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 271 records · Page 15

High power, gel polymer lithium-ion cells with improved low temperature performance for NASA and DoD applications

Both NASA and the U.S. Army have interest in developing secondary energy storage devices that are capable of meeting the demanding performance requirements of aerospace and man-portable applications. In order to meet these demanding requirements, gel-polymer electrolyte-based lithium-ion cells are being actively considered, due to their promise of providing high specific energy and enhanced safety aspects.

high power li-ion batteries↗

Fault Detection, Isolation and Recovery (FDIR) Portable Liquid Oxygen Hardware Demonstrator

The Fault Detection, Isolation and Recovery (FDIR) hardware demonstration will highlight the effort being conducted by Constellation's Ground Operations (GO) to provide the Launch Control System (LCS) with system-level health management during vehicle processing and countdown activities. A proof-of-concept demonstration of the FDIR prototype established the capability of the software to provide real-time fault detection and isolation using generated Liquid Hydrogen data. The FDIR portable testbed unit (presented here) aims to enhance FDIR by providing a dynamic simulation of Constellation subsystems that feed the FDIR software live data based on Liquid Oxygen system properties. The LO2 cryogenic ground system has key properties that are analogous to the properties of an electronic circuit. The LO2 system is modeled using electrical components and an equivalent circuit is designed on a printed circuit board to simulate the live data. The portable testbed is also be equipped with data acquisition and communication hardware to relay the measurements to the FDIR application running on a PC. This portable testbed is an ideal capability to perform FDIR software testing, troubleshooting, training among others.

Oostdyk, Rebecca L.↗

Thermal Analysis of Compressible CO2 Flow for Major Equipment of Fire Detection System

A thermal analysis of the compressible CO2 flow for the Portable Fire Extinguisher (PFE) system has been performed. The purpose of this analysis is to determine the discharged CO2 mass from the PFE tank through the Temporary Sleep Station (TeSS) nozzle in reflecting to the latest design of the extended nozzle, and to evaluate the thermal issues associated to the latest nozzle configuration. A SINDA/FLUINT model has been developed for this analysis. The model includes the PFE tank and the TeSS nozzle, and both have initial temperature of 72 of. In order to investigate the thermal effect on the nozzle due to discharging C02, the PFE TeSS nozzle pipe has been divided into three segments. This model also includes heat transfer predictions for PFE tank inner and outer wall surfaces. The simulation results show that the CO2 discharge rates have fulfilled the minimum flow requirements that the PFE system discharges 3.0 Ibm CO2 in 10 seconds and 5.5 Ibm of CO2 in 45 seconds during its operation. At 45 seconds, the PFE tank wall temperature is 63 OF, and the TeSS nozzle cover wall temperatures for the three segments are 47 OF, 53 OF and 37 OF, respectively. Thermal insulation for personal protection is used for the first two segments of the TeSS nozzle. The simulation results also indicate that at 50 seconds, the remaining CO2 in the tank may be near the triple point (gas, liquid and solid) state and, therefore, restricts the flow.

Zhang, Michael Y.↗

Thermal Analysis of Compressible CO2 Flow for PFE TeSS Nozzle of Fire Detection System

A thermal analysis of the compressible CO2 flow for the Portable Fire Extinguisher (PFE) system has been performed. A SINDA/FLUINT model has been developed for this analysis. The model includes the PFE tank and the TeSS nozzle, and both have initial temperature of 72 F. In order to investigate the thermal effect on the nozzle due to discharging CO2, the PFE TeSS nozzle pipe has been divided into three segments. This model also includes heat transfer predictions for PFE tank inner and outer wall surfaces. The simulation results show that the CO2 discharge rates have fulfilled the minimum flow requirements that the PFE system discharges 3.0 Ibm CO2 in 10 seconds and 5.5 Ibm of CO2 in 45 seconds during its operation. At 45 seconds, the PFE tank wall temperature is 63 F, and the TeSS nozzle cover wall temperatures for the three segments are 47 F, 53 F and 37 F, respectively. Thermal insulation for personal protection is used for the first two segments of the TeSS nozzle. The simulation results also indicate that at 50 seconds, the remaining CO2 in the tank may be near the triple point (gas, liquid and solid) state and, therefore, restricts the flow.

