From: Michael Matz <matz@suse.de>
To: Jeff Law <jlaw@tachyum.com>
Cc: GCC Patches <gcc-patches@gcc.gnu.org>
Subject: Re: Aligning stack offsets for spills
Date: Tue, 8 Jun 2021 14:08:03 +0000 (UTC) [thread overview]
Message-ID: <alpine.LSU.2.22.394.2106081402410.3803@wotan.suse.de> (raw)
In-Reply-To: <98179c8e-bcec-83ed-5b99-6f54791bd7cd@tachyum.com>
Hello,
On Mon, 7 Jun 2021, Jeff Law wrote:
>
> So, as many of you know I left Red Hat a while ago and joined Tachyum. We're
> building a new processor and we've come across an issue where I think we need
> upstream discussion.
>
> I can't divulge many of the details right now, but one of the quirks of our
> architecture is that reg+d addressing modes for our vector loads/stores
> require the displacement to be aligned. This is an artifact of how these
> instructions are encoded.
>
> Obviously we can emit a load of the address into a register when the
> displacement isn't aligned. From a correctness point that works perfectly.
> Unfortunately, it's a significant performance hit on some standard benchmarks
> (spec) where we have a great number of spills of vector objects into the stack
> at unaligned offsets in the hot parts of the code.
>
>
> We've considered 3 possible approaches to solve this problem.
>
> 1. When the displacement isn't properly aligned, allocate more space in
> assign_stack_local so that we can make the offset aligned. The downside is
> this potentially burns a lot of stack space, but in practice the cost was
> minimal (16 bytes in a 9k frame) From a performance standpoint this works
> perfectly.
>
> 2. Abuse the register elimination code to create a second pointer into the
> stack. Spills would start as <virtual> + offset, then either get eliminated
> to sp+offset' when the offset is aligned or gpr+offset'' when the offset
> wasn't properly aligned. We started a bit down this path, but with #1 working
> so well, we didn't get this approach to proof-of-concept.
>
> 3. Hack up the post-reload optimizers to fix things up as best as we can.
> This may still be advantageous, but again with #1 working so well, we didn't
> explore this in any significant way. We may still look at this at some point
> in other contexts.
>
> Here's what we're playing with. Obviously we'd need a target hook to
> drive this behavior. I was thinking that we'd pass in any slot offset
> alignment requirements (from the target hook) to assign_stack_local and
> that would bubble down to this point in try_fit_stack_local:
Why is the machinery involving STACK_SLOT_ALIGNMENT and
spill_slot_alignment() (for spilling) or get_stack_local_alignment() (for
backing stack slots) not working for you? If everything is setup
correctly the input alignment to try_fit_stack_local ought to be correct
already.
Ciao,
Michael.
next prev parent reply other threads:[~2021-06-08 14:08 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-07 19:00 Jeff Law
2021-06-08 6:56 ` Richard Biener
2021-06-08 15:00 ` Jeff Law
2021-06-08 14:08 ` Michael Matz [this message]
2021-06-08 14:47 ` Jeff Law
2021-06-08 14:55 ` Jakub Jelinek
2021-06-08 15:06 ` H.J. Lu
2021-06-08 15:18 ` Jeff Law
2021-06-08 15:56 ` Michael Matz
2021-06-10 22:49 ` Jeff Law
2021-06-10 19:28 ` Peter Bergner
2021-06-10 21:34 ` Segher Boessenkool
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=alpine.LSU.2.22.394.2106081402410.3803@wotan.suse.de \
--to=matz@suse.de \
--cc=gcc-patches@gcc.gnu.org \
--cc=jlaw@tachyum.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).