Search NASA⌕ Search

SEARCH · Search NASA

Results for “Asynchronous programming”

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 163 records · Page 9

Simplified Parallel Domain Traversal

Many data-intensive scientific analysis techniques require global domain traversal, which over the years has been a bottleneck for efficient parallelization across distributed-memory architectures. Inspired by MapReduce and other simplified parallel programming approaches, we have designed DStep, a flexible system that greatly simplifies efficient parallelization of domain traversal techniques at scale. In order to deliver both simplicity to users as well as scalability on HPC platforms, we introduce a novel two-tiered communication architecture for managing and exploiting asynchronous communication loads. We also integrate our design with advanced parallel I/O techniques that operate directly on native simulation output. We demonstrate DStep by performing teleconnection analysis across ensemble runs of terascale atmospheric CO{sub 2} and climate data, and we show scalability results on up to 65,536 IBM BlueGene/P cores.

99 GENERAL AND MISCELLANEOUS↗

WADeG Cell Phone

The on cell phone software captures the images from the CMOS camera periodically, stores the pictures, and periodically transmits those images over the cellular network to the server. The cell phone software consists of several modules: CamTest.cpp, CamStarter.cpp, StreamIOHandler .cpp, and covertSmartDevice.cpp. The camera application on the SmartPhone is CamStarter, which is "the" user interface for the camera system. The CamStarter user interface allows a user to start/stop the camera application and transfer files to the server. The CamStarter application interfaces to the CamTest application through registry settings. Both the CamStarter and CamTest applications must be separately deployed on the smartphone to run the camera system application. When a user selects the Start button in CamStarter, CamTest is created as a process. The smartphone begins taking small pictures (CAPTURE mode), analyzing those pictures for certain conditions, and saving those pictures on the smartphone. This process will terminate when the user selects the Stop button. The camtest code spins off an asynchronous thread, StreamIOHandler, to check for pictures taken by the camera. The received image is then tested by StreamIOHandler to see if it meets certain conditions. If those conditions are met, the CamTest program is notified through the setting of a registry key value and the image is saved in a designated directory in a custom BMP file which includes a header and the image data. When the user selects the Transfer button in the CamStarter user interface, the covertsmartdevice code is created as a process. Covertsmartdevice gets all of the files in a designated directory, opens a socket connection to the server, sends each file, and then terminates.

Cogliati, JoshuaJ.↗

A magnetic bubble domain flight recorder

A feasibility model of an all-electronic bubble memory system has been constructed. It uses a small 60k bit bubble recorder consisting of 6 chips of 10k bits each mounted in three separate packages operating as a FIFO at a 150 KHz bubble data rate. In addition to serving as a direct tape recorder replacement, the bubble recorder can be programmed for random access to each individual chip for ranom block access operation or for self-checking or by-passing any malfunctioning memory chip. Read and write operations can be performed asynchronously from very low frequency up to basic recording field frequency. A large 50M bit prototype is planned.

Chen, T. T.↗

Asynchronous Object Storage with QoS for Scientific and Commercial Big Data

This paper presents our design for an asynchronous object storage system intended for use in scientific and commercial big data workloads. Use cases from the target workload do- mains are used to motivate the key abstractions used in the application programming interface (API). The architecture of the Scalable Object Store (SOS), a prototype object stor- age system that supports the API s facilities, is presented. The SOS serves as a vehicle for future research into scalable and resilient big data object storage. We briefly review our research into providing efficient storage servers capable of providing quality of service (QoS) contracts relevant for big data use cases.

Cloud Storage↗

Accelerating DCA++ (Dynamical Cluster Approximation) Scientific Application on the Summit supercomputer

Optimizing scientific applications on today’s accelerator-based high performance computing systems can be challenging, especially when multiple GPUs and CPUs with heterogeneous memories and persistent non-volatile memories are present. An example is Summit, an accelerator-based system at the Oak Ridge Leadership Computing Facility (OLCF) that is rated as the world’s fastest supercomputer to-date. New strategies are thus needed to expose the parallelism in legacy applications, while being amenable to efficient mapping to the underlying architecture.In this paper we discuss our experiences and strategies to port a scientific application, DCA++, to Summit. DCA++ is a highperformance research application that solves quantum manybody problems with a cutting edge quantum cluster algorithm, the dynamical cluster approximation.Our strategies aim to synergize the strengths of the different programming models in the code. These include: (a) streamlining the interactions between the CPU threads and the GPUs, (b) implementing computing kernels on the GPUs and decreasing CPU-GPU memory transfers, (c) allowing asynchronous GPU communications, and (d) increasing compute intensity by combining linear algebraic operations.Full-scale production runs using all 4600 Summit nodes attained a peak performance of 73.5 PFLOPS with a mixed precision implementation.We observed a perfect strong and weak scaling for the quantum Monte Carlo solver in DCA++, while encountering about 2× input/output (I/O) and MPI communication overhead on the time-to-solution for the full machine run. Our hardware agnostic optimizations are designed to alleviate the communication and I/O challenges observed, while improving the compute intensity and obtaining optimal performance on a complex, hybrid architecture like Summit.