Zhang, Y. Michael↗

Development Specification for the Feedwater Supply Assembly (FSA), FSA-431 with Integrated Auxiliary Feedwater Supply Assembly (AFSA), FSA-531

The FSA with Integrated Aux FSA Specification establishes the requirements for design, performance, and testing of the FSA-431/FSA-531 assembly in compliance with CTSD-ADV-780, Development Specification for the Advanced EMU (AEMU) Portable Life Support System (PLSS). This section contains the technical design and performance requirements for the integrated assembly of the Feedwater Supply Assembly and Auxiliary Feedwater Supply Assembly for the Advanced EVA Development Portable Life Support Subsystem (PLSS).

Anchondo, Ian↗

Automatic Generation of Directive-Based Parallel Programs for Shared Memory Parallel Systems

The shared-memory programming model is a very effective way to achieve parallelism on shared memory parallel computers. As great progress was made in hardware and software technologies, performance of parallel programs with compiler directives has demonstrated large improvement. The introduction of OpenMP directives, the industrial standard for shared-memory programming, has minimized the issue of portability. Due to its ease of programming and its good performance, the technique has become very popular. In this study, we have extended CAPTools, a computer-aided parallelization toolkit, to automatically generate directive-based, OpenMP, parallel programs. We outline techniques used in the implementation of the tool and present test results on the NAS parallel benchmarks and ARC3D, a CFD application. This work demonstrates the great potential of using computer-aided tools to quickly port parallel programs and also achieve good performance.

Jin, Hao-Qiang↗

Hardware in the Loop Testing of an Iodine-Fed Hall Thruster

CUBESATS are relatively new spacecraft platforms that are typically deployed from a launch vehicle as a secondary payload,1 providing low-cost access to space for a wide range of end-users. These satellites are comprised of building blocks having dimensions of 10x10x10 cm cu and a mass of 1.33 kg (a 1-U size). While providing low-cost access to space, a major operational limitation is the lack of a propulsion system that can fit within a CubeSat and is capable of executing high delta v maneuvers. This makes it difficult to use CubeSats on missions requiring certain types of maneuvers (i.e. formation flying, spacecraft rendezvous). Recently, work has been performed investigating the use of iodine as a propellant for Hall-effect thrusters (HETs) 2 that could subsequently be used to provide a high specific impulse path to CubeSat propulsion. Iodine stores as a dense solid at very low pressures, making it acceptable as a propellant on a secondary payload. It has exceptionally high ρIsp (density times specific impulse), making it an enabling technology for small satellite near-term applications and providing the potential for systems-level advantages over mid-term high power electric propulsion options. Iodine flow can also be thermally regulated, subliming at relatively low temperature ( less than100 C) to yield I2 vapor at or below 50 torr. At low power, the measured performance of an iodine-fed HET is very similar to that of a state-of-the-art xenon-fed thruster. Just as importantly, the current-voltage discharge characteristics of low power iodine-fed and xenon-fed thrusters are remarkably similar, potentially reducing development and qualifications costs by making it possible to use an already-qualified xenon-HET PPU in an iodine-fed system. Finally, a cold surface can be installed in a vacuum test chamber on which expended iodine propellant can deposit. In addition, the temperature doesn't have to be extremely cold to maintain a low vapor pressure in the vacuum chamber (it is under 10(exp -6) torr at -75 C), making it possible to 'cryopump' the propellant with lower-cost recirculating refrigerant-based systems as opposed to using liquid nitrogen or low temperature gaseous helium cryopanels. In the present paper, we describe testing performed using an iodine-fed 200 W Hall thruster mounted to a thrust stand and operated in conjunction with MSFCs Small Projects Rapid Integration and Test Environment (SPRITE) Portable Hardware In the Loop (PHIL) hardware. This work is performed in support of the iodine satellite (iSAT) project, which aims to fly a 200-W iodine-fed thruster on a 12-U CubeSat. The SPRITE PHIL hardware allows a given vehicle to do a checkout of its avionics algorithm by allowing it to monitor and feed data to simulated sensors and effectors in a digital environment. These data are then used to determine the attitude of the vehicle and a separate computer is used to interpret the data set and visualize it using a 3D graphical interface. The PHIL hardware allows the testing of the vehicles bus by providing 'real' hardware interfaces (in the case of this test a real RS422 bus) and specific components can be modeled to show their interactions with the avionics algorithm (e.g. a thruster model). For the iSAT project the PHIL is used to visualize the operating cycle of the thruster and the subsequent effect this thrusting has on the attitude of the satellite over a given period of time. The test is controlled using software running on an Andrews Space Cortex 160 flight computer. This computer is the current baseline for a full iSAT mission. While the test could be conducted with a lab computer and software, the team chose to exercise the propulsion system with a representative CubeSat-class computer. For purposes of this test, the "flight" software monitored the propulsion and PPU systems, controlled operation of the thruster, and provided thruster state data to the PHIL simulation. Commands to operate the thruster were initiated from an operator's workstation outside the vacuum chamber and passed through the Cortex 160 to exercise portions of the flight avionics. Two custom-designed pieces of electronics hardware have been designed to operate the propellant feed system. One piece of hardware is an auxiliary board that controls a latch valve, proportional flow control valves (PFCVs) and valve heaters as well as measuring pressures, temperatures and PFCV feedback voltage. An onboard FPGA provides a serial link for issuing commands and manages all lower level input-output functions. The other piece of hardware is a power distribution board, which accepts a standard bus voltage input and converts this voltage into all the different current-voltage types required to operate the auxiliary board. These electronics boards are located in the vacuum chamber near the thruster, exposing this hardware to both the vacuum and plasma environments they would encounter during a mission, with these components communicating to the flight computer through an RS-422 interface. The auxiliary board FPGA provides a 28V MOSFET switch circuit with a 20ms pulse to open or close the iodine propellant feed system latch valve. The FPGA provides a pulse width modulation (PWM) signal to a DC/DC boost converter to produce the 12-120V needed for control of the proportional flow control valve. There are eight MOSFET-switched heating circuits in the system. Heaters are 28V and located in the latch valve, PFCV, propellant tank and propellant feed lines. Both the latch valve and PFCV have thermistors built into them for temperature monitoring. There are also seven resistance temperature device (RTD) circuits on the auxiliary board that can be used to measure the propellant tank and feedline temperatures. The signals are conditioned and sent to an analog to digital converter (ADC), which is directly commanded and controlled by the FPGA.

