From: Dan Malek <dan@embeddededge.com>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Joakim Tjernlund <Joakim.Tjernlund@lumentis.se>,
linuxppc-dev@lists.linuxppc.org, drow@false.org
Subject: Re: Improved copy_page() function, about 30% speed up for mpc860!
Date: Mon, 03 Mar 2003 19:51:42 -0500 [thread overview]
Message-ID: <3E63F89E.9030408@embeddededge.com> (raw)
In-Reply-To: 1046737789.885.15.camel@zion.wanadoo.fr
Benjamin Herrenschmidt wrote:
> If you know precisely what version of the chip has this bug fixed,
> then you can define a CPU feature bit, and enclose the dcbz in
> a CPU feature conditional section. That way, they will get nop'ed
> out on faulty CPUs.
The problem is we don't know because it was never a documented
problem. It was very difficult to find, so I'm not surprised it
didn't always show up on the silicon errata. Further, there may
not be enough information in the cpu identification registers to
determine this level of silicon revision.
We just can't nop the dcbz, we have to add explicit instructions
to perform the function if dcbz or other cache instructions don't
work properly. It's also in an area where we have to be sensitive
to cache utilization. We could end up with a situation where there
are lots of nops (using cpu features) or branches where reloading
the i-cache could kill all of the optimization we gained by making
the d-cache more efficient.
Thanks.
-- Dan
** Sent via the linuxppc-dev mail list. See http://lists.linuxppc.org/
next prev parent reply other threads:[~2003-03-04 0:51 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-03-02 17:50 Improved copy_page() function, about 30% speed up for mpc860! Joakim Tjernlund
2003-03-03 21:18 ` Dan Malek
2003-03-03 23:16 ` Joakim Tjernlund
2003-03-04 0:43 ` Dan Malek
2003-03-04 0:54 ` Daniel Jacobowitz
2003-03-04 3:38 ` Dan Malek
2003-03-04 8:29 ` Joakim Tjernlund
2003-03-04 13:33 ` Dan Malek
2003-03-04 15:24 ` Joakim Tjernlund
2003-03-04 17:00 ` Dan Malek
2003-03-04 22:01 ` Joakim Tjernlund
2003-03-04 22:41 ` Dan Malek
2003-03-04 23:20 ` Joakim Tjernlund
2003-03-04 23:35 ` Tom Rini
2003-03-04 23:45 ` Joakim Tjernlund
2003-03-05 0:05 ` Tom Rini
2003-03-05 0:19 ` Joakim Tjernlund
2003-03-05 17:12 ` Tom Rini
2003-03-05 17:50 ` Joakim Tjernlund
2003-03-05 17:15 ` Dan Malek
[not found] ` <1046737789.885.15.camel@zion.wanadoo.fr>
2003-03-04 0:51 ` Dan Malek [this message]
-- strict thread matches above, loose matches on Subject: below --
2003-02-27 13:08 Joakim Tjernlund
2003-02-27 15:45 ` Joakim Tjernlund
2003-02-28 17:31 ` Joakim Tjernlund
2003-03-03 21:28 ` Dan Malek
2003-03-04 0:09 ` Joakim Tjernlund
2003-03-04 0:19 ` Paul Mackerras
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=3E63F89E.9030408@embeddededge.com \
--to=dan@embeddededge.com \
--cc=Joakim.Tjernlund@lumentis.se \
--cc=benh@kernel.crashing.org \
--cc=drow@false.org \
--cc=linuxppc-dev@lists.linuxppc.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).