From: Joern Rennecke <amylaar@spamcop.net>
To: Jeff Law <law@redhat.com>
Cc: "H.J. Lu" <hjl.tools@gmail.com>,
Quentin Neill <quentin.neill.gnu@gmail.com>,
binutils@sourceware.org, gcc@gcc.gnu.org
Subject: Re: Scheduling x86 dispatch windows
Date: Thu, 10 Jun 2010 20:38:00 -0000 [thread overview]
Message-ID: <20100610162506.s1zhccts8400wg0w-nzlynne@webmail.spamcop.net> (raw)
In-Reply-To: <4C1144F7.1040708@redhat.com>
Quoting Jeff Law <law@redhat.com>:
> That adds quite a bit of complication to the compiler though -- getting
> the instruction lengths right (and thus proper packing & alignment) can
> be extremely difficult. I did some experiments with this on a target
> with *fixed* instruction lengths a while back and even though the port
> tried hard to get lengths right, it would routinely miss something.
> Ultimately I decided that it forcing the compiler to know instruction
> lengths with a very high degree of accuracy wasn't a sane thing to do.
> Dealing with variable instruction lengths just adds yet another
> complexity to the situation. Then add the complication of needing to
> add specific prefixes or nops and it just gets downright ugly.
I did add alignment-aware & exact branch shortening to the ARCompact port,
but ultimately the added complexity due to this was also a factor why the
port couldn't go into mainline without an active maintainer.
The code is available on branches.
See PR target/39303.
next prev parent reply other threads:[~2010-06-10 20:25 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-06-10 17:24 reza yazdani
2010-06-10 19:52 ` Quentin Neill
2010-06-10 20:12 ` H.J. Lu
2010-06-10 20:25 ` Jeff Law
2010-06-10 20:38 ` Joern Rennecke [this message]
2010-06-10 21:54 ` Quentin Neill
2010-06-10 22:09 ` H.J. Lu
2010-06-10 22:40 ` Quentin Neill
2010-06-10 22:48 ` H.J. Lu
2010-06-11 23:36 ` Quentin Neill
2010-06-12 18:54 ` H.J. Lu
2010-06-13 21:54 ` H.J. Lu
2010-06-14 13:37 ` Michael Matz
2010-06-14 16:06 ` Jakub Jelinek
2010-06-11 0:44 ` Daniel Jacobowitz
2010-06-11 5:58 ` Quentin Neill
2010-06-11 16:46 ` Daniel Jacobowitz
2010-06-11 19:21 ` Quentin Neill
2010-06-11 19:41 ` H.J. Lu
2010-06-11 19:50 ` Jakub Jelinek
2010-06-12 11:25 ` Andi Kleen
2010-06-12 22:45 ` Ian Lance Taylor
2010-06-13 12:35 ` Andi Kleen
2010-06-13 13:09 ` Joern Rennecke
2010-06-13 14:36 ` Andi Kleen
2010-06-13 15:02 ` Joern Rennecke
2010-06-13 19:56 ` Chris Lattner
2010-06-13 16:28 ` Frank Ch. Eigler
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=20100610162506.s1zhccts8400wg0w-nzlynne@webmail.spamcop.net \
--to=amylaar@spamcop.net \
--cc=binutils@sourceware.org \
--cc=gcc@gcc.gnu.org \
--cc=hjl.tools@gmail.com \
--cc=law@redhat.com \
--cc=quentin.neill.gnu@gmail.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).