Balduzzi, Giovanni↗

Photovoltaic Inverter Controllers Seeking AC Optimal Power Flow Solutions

This paper considers future distribution networks featuring inverter-interfaced photovoltaic (PV) systems, and addresses the synthesis of feedback controllers that seek real- and reactive-power inverter setpoints corresponding to AC optimal power flow (OPF) solutions. The objective is to bridge the temporal gap between long-term system optimization and real-time inverter control, and enable seamless PV-owner participation without compromising system efficiency and stability. The design of the controllers is grounded on a dual ..epsilon..-subgradient method, while semidefinite programming relaxations are advocated to bypass the non-convexity of AC OPF formulations. Global convergence of inverter output powers is analytically established for diminishing stepsize rules for cases where: i) computational limits dictate asynchronous updates of the controller signals, and ii) inverter reference inputs may be updated at a faster rate than the power-output settling time.

14 SOLAR ENERGY↗

High performance graphics processor based computed tomography reconstruction algorithms for nuclear and other large scale applications.

The goal of this work is to develop a fast computed tomography (CT) reconstruction algorithm based on graphics processing units (GPU) that achieves significant improvement over traditional central processing unit (CPU) based implementations. The main challenge in developing a CT algorithm that is capable of handling very large datasets is parallelizing the algorithm in such a way that data transfer does not hinder performance of the reconstruction algorithm. General Purpose Graphics Processing (GPGPU) is a new technology that the Science and Technology (S&T) community is starting to adopt in many fields where CPU-based computing is the norm. GPGPU programming requires a new approach to algorithm development that utilizes massively multi-threaded environments. Multi-threaded algorithms in general are difficult to optimize since performance bottlenecks occur that are non-existent in single-threaded algorithms such as memory latencies. If an efficient GPU-based CT reconstruction algorithm can be developed; computational times could be improved by a factor of 20. Additionally, cost benefits will be realized as commodity graphics hardware could potentially replace expensive supercomputers and high-end workstations. This project will take advantage of the CUDA programming environment and attempt to parallelize the task in such a way that multiple slices of the reconstruction volume are computed simultaneously. This work will also take advantage of the GPU memory by utilizing asynchronous memory transfers, GPU texture memory, and (when possible) pinned host memory so that the memory transfer bottleneck inherent to GPGPU is amortized. Additionally, this work will take advantage of GPU-specific hardware (i.e. fast texture memory, pixel-pipelines, hardware interpolators, and varying memory hierarchy) that will allow for additional performance improvements.

97 MATHEMATICS AND COMPUTING↗

Optical multiple access techniques for on-board routing

The purpose of this research contract was to design and analyze an optical multiple access system, based on Code Division Multiple Access (CDMA) techniques, for on board routing applications on a future communication satellite. The optical multiple access system was to effect the functions of a circuit switch under the control of an autonomous network controller and to serve eight (8) concurrent users at a point to point (port to port) data rate of 180 Mb/s. (At the start of this program, the bit error rate requirement (BER) was undefined, so it was treated as a design variable during the contract effort.) CDMA was selected over other multiple access techniques because it lends itself to bursty, asynchronous, concurrent communication and potentially can be implemented with off the shelf, reliable optical transceivers compatible with long term unattended operations. Temporal, temporal/spatial hybrids and single pulse per row (SPR, sometimes termed 'sonar matrices') matrix types of CDMA designs were considered. The design, analysis, and trade offs required by the statement of work selected a temporal/spatial CDMA scheme which has SPR properties as the preferred solution. This selected design can be implemented for feasibility demonstration with off the shelf components (which are identified in the bill of materials of the contract Final Report). The photonic network architecture of the selected design is based on M(8,4,4) matrix codes. The network requires eight multimode laser transmitters with laser pulses of 0.93 ns operating at 180 Mb/s and 9-13 dBm peak power, and 8 PIN diode receivers with sensitivity of -27 dBm for the 0.93 ns pulses. The wavelength is not critical, but 830 nm technology readily meets the requirements. The passive optical components of the photonic network are all multimode and off the shelf. Bit error rate (BER) computations, based on both electronic noise and intercode crosstalk, predict a raw BER of (10 exp -3) when all eight users are communicating concurrently. If better BER performance is required, then error correction codes (ECC) using near term electronic technology can be used. For example, the M(8,4,4) optical code together with Reed-Solomon (54,38,8) encoding provides a BER of better than (10 exp -11). The optical transceiver must then operate at 256 Mb/s with pulses of 0.65 ns because the 'bits' are now channel symbols.

