Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Multiple processors”

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

Far Ultraviolet Imaging from the Image Spacecraft

Direct imaging of the magnetosphere by the IMAGE spacecraft will be supplemented by observation of the global aurora. The IMAGE satellite instrument complement includes three Far Ultraviolet (FUV) instruments. The Wideband Imaging Camera (WIC) will provide broad band ultraviolet images of the aurora for maximum spatial and temporal resolution by imaging the LBH N2 bands of the aurora. The Spectrographic Imager (SI), a novel form of monochromatic imager, will image the aurora, filtered by wavelength. The proton-induced component of the aurora will be imaged separately by measuring the Doppler-shifted Lyman-a. Finally, the GEO instrument will observe the distribution of the geocoronal emission to obtain the neutral background density source for charge exchange in the magnetosphere. The FUV instrument complement looks radially outward from the rotating IMAGE satellite and, therefore, it spends only a short time observing the aurora and the Earth during each spin. To maximize photon collection efficiency and use efficiently the short time available for exposures the FUV auroral imagers WIC and SI both have wide fields of view and take data continuously as the auroral region proceeds through the field of view. To minimize data volume, the set of multiple images are electronically co-added by suitably shifting each image to compensate for the spacecraft rotation. In order to minimize resolution loss, the images have to be distort ion-corrected in real time. The distortion correction is accomplished using high speed look up tables that are pre-generated by least square fitting to polynomial functions by the on-orbit processor. The instruments were calibrated individually while on stationary platforms, mostly in vacuum chambers. Extensive ground-based testing was performed with visible and near UV simulators mounted on a rotating platform to emulate their performance on a rotating spacecraft.

Mende, S. B.↗

Initial Kernel Timing Using a Simple PIM Performance Model

This presentation will describe some initial results of paper-and-pencil studies of 4 or 5 application kernels applied to a processor-in-memory (PIM) system roughly similar to the Cascade Lightweight Processor (LWP). The application kernels are: * Linked list traversal * Sun of leaf nodes on a tree * Bitonic sort * Vector sum * Gaussian elimination The intent of this work is to guide and validate work on the Cascade project in the areas of compilers, simulators, and languages. We will first discuss the generic PIM structure. Then, we will explain the concepts needed to program a parallel PIM system (locality, threads, parcels). Next, we will present a simple PIM performance model that will be used in the remainder of the presentation. For each kernel, we will then present a set of codes, including codes for a single PIM node, and codes for multiple PIM nodes that move data to threads and move threads to data. These codes are written at a fairly low level, between assembly and C, but much closer to C than to assembly. For each code, we will present some hand-drafted timing forecasts, based on the simple PIM performance model. Finally, we will conclude by discussing what we have learned from this work, including what programming styles seem to work best, from the point-of-view of both expressiveness and performance.

BRIEFING CHARTS↗

GTOSS: Generalized Tethered Object Simulation System

GTOSS represents a tether analysis complex which is described by addressing its family of modules. TOSS is a portable software subsystem specifically designed to be introduced into the environment of any existing vehicle dynamics simulation to add the capability of simulating multiple interacting objects (via multiple tethers). These objects may interact with each other as well as with the vehicle into whose environment TOSS is introduced. GTOSS is a stand alone tethered system analysis program, representing an example of TOSS having been married to a host simulation. RTOSS is the Results Data Base (RDB) subsystem designed to archive TOSS simulation results for future display processing. DTOSS is a display post processors designed to utilize the RDB. DTOSS extracts data from the RDB for multi-page printed time history displays. CTOSS is similar to DTOSS, but is designed to create ASCII plot files. The same time history data formats provided for DTOSS (for printing) are available via CTOSS for plotting. How these and other modules interact with each other is discussed.

Lang, David D.↗

Certainty grids for mobile robots

A numerical representation of uncertain and incomplete sensor knowledge called Certainty Grids has been used successfully in several mobile robot control programs, and has proven itself to be a powerful and efficient unifying solution for sensor fusion, motion planning, landmark identification, and many other central problems. Researchers propose to build a software framework running on processors onboard the new Uranus mobile robot that will maintain a probabilistic, geometric map of the robot's surroundings as it moves. The certainty grid representation will allow this map to be incrementally updated in a uniform way from various sources including sonar, stereo vision, proximity and contact sensors. The approach can correctly model the fuzziness of each reading, while at the same time combining multiple measurements to produce sharper map features, and it can deal correctly with uncertainties in the robot's motion. The map will be used by planning programs to choose clear paths, identify locations (by correlating maps), identify well-known and insufficiently sensed terrain, and perhaps identify objects by shape. The certainty grid representation can be extended in the same dimension and used to detect and track moving objects.

