DPDK patches and discussions
 help / color / mirror / Atom feed
From: Ruifeng Wang <Ruifeng.Wang@arm.com>
To: "thomas@monjalon.net" <thomas@monjalon.net>,
	"Juraj Linkeš" <juraj.linkes@pantheon.tech>
Cc: "bruce.richardson@intel.com" <bruce.richardson@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"jerinj@marvell.com" <jerinj@marvell.com>,
	Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>,
	nd <nd@arm.com>, nd <nd@arm.com>
Subject: Re: [dpdk-dev] [PATCH] build: add -moutline-atomics to default Arm build
Date: Fri, 9 Oct 2020 07:07:32 +0000	[thread overview]
Message-ID: <VI1PR0802MB2351BC7967F36E1607A45DDF9E080@VI1PR0802MB2351.eurprd08.prod.outlook.com> (raw)
In-Reply-To: <1936141.z0H9v2j6Xj@thomas>


> -----Original Message-----
> From: Thomas Monjalon <thomas@monjalon.net>
> Sent: Friday, October 9, 2020 2:53 PM
> To: Juraj Linkeš <juraj.linkes@pantheon.tech>; Ruifeng Wang
> <Ruifeng.Wang@arm.com>
> Cc: bruce.richardson@intel.com; dev@dpdk.org; jerinj@marvell.com;
> Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>; nd <nd@arm.com>
> Subject: Re: [dpdk-dev] [PATCH] build: add -moutline-atomics to default Arm
> build
> 
> 09/10/2020 07:29, Ruifeng Wang:
> > From: Thomas Monjalon <thomas@monjalon.net>
> > > 01/10/2020 08:19, Juraj Linkeš:
> > > > -moutline-atomics allows LSE instructions to be used if available
> > > > when compiling for ARMv8.0 instruction set. It's enabled by
> > > > default on newer compilers, such as gcc-10.1. Enable the option so
> > > > that earlier compiler versions that support it but don't enable it by
> default build with it.
> > > >
> > > > Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
> > > > ---
> > > >  machine_args_generic = [
> > > > -	['default', ['-march=armv8-a+crc']],
> > > > +	['default', ['-march=armv8-a+crc', '-moutline-atomics']],
> > > >  	['native', ['-march=native']],
> > > >  	['0xd03', ['-mcpu=cortex-a53']],
> > > >  	['0xd04', ['-mcpu=cortex-a35']],
> > >
> > > Why is it added only to the target "default"?
> > >
> > Because 'default' target generates Armv8.0 instruction set which doesn't
> include LSE extension.
> > The flag enables LSE instructions when code runs on platforms that
> implements LSE extension.
> >
> > For other targets, machine specific 'mcpu' or 'march' flags are used. LSE
> extension availability can be inferred from the given flags.
> > So there is not need to add '-moutline-atomics' to them.
> 
> OK
> It's not obvious that the -mcpu flags implicitly include it.
> What do you think adding such explanation in a v2?
> 
Agree. Better to add explanation that this flag benefits distribution build which uses Armv8.0-a as baseline.
More information refer to: https://community.arm.com/developer/tools-software/tools/b/tools-software-ides-blog/posts/making-the-most-of-the-arm-architecture-in-gcc-10


  reply	other threads:[~2020-10-09  7:07 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-01  6:19 Juraj Linkeš
2020-10-06 20:14 ` Thomas Monjalon
2020-10-09  5:29   ` Ruifeng Wang
2020-10-09  6:52     ` Thomas Monjalon
2020-10-09  7:07       ` Ruifeng Wang [this message]
2020-10-09  9:50 ` [dpdk-dev] [PATCH v2] " Juraj Linkeš
2020-10-13 13:16   ` Thomas Monjalon

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=VI1PR0802MB2351BC7967F36E1607A45DDF9E080@VI1PR0802MB2351.eurprd08.prod.outlook.com \
    --to=ruifeng.wang@arm.com \
    --cc=Honnappa.Nagarahalli@arm.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    --cc=juraj.linkes@pantheon.tech \
    --cc=nd@arm.com \
    --cc=thomas@monjalon.net \
    /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).