DPDK patches and discussions
 help / color / mirror / Atom feed
From: Thomas Monjalon <thomas@monjalon.net>
To: Luca Boccassi <bluca@debian.org>
Cc: dev@dpdk.org, jerinj@marvell.com, bruce.richardson@intel.com,
	Christian Ehrhardt <christian.ehrhardt@canonical.com>,
	Yongseok Koh <yskoh@mellanox.com>
Subject: Re: [dpdk-dev] [PATCH v2] build: mention machine=default and its use in documentation
Date: Wed, 17 Apr 2019 22:17:37 +0200	[thread overview]
Message-ID: <1688708.SlylYsn8Qu@xps> (raw)
In-Reply-To: <20190114134106.17383-1-bluca@debian.org>

14/01/2019 14:41, Luca Boccassi:
> Document the new value, as it's useful for distributions and users
> who need to use a stable baseline -march
> 
> Signed-off-by: Luca Boccassi <bluca@debian.org>
> Reviewed-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
> ---
> +NOTE: machine=default will use the minimum required -march on all architectures
> +regardless of the capabilities of the machine where the build is happening.

This option is not really selecting the minimum but something which works
on every flavours of the CPU architecture.
For instance, on ARM it can select a cacheline of 128B to make it work
with 64B and 128B micro-architectures.

After discussing with Bruce and Luca I was convinced that "default"
is not a good name, and "machine=any" would be better.
The name "default" may also refer, in some contexts, to the config
of the basic/standard CPU design.
Even worst, "default" is not the default machine in DPDK...

Today I am not sure what is the best meaningful name,
and I tend to think that "default" is well understood by everyone.
So I am OK to apply this patch, but please replace
	"minimum required -march"
by
	"config working"
or something similar, thanks.

  parent reply	other threads:[~2019-04-17 20:17 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-14 11:23 [dpdk-dev] [PATCH] " Luca Boccassi
2019-01-14 13:32 ` Christian Ehrhardt
2019-01-14 13:44   ` Luca Boccassi
2019-01-14 13:41 ` [dpdk-dev] [PATCH v2] " Luca Boccassi
2019-02-27 12:16   ` Luca Boccassi
2019-03-18 20:12     ` Jerin Jacob Kollanukkaran
2019-03-18 20:12       ` Jerin Jacob Kollanukkaran
2019-04-17 20:17   ` Thomas Monjalon [this message]
2019-04-17 20:17     ` Thomas Monjalon
2019-04-18  9:30     ` Luca Boccassi
2019-04-18  9:30       ` Luca Boccassi
2019-04-18  9:30 ` [dpdk-dev] [PATCH v3] " luca.boccassi
2019-04-18  9:30   ` luca.boccassi
2019-04-18 14:06   ` Thomas Monjalon
2019-04-18 14:06     ` 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=1688708.SlylYsn8Qu@xps \
    --to=thomas@monjalon.net \
    --cc=bluca@debian.org \
    --cc=bruce.richardson@intel.com \
    --cc=christian.ehrhardt@canonical.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    --cc=yskoh@mellanox.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 NNTP newsgroup(s).