Irregular Big Data Computed Tomography on Multiple Graphics Processors Improves Energy-Efficiency Metrics for Industrial Applications.
Abstract not provided.
SEARCH · Engineering Papers
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.
Abstract not provided.
Abstract not provided.
Abstract not provided.
This disclosure provides systems, methods, and apparatus for collective memory transfers. A control unit may be configured to coordinate a transfer of data between a memory and processor cores. For a read data transfer operation, the control unit may receive a trigger packet identifying a read data transfer operation and identifying a first plurality of data lines based on data values included in the trigger packet. The control unit may read the first plurality of data lines from the memory sequentially and send a second plurality of data lines to the processor cores. For a write data transfer operation, the control unit may send a request for at least one data line to a plurality of processor cores, may receive and reorder the requested data lines, and may write the data lines to a memory. The control unit may determine a mapping between processor cores and the memory.
The multiple-fold clustered processor mesh array is a triangular organization of clustered processing elements. This multiple-fold array maintains functional equivalence to the nearest neighbor mesh computer with uni-directional interprocessor communications, but with half the number of connection wires. In addition, the connectivity of the multiple-folded organization is superior to the standard square mesh due to the improved connectivity between the clustered processors. One of the primary application areas targeted is High Performance Architectures for image processing.
Hyperswitch Communications Network (HCN) computer is prototype multiple-processor computer being developed. Incorporates improved version of hyperswitch communication network described in "Hyperswitch Network For Hypercube Computer" (NPO-16905). Designed to support high-level software and expansion of itself. HCN computer is message-passing, multiple-instruction/multiple-data computer offering significant advantages over older single-processor and bus-based multiple-processor computers, with respect to price/performance ratio, reliability, availability, and manufacturing. Design of HCN operating-system software provides flexible computing environment accommodating both parallel and distributed processing. Also achieves balance among following competing factors; performance in processing and communications, ease of use, and tolerance of (and recovery from) faults.
A data highway terminal controller with transmission controllers assigned to each processor in a set of multiple processors is described. Shared-use terminals are loop connected to the processors via the controllers.
A compute processor allocator architecture for allocating compute processors to run applications in a multiple processor computing apparatus is distributed among a subset of processors within the computing apparatus. Each processor of the subset includes a compute processor allocator. The compute processor allocators can share a common database of information pertinent to compute processor allocation. A communication path permits retrieval of information from the database independently of the compute processor allocators.
PFLOTRAN, a next-generation reactive flow and transport code for modeling subsurface processes, has been designed from the ground up to run efficiently on machines ranging from leadership-class supercomputers to laptops. Based on an object-oriented design, the code is easily extensible to incorporate additional processes. It can interface seamlessly with Fortran 9X, C and C++ codes. Domain decomposition parallelism is employed, with the PETSc parallel framework used to manage parallel solvers, data structures and communication. Features of the code include a modular input file, implementation of high-performance I/O using parallel HDF5, ability to perform multiple realization simulations with multiple processors per realization in a seamless manner, and multiple modes for multiphase flow and multicomponent geochemical transport. Chemical reactions currently implemented in the code include homogeneous aqueous complexing reactions and heterogeneous mineral precipitation/dissolution, ion exchange, surface complexation and a multirate kinetic sorption model. PFLOTRAN has demonstrated petascale performance using 217 processor cores on problems composed of over 2 billion degrees of freedom. The code is currently being applied to simulate uranium transport at the Hanford 300 Area and CO2 sequestration in deep geologic formations.
PFLOTRAN, a next-generation reactive flow and transport code for modeling subsurface processes, has been designed from the ground up to run efficiently on machines ranging from leadership-class supercomputers to laptops. Based on an object-oriented design, the code is easily extensible to incorporate additional processes. It can interface seamlessly with Fortran 9X, C and C++ codes. Domain decomposition parallelism is employed, with the PETSc parallel framework used to manage parallel solvers, data structures and communication. Features of the code include a modular input file, implementation of high-performance I/O using parallel HDF5, ability to perform multiple realization simulations with multiple processors per realization in a seamless manner, and multiple modes for multiphase flow and multicomponent geochemical transport. Chemical reactions currently implemented in the code include homogeneous aqueous complexing reactions and heterogeneous mineral precipitation/dissolution, ion exchange, surface complexation and a multirate kinetic sorption model. PFLOTRAN has demonstrated petascale performance using 2{sup 17} processor cores with over 2 billion degrees of freedom. Accomplishments achieved to date include applications to the Hanford 300 Area and modeling CO{sub 2} sequestration in deep geologic formations.
