Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel 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 1,549 records · Page 86

GASNet-EX RMA Communication Performance on Recent Supercomputing Systems

Partitioned Global Address Space (PGAS) programming models, typified by systems such as Unified Parallel C (UPC) and Fortran coarrays, expose one-sided Remote Memory Access (RMA) communication as a key building block for High Performance Computing (HPC) applications. Architectural trends in supercomputing make such programming models increasingly attractive, and newer, more sophisticated models such as UPC++, Legion and Chapel that rely upon similar communication paradigms are gaining popularity. GASNet-EX is a portable, open-source, high-performance communication library designed to efficiently support the networking requirements of PGAS runtime systems and other alternative models in emerging exascale machines. The library is an evolution of the popular GASNet communication system, building upon 20 years of lessons learned. We present microbenchmark results which demonstrate the RMA performance of GASNet-EX is competitive with MPI implementations on four recent, high-impact, production HPC systems. These results are an update relative to previously published results on older systems. The networks measured here are representative of hardware currently used in six of the top ten fastest supercomputers in the world, and all of the exascale systems on the U.S. DOE road map.

Hargrove, Paul H↗

UCX: An Open Source Framework for HPC Network APIs and Beyond, In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects

This paper presents Unified Communication X (UCX), a set of network APIs and their implementations for high throughput computing. UCX comes from the combined effort of national laboratories, industry, and academia to design and implement a high-performing and highly-scalable network stack for next generation applications and systems. UCX design provides the ability to tailor its APIs and network functionality to suit a wide variety of application domains and hardware. We envision these APIs to satisfy the networking needs of many programming models such as Message Passing Interface (MPI), OpenSHMEM, Partitioned Global Address Space (PGAS) languages, task-based paradigms and I/O bound applications. To evaluate the design we implement the APIs and protocols, and measure the performance of overhead-critical network primitives fundamental for implementing many parallel programming models and system libraries. Our results show that the latency, bandwidth, and message rate achieved by the portable UCX prototype is very close to that of the underlying driver. With UCX, we achieved a message exchange latency of 0.89 us, a bandwidth of 6138.5 MB/s, and a message rate of 14 million messages per second. As far as we know, this is the highest bandwidth and message rate achieved by any network stack (publicly known) on this hardware.

Computer Science↗

The Massively Parallel Processor and its applications

A long-term experimental development program conducted at Goddard Space Flight Center to implement an ultrahigh-speed data processing system known as the Massively Parallel Processor (MPP) is described. The MPP is a single instruction multiple data stream computer designed to perform logical, integer, and floating point arithmetic operations on variable word length data. Information is presented on system architecture, the system configuration, the array unit architecture, individual processing units, and expected operating rates for several image processing applications (including the processing of Landsat data).

Strong, J. P.↗

Mathematical model partitioning and packing for parallel computer calculation

This paper deals with the development of multiprocessor simulations from a serial set of ordinary differential equations describing a physical system. The identification of computational parallelism within the model equations is discussed. A technique is presented for identifying this parallelism and for partitioning the equations for parallel solution on a multiprocessor. Next, an algorithm which packs the equations into a minimum number of processors is described. The results of applying the packing algorithm to a turboshaft engine model are presented.

Arpasi, Dale J.↗

WE-AB-BRB-09: Real Time In Vivo Scintillating Fiber Array Detector for Medical LINACS

Purpose: An in vivo transmission scintillation fiber detector was developed to monitor patient treatment in real time for the enhancement of patient safety and treatment accuracy. The detector system is capable of monitoring each pulse from a medical LINAC during treatment to determine the dose delivered as treatment progresses. Methods: The detector system consists of 60 parallel scintillating fibers coupled to fast data processing optoelectronics that can monitor the beam fluence in real time. Each 2.5mm{sup 2} square fiber is aligned with an MLC leaf pair and is long enough to capture a 40cm field. The fibers are embedded within a water equivalent polymer substrate that is secured in the LINAC accessory tray. The fibers are coupled to high speed photosensors and front end amplifiers that filter noise and pass each pulse to a high speed analog-to-digital converter. The system components are capable of detecting pulse repetition times shorter than what is delivered by a medical LINAC to ensure true real time data acquisition. Results: The system was able to capture and record the signal from each linac pulse and display the information in real time with no pulse pile up. It was found that the fiber array attenuates 2.65% of the beam which can easily be compensated for in treatment planning. The fibers responded linearly with dose, are independent of clinical beam energies, and are independent of dose rate. Calibration of the system was performed as a function of beam energy, beam size, dose rate, and monitor units to optimize beam fluence error detection. Conclusion: The detector system presented provides true real time in vivo beam monitoring to enhance patient safety and treatment delivery accuracy. Furthermore, the detector can be used for current patient specific QA.

