From: "Venkatesan, Venky" <venky.venkatesan@intel.com>
To: Stephen Hemminger <stephen@networkplumber.org>,
jigsaw <jigsaw@gmail.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] Is it possible to have dpdk running with no dependency on a nic ?
Date: Mon, 17 Feb 2014 17:52:20 +0000 [thread overview]
Message-ID: <1FD9B82B8BF2CF418D9A1000154491D973FEEC89@ORSMSX102.amr.corp.intel.com> (raw)
In-Reply-To: <20140217084150.4a2d1f4c@nehalam.linuxnetplumber.net>
If in-lining is that big a concern, you could create your own wrapper function and explicitly mark it no-inline. Personally, I haven't seen any inordinate increase in i-cache miss rates because of in-lining on the applications we have - prefetchers on IA are usually capable of keeping up. However, every application is different enough that there really is no "general" rule here.
-Venky
-----Original Message-----
From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Stephen Hemminger
Sent: Monday, February 17, 2014 8:42 AM
To: jigsaw
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] Is it possible to have dpdk running with no dependency on a nic ?
On Mon, 17 Feb 2014 14:49:47 +0200
jigsaw <jigsaw@gmail.com> wrote:
> Hi Stephen,
>
> Have you tried link time optimization on DPDK application? Does it
> decrease the I-cache miss rate evidently?
>
> thx &
> rgds,
> -Qinglai
>
We use link-time-optimization without any problem.
No big performance gain, but I really don't think all the inlining of big functions is necessary.
prev parent reply other threads:[~2014-02-17 17:51 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-12 18:21 Ymo Lists
2014-02-13 20:19 ` Ymo Lists
2014-02-14 8:42 ` Vivek Soni
2014-02-14 17:20 ` Ymo Lists
2014-02-14 18:20 ` Jayakumar, Muthurajan
2014-02-14 20:11 ` Ymo Lists
2014-02-16 19:02 ` Stephen Hemminger
2014-02-17 12:49 ` jigsaw
2014-02-17 16:41 ` Stephen Hemminger
2014-02-17 17:52 ` Venkatesan, Venky [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=1FD9B82B8BF2CF418D9A1000154491D973FEEC89@ORSMSX102.amr.corp.intel.com \
--to=venky.venkatesan@intel.com \
--cc=dev@dpdk.org \
--cc=jigsaw@gmail.com \
--cc=stephen@networkplumber.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).