Mendez, Antonio J.↗

Asynchronous Runtimes in Action: An Introspective Framework for a Next Gen Runtime

One of the most critical challenges that new high performance systems face is the lack of system software support for these large scale systems. Investment on system stack components is essential in the development, debugging and optimization of the new emerging programming models. These emerging models have the promise to better utilize the vast hardware resources available in current and future systems. To aid in the development of applications and new system stacks, runtimes, as instances of their respective execution models, need to produce facilities to introspect their inner workings and allow an indepth attribution of performance bottlenecks and computational patterns. In other words, the runtime systems need to reduce their opacity to observers so that users of a novel program execution model can adapt their designs to fit the intended model usage, regardless of the layer that they are working on. This design/development loop (akin to co-design) enables synergistic opportunities across the entire computational stack. This paper presents the design and implementation of a simple “gray” box performance attribution harness running inside a fine grain runtime system: the Open Community Runtime (OCR). We showcase what such a framework can indicate regarding the runtime behavior while running at scale. To this end, we have designed a set of synthetic scenarios aimed to test the runtime at their best and worst cases. We present an analysis of the most important runtime features, properties and idiosyncrasies that will affect the development of new runtime features, algorithmic selection, and application development.

high performance distributed runtimes↗

Highly Asynchronous VisitOr Queue Graph Toolkit

HAVOQGT is a C++ framework that can be used to create highly parallel graph traversal algorithms. The framework stores the graph and algorithmic data structures on external memory that is typically mapped to high performance locally attached NAND FLASH arrays. The framework supports a vertex-centered visitor programming model. The frameworkd has been used to implement breadth first search, connected components, and single source shortest path.

Pearce, R.↗

Highly Asynchronous VisitOr Queue Graph Toolkit

HAVOQGT is a C++ framework that can be used to create highly parallel graph traversal algorithms. The framework stores the graph and algorithmic data structures on external memory that is typically mapped to high performance locally attached NAND FLASH arrays. The framework supports a vertex-centered visitor programming model. The frameworkd has been used to implement breadth first search, connected components, and single source shortest path.

Pearce, R.↗

Vortex information display system program description manual

A vortex information display system is described which provides flexible control through system-user interaction for collecting wing-tip-trailing vortex data, processing this data in real time, displaying the processed data, storing raw data on magnetic tape, and post processing raw data. The data is received from two asynchronous laser Doppler velocimeters (LDV's) and includes position, velocity, and intensity information. The raw data is written onto magnetic tape for permanent storage and is also processed in real time to locate vortices and plot their positions as a function of time. The interactive capability enables the user to make real time adjustments in processing data and provides a better definition of vortex behavior. Displaying the vortex information in real time produces a feedback capability to the LDV system operator allowing adjustments to be made in the collection of raw data. Both raw data and processing can be continually upgraded during flyby testing to improve vortex behavior studies. The post-analysis capability permits the analyst to perform in-depth studies of test data and to modify vortex behavior models to improve transport predictions.

Conway, R.↗

Rethinking Programming Paradigms in the QC-HPC Context

Programming for today’s quantum computers is making significant strides toward modern workflows compatible with high performance computing (HPC), but fundamental challenges still remain in the integration of these vastly different technologies. Quantum computing (QC) programming languages share some common ground, as well as their emerging runtimes and algorithmic modalities. In this short paper, we explore avenues of refinement for the quantum processing unit (QPU) in the context of many-tasks management, asynchronous or otherwise, in order to understand the value it can play in linking QC with HPC. Through examples, we illustrate how its potential for scientific discovery might be realized.

Wong, Elaine↗

DARMA-EMPIRE Integration and Performance Assessment – Interim Report

We begin by presenting an overview of the general philosophy that is guiding the novel DARMA developments, followed by a brief reminder about the background of this project. We finally present the FY19 design requirements. As the Exascale era arises, DARMA is uniquely positioned at the forefront of asychronous many-task (AMT) research and development (R&D) to explore emerging programming model paradigms for next-generation HPC applications at Sandia, across NNSA labs, and beyond. The DARMA project explores how to fundamentally shift the expression(PM) and execution(EM)of massively concurrent HPC scientific algorithms to be more asynchronous, resilient to executional aberrations in heterogeneous/unpredictable environments, and data-dependency conscious—thereby enabling an intelligent, dynamic, and self-aware runtime to guide execution.