Moravec, H. P.↗

Interior Noise Reduction by Adaptive Feedback Vibration Control

The objective of this project is to investigate the possible use of adaptive digital filtering techniques in simultaneous, multiple-mode identification of the modal parameters of a vibrating structure in real-time. It is intended that the results obtained from this project will be used for state estimation needed in adaptive structural acoustics control. The work done in this project is basically an extension of the work on real-time single mode identification, which was performed successfully using a digital signal processor (DSP) at NASA, Langley. Initially, in this investigation the single mode identification work was duplicated on a different processor, namely the Texas Instruments TMS32OC40 DSP. The system identification results for the single mode case were very good. Then an algorithm for simultaneous two mode identification was developed and tested using analytical simulation. When it successfully performed the expected tasks, it was implemented in real-time on the DSP system to identify the first two modes of vibration of a cantilever aluminum beam. The results of the simultaneous two mode case were good but some problems were identified related to frequency warping and spurious mode identification. The frequency warping problem was found to be due to the bilinear transformation used in the algorithm to convert the system transfer function from the continuous-time domain to the discrete-time domain. An alternative approach was developed to rectify the problem. The spurious mode identification problem was found to be associated with high sampling rates. Noise in the signal is suspected to be the cause of this problem but further investigation will be needed to clarify the cause. For simultaneous identification of more than two modes, it was found that theoretically an adaptive digital filter can be designed to identify the required number of modes, but the algebra became very complex which made it impossible to implement in the DSP system used in this study. The on-line identification algorithm developed in this research will be useful in constructing a state estimator for feedback vibration control.

Lim, Tae W.↗

Impacts of the IBM Cell Processor to Support Climate Models

NASA is interested in the performance and cost benefits for adapting its applications to the IBM Cell processor. However, its 256KB local memory per SPE and the new communication mechanism, make it very challenging to port an application. We selected the solar radiation component of the NASA GEOS-5 climate model, which: (1) is representative of column physics (approximately 50% computational time), (2) has a high computational load relative to transferring data from and to main memory, (3) performs independent calculations across multiple columns. We converted the baseline code (single-precision, Fortran) to C and ported it with manually SIMDizing 4 independent columns and found that a Cell with 8 SPEs can process 2274 columns per second. Compared with the baseline results, the Cell is approximately 5.2X, approximately 8.2X, approximately 15.1X faster than a core on Intel Woodcrest, Dempsey, and Itanium2, respectively. We believe this dramatic performance improvement makes a hybrid cluster with Cell and traditional nodes competitive.

Zhou, Shujia↗

Parallelization of irregularly coupled regular meshes

Regular meshes are frequently used for modeling physical phenomena on both serial and parallel computers. One advantage of regular meshes is that efficient discretization schemes can be implemented in a straight forward manner. However, geometrically-complex objects, such as aircraft, cannot be easily described using a single regular mesh. Multiple interacting regular meshes are frequently used to describe complex geometries. Each mesh models a subregion of the physical domain. The meshes, or subdomains, can be processed in parallel, with periodic updates carried out to move information between the coupled meshes. In many cases, there are a relatively small number (one to a few dozen) subdomains, so that each subdomain may also be partitioned among several processors. We outline a composite run-time/compile-time approach for supporting these problems efficiently on distributed-memory machines. These methods are described in the context of a multiblock fluid dynamics problem developed at LaRC.

Chase, Craig↗

Performance Analysis of a Hybrid Overset Multi-Block Application on Multiple Architectures

This paper presents a detailed performance analysis of a multi-block overset grid compu- tational fluid dynamics app!ication on multiple state-of-the-art computer architectures. The application is implemented using a hybrid MPI+OpenMP programming paradigm that exploits both coarse and fine-grain parallelism; the former via MPI message passing and the latter via OpenMP directives. The hybrid model also extends the applicability of multi-block programs to large clusters of SNIP nodes by overcoming the restriction that the number of processors be less than the number of grid blocks. A key kernel of the application, namely the LU-SGS linear solver, had to be modified to enhance the performance of the hybrid approach on the target machines. Investigations were conducted on cacheless Cray SX6 vector processors, cache-based IBM Power3 and Power4 architectures, and single system image SGI Origin3000 platforms. Overall results for complex vortex dynamics simulations demonstrate that the SX6 achieves the highest performance and outperforms the RISC-based architectures; however, the best scaling performance was achieved on the Power3.

