Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!ukma!xanth!mcnc!ecsvax!urjlew
From: urjlew@ecsvax.UUCP (Rostyk Lewyckyj)
Newsgroups: comp.lang.fortran
Subject: Re: Parallelizing Techniques
Summary: IBM
Keywords: parallelizing, compiler, vectorizing
Message-ID: <6790@ecsvax.UUCP>
Date: 8 Apr 89 17:53:30 GMT
References: <17287@cisunx.UUCP>
Organization: UNC Educational Computing Service
Lines: 47

In article <17287@cisunx.UUCP>, dpl@cisunx.UUCP (David P. Lithgow) writes:
@ To all compiler gurus:
@ 
@ 	I am looking for references to Cray/VAX/FPS (and any other system)
@ and their FORTRAN (or other, perhaps Ada) compilers' ability to detect
@ opportunities for parallelism or vectorization inside and outside the compiler.
@ Since many languages can be used to write code for parallel systems, but they
@ support it outside the compiler (by providing explicit library calls to
@ the programmer to implement it for him/herself), I am not restricting my
@ search.
@ 
@ 	I know of the VAX/VMS PPL$ library routines, and I'd like to
@ find a pointer or two to Cray Micro/Macro tasking, and other compilers'
@ means of detecting parallelism (or vectorizable code).  Note that some
@ of the most productive work seems to have gone ahead in VLIW systems...
@ 
@ 	Are there any current Ada compilers which automatically vectorize or
@ parallelize?
@ 
@ 					-David P. Lithgow
@ --
@ David P. Lithgow                Sr. Systems Analy./Pgmr., Univ. of Pittsburgh

Hie thee to your local IBM representative and let him inform you
about IBMs parallel FOrtran products for the 3090 supercomputers:
compiler, debugging tools (PTOOL) etc., libraries (ESSL v3.) etc.
Contact the good folk at the Cornell National Supercomputer Facility.
They can tell you about non IBM tools.
Contact Rice University (Dr. Kemeny ?)

Parallelization is a compiler option that the user must ask for. 
Just as different levels of optimization, vectorization, or a machine code 
listing, must be asked for. In addition to the automatic parallelization there
are IBM extensions to the Fortran language which allow the programmer
to explicitly control parallelism: fork processes, set up private vs
shared strage, synchronize, divide work among available processors,
etc.
I don't think that current IBM 3090 architecture is capable of
scheduling individual arithmetic operations within a single Fortran
statement across multiple processors economically, so the slest
granularity of parallelization is across do loops. i.e. there is
nothing equivalent to CRAY micro/auto tasking.
-----------------------------------------------
  Reply-To:  Rostyslaw Jarema Lewyckyj
             urjlew@ecsvax.UUCP ,  urjlew@tucc.bitnet
       or    urjlew@tucc.tucc.edu    (ARPA,SURA,NSF etc. internet)
       tel.  (919)-962-9107