Advances in computer architecture, computer science, computational methods, and constituent technologies are expected to lead to significant advances in the performance of scientific supercomputing system capabilities over the next decade. By the year 2000, single 1-in-sq dies are projected to incorporate four processors, each of which would be operating faster than 750 million instructions per second (MIPS) for a total on-chip processing performance in excess of 2000 MIPS. Scalable parallel processors can be expected to contain thousands of such multiple processor chips. In general, semiconductor performance advances appear to change about one order of magnitude every five years. Rotating magnetic memory and communications technology are not advancing as rapidly, with the result that the allocation of functions within the system configurations fo future supercomputer systems will require important changes. Availability of massively parallel heterogeneous processing capabilities should be a catalyst leading to new approaches for applications.
Topics covered include: Semiautonomous Avionics-and-Sensors System for a UAV; Biomimetic/Optical Sensors for Detecting Bacterial Species; System Would Detect Foreign-Object Damage in Turbofan Engine; Detection of Water Hazards for Autonomous Robotic Vehicles; Fuel Cells Utilizing Oxygen From Air at Low Pressures; Hybrid Ion-Detector/Data-Acquisition System for a TOF-MS; Spontaneous-Desorption Ionizer for a TOF-MS; Equipment for On-Wafer Testing From 220 to 325 GHz; Computing Isentropic Flow Properties of Air/R-134a Mixtures; Java Mission Evaluation Workstation System; Using a Quadtree Algorithm To Assess Line of Sight; Software for Automated Generation of Cartesian Meshes; Optics Program Modified for Multithreaded Parallel Computing; Programs for Testing Processor-in-Memory Computing Systems; PVM Enhancement for Beowulf Multiple-Processor Nodes; Ion-Exclusion Chromatography for Analyzing Organics in Water; Selective Plasma Deposition of Fluorocarbon Films on SAMs; Water-Based Pressure-Sensitive Paints; System Finds Horizontal Location of Center of Gravity; Predicting Tail Buffet Loads of a Fighter Airplane; Water Containment Systems for Testing High-Speed Flywheels; Vapor-Compression Heat Pumps for Operation Aboard Spacecraft; Multistage Electrophoretic Separators; Recovering Residual Xenon Propellant for an Ion Propulsion System; Automated Solvent Seaming of Large Polyimide Membranes; Manufacturing Precise, Lightweight Paraboloidal Mirrors; Analysis of Membrane Lipids of Airborne Micro-Organisms; Noninvasive Diagnosis of Coronary Artery Disease Using 12-Lead High-Frequency Electrocardiograms; Dual-Laser-Pulse Ignition; Enhanced-Contrast Viewing of White-Hot Objects in Furnaces; Electrically Tunable Terahertz Quantum-Cascade Lasers; Few-Mode Whispering-Gallery-Mode Resonators; Conflict-Aware Scheduling Algorithm; and Real-Time Diagnosis of Faults Using a Bank of Kalman Filters.
The goal of this project has been to develop a lossless compression algorithm for message-passing libraries that can accelerate HPC systems by reducing the communication time. Because both compression and decompression have to be performed in software in real time, the algorithm has to be extremely fast while still delivering a good compression ratio. During the first half of this project, they designed a new compression algorithm called FPC for scientific double-precision data, made the source code available on the web, and published two papers describing its operation, the first in the proceedings of the Data Compression Conference and the second in the IEEE Transactions on Computers. At comparable average compression ratios, this algorithm compresses and decompresses 10 to 100 times faster than BZIP2, DFCM, FSD, GZIP, and PLMI on the three architectures tested. With prediction tables that fit into the CPU's L1 data acache, FPC delivers a guaranteed throughput of six gigabits per second on a 1.6 GHz Itanium 2 system. The C source code and documentation of FPC are posted on-line and have already been downloaded hundreds of times. To evaluate FPC, they gathered 13 real-world scientific datasets from around the globe, including satellite data, crash-simulation data, and messages from HPC systems. Based on the large number of requests they received, they also made these datasets available to the community (with permission of the original sources). While FPC represents a great step forward, it soon became clear that its throughput was too slow for the emerging 10 gigabits per second networks. Hence, no speedup can be gained by including this algorithm in an MPI library. They therefore changed the aim of the second half of the project. Instead of implementing FPC in an MPI library, they refocused their efforts to develop a parallel compression algorithm to further boost the throughput. After all, all modern high-end microprocessors contain multiple CPUs on a single die and will undoubtedly contain even larger numbers of CPUs in the future. Hence, a compute node in a parallel system is likely to have multiple processors per interconnection link. Thus, they investigated how to best exploit multiple CPUs to compress and decompress data for a single link, i.e., they developed a parallel version of the FPC algorithm called pFPC. On a 4-core 3 GHz Xeon system, pFPC exceeds 10 gigabits per second both in compression and decompression throughput while still reaching a compression ratio of 18%, which is reasonable for their double-precision floating-point datasets. At half this throughput, it achieves a 41% compression ratio. Moreover, the algorithm scales well to four cores and promises even higher throughputs on larger machines. Additional results and a description of the pFPC algorithm have recently been published in the proceedings of the Data Compression Conference. The C source code of pFPC is also publicly available.