Djomehri, M. Jahed↗

Checksumming strategies for data in volatile memories

The increase in the number of processors needed to build exascale systems implies that the mean time between failure will further decrease, making it increasingly important to develop scalable techniques for fault tolerance. In this paper we develop an efficient checksum-based approach to fault tolerance for data in volatile memory systems, i.e., an approach without the need to save any data on stable persistent storage. The developed scheme is applicable in multiple scenarios, including: 1) online recovery of large read-only data structures from the memory of failed nodes, with very low storage overhead 2) online recovery from soft errors in blocked data, and 3) online recovery of read/write data via in-memory check-pointing. The approach uses a logical multi-dimension view of the data to be protected. Changing the dimensionality of the data view enables a trade-off between multiple factors, including the storage overheads, the checksum generation time, the failure recovery time, and the number of faults that can be tolerated. Experimental results demonstrating effectiveness are presented on a Cray XE6 system.

Arafat, Md H.↗

Computing Maximum Cardinality Matchings in Parallel on Bipartite Graphs via Tree-Grafting

It is difficult to obtain high performance when computing matchings on parallel processors because matching algorithms explicitly or implicitly search for paths in the graph, and when these paths become long, there is little concurrency. In spite of this limitation, we present a new algorithm and its shared-memory parallelization that achieves good performance and scalability in computing maximum cardinality matchings in bipartite graphs. This algorithm searches for augmenting paths via specialized breadth-first searches (BFS) from multiple source vertices, hence creating more parallelism than single source algorithms. Algorithms that employ multiple-source searches cannot discard a search tree once no augmenting path is discovered from the tree, unlike algorithms that rely on single-source searches. We describe a novel tree-grafting method that eliminates most of the redundant edge traversals resulting from this property of multiple-source searches. We also employ the recent direction-optimizing BFS algorithm as a subroutine to discover augmenting paths faster. Our algorithm compares favorably with the current best algorithms in terms of the number of edges traversed, the average augmenting path length, and the number of iterations. Here, we provide a proof of correctness for our algorithm. Our NUMA-aware implementation is scalable to 80 threads of an Intel multiprocessor and to 240 threads on an Intel Knights Corner coprocessor. On average, our parallel algorithm runs an order of magnitude faster than the fastest algorithms available. The performance improvement is more significant on graphs with small matching number.

97 MATHEMATICS AND COMPUTING↗

Effects of error sources on the parallelism of an optical matrix-vector processor

The error sources in a high accuracy optical matrix-vector processor are analyzed by numerical simulation in terms of their effects on the parallelism and speed of the processor. These effects are detailed for radices -2, -4 and -8. Radix -4 is shown to provide maximum parallel processing capabilities under the effects of the system's error sources. Processing speed is shown to be a function of matrix partitioning and the number of parallel processing channels. Consequently, radix -4 operation provides a higher processing speed than radix -2 and -8 for most matrix-vector multiplications when error source effects are considered.

Perlee, Caroline J.↗

Manned maneuvering unit applications for automated rendezvous and capture

Automated Rendezvous and Capture (AR&C) is an important technology to multiple National Aeronautics and Space Administration (NASA) programs and centers. The recent Johnson Spacecraft Center (JSC) AR&C Quality Function Deployment (QFD) has listed on-orbit demonstration of related technologies as a near term priority. Martin Marietta has been evaluating use of the Manned Maneuvering Unit (MMU) for a low cost near term on-orbit demonstration of AR&C technologies such as control algorithms, sensors, and processors as well as system level performance. The MMU Program began in 1979 as the method of repairing the Space Shuttle (STS) Thermal Protection System (the tiles). The units were not needed for this task, but were successfully employed during three Shuttle flights in 1984: a test flight was flown in in February as proof of concept, in April the MMU participated in the Solar Max Repair Mission, and in November the MMU's returned to space to successfully rescue the two errant satellites, Westar and Palapa. In the intervening years, the MMU simulator and MMU Qualification Test Unit (QTU) have been used for Astronaut training and experimental evaluations. The Extra-Vehicular Activities (EVA) Retriever has used the QTU, in an unmanned form, as a free-flyer on the Johnson Space Center (JSC) Precision Air Bearing Floor (PABF). Currently, the MMU is undergoing recertification for flight. The two flight units were removed from storage in September, 1991 and evaluation tests were performed. The tests demonstrated that the units are in good shape with no discrepancies that would preclude further use. The Return to Flight effort is currently clearing up recertification issues and evaluating the design against the present Shuttle environments.

