From: Mostafa Hagog <MUSTAFA@il.ibm.com>
To: Richard Henderson <rth@redhat.com>
Cc: Canqun Yang <canqun@nudt.edu.cn>,
gcc@gcc.gnu.org, Ayal Zaks <ZAKS@il.ibm.com>
Subject: Re: SMS scheduling
Date: Thu, 30 Sep 2004 11:29:00 -0000 [thread overview]
Message-ID: <OFB76CBD7D.A253EAEA-ONC2256F1F.002FED7D-C2256F1F.0030A978@il.ibm.com> (raw)
In-Reply-To: <20040930084214.GA6698@redhat.com>
Richard Henderson <rth@redhat.com> wrote on 30/09/2004 10:42:14:
> On Thu, Sep 30, 2004 at 10:03:37AM +0200, Mostafa Hagog wrote:
> > For 4.0 SMS intra-loop memory dependencies are detected using
> > the alias.c (as in haifa-sched) for inter-loop memory dependencies
> > we are very conservative and assume that all memory accesses are
> > aliased.
>
> alias.c is flow insensative, and thus as conservative as you
> could want. Why aren't you using it all the time?
The answer is within your question; flow insensitive.
In SMS we are interested in loop-carried dependancies
and this is not provided by alias.c. One thought is to
propagate the dependency information from trees down to the
RTL (Sebastian Bob looked into this). This is a long term
working item for SMS.
Mostafa.
next prev parent reply other threads:[~2004-09-30 8:51 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-09-28 12:57 Canqun Yang
2004-09-29 15:36 ` Mostafa Hagog
2004-09-30 8:50 ` Mostafa Hagog
2004-09-30 8:51 ` Richard Henderson
2004-09-30 10:57 ` Mostafa Hagog
2004-09-30 11:26 ` Richard Henderson
2004-09-30 11:29 ` Mostafa Hagog [this message]
2004-09-30 19:34 ` Richard Henderson
2004-10-03 17:59 ` Mostafa Hagog
2004-10-04 1:06 ` Richard Henderson
2004-10-04 12:14 ` Mostafa Hagog
2004-10-04 17:20 ` Richard Henderson
2004-10-04 23:03 ` Ayal Zaks
2004-10-02 12:25 ` Canqun Yang
2004-10-03 19:54 ` Mostafa Hagog
2004-10-09 17:55 ` Canqun Yang
2004-10-24 19:54 ` Mostafa Hagog
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=OFB76CBD7D.A253EAEA-ONC2256F1F.002FED7D-C2256F1F.0030A978@il.ibm.com \
--to=mustafa@il.ibm.com \
--cc=ZAKS@il.ibm.com \
--cc=canqun@nudt.edu.cn \
--cc=gcc@gcc.gnu.org \
--cc=rth@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).