60 APPLIED LIFE SCIENCES↗

Uncovering I/O demands on HPC platforms: Peeking under the hood of Santos Dumont

High-Performance Computing (HPC) platforms are required to solve the most diverse large-scale scientific problems in various research areas, such as biology, chemistry, physics, and health sciences. Researchers use a multitude of scientific softwares, which have different requirements. These include input and output operations, which directly impact performance due to the existing difference in processing and data access speeds. Thus, supercomputers must efficiently handle mixed workload when storing data from the applications. Understanding the set of applications and their performance running in a supercomputer is paramount to understanding the storage system's usage, pinpointing possible bottlenecks, and guiding optimization techniques. This research proposes a methodology and visualization tool to evaluate a supercomputer's data storage infrastructure's performance, taking into account the diverse workload and demands of the system over a long period of operation. As a study case, we focus on the Santos Dumont supercomputer, identifying inefficient usage, problematic performance factors, and providing guidelines on how to tackle those issues.

97 MATHEMATICS AND COMPUTING↗

A new architecture for fast ultrasound imaging

Some ultrasound imaging applications require high frame rate, for example 3D imaging and automated inspections of large components. Being the signal-processing throughput of the system the main bottleneck, parallel beamforming is required to achieve hundreds to thousands of images per second. Simultaneous A-scan line beamforming in all active channels is required to reach the intended high frame rate. To this purpose, a new parallel beamforming architecture that exploits the currently available processing resources available in state-of-the-art FPGAs is proposed. The work aims to get the optimal resource usage, high scalability and flexibility for different applications. To achieve these goals, the basic beamforming function is reformulated to be adapted to the DSP-cell architecture of state-of-the-art FPGAs. This allows performing simultaneous dynamic focusing on multiple A-scan lines. Some realistic examples are analyzed, evaluating resource requirements and maximum operating frequency. For example, a 128-channel system, with 128 scan lines and acquiring at 20 MSPS, can be built with 4 mid-range FPGAs, achieving up to 18000 frames per second, just limited by the maximum PRF. The gold standard Synthetic Transmit Aperture method (also called Total Focusing Method) can be carried out in real time at a processing rate of 140 high-resolution images per second (16 cm depth on steel)

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Deploying Server-side File System Monitoring at NERSC

The Franklin Cray XT4 at the NERSC center was equipped with the server-side I/O monitoring infrastructure Cerebro/LMT, which is described here in detail. Insights gained from the data produced include a better understanding of instantaneous data rates during file system testing, file system behavior during regular production time, and long-term average behaviors. Information and insights gleaned from this monitoring support efforts to proactively manage the I/O infrastructure on Franklin. A simple model for I/O transactions is introduced and compared with the 250 million observations sent to the LMT database from August 2008 to February 2009.

97 MATHEMATICS AND COMPUTING↗

TRACE Analysis of Loss of Flow for the APR1400

The APR1400 is a pressurized water reactor (PWR). The APR1400 nuclear steam supply system consists of a reactor pressure vessel (RPV), which contains the reactor core, and two primary reactor coolant system loops connected in parallel to the RPV. Each coolant loop consists of a hot leg (HL), a u-tube steam generator (SG), two reactor coolant pumps (RCPs) and two cold legs (CLs). A pressurizer is connected to the hot leg on one of the coolant loops. During normal operation, the RCPs circulate high pressure water through the reactor core to remove the heat. The heated water exits the RPV and passes through the hot legs into the steam generator tubes. Heat is transferred through the walls of the steam generator tubes into a lower pressure secondary coolant system. Cooled primary system water from the steam generators is returned through the RCPs and cold legs to the RPV. The RCPs operate at constant speed; the primary coolant system is designed to provide a prescribed rate of coolant flow through the reactor core. The APR1400 SG secondary coolant system pressure is controlled through modulation of valves in the steam lines to maintain a prescribed turbine inlet pressure. The SG secondary coolant inventory is controlled by using a feedwater control system to maintain a prescribed liquid level in the steam generator downcomer. This water inventory level is sufficient to cover the outer surfaces of the steam generator tubes while preventing overfill that would cause liquid to pass from the steam generators through the steam lines into the turbine system. In the current work, the Nuclear Regulatory Commission's reactor systems analysis code, TRACE?2 was used to perform an analysis of a loss of flow anticipated operational occurrence (AOO). The loss of flow is initiated by a loss of off-site power (LOOP), resulting in a trip of the RCPs. The regulatory purpose of the current work is to confirm safety analyses documented in the APR1400 Design Control Document (DCD)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Experimental Studies Of Pilot Performance At Collision Avoidance During Closely Spaced Parallel Approaches