Brehm, Donald L.↗

Leukemia, lymphoma and multiple myeloma mortality (1950–1999) and incidence (1969–1999) in the Eldorado uranium workers cohort

Uranium workers are chronically exposed to low levels of radon decay products (RDP) and gamma (γ) radiation. Risks of leukemia from acute and high doses of γ-radiation are well-characterized, but risks from lower doses and dose-rates and from RDP exposures are controversial. Few studies have evaluated risks of other hematologic cancers in uranium workers. The purpose of this study was to analyze radiation-related risks of hematologic cancers in the cohort of Eldorado uranium miners and processors first employed in 1932–1980 in relation to cumulative RDP exposures and γ-ray doses. The average cumulative RDP exposure was 100.2 working level months and the average cumulative whole-body γ-radiation dose was 52.2 millisievert. We identified 101 deaths and 160 cases of hematologic cancers in the cohort. Overall, male workers had lower mortality and cancer incidence rates for all outcomes compared with the general Canadian male population, a likely healthy worker effect. No statistically significant association between RDP exposure or γ-ray doses, or a combination of both, and mortality or incidence of any hematologic cancer was found. We observed consistent but non-statistically significant increases in risks of chronic lymphocytic leukemia (CLL) and Hodgkin lymphoma (HL) incidence and non-Hodgkin lymphoma (NHL) mortality with increasing γ-ray doses. These findings are consistent with recent studies of increased risks of CLL and NHL incidence after γ-radiation exposure. Further research is necessary to understand risks of other hematologic cancers from low-dose exposures to γ-radiation. - Highlights: • We analyzed long-term follow-up for hematologic cancers of the Eldorado uranium workers. • Workers were exposed to a unique combination of radon decay products (RDP) and gamma (γ) ray doses. • Exposures to RDP and γ-ray doses were not associated with significantly increased risks of cancers. • Radiation risks of chronic lymphocytic leukemia (CLL) and Hodgkin lymphoma were increased. • Study findings provide additional support for radiation-related risks of CLL.

54 ENVIRONMENTAL SCIENCES↗

Implementation of Adaptive Digital Controllers on Programmable Logic Devices

Much has been made of the capabilities of FPGA's (Field Programmable Gate Arrays) in the hardware implementation of fast digital signal processing (DSP) functions. Such capability also makes and FPGA a suitable platform for the digital implementation of closed loop controllers. There are myriad advantages to utilizing an FPGA for discrete-time control functions which include the capability for reconfiguration when SRAM- based FPGA's are employed, fast parallel implementation of multiple control loops and implementations that can meet space level radiation tolerance in a compact form-factor. Other researchers have presented the notion that a second order digital filter with proportional-integral-derivative (PID) control functionality can be implemented in an FPGA. At Marshall Space Flight Center, the Control Electronics Group has been studying adaptive discrete-time control of motor driven actuator systems using digital signal processor (DSF) devices. Our goal is to create a fully digital, flight ready controller design that utilizes an FPGA for implementation of signal conditioning for control feedback signals, generation of commands to the controlled system, and hardware insertion of adaptive control algorithm approaches. While small form factor, commercial DSP devices are now available with event capture, data conversion, pulse width modulated outputs and communication peripherals, these devices are not currently available in designs and packages which meet space level radiation requirements. Meeting our goals requires alternative compact implementation of such functionality to withstand the harsh environment encountered on spacecraft. Radiation tolerant FPGA's are a feasible option for reaching these goals.

Gwaltney, David A.↗

Method and apparatus for pulse width modulation control of an AC induction motor

An inverter is connected between a source of DC power and a three-phase AC induction motor, and a micro-processor-based circuit controls the inverter using pulse width modulation techniques. In the disclosed method of pulse width modulation, both edges of each pulse of a carrier pulse train are equally modulated by a time proportional to sin .THETA., where .THETA. is the angular displacement of the pulse center at the motor stator frequency from a fixed reference point on the carrier waveform. The carrier waveform frequency is a multiple of the motor stator frequency. The modulated pulse train is then applied to each of the motor phase inputs with respective phase shifts of 120.degree. at the stator frequency. Switching control commands of electronic switches in the inverter are stored in a random access memory (RAM) and the locations of the RAM are successively read out in a cyclic manner, each bit of a given RAM location controlling a respective phase input of the motor. The DC power source preferably comprises rechargeable batteries and all but one of the electronic switches in the inverter can be disabled, the remaining electronic switch being part of a flyback DC-DC converter circuit for recharging the battery.

