Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!purdue!ames!lll-winken!maddog.llnl.gov!brooks
From: brooks@maddog.llnl.gov
Newsgroups: gnu.gcc
Subject: Loop unrolling in GCC
Message-ID: <25539@lll-winken.LLNL.GOV>
Date: 19 May 89 15:45:12 GMT
Sender: usenet@lll-winken.LLNL.GOV
Reply-To: brooks@maddog.llnl.gov ()
Distribution: gnu
Organization: Lawrence Livermore National Laboratory
Lines: 8

Has anyone with suitable experience with GCC internals considered
the difficulty of adding a "loop unrolling" feature to GCC?  It would
be portable and with a suitable pipeline scheduling strategy would be
a big win for some of the modern pipelined processors.

Anyone know where you would start on this one?

brooks@maddog.llnl.gov, brooks@maddog.uucp