This is the mail archive of the gcc@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: Comparison of Itanium gcc 4.1 and 4.2 on Spec2000

From: Robert Dewar <dewar at adacore dot com>
To: Joe Buck <Joe dot Buck at synopsys dot COM>
Cc: "Vladimir N. Makarov" <vmakarov at redhat dot com>, Mark Mitchell <mark at codesourcery dot com>, gcc at gcc dot gnu dot org
Date: Fri, 23 Feb 2007 20:27:38 -0500
Subject: Re: Comparison of Itanium gcc 4.1 and 4.2 on Spec2000
References: <45DEF8C4.6020409@redhat.com> <45DF0F7C.20604@codesourcery.com> <45DF11B9.9090208@redhat.com> <20070224011215.GB31180@synopsys.com>

Joe Buck wrote:

Perhaps I'm missing something obvious, but often conservative aliasing
results in reading lots of extra data from memory.  How can speculation
compensate for that?  It seems that the best you can do is reduce the
penalty, if you can do something in parallel with the extra I/O.


You can speculate that a memory location is not changed, and if it is
then and only then do you get the extra load?

References:
- Comparison of Itanium gcc 4.1 and 4.2 on Spec2000
  - From: Vladimir N. Makarov
- Re: Comparison of Itanium gcc 4.1 and 4.2 on Spec2000
  - From: Mark Mitchell
- Re: Comparison of Itanium gcc 4.1 and 4.2 on Spec2000
  - From: Vladimir N. Makarov
- Re: Comparison of Itanium gcc 4.1 and 4.2 on Spec2000
  - From: Joe Buck

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]