Efforts to increase airport capacity include studies of aircraft systems that would enable simultaneous approaches to closely spaced parallel runway in Instrument Meteorological Conditions (IMC). The time-critical nature of a parallel approach results in key design issues for current and future collision avoidance systems. Two part-task flight simulator studies have examined the procedural and display issues inherent in such a time-critical task, the interaction of the pilot with a collision avoidance system, and the alerting criteria and avoidance maneuvers preferred by subjects.

Pritchett, Amy R.↗

Secure Network-Centric Aviation Communication (SNAC)

The existing National Airspace System (NAS) communications capabilities are largely unsecured, are not designed for efficient use of spectrum and collectively are not capable of servicing the future needs of the NAS with the inclusion of new operators in Unmanned Aviation Systems (UAS) or On Demand Mobility (ODM). SNAC will provide a ubiquitous secure, network-based communications architecture that will provide new service capabilities and allow for the migration of current communications to SNAC over time. The necessary change in communication technologies to digital domains will allow for the adoption of security mechanisms, sharing of link technologies, large increase in spectrum utilization, new forms of resilience and redundancy and the possibly of spectrum reuse. SNAC consists of a long term open architectural approach with increasingly capable designs used to steer research and development and enable operating capabilities that run in parallel with current NAS systems.

Communications↗

Parallelization of Rocket Engine Simulator Software (PRESS)

Parallelization of Rocket Engine System Software (PRESS) project is part of a collaborative effort with Southern University at Baton Rouge (SUBR), University of West Florida (UWF), and Jackson State University (JSU). The second-year funding, which supports two graduate students enrolled in our new Master's program in Computer Science at Hampton University and the principal investigator, have been obtained for the period from October 19, 1996 through October 18, 1997. The key part of the interim report was new directions for the second year funding. This came about from discussions during Rocket Engine Numeric Simulator (RENS) project meeting in Pensacola on January 17-18, 1997. At that time, a software agreement between Hampton University and NASA Lewis Research Center had already been concluded. That agreement concerns off-NASA-site experimentation with PUMPDES/TURBDES software. Before this agreement, during the first year of the project, another large-scale FORTRAN-based software, Two-Dimensional Kinetics (TDK), was being used for translation to an object-oriented language and parallelization experiments. However, that package proved to be too complex and lacking sufficient documentation for effective translation effort to the object-oriented C + + source code. The focus, this time with better documented and more manageable PUMPDES/TURBDES package, was still on translation to C + + with design improvements. At the RENS Meeting, however, the new impetus for the RENS projects in general, and PRESS in particular, has shifted in two important ways. One was closer alignment with the work on Numerical Propulsion System Simulator (NPSS) through cooperation and collaboration with LERC ACLU organization. The other was to see whether and how NASA's various rocket design software can be run over local and intra nets without any radical efforts for redesign and translation into object-oriented source code. There were also suggestions that the Fortran based code be encapsulated in C + + code thereby facilitating reuse without undue development effort. The details are covered in the aforementioned section of the interim report filed on April 28, 1997.

Cezzar, Ruknet↗

Optimal processor assignment for pipeline computations

The availability of large scale multitasked parallel architectures introduces the following processor assignment problem for pipelined computations. Given a set of tasks and their precedence constraints, along with their experimentally determined individual responses times for different processor sizes, find an assignment of processor to tasks. Two objectives are of interest: minimal response given a throughput requirement, and maximal throughput given a response time requirement. These assignment problems differ considerably from the classical mapping problem in which several tasks share a processor; instead, it is assumed that a large number of processors are to be assigned to a relatively small number of tasks. Efficient assignment algorithms were developed for different classes of task structures. For a p processor system and a series parallel precedence graph with n constituent tasks, an O(np2) algorithm is provided that finds the optimal assignment for the response time optimization problem; it was found that the assignment optimizing the constrained throughput in O(np2log p) time. Special cases of linear, independent, and tree graphs are also considered.

