Introduction to programming multiple-processor computers

Hicks, H. R.; Lynch, V. E.

doi:10.2172/5857628

Title: Introduction to programming multiple-processor computers

Full Record
Other Related Research

Abstract

FORTRAN applications programs can be executed on multiprocessor computers in either a unitasking (traditional) or multitasking form. The latter allows a single job to use more than one processor simultaneously, with a consequent reduction in wall-clock time and, perhaps, the cost of the calculation. An introduction to programming in this environment is presented. The concepts of synchronization and data sharing using EVENTS and LOCKS are illustrated with examples. The strategy of strong synchronization and the use of synchronization templates are proposed. We emphasize that incorrect multitasking programs can produce irreproducible results, which makes debugging more difficult.

Authors:: Hicks, H. R.; Lynch, V. E.

Publication Date:: Mon Apr 01 00:00:00 EST 1985

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

OSTI Identifier:: 5857628

Report Number(s):: ORNL/TM-9493
ON: DE85010274; TRN: 85-012592

DOE Contract Number:: AC05-84OR21400

Resource Type:: Technical Report

Country of Publication:: United States

Language:: English

Subject:: 70 PLASMA PHYSICS AND FUSION TECHNOLOGY; PROGRAMMING; COMPUTERS; CRAY COMPUTERS; FORTRAN; PROGRAMMING LANGUAGES; 700209* - Fusion Power Plant Technology- Component Development & Materials Testing

Citation Formats


                    Hicks, H. R., and Lynch, V. E. Introduction to programming multiple-processor computers.  United States: N. p., 1985. 
        Web.  doi:10.2172/5857628.

Copy to clipboard


                    Hicks, H. R., & Lynch, V. E. Introduction to programming multiple-processor computers.  United States.  https://doi.org/10.2172/5857628

Copy to clipboard


                    Hicks, H. R., and Lynch, V. E. 1985.  
        "Introduction to programming multiple-processor computers".  United States.  https://doi.org/10.2172/5857628.  https://www.osti.gov/servlets/purl/5857628.

Copy to clipboard


                    
@article{osti_5857628,

  title        = {Introduction to programming multiple-processor computers},

  author       = {Hicks, H. R. and Lynch, V. E.},

  abstractNote = {FORTRAN applications programs can be executed on multiprocessor computers in either a unitasking (traditional) or multitasking form. The latter allows a single job to use more than one processor simultaneously, with a consequent reduction in wall-clock time and, perhaps, the cost of the calculation. An introduction to programming in this environment is presented. The concepts of synchronization and data sharing using EVENTS and LOCKS are illustrated with examples. The strategy of strong synchronization and the use of synchronization templates are proposed. We emphasize that incorrect multitasking programs can produce irreproducible results, which makes debugging more difficult.},

  doi          = {10.2172/5857628},

  url          = {https://www.osti.gov/biblio/5857628},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Mon Apr 01 00:00:00 EST 1985},

  month        = {Mon Apr 01 00:00:00 EST 1985}

}

Copy to clipboard

Technical Report:

View Technical Report (0.48 MB)

https://doi.org/10.2172/5857628

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

An introduction to programming multiple-processor computers

Journal Article Hicks, H; Lynch, V - J. Comput. Phys.; (United States)

Fortran applications programs can be executed on multiprocessor computers in either a unitasking (traditional) or multitasking form. The later allows a single job to use more than one processor simultaneously, with a consequent reduction in elapsed time and, perhaps, the cost of the calculation. An introduction to programming in this environment is presented. The concept of synchronization and data sharing using EVENTS and LOCKS are illustrated with examples. The strategy of strong synchronization and the use of synchronization templates are proposed. We emphasize that incorrect multitasking programs can produce irreducible results, which makes debugging more difficult.
https://doi.org/10.1016/0021-9991(86)90088-4
Access ordering and coherence in shared-memory multi-processors

Book Scheurich, C

Shared memory forms a convenient communication medium in a multitasking multiprocessor system. However, different multiprocessors can execute the same program in different manners, possibly yielding incorrect results because the machines adhere to different rules. Differences in behavior are due to the varying approaches of designers to attack the shared memory access latency problem in multiprocessors. In particular, the manner in which multiple copies of data are controlled and the manner in which memory accesses are sequenced, propagated, and buffered has impact on the behavior of the multiprocessor. Three shared memory execution models, referred to as concurrency models, are defined. Themore »« less
Debugging and analysis of large-scale parallel programs. Doctoral thesis

Technical Report Mellor-Crummey, J

One of the most serious problems in the development cycle of large-scale parallel programs is the lack of tools for debugging and performance analysis. Parallel programs are more difficult to analyze than their sequential counterparts for several reasons. First, race conditions in parallel programs can cause non-deterministic behavior, which reduces the effectiveness of traditional cyclic debugging techniques. Second, invasive, interactive analysis can distort a parallel program's execution beyond recognition. Finally, comprehensive analysis of a parallel program's execution requires collection, management, and presentation of an enormous amount of information. This dissertation addresses the problem of debugging and analysis of large-scale parallelmore »« less
Nonpreemptive run-time scheduling issues on a multitasked, multiprogrammed multiprocessor with dependencies, bidimensional tasks, folding, and dynamic graphs

Thesis/Dissertation Miller, A

Increases in high-speed hardware have mandated studies in software techniques to exploit the parallel capabilities. This thesis examines the effects a run-time scheduler has on a multiprocessor. The model consists of directed, acyclic graphs,generated from serial FORTRAN benchmark programs by the parallel compiler Parafrase. A multitasked, multiprogrammed environment is created. Dependencies are generated by the compiler. Tasks are bidimensional, i.e., they may specify both time and processor requests. Processor requests may be folded into execution time by the scheduler. The graphs may arrive at arbitrary time intervals. The general case is NP-hard, thus, a variety of heuristics are examined bymore »« less
Nonpreemptive run-time scheduling issues on a multitasked, multiprogrammed multiprocessor with dependencies, bidimensional tasks, folding and dynamic graphs

Technical Report Miller, Allan

Increases in high speed hardware have mandated studies in software techniques to exploit the parallel capabilities. This thesis examines the effects a run-time scheduler has on a multiprocessor. The model consists of directed, acyclic graphs, generated from serial FORTRAN benchmark programs by the parallel compiler Parafrase. A multitasked, multiprogrammed environment is created. Dependencies are generated by the compiler. Tasks are bidimensional, i.e., they may specify both time and processor requests. Processor requests may be folded into execution time by the scheduler. The graphs may arrive at arbitrary time intervals. The general case is NP-hard, thus, a variety of heuristics aremore »« less
https://doi.org/10.2172/5546139

Full Text Available

Similar Records