incorporated, in Victorville, California

On February 14, 2002, the FCC adopted a FIRST REPORT AND ORDER, released it on April 22, 2002, and on May 16, 2002 published in the Federal Register a Final Rule, permitting marketing and operation of new products incorporating UWB technology. Wireless product developers are working to rapidly bring this versatile, powerful and expectedly inexpensive technology into numerous consumer wireless devices. Past studies addressing the potential for passenger-carried portable electronic devices (PEDs) to interfere with aircraft electronic systems suggest that UWB transmitters may pose a significant threat to aircraft communication and navigation radio receivers. NASA, United Airlines and Eagles Wings Incorporated have performed preliminary testing that clearly shows the potential for handheld UWB transmitters to cause cockpit failure indications for the air traffic control radio beacon system (ATCRBS), blanking of aircraft on the traffic alert and collision avoidance system (TCAS) displays, and cause erratic motion and failure of instrument landing system (ILS) localizer and glideslope pointers on the pilot horizontal situation and attitude director displays. This report provides details of the preliminary testing and recommends further assessment of aircraft systems for susceptibility to UWB electromagnetic interference.

Ely, Jay J.↗

Ultrawideband Electromagnetic Interference to Aircraft Radios

A very recent FCC Final Rule now permits marketing and operation of new products that incorporate Ultrawideband (UWB) technology into handheld devices. Wireless product developers are working to rapidly bring this versatile, powerful and expectedly inexpensive technology into numerous consumer wireless devices. Past studies addressing the potential for passenger-carried portable electronic devices (PEDs) to interfere with aircraft electronic systems suggest that UWB transmitters may pose a significant threat to aircraft communication and navigation radio receivers. NASA, United Airlines and Eagles Wings Incorporated have performed preliminary testing that clearly shows the potential for handheld UWB transmitters to cause cockpit failure indications for the air traffic control radio beacon system (ATCRBS), blanking of aircraft on the traffic alert and collision avoidance system (TCAS) displays, and cause erratic motion and failure of instrument landing system (ILS) localizer and glideslope pointers on the pilot horizontal situation and attitude director displays. This paper provides details of the preliminary testing and recommends further assessment of aircraft systems for susceptibility to UWB electromagnetic interference.

Ely, Jay J.↗