97 MATHEMATICS AND COMPUTING↗

Delivery Ring Spill Characterization and Impulse Study

High-intensity particle physics experiments require uniform beam extraction to prevent instantaneous rate spikes from overwhelming detector systems. By analyzing accelerator parameters and extracted beam dynamics, we directly inform spill regulation systems that make real-time adjustments to minimize non-uniformity. This Department of Energy Visiting Faculty Program project transitioned from characterizing Main Injector half-integer slow extraction for SpinQuest to Delivery Ring third-integer slow extraction for Mu2e. Working alongside the Fast Adaptive Neural Control (FANC) group, we developed an automated pipeline that aligns asynchronous instrument channels, embeds quality metrics, and isolates clean spill populations. Analyzing baseline spills alongside a dedicated quadrupole impulse study allowed us to quantify noise structures while mapping time-varying beam response and transit-delay dynamics. These empirical measurements directly ground digital twin models, supporting FANC’s deployment of real-time, FPGA-based neural network controllers in the Mu2e Spill Regulation System.

Dolen, James William [Purdue U., West Lafayette] (↗

Digital Interface Board to Control Phase and Amplitude of Four Channels

An increasing number of parts are designed with digital control interfaces, including phase shifters and variable attenuators. When designing an antenna array in which each antenna has independent amplitude and phase control, the number of digital control lines that must be set simultaneously can grow very large. Use of a parallel interface would require separate line drivers, more parts, and thus additional failure points. A convenient form of control where single-phase shifters or attenuators could be set or the whole set could be programmed with an update rate of 100 Hz is needed to solve this problem. A digital interface board with a field-programmable gate array (FPGA) can simultaneously control an essentially arbitrary number of digital control lines with a serial command interface requiring only three wires. A small set of short, high-level commands provides a simple programming interface for an external controller. Parity bits are used to validate the control commands. Output timing is controlled within the FPGA to allow for rapid update rates of the phase shifters and attenuators. This technology has been used to set and monitor eight 5-bit control signals via a serial UART (universal asynchronous receiver/transmitter) interface. The digital interface board controls the phase and amplitude of the signals for each element in the array. A host computer running Agilent VEE sends commands via serial UART connection to a Xilinx VirtexII FPGA. The commands are decoded, and either outputs are set or telemetry data is sent back to the host computer describing the status and the current phase and amplitude settings. This technology is an integral part of a closed-loop system in which the angle of arrival of an X-band uplink signal is detected and the appropriate phase shifts are applied to the Ka-band downlink signal to electronically steer the array back in the direction of the uplink signal. It will also be used in the non-beam-steering case to compensate for phase shift variations through power amplifiers. The digital interface board can be used to set four 5-bit phase shifters and four 5-bit attenuators and monitor their current settings. Additionally, it is useful outside of the closed-loop system for beamsteering alone. When the VEE program is started, it prompts the user to initialize variables (to zero) or skip initialization. After that, the program enters into a continuous loop waiting for the telemetry period to elapse or a button to be pushed. A telemetry request is sent when the telemetry period is elapsed (every five seconds). Pushing one of the set or reset buttons will send the appropriate command. When a command is sent, the interface status is returned, and the user will be notified by a pop-up window if any error has occurred. The program runs until the End Program button is depressed.

Smith, Amy E.↗

XPRESS: eXascale PRogramming Environment and System Software, Final Report

The University of Oregon (UO) was a partner in the XPRESS project together with Sandia National Laboratories (SNL), Indiana University (IU), Lawrence Berkeley National Laboratory (LBL), Louisiana State University (LSU), Oak Ridge National Laboratory (ORNL), University of Houston (UH), and University of North Carolina (RENCI). UO's objective in the project was to develop "APEX (Asynchronous Performance Environment for eXascale)": performance measurement, analysis, feedback and control infrastructure to asynchronous tasking runtimes, specifically HPX (LSU) and HPX-5 (IU). During the project period, our efforts focused on the need to measure complex tasking models where the traditional instrumentation methods would not work due to an absent/meaningless call-path context and runtime control of task pre-emption and resumption, usually on a different operating system thread. In addition to the challenges of performance measurement, we developed a framework to provide information from all levels of the stack (hardware, operating system, runtime, application) to a feedback & control mechanism for controlling concurrency, task granularity, networking parameters, and other aspects of execution in order to improve execution performance, throughput and/or efficiency. UO demonstrated these developments on leading edge HPC machines at large scale, including a 2017 Gordon Bell submission in which APEX was used to optimize key bottlenecks in an astrophysics application. The following final report summarizes our accomplishments during the XPRESS project.

99 GENERAL AND MISCELLANEOUS↗

Optimization by nonhierarchical asynchronous decomposition

Large scale optimization problems are tractable only if they are somehow decomposed. Hierarchical decompositions are inappropriate for some types of problems and do not parallelize well. Sobieszczanski-Sobieski has proposed a nonhierarchical decomposition strategy for nonlinear constrained optimization that is naturally parallel. Despite some successes on engineering problems, the algorithm as originally proposed fails on simple two dimensional quadratic programs. The algorithm is carefully analyzed for quadratic programs, and a number of modifications are suggested to improve its robustness.

Shankar, Jayashree↗