Buildroot Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
To: buildroot@busybox.net
Subject: [Buildroot] ARM cores
Date: Mon, 24 Jan 2011 18:04:28 +0100	[thread overview]
Message-ID: <20110124180428.3bcbe29f@surf> (raw)
In-Reply-To: <87y66athl7.fsf@macbook.be.48ers.dk>

On Mon, 24 Jan 2011 17:03:00 +0100
Peter Korsgaard <jacmet@uclibc.org> wrote:

> Not available? Doesn't almost all A8 implementations have NEON?

According to http://wiki.debian.org/ArmHardFloatPort, CPUs such as
Marvell Dove and Nvidia Tegra 2 are ARMv7 CPUs, but they don't have
NEON support. NEON is an extension, so it isn't necessarly part of ARM
cores.

> Do we have any packages that cannot work on !NEON arms? (E.G. where it isn't
> just an optimization)

In mplayer, we have:

ifeq ($(call qstrip,$(BR2_GCC_TARGET_ARCH)),armv7-a)
MPLAYER_CONF_OPTS += --enable-neon
endif

(This is code that I added, it's an approximation, since as said above,
not all ARMv7 CPUs have NEON support).

Once mplayer is compiled with --enable-neon, it will presumably not
work on !NEON arms.

Instead of having the list of gazillions ARM SoC, we could also extend
a bit our architecture-specific options:

 * Has NEON support ?
   shown only if > ARMv7 is selected

 * Floating point type (with a choice of soft-float, VFPv2, VFPv3)

 * Floating point ABI (soft, softfp, hard)

But it means that the user needs more knowledge on the details of the
ARM SoC he is using. But it's probably the only realistic solution.

Regards,

Thomas
-- 
Thomas Petazzoni, Free Electrons
Kernel, drivers, real-time and embedded Linux
development, consulting, training and support.
http://free-electrons.com

  reply	other threads:[~2011-01-24 17:04 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-23 22:41 [Buildroot] [PATCH 3rd RESEND 0/6] GStreamer patches, and TI OMAP3 DSP stuff Felipe Contreras
2011-01-23 22:41 ` [Buildroot] [PATCH 3rd RESEND 1/6] gstreamer: remove unnecessary feature Felipe Contreras
2011-01-24  8:42   ` Peter Korsgaard
2011-01-23 22:41 ` [Buildroot] [PATCH 3rd RESEND 2/6] Fix gstreamer packages for make 3.82 Felipe Contreras
2011-01-24  8:39   ` Peter Korsgaard
2011-01-25  2:51     ` Felipe Contreras
2011-01-25  9:01       ` Peter Korsgaard
2011-01-23 22:41 ` [Buildroot] [PATCH 3rd RESEND 3/6] Add tidsp-binaries package Felipe Contreras
2011-01-24  8:53   ` Peter Korsgaard
2011-01-23 22:41 ` [Buildroot] [PATCH 3rd RESEND 4/6] Add gst-dsp package Felipe Contreras
2011-01-24  8:54   ` Peter Korsgaard
2011-01-23 22:41 ` [Buildroot] [PATCH 3rd RESEND 5/6] Add dsp-tools package Felipe Contreras
2011-01-24  8:54   ` Peter Korsgaard
2011-01-23 22:41 ` [Buildroot] [PATCH 3rd RESEND 6/6] Add gst-omapfb package Felipe Contreras
2011-01-24  8:58   ` Peter Korsgaard
2011-01-24 15:57     ` [Buildroot] ARM cores Thomas Petazzoni
2011-01-24 16:03       ` Peter Korsgaard
2011-01-24 17:04         ` Thomas Petazzoni [this message]
2011-01-24 20:06           ` Peter Korsgaard
2011-01-24 16:08       ` Eric BENARD
2011-01-24 17:08         ` Thomas Petazzoni
2011-01-25  2:55     ` [Buildroot] [PATCH 3rd RESEND 6/6] Add gst-omapfb package Felipe Contreras
2011-01-25  9:02       ` Peter Korsgaard

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=20110124180428.3bcbe29f@surf \
    --to=thomas.petazzoni@free-electrons.com \
    --cc=buildroot@busybox.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