Polzin, Kurt A.↗

Loads Produced During the Ingression and Egression of the Portable Foot Restraint on the Hubble Space Telescope

The Hubble Space Telescope (HST) was deployed from the Space Shuttle Discovery on April 25, 1990. It is capable of performing observations in the visible, near-ultraviolet, and near-infrared (1150 A to 1 mm). The HST weighs 12 tons, and collects light with an 8-ft-diameter mirror. The attitude control and maneuvering is performed by four of six gyroscopes, or reaction wheels. The HST contains fine guidance sensors that lock onto guide stars to reduce the spacecraft drift and increase the pointing accuracy. The HST was designed to last 15 years, with crewed service missions approximately every three years. The first service mission, STS-61, took place in 1993. The second service mission took place in 1997. In 1999, the STS-103 crew performed the third service mission to the HST. This mission's purpose was to replace the right sensor units and make improvements on the fine guidance sensors. To perform these tasks on the HST, the STS-103 crewmembers used a portable foot restraint to anchor themselves to the HST in the zero-gravity environment. The solar arrays currently used on the telescope are second-generation, and therefore susceptible to loads placed on the telescope. The crew and Mission Operations Directorate worried about the damage that the crew could possibly cause during ingress and egress of the PFR and by transferring loads to the solar arrays. The purpose of this study is to inform the crewmembers of the loads they are imparting on the HST, and train them to decrease these loads to a safer level. Minimizing these loads will significantly decrease the chance of crewmembers causing damage to the solar arrays while repairing the HST.

Ramsey, Susan↗

Development Specification for the Portable Life Support System (PLSS) Thermal Loop Pump

The AEMU Thermal Loop Pump Development Specification establishes the requirements for design, performance, and testing of the Water Pump as part of the Thermal System of the Advanced Portable Life Support System (PLSS). It is envisioned that the Thermal Loop Pump is a positive displacement pump that provides a repeatable volume of flow against a given range of back-pressures provided by the various applications. The intention is to operate the pump at a fixed speed for the given application. The primary system is made up of two identical and redundant pumps of which only one is in operation at given time. The Auxiliary Loop Pump is an identical pump design to the primary pumps but is operated at half the flow rate. Inlet positive pressure to the pumps is provided by the upstream Flexible Supply Assembly (FSA-431 and FSA-531) which are physically located inside the suit volume and pressurized by suit pressure. An integrated relief valve, placed in parallel to the pump's inlet and outlet protects the pump and loop from over-pressurization. An integrated course filter is placed upstream of the pump's inlet to provide filtration and prevent potential debris from damaging the pump.

