linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Jimi Xenidis <jimix@pobox.com>
To: Anton Blanchard <anton@samba.org>
Cc: Kumar Gala <kumar.gala@gmail.com>,
	paulus@samba.org, linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH] powerpc: POWER7 optimised memcpy using VMX and enhanced prefetch
Date: Tue, 18 Dec 2012 07:21:16 -0600	[thread overview]
Message-ID: <BD2B3ACC-39AD-4084-8E62-72A543EA3811@pobox.com> (raw)
In-Reply-To: <20121217223333.6cb00476@kryten>


On Dec 17, 2012, at 5:33 AM, Anton Blanchard <anton@samba.org> wrote:

>=20
> Hi Jimi,
>=20
>> I know this is a little late, but shouldn't these power7 specific
>> thingies be in "obj-$(CONFIG_PPC_BOOK3S_64)". The reason I ask is
>> that my compiler pukes on "dcbtst" and as I deal with that I wanted
>> to point this out.
>=20
> I guess we could do that.

I think it is the right idea since it is unclear that your optimizations =
would actually help an embedded system where most of these cache =
prefetches are NOPs and only wait decode/dispatch cycles.

> It's a bit strange your assembler is
> complaining about the dcbtst instructions since we wrap them with
> power4:

Not really, the binutils is a little old (RHEL 6.2), unfortunately it =
_is_ the toolchain most people are using at the moment.
It will take me a while to get everyone using newer ones since most are =
scientists using the packages they get.

My suggestion was really for correctness,  My current patches for BG/Q =
introduce a macro replacement.
-jx


>=20
> .machine push
> .machine "power4"
>        dcbt    r0,r4,0b01000
>        dcbt    r0,r7,0b01010
>        dcbtst  r0,r9,0b01000
>        dcbtst  r0,r10,0b01010
>        eieio
>        dcbt    r0,r8,0b01010   /* GO */
> .machine pop
>=20
> Anton

      parent reply	other threads:[~2012-12-18 13:21 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-05-31  6:22 [PATCH] powerpc: POWER7 optimised memcpy using VMX and enhanced prefetch Anton Blanchard
2012-12-07 23:20 ` Jimi Xenidis
2012-12-17 11:33   ` Anton Blanchard
2012-12-18  0:26     ` Peter Bergner
2012-12-18 13:28       ` Jimi Xenidis
2012-12-18 14:14         ` David Laight
2012-12-18 16:31         ` Peter Bergner
2013-01-09 22:19           ` Jimi Xenidis
2013-01-09 23:06             ` Peter Bergner
2012-12-18 13:21     ` Jimi Xenidis [this message]

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=BD2B3ACC-39AD-4084-8E62-72A543EA3811@pobox.com \
    --to=jimix@pobox.com \
    --cc=anton@samba.org \
    --cc=kumar.gala@gmail.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=paulus@samba.org \
    /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 NNTP newsgroup(s).