SAL Home PARALLEL Communication Libraries

Global Arrays

The Global Array (GA) toolkit provides an efficient and portable "shared-memory" programming interface for distributed-memory computers. Each process in a MIMD parallel program can asynchronously access logical blocks of physically distributed matrices, without need for explicit cooperation by other processes. Unlike other shared-memory environments, the GA model exposes to the programmer the Nonuniform Memory Access (NUMA) characteristics of the high performance computers and acknowledges that access to remote data is slower than to local data. The locality information for the shared data is available and a very efficient access to the local data is provided.

Current Version:   2.3

License Type:   Free,

Home Site:

Source Code Availability: Yes

Available Binary Packages:

  • Debian Package: No
  • RedHat RPM Package: No
  • Other Packages: No

Targeted Platforms:

IBM SP 1/2, CRAY T3D/E, Intel IPSC/860, Delta, Paragon, KSR-1/2, CONVEX Exemplar, SGI PowerChallenge and Origin, clusters of workstations including: SUN, SGI, IBM RS/6000, DEC Alpha, and Linux.

Software/Hardware Requirements:

Compilers: gcc, f2c or g77
Message passing libraries: MPI or TCGMSG (included with the distribution)

Other Links:

Mailing Lists/USENET News Groups:


User Comments:

  • None

See A Screen Shot?

visualizer for GA trace data.

  SAL Home   |   Parallel Computing   |   Communication Libraries

Comments? SAL@KachinaTech.COM
Copyright © 1995-2001 by Herng-Jeng Jou
Copyright © 1997-2001 by Kachina Technologies, Inc.
All rights reserved.