Anchondo, Ian↗

Development of a Fan for Future Space Suit Applications

NASA's next generation space suit system will place new demands on the fan used to circulate breathing gas through the ventilation loop of the portable life support system. Long duration missions with frequent extravehicular activities (EVAs), the requirement for significant increases in reliability and durability, and a mission profile that imposes strict limits on weight, volume and power create the basis for a set of requirements that demand more performance than is available from existing fan designs. This paper describes the development of a new fan to meet these needs. A centrifugal fan was designed with a normal operating speed of approximately 39,400 rpm to meet the ventilation flow requirements while also meeting the aggressive minimal packaging, weight and power requirements. The prototype fan also operates at 56,000 rpm to satisfy a second operating condition associated with a single fan providing ventilation flow to two spacesuits connected in series. This fan incorporates a novel nonmetallic "can" to keep the oxygen flow separate from the motor electronics, thus eliminating ignition potential. The nonmetallic can enables a small package size and low power consumption. To keep cost and schedule within project bounds a commercial motor controller was used. The fan design has been detailed and implemented using materials and approaches selected to address anticipated mission needs. Test data is presented to show how this fan performs relative to anticipated ventilation requirements for the EVA portable life support system. Additionally, data is presented to show tolerance to anticipated environmental factors such as acoustics, shock, and vibration. Recommendations for forward work to progress the technology readiness level and prepare the fan for the next EVA space suit system are also discussed.

Paul. Heather L.↗

MUPPET: An automated OpenMP mutation testing framework for performance optimization

MUPPET is a tool for OpenMP programs that identifies program modifications, called mutations, aimed at improving program performance. Existing performance optimization techniques, including profiling-based and auto-tuning techniques, fail to indicate program modifications at the source level thus preventing their portability across compilers. MUPPET aims to help HPC developers reason about performance defects and missed opportunities to improve performance at the source code level.

Parasyris, Konstantinos↗

Scaling neural simulations in STACS

Abstract As modern neuroscience tools acquire more details about the brain, the need to move towards biological-scale neural simulations continues to grow. However, effective simulations at scale remain a challenge. Beyond just the tooling required to enable parallel execution, there is also the unique structure of the synaptic interconnectivity, which is globally sparse but has relatively high connection density and non-local interactions per neuron. There are also various practicalities to consider in high performance computing applications, such as the need for serializing neural networks to support potentially long-running simulations that require checkpoint-restart. Although acceleration on neuromorphic hardware is also a possibility, development in this space can be difficult as hardware support tends to vary between platforms and software support for larger scale models also tends to be limited. In this paper, we focus our attention on Simulation Tool for Asynchronous Cortical Streams (STACS), a spiking neural network simulator that leverages the Charm++ parallel programming framework, with the goal of supporting biological-scale simulations as well as interoperability between platforms. Central to these goals is the implementation of scalable data structures suitable for efficiently distributing a network across parallel partitions. Here, we discuss a straightforward extension of a parallel data format with a history of use in graph partitioners, which also serves as a portable intermediate representation for different neuromorphic backends. We perform scaling studies on the Summit supercomputer, examining the capabilities of STACS in terms of network build and storage, partitioning, and execution. We highlight how a suitably partitioned, spatially dependent synaptic structure introduces a communication workload well-suited to the multicast communication supported by Charm++. We evaluate the strong and weak scaling behavior for networks on the order of millions of neurons and billions of synapses, and show that STACS achieves competitive levels of parallel efficiency.

59 BASIC BIOLOGICAL SCIENCES↗

Low-cost, portable fire hose tester

Availability of pumping unit permits scheduling and performing required periodic hose tests in proper manner while retaining full fire equipment readiness. Use of pumping unit preserves operating life and capability of pumper truck.

Jocke, R. F.↗

Accelerating Application Bulk Synchronous Writes in HPC Environments

High-bandwidth storage tiers are becoming more common for their capability to absorb high-rate, bursty I/Os. Notably, the designs of these fast storage tiers differ from system to system. The variation of these layers and non-uniform methods of access can pose chal- lenges for applications seeking to run at multiple HPC facilities. Therefore, in this work, we present Spectral, a rapid-output ab- straction library to accelerate application, bulk-synchronous writes on HPC systems. We design Spectral to enable applications to use high-bandwidth storage, such as node-local storage and dis- tributed, write-caches (e.g., burst buffers) transparently without requiring modifications to the application or file system source code. The key idea is to allow applications to spend most of the time performing productive work and to not require any source code changes for maximum portability on different HPC archi- tectures. Spectral internally re-routes write-only files through available, high-performance I/O resources before ultimately mi- grating them to the shared global parallel file system. For instance, on Summit, Spectral transparently places application outputs on node-local storage and then utilizes asynchronous migration to the center-wide GPFS file system. We evaluate Spectral on the Summit HPC system (1024 nodes) using the IOR benchmark and real scientific applications. Spectral shows linear performance scaling, improving application write performance by over an order of magnitude when compared to GPFS.

Khan, Awais↗

Particle simulation in a multiprocessor environment

A parallel implementation of a particle simulation method that is portable between a wide class of multiprocessor computers is presented. A fine grain spatial decomposition is utilized where several subdomains having a regular structure are computed at each processing node. This leads directly to an efficient and straightforward load balancing scheme if the number of subdomains at each processor is permitted to vary in an appropriate manner. Three dimensional simulations incorporating full thermochemical nonequilibrium are possible using the resulting code. Vectorizable algorithms are retained from earlier work allowing efficient use of deeply pipelined node processors where available. Performance results are presented from three different machine architectures demonstrating the portability of the code. On a 128-node Intel iPSC/860, performance is twice that of a single Cray-Y/MP CPU running a highly vectorized simulation code. Speedup is linear over the full range of number of processors on all target machines, indicating scalability of the method to higher degrees of parallelism.

Mcdonald, Jeffrey D.↗

IRIS Reimagined: Advancements in Intelligent Runtime System for Task-Based Programming

Task-based programming models are gaining traction in scientific computing. IRIS is a portable runtime system that exploits multiple heterogeneous programming systems and can discover available resources and manage multiple diverse programming systems (e.g., CUDA, Hexagon, HIP, Level Zero, OpenCL, and OpenMP) simultaneously. It accounts for the constraints of task dependencies and provides customizable scheduling policies to map those tasks to heterogeneous devices. In this paper, we present new capabilities added to IRIS to improve its portability for heterogeneous programming, build-friendliness, and performance efficiency. The new additions include vendor-specific kernel support, a runtime system with a foreign function interface to eliminate writing wrapper or boilerplate code for heterogeneous kernels, an easy-to-use and configurable CMake-based build environment, automatic and efficient data transfers and orchestration, and the Hunter and DAGGER toolchains to evaluate IRIS’s task scheduling algorithms.

Miniskar, Narasinga Rao↗

Program for Development of Artificial Intelligence

C Language Integrated Production System (CLIPS) computer program is shell for developing expert systems. Designed to enable research, development, and delivery of artificial intelligence on conventional computers. Primary design goals for CLIPS are portability, efficiency, and functionality. Meets or out-performs most microcomputer- and minicomputer-based artificial-intelligence tools. Written in C.

Riley, Gary↗

A direct broadcast satellite-audio experiment

System studies have been carried out over the past three years at the Jet Propulsion Laboratory (JPL) on digital audio broadcasting (DAB) via satellite. The thrust of the work to date has been on designing power and bandwidth efficient systems capable of providing reliable service to fixed, mobile, and portable radios. It is very difficult to predict performance in an environment which produces random periods of signal blockage, such as encountered in mobile reception where a vehicle can quickly move from one type of terrain to another. For this reason, some signal blockage mitigation techniques were built into an experimental DAB system and a satellite experiment was conducted to obtain both qualitative and quantitative measures of performance in a range of reception environments. This paper presents results from the experiment and some conclusions on the effectiveness of these blockage mitigation techniques.

Vaisnys, Arvydas↗