Geppert, Steven↗

Evaluation of the Monotonic Lagrangian Grid and Lat-Long Grid for Air Traffic Management

The Air Traffic Monotonic Lagrangian Grid (ATMLG) is used to simulate a 24 hour period of air traffic flow in the National Airspace System (NAS). During this time period, there are 41,594 flights over the United States, and the flight plan information (departure and arrival airports and times, and waypoints along the way) are obtained from an Federal Aviation Administration (FAA) Enhanced Traffic Management System (ETMS) dataset. Two simulation procedures are tested and compared: one based on the Monotonic Lagrangian Grid (MLG), and the other based on the stationary Latitude-Longitude (Lat- Long) grid. Simulating one full day of air traffic over the United States required the following amounts of CPU time on a single processor of an SGI Altix: 88 s for the MLG method, and 163 s for the Lat-Long grid method. We present a discussion of the amount of CPU time required for each of the simulation processes (updating aircraft trajectories, sorting, conflict detection and resolution, etc.), and show that the main advantage of the MLG method is that it is a general sorting algorithm that can sort on multiple properties. We discuss how many MLG neighbors must be considered in the separation assurance procedure in order to ensure a five-mile separation buffer between aircraft, and we investigate the effect of removing waypoints from aircraft trajectories. When aircraft choose their own trajectory, there are more flights with shorter duration times and fewer CD&R maneuvers, resulting in significant fuel savings.

Kaplan, Carolyn↗

An Adaptive Memory Interface Controller for Improving Bandwidth Utilization of Hybrid and Reconfigurable Systems

Emerging applications such as data mining, bioinformatics, knowledge discovery, social network analysis are irregular. They use data structures based on pointers or linked lists, such as graphs, unbalanced trees or unstructures grids, which generates unpredictable memory accesses. These data structures usually are large, but difficult to partition. These applications mostly are memory bandwidth bounded and have high synchronization intensity. However, they also have large amounts of inherent dynamic parallelism, because they potentially perform a task for each one of the element they are exploring. Several efforts are looking at accelerating these applications on hybrid architectures, which integrate general purpose processors with reconfigurable devices. Some solutions, which demonstrated significant speedups, include custom-hand tuned accelerators or even full processor architectures on the reconfigurable logic. In this paper we present an approach for the automatic synthesis of accelerators from C, targeted at irregular applications. In contrast to typical High Level Synthesis paradigms, which construct a centralized Finite State Machine, our approach generates dynamically scheduled hardware components. While parallelism exploitation in typical HLS-generated accelerators is usually bound within a single execution flow, our solution allows concurrently running multiple execution flow, thus also exploiting the coarser grain task parallelism of irregular applications. Our approach supports multiple, multi-ported and distributed memories, and atomic memory operations. Its main objective is parallelizing as many memory operations as possible, independently from their execution time, to maximize the memory bandwidth utilization. This significantly differs from current HLS flows, which usually consider a single memory port and require precise scheduling of memory operations. A key innovation of our approach is the generation of a memory interface controller, which dynamically maps concurrent memory accesses to multiple ports. We present a case study on a typical irregular kernel, Graph Breadth First search (BFS), exploring different tradeoffs in terms of parallelism and number of memories.

BFS↗

Accelerating science: The usage of commercial clouds in ATLAS Distributed Computing

The ATLAS experiment at CERN is one of the largest scientific machines built to date and will have ever growing computing needs as the Large Hadron Collider collects an increasingly larger volume of data over the next 20 years. ATLAS is conducting R&D projects on Amazon Web Services and Google Cloud as complementary resources for distributed computing, focusing on some of the key features of commercial clouds: lightweight operation, elasticity and availability of multiple chip architectures. The proof of concept phases have concluded with the cloud-native, vendoragnostic integration with the experiment’s data and workload management frameworks. Google Cloud has been used to evaluate elastic batch computing, ramping up ephemeral clusters of up to O(100k) cores to process tasks requiring quick turnaround. Amazon Web Services has been exploited for the successful physics validation of the Athena simulation software on ARM processors. We have also set up an interactive facility for physics analysis allowing endusers to spin up private, on-demand clusters for parallel computing with up to 4 000 cores, or run GPU enabled notebooks and jobs for machine learning applications. The success of the proof of concept phases has led to the extension of the Google Cloud project, where ATLAS will study the total cost of ownership of a production cloud site during 15 months with 10k cores on average, fully integrated with distributed grid computing resources and continue the R&D projects.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