Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Program partitioning for NUMA multiprocessor computer systems. [Nonuniform memory access]

Journal Article · · Journal of Parallel and Distributed Computing; (United States)
;  [1]
  1. Lawrence Livermore National Lab., CA (United States)
Program partitioning and scheduling are essential steps in programming non-shared-memory computer systems. Partitioning is the separation of program operations into sequential tasks, and scheduling is the assignment of tasks to processors. To be effective, automatic methods require an accurate representation of the model of computation and the target architecture. Current partitioning methods assume today's most prevalent models -- macro dataflow and a homogeneous/two-level multicomputer system. Based on communication channels, neither model represents well the emerging class of NUMA multiprocessor computer systems consisting of hierarchical read/write memories. Consequently, the partitions generated by extant methods do not execute well on these systems. In this paper, the authors extend the conventional graph representation of the macro-dataflow model to enable mapping heuristics to consider the complex communication options supported by NUMA architectures. They describe two such heuristics. Simulated execution times of program graphs show that the model and heuristics generate higher quality program mappings than current methods for NUMA architectures.
DOE Contract Number:
W-7405-ENG-48
OSTI ID:
5703692
Journal Information:
Journal of Parallel and Distributed Computing; (United States), Journal Name: Journal of Parallel and Distributed Computing; (United States) Vol. 19:3; ISSN JPDCER; ISSN 0743-7315
Country of Publication:
United States
Language:
English

Similar Records

Program partitioning and scheduling for NUMA computer architectures
Thesis/Dissertation · Mon Feb 28 23:00:00 EST 1994 · OSTI ID:10182814

General approach to multiprocessor scheduling
Thesis/Dissertation · Thu Dec 31 23:00:00 EST 1987 · OSTI ID:5501704

Allocation for the SANDAC multiprocessor system
Book · Tue Dec 31 23:00:00 EST 1985 · OSTI ID:5045854