1,721,293 research outputs found
What have we learnt from using real parallel machines to solve real problems?
No full textWe briefly review some key scientific and parallel processing issues in a selection of some 84 existing applications of parallel machines. We include the MIMD hypercube transputer array, BBN Butterfly, and the SIMD ICL DAP, Goodyear MPP and Connection Machine from Thinking Machines. We use a space-time analogy to classify problems and show how a division into synchronous, loosely synchronous and asynchronous problems is helpful. This classifies problems into those suitable for SIMD or MIMD machines and isolates the asynchronous class as that for which major uncertainties as to possible parallelism exist. Interestingly about half of the scientific applications run excellently on SIMD machines with the other half able to take especial advantage of the MIMD architecture
A string theory for time dependent complex systems and its application to automatic decomposition
No full textWe introduce a string or world line formalism that provides a general description of time dependent complex systems. We show that it can be applied to mapping general problems onto both sequential and parallel computers. In principle it unifies the concepts of an optimizing compiler with that of parallel decomposition. We show that it reproduces and smoothly interpolates both our original load balancing methods for loosely synchronous problems and optimal communication and combining algorithms such as index and fold. We evaluate two explicit implementations, the neural_router and neural_accumulator, which use an optimizing neural network
The Flux-corrected transport algorithm on the NCUBE hypercube
No full textThis work describes the implementation of a finite-difference algorithm, incorporating the flux-corrected transport technique, on the NCUBE hypercube. The algorithm is used to study two-dimensional, convectively-dominated fluid flows, and as a sample problem the onset and growth of the Kelvin-Helmholtz instability is investigated. Timing results are presented for a number of different sized problems on hypercubes of dimension up to 9. These results are interpreted by means of a simple performance model. The extension of the algorithm to the three-dimensional case is also discussed
Recommended from our members
STREAM2016: Streaming Requirements, Experience, Applications and Middleware Workshop: Workshop Final Report
Get PDFThe Department of Energy (DOE) Office of Science (SC) facilities
including accelerators, light sources and neutron sources and sensors
that study, the environment, and the atmosphere, are producing
streaming data that needs to be analyzed for next-generation
scientific discoveries. There has been an explosion of new research
and technologies for stream analytics arising from the academic and
private sectors. However, there has been no corresponding effort in
either documenting the critical research opportunities or building a
community that can create and foster productive collaborations. The
two-part workshop series, STREAM: Streaming Requirements, Experience,
Applications and Middleware Workshop (STREAM2015 and STREAM2016), were
conducted to bring the community together and identify gaps and future
efforts needed by both NSF and DOE.
This report describes the discussions, outcomes and conclusions from
STREAM2016: Streaming Requirements, Experience, Applications and
Middleware Workshop, the second of these workshops held on March
22-23, 2016 in Tysons, VA. STREAM2016 focused on the Department of
Energy (DOE) applications, computational and experimental facilities,
as well software systems. Thus, the role of “streaming and steering”
as a critical mode of connecting the experimental and computing
facilities was pervasive through the workshop. Given the overlap in
interests and challenges with industry, the workshop had significant
presence from several innovative companies and major contributors.
The requirements that drive the proposed research directions,
identified in this report, show an important opportunity for building
competitive research and development program around streaming
data. These findings and recommendations are consistent with vision
outlined in NRC Frontiers of Data and National Strategic Computing
Initiative (NCSI) [1, 2]. The discussions from the workshop are
captured as topic areas covered in this report's sections. The report
discusses four research directions driven by current and future
application requirements reflecting the areas identified as important
by STREAM2016. These include (i) Algorithms, (ii) Programming Models,
Languages and Runtime Systems (iii) Human-in-the-loop and Steering in
Scientific Workflow and (iv) Facilities
Optimal matrix algorithms on homogeneous hypercubes
No full textThis paper describes a set of concurrent algorithms for matrix algebra, based on a library of collective communication routines for the hypercube. We show how a systematic application of scattering reduces load imbalance. A number of examples are considered (Gaussian elimination, Gauss-Jordan matrix inversion, the power method for eigenvectors, and tridiagonalisation by Householder's method), and the concurrent efficiencies are discussed
A universal concurrent algorithm for plasma particle-in-cell simulation codes
No full texte have developed a new algorithm for implementation of plasma particle-in-cell (PIC) simulation codes on concurrent processors. This algorithm, termed the universal concurrent PIC algorithm (UC-PIC), has been utilized in a one-dimensional electrostatic PIC code on the JPL Mark III Hypercube parallel computer. To decompose the problem using the UC-PIC algorithm, the physical domain of the simulation is divided into sub-domains, equal in number to the number of processors, such that all sub-domains have roughly equal numbers of particles. For problems with non-uniform particle densities, these sub-domains will be of unequal physical size. Each processor is assigned, a sub-domain, with nearest neighbor sub-domains assigned to nearest neighbor processors. Using this algorithm in the Mark III PIC code, the increase in speed in going from 1 to 32 processors for the dominant portion of code (push time, defined below) was 29, yielding a parallel efficiency of 90%. Although implemented on a hypercube concurrent computer, this algorithm should be also be efficient for PIC codes on other parallel architectures and on sequential computers where part of the data resides in external memory
PC-CUBE: A Personal Computer Based Hypercube
Get PDFPC-CUBE is an ensemble of IBM PCs or close compatibles connected in the hypercube topology with ordinary computer cables. Communication occurs at the rate of 115.2 K-band via the RS-232 serial links. Available for PC-CUBE is the Crystalline Operating System III (CrOS III), Mercury Operating System, CUBIX and PLOTIX which are parallel I/O and graphics libraries. A CrOS performance monitor was developed to facilitate the measurement of communication and computation time of a program and their effects on performance. Also available are CXLISP, a parallel version of the XLISP interpreter; GRAFIX, some graphics routines for the EGA and CGA; and a general execution profiler for determining execution time spent by program subroutines. PC-CUBE provides a programming environment similar to all hypercube systems running CrOS III, Mercury and CUBIX. In addition, every node (personal computer) has its own graphics display monitor and storage devices. These allow data to be displayed or stored at every processor, which has much instructional value and enables easier debugging of applications. Some application programs which are taken from the book Solving Problems on Concurrent Processors (Fox 88) were implemented with graphics enhancement on PC-CUBE. The applications range from solving the Mandelbrot set, Laplace equation, wave equation, long range force interaction, to WaTor, an ecological simulation
MAC-CUBE, the Macintosh-based hypercube
No full textThe MAC-CUBE is a Macintosh-based hypercube. It uses AppleTalk hardware and software as the medium for the nodal connections. At the physical level AppleTalk has a bus topology. Hypercube connectivity is emulated on the AppleTalk local area network while the hypercube communication protocol is integrated in the AppleTalk software. Available for MAC-CUBE is the Crystalline Operating System III (CrOS III.) MAC-CUBE provides a programming environment similar to any other hypercube systems running CrOS III. It allows inexpensive hands-on experience with a concurrent machine. Data can be displayed on graphics monitor and/or stored locally at each node. In addition to the low cost, these capabilities of the Mac-Cube makes it an indispensable instructional and development tool for parallel processing. Some application programs which are taken from the book Solving Problems on Concurrent Processors [Fox 88] have been implemented with graphics enhancement on Mac-Cube. The applications are solving the Mandelbrot set in the complex plane, and solving a 2-dimensional Laplace equation using finite difference
- …
