Advanced large-scale and high-speed multiprocessor system for scientific applications CRAY X-MP-4 series

Chen, S S

Title: Advanced large-scale and high-speed multiprocessor system for scientific applications CRAY X-MP-4 series

Full Record
Other Related Research

Abstract

This paper offers an overview of CRAY X-MP-4 system, a general purpose multiprocessor system for multitasking applications. Diagrams illustrate the overall system organization, data flow, vector computations and vector loop families benchmark timings. The CRAY X-MP-4 has scalar and vector applications.

Authors:: Chen, S S

Publication Date:: Sun Jun 01 00:00:00 EDT 1986

Research Org.:: Cray Research Inc., Chippewa Falls, WI

OSTI Identifier:: 7127175

Report Number(s):: CONF-8509213-
Journal ID: CODEN: JSTPB

Resource Type:: Conference

Journal Name:: J. Stat. Phys.; (United States)

Additional Journal Information:: Journal Volume: 43:5/6; Conference: Frontiers of quantum Monte Carlo conference, Los Alamos, NM, USA, 3 Sep 1985

Country of Publication:: United States

Language:: English

Subject:: 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; CRAY COMPUTERS; COMPUTER ARCHITECTURE; PARALLEL PROCESSING; USES; ALGORITHMS; ARRAY PROCESSORS; COMPUTER CODES; COMPUTERIZED SIMULATION; DATA-FLOW PROCESSING; DIAGRAMS; GAMMA TRANSPORT THEORY; MONTE CARLO METHOD; PERFORMANCE; PLASMA SIMULATION; SEISMIC WAVES; SUPERCOMPUTERS; TASK SCHEDULING; VECTOR PROCESSING; COMPUTERS; DATA PROCESSING; DIGITAL COMPUTERS; MATHEMATICAL LOGIC; PROCESSING; PROGRAMMING; SIMULATION; TRANSPORT THEORY; 990210* - Supercomputers- (1987-1989)

Citation Formats


                    Chen, S S. Advanced large-scale and high-speed multiprocessor system for scientific applications CRAY X-MP-4 series.  United States: N. p., 1986. 
        Web.

Copy to clipboard


                    Chen, S S. Advanced large-scale and high-speed multiprocessor system for scientific applications CRAY X-MP-4 series.  United States.

Copy to clipboard


                    Chen, S S. 1986.  
        "Advanced large-scale and high-speed multiprocessor system for scientific applications CRAY X-MP-4 series".  United States.

Copy to clipboard


                    
@article{osti_7127175,

  title        = {Advanced large-scale and high-speed multiprocessor system for scientific applications CRAY X-MP-4 series},

  author       = {Chen, S S},

  abstractNote = {This paper offers an overview of CRAY X-MP-4 system, a general purpose multiprocessor system for multitasking applications. Diagrams illustrate the overall system organization, data flow, vector computations and vector loop families benchmark timings. The CRAY X-MP-4 has scalar and vector applications.},

  doi          = {},

  url          = {https://www.osti.gov/biblio/7127175},
  journal      = {J. Stat. Phys.; (United States)},
number       = ,

  volume       = 43:5/6,

  place        = {United States},

  year         = {Sun Jun 01 00:00:00 EDT 1986},

  month        = {Sun Jun 01 00:00:00 EDT 1986}

}

Copy to clipboard

Conference:

Other availability

Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Multitasking 3-D forward modeling using high-order finite difference methods on the Cray X-MP/416

Journal Article Terki-Hassaine, O; Leiss, E - Int. J. Supercomput. Appl.; (United States)

The CRAY X-MP/416 was used to multitask 3-D forward modeling by the high-order finite difference method. Flowtrace analysis reveals that the most expensive operation in the unitasked program is a matrix vector multiplication. The in-core and out-of-core versions of a reentrant subroutine can perform any fraction of the matrix vector multiplication independently, a pattern compatible with multitasking. The matrix vector multiplication routine can be distributed over two to four processors. The rest of the program utilizes the microtasking feature that lets the system treat independent iterations of DO-loops as subtasks to be performed by any available processor. The availability ofmore »« less
https://doi.org/10.1177/109434208800200104
Experience of implementing applicative parallelism on Cray X-MP

Conference Lee, Ching-Cheng

The traditional approach on Cray multiprocessing has been multitasking in FORTRAN environments with operating system support. This kind of approach usually requires explicit user intervention to restructure or reformulated the algorithms to control parallel execution. However, it is error-prone and in most cases, only coarse-grain parallelism such as subrountines or functions was explored. In this paper, an implemention of micro-tasking for an applicative language called SISAL on Cray X-MP is reported. The experience indicates where the automatic approach to parallelization works well, as well as sources of inefficient behavior on the Cray X-MP. The experience also suggests some future improvementsmore »« less
Multitasking the three-dimensional shock wave code CTH on the Cray X-MP/416

Conference McGlaun, J; Thompson, S

CTH is a software system under development at Sandia National Laboratories Albuquerque that models multidimensional, multi-material, large-deformation, strong shock wave physics. CTH was carefully designed to both vectorize and multitask on the Cray X-MP/416. All of the physics routines are vectorized except the thermodynamics and the interface tracer. All of the physics routines are multitasked except the boundary conditions. The Los Alamos National Laboratory multitasking library was used for the multitasking. The resulting code is easy to maintain, easy to understand, gives the same answers as the unitasked code, and achieves a measured speedup of approximately 3.5 on the fourmore »« less
Speedup predictions for large scientific parallel programs on Cray X-MP-like architectures. Revision

Conference Williams, E; Bobrowicz, F

How much speedup can we expect for large scientific parallel programs running on supercomputers. For insight into this problem we extend the parallel processing environment currently existing on the Cray X-MP (a shared memory multiprocessor with at most four processors) to a simulated N-processor environment, where N less than or equal to 1. Several large scientific parallel programs from Los Alamos National Laboratory were run in this simulated environment, and speedups were predicted. A speedup of 14.4 on 16 processors was measured for one of the three most used codes at the Laboratory.
Large-scale unconstrained optimization on the FPS 164 and Cray X-MP vector processors

Journal Article Lescrenier, M; Tointt, P - Int. J. Supercomput. Appl.; (United States)

Among methods for large-scale unconstrained optimization, partitioned quasi-Newton methods seem fairly suitable for vector computing. This paper reports on efforts to adapt a method of this type to vector processors. The conclusion is that a satisfying improvement in performance can be obtained, especially when the inner loops deal with the elements of the objective function. Performances on FPS 164 and CRAY X-MP machines are compared.
https://doi.org/10.1177/109434208800200105

Similar Records