Nicol, David M.↗

The pre-conceptual design of the nuclear island of ASTRID

The CEA is involved in a substantial effort on the ASTRID (Advanced Sodium Technological Reactor for Industrial Demonstration) pre-conceptual design in cooperation with EDF, as experienced Sodium-cooled Fast Reactor (SFR) operator, AREVA, as experienced SFR Nuclear Island engineering company and components designer, ALSTOM POWER as energy conversion system designer and COMEX NUCLEAIRE as mechanical systems designer. The CEA is looking for other partnerships, in France and abroad. The ASTRID preliminary design is based on a sodium-cooled pool reactor of 1500 MWth generating about 600 MWe, which is required to guarantee the representativeness of the reactor core and the main components with regard to future commercial reactors. ASTRID lifetime target is 60 years. Two Energy Conversion Systems are studied in parallel until the end of 2012: Rankine steam cycle or Brayton gas based energy conversion cycle. ASTRID design is guided by the following major objectives: improved safety, simplification of structures, improved In Service Inspection and Repair (ISIR), improved manufacturing conditions for cost reduction and increased quality, reduction of risks related to sodium fires and water/sodium reaction, and improved robustness against external hazards. The core is supported by a diagrid, which lay on a strong back to transfer the weight to the main vessel. AREVA is involved in a substantial effort in order to improve the core support structure in particular regarding the ISIR and the connection to primary pump. In the preliminary design, the primary system is formed by the main vessel and the upper closure comprising the reactor roof, two rotating plugs - used for fuel handling - and the components plugs located in the roof penetrations. The Above Core Structure deflects the sodium flow in the hot pool and provides support to core instrumentation and guidance of the control rod drive mechanisms. The number of the major components in the main vessel, primary pumps, Intermediate Heat Exchangers, and Decay Heat Exchangers are now under consideration. Under normal conditions, power release is achieved using the steam/water plant (in case of Rankine steam cycle) or the gas plant (in case of Brayton gas cycle). The diverse design and operating modes of Decay Heat Removal systems provide protection against common cause failures. A Decay Heat Removal system through the reactor vault is in particular studied with the objective to complement Direct Reactor Cooling systems. At this stage of the studies, the secondary system comprises four independent sodium loops (two and three sodium loops configurations are also investigated). Each loop includes one mechanical pump (or a large capacity Annular Linear Induction Electromagnetic Pump), and three modular Steam Generator Units characterized by once through straight tube units with a ferritic tube bundle; nevertheless, helical coil steam generator with tubes made of Alloy 800, and inverted type steam generator with a ferritic tube bundle are also investigated. The limited power of each modular Steam Generator Unit allows the whole secondary loop to withstand a large water/sodium reaction consecutive to the postulated simultaneous rupture of all the heat exchange tubes of one module. The arrangement of the components is based on the 'Regain' concept, in which the secondary pump is situated at a low level in the circuit; conventional arrangement, as SUPERPHENIX type, is a back-up option. Alternative arrangements based on gas cycles are also studied together with Na-gas heat exchanger design. This paper presents a status of the ASTRID pre-conceptual design. The most promising options are highlighted as well as less risky and back-up options. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

CTH Version 11.0

The CTH suite of computer codes is a flexible software system designed to treat a wide range of shock wave propagation and material motion phenomena in one, two or three dimensions. CTH has models suitable for most conditions encountered in shock physics including material strength, fracture, distended materials, high explosives, and a variety of boundary conditions. The material equation-of-state models allow description of most states of matter normally encountered in shock physics. A powerful suite of on-the-fly and post-processing analysis options are available which can generate three-dimensional, two-dimensional, and one-dimensional color and contour plots. History plots of thermo-mechanical data at spatially fixed and material fixed points can be generated. CTH is available for a variety of computers ranging from a single PC to massively-parallel distributed-data systems.

Source record↗

Partitioning And Packing Equations For Parallel Processing

Algorithm developed to identify parallelism in set of coupled ordinary differential equations that describe physical system and to divide set into parallel computational paths, along with parts of solution proceeds independently of others during at least part of time. Path-identifying algorithm creates number of paths consisting of equations that must be computed serially and table that gives dependent and independent arguments and "can start," "can end," and "must end" times of each equation. "Must end" time used subsequently by packing algorithm.

Arpasi, Dale J.↗