Xref: utzoo comp.arch:10169 comp.misc:6286
Path: utzoo!attcan!uunet!cs.utexas.edu!tut.cis.ohio-state.edu!purdue!gatech!prism!loligo!mccalpin
From: mccalpin@loligo.cc.fsu.edu (John McCalpin)
Newsgroups: comp.arch,comp.misc
Subject: Re: front ends to crays...
Summary: front ends are not dead
Message-ID: <758@loligo.cc.fsu.edu>
Date: 8 Jun 89 19:37:21 GMT
References: <5674@hubcap.clemson.edu> <32216@apple.Apple.COM>
Reply-To: mccalpin@loligo.cc.fsu.edu (John McCalpin)
Organization: Supercomputer Computations Research Institute
Lines: 26

In article <> hubcap@hubcap.clemson.edu (Mike Marshall) writes:
>What would make a good front end for a YMP, and why? 

In article <> malcolm@Apple.COM (Malcolm Slaney) replies:
>Why do you need a front end machine?  (This is comp.arch, after all.)
>I think it is time to put the concept of a front end machine to bed.

Some reasons for a front-end machine:

(1) Cray MIPS are definitely not cheap, and it is difficult to
    convince users not to run inefficient or inappropriate codes
    on the back end.
(2) Cray disks are definitely not cheap.  A front-end with very
    good I/O performance and lots of slots for cheap 1 GB SMD disks
    can be very useful (provided it supports the Cray 100 MB/s 
    high-speed channel).
(3) Cray memory is neither cheap nor abundant.  Any jobs which do
    not need to be on the Cray should not be on the Cray taking up 
    memory from applications that need it.
(4) A centralized front-end provides an appropriate spot for things
    like mailers, mailing lists, news, etc.  This is slightly more
    difficult to do in a "workstation & supercomputer only" environment.
-- 
John D. McCalpin - Dept of Oceanography - Florida State University
mccalpin@masig1.ocean.fsu.edu		mccalpin@nu.cs.fsu.edu
mccalpin@fsu (BITNET or MFENET)		SCRI::MCCALPIN (SPAN)