[comp.arch] Parallaxis - new version

braunl@az3.ifistg.uucp (06/12/90)

___________________________________________________________________

  THE  P A R A L L A X I S  MASSIVELY PARALLEL PROGRAMMING SYSTEM
___________________________________________________________________

Now Parallaxis version 1.2 is available with a few bugs fixed.
It is available via "anonymous ftp" from:
    ifigw.informatik.uni-stuttgart.de    (129.69.211.1)
    in subdirectory    pub/parallaxis

Please send remarks or bug reports directly to:
    braunl@informatik.uni-stuttgart.de
but FIRST, make sure you are using the latest version of the system.

Text file BUGS_FIXED documents problems with earlier versions that
have been fixed. Text file DOCU_SHORT gives a limited overview about
the Parallaxis system, including the language's syntax, but does NOT 
replace the user manual.

In addition to the current versions for:
  * Apollo              (AEGIS 9.7)
  * Sun3                (OS 4.0)
  * Sun4 / Sparcstation (OS 4.0)
  * IBM-PC              (DOS)    and
  * Apple Macintosh     (MAC OS)

we now also provide versions for:
  * HP 9000/300         (Unix)   and
  * HP /800 series      (Unix)

Please, keep in mind that you still need the "Parallaxis User Manual"
(which is not available via ftp) for serious use! So when returning
the registration sheet, please indicate that you received the system 
through the net and you just need the manual.


REMINDER:

Parallaxis is a procedural programming language based on Modula-2,
but extended for data parallel programming. It was developed at the
Universitaet Stuttgart (Germany) and is now available as public
domain software.

Here, the main approach for machine independent parallel programming
is to combine a description of the (virtual) parallel machine with
the parallel algorithm that is bound for that particular architecture.
Parallaxis allows the structured programming of SIMD systems with a
central host and a large number of identical processors. The declaration
includes the number of identical processors with local memory (PEs), 
the names of communication ports, and the network topology for data 
exchange among PEs. With this information contained in each program, 
the parallel algorithm becomes simpler (e.g. symbolic names for 
communication directions) and easier to understand.

=======================================================================
Thomas Braunl               e-mail:  braunl@informatik.uni-stuttgart.de
Univ. Stuttgart IFI,  Azenbergstr. 12,  D-7000 Stuttgart 1,  W.-Germany
=======================================================================

=======================================================================
Thomas Braunl               e-mail:  braunl@informatik.uni-stuttgart.de
Univ. Stuttgart IFI,  Azenbergstr. 12,  D-7000 Stuttgart 1,  W.-Germany
=======================================================================