This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [wwwdocs] optimizer improvements for GCC 4.1 changes.html
- From: Gerald Pfeifer <gerald at pfeifer dot com>
- To: Dorit Naishlos <DORIT at il dot ibm dot com>
- Cc: gcc-patches at gcc dot gnu dot org, Steven Bosscher <stevenb at suse dot de>
- Date: Tue, 2 Aug 2005 00:07:01 +0200 (CEST)
- Subject: Re: [wwwdocs] optimizer improvements for GCC 4.1 changes.html
- References: <OF1BACABA8.4CCE56B4-ONC2257049.0045E064-C2257049.00467AF1@il.ibm.com>
On Mon, 25 Jul 2005, Dorit Naishlos wrote:
>>> + <li>Improvements to peeling for alignment.</li>
>> Anything more specific you could add?
> The improvements to peeling for alignment can be summarized as:
> "Generate better code when the misalignment of an access is known at
> compile time, or when different accesses are known to have the same
> misalignment, even if the misalignment amount itself is unknown."
Thanks for the explanation, Dorit. I added this on top of Steven's
patch.
Gerald
Index: changes.html
===================================================================
RCS file: /cvs/gcc/wwwdocs/htdocs/gcc-4.1/changes.html,v
retrieving revision 1.3
diff -u -3 -p -r1.3 changes.html
--- changes.html 24 Jul 2005 22:14:55 -0000 1.3
+++ changes.html 1 Aug 2005 22:05:23 -0000
@@ -96,7 +96,11 @@
<ul>
<li>Incrementally preserve SSA form when vectorizing.</li>
<li>Incrementally preserve loop-closed form when vectorizing.</li>
- <li>Improvements to peeling for alignment.</li>
+ <li>Improvements to peeling for alignment:
+ generate better code when the misalignment of an access
+ is known at compile time, or when different accesses are
+ known to have the same misalignment, even if the
+ misalignment amount itself is unknown.</li>
<li>Consider dependence distance in the vectorizer.</li>
<li>Externalize generic parts of data reference analysis to
make this analysis available to other passes.</li>