Cloud data centers are projected to be the fastest growing segment of the server market through 2015, according to IDC. Increasingly people and businesses rely on the Cloud to deliver digital content quickly and efficiently. Recovery Act funding from the Department of Energy has helped SeaMicro's technologies enhance the total cost of operation, performance and energy efficiency in large data center and Cloud environments. SeaMicro's innovative supercomputer fabric connects thousands of processor cores, memory, storage and input/output traffic. The company's fabric supports multiple processor instruction sets. Current systems featuring SeaMicro technology typically use one quarter the power and take one sixth the space of traditional servers with the same compute performance, yet deliver up to 12 times the bandwidth per core. Mozilla and eHarmony are two customers successfully using SeaMicro's technology. Numerous non-public customers have been successfully using the SeaMicro product in test and production facilities. As a result of the Recovery Act funding from the U.S. Department of Energy, more than 50 direct jobs were created at SeaMicro. To date, they primarily have been high-value, engineering jobs. Hardware, software and manufacturing engineering positions have been created, as well as sales and sales engineering. The positions have allowed SeaMicro to significantly accelerate engineering development and accelerate commercialization. As a result, commercialization and delivery to market are months ahead of initial schedule. Additional jobs were indirectly created through the development of the SeaMicro product. Through many years of research and hard work prior to receipt of public funding, SeaMicro was awarded 2 patents for its work. SeaMicro's product led the way for industry leaders to reconsider the market for low power servers and create new product lines. With valuable support of the U.S. Department of Energy and through SeaMicro's product, the market has been reshaped by the company's unique approach and ground breaking technology.
In a multiple processor computing apparatus, directional routing restrictions and a logical channel construct permit fault tolerant, deadlock-free routing. Processor allocation can be performed by creating a linear ordering of the processors based on routing rules used for routing communications between the processors. The linear ordering can assume a loop configuration, and bin-packing is applied to this loop configuration. The interconnection of the processors can be conceptualized as a generally rectangular 3-dimensional grid, and the MC allocation algorithm is applied with respect to the 3-dimensional grid.
The presentation discusses recent studies on the performance of the two parallel versions of the aerodynamics CFD code, OVERFLOW_MPI and _MLP. Developed at NASA Ames, the serial version, OVERFLOW, is a multidimensional Navier-Stokes flow solver based on overset (Chimera) grid technology. The code has recently been parallelized in two ways. One is based on the explicit message-passing interface (MPI) across processors and uses the _MPI communication package. This approach is primarily suited for distributed memory systems and workstation clusters. The second, termed the multi-level parallel (MLP) method, is simple and uses shared memory for all communications. The _MLP code is suitable on distributed-shared memory systems. For both methods, the message passing takes place across the processors or processes at the advancement of each time step. This procedure is, in effect, the Chimera boundary conditions update, which is done in an explicit "Jacobi" style. In contrast, the update in the serial code is done in more of the "Gauss-Sidel" fashion. The programming efforts for the _MPI code is more complicated than for the _MLP code; the former requires modification of the outer and some inner shells of the serial code, whereas the latter focuses only on the outer shell of the code. The _MPI version offers a great deal of flexibility in distributing grid zones across a specified number of processors in order to achieve load balancing. The approach is capable of partitioning zones across multiple processors or sending each zone and/or cluster of several zones into a single processor. The message passing across the processors consists of Chimera boundary and/or an overlap of "halo" boundary points for each partitioned zone. The MLP version is a new coarse-grain parallel concept at the zonal and intra-zonal levels. A grouping strategy is used to distribute zones into several groups forming sub-processes which will run in parallel. The total volume of grid points in each group are approximately balanced. A proper number of threads are initially allocated to each group, and in subsequent iterations during the run-time, the number of threads are adjusted to achieve load balancing across the processes. Each process exploits the multitasking directives already established in Overflow.
A description of the functions and data structures is defined that would be necessary to implement the Chapel concept of distributions, domains, allocation, access, and interfaces to the compiler for transformations from Chapel source to their run-time implementation for these concepts. A complete set of object-oriented operators is defined that enables one to access elements of a distributed array through regular arithmetic index sets, giving the programmer the illusion that all the elements are collocated on a single processor. This means that arbitrary regions of the arrays can be fragmented and distributed across multiple processors with a single point of access. This is important because it can significantly improve programmer productivity by allowing the programmers to concentrate on the high-level details of the algorithm without worrying about the efficiency and communication details of the underlying representation.
A method is presented for executing a direct simulation Monte Carlo (DSMC) analysis using parallel processing. The method is based on using domain decomposition to distribute the work load among multiple processors, and the DSMC analysis is performed completely in parallel. Message passing is used to transfer molecules between processors and to provide the synchronization necessary for the correct physical simulation. Benchmark problems are described for testing the method and results are presented which demonstrate the performance on two commercially available multicomputers. The results show that reasonable parallel speedup and efficiency can be obtained if the problem is properly sized to the number of processors. It is projected that with a massively parallel system, performance exceeding that of current supercomputers is possible.