DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>
To: Chaeyong Chong <cychong@gmail.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
	Chaeyong Chong <cychong@samsung.com>,
	"stable@dpdk.org" <stable@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] mk: Detect AVX2 capability based on the target CPU architecture
Date: Sun, 22 Jul 2018 09:19:02 +0000	[thread overview]
Message-ID: <2601191342CEEE43887BDE71AB977258DF51920C@irsmsx105.ger.corp.intel.com> (raw)
In-Reply-To: <20180721145342.6503-1-cychong@gmail.com>



> -----Original Message-----
> From: Chaeyong Chong [mailto:cychong@gmail.com]
> Sent: Saturday, July 21, 2018 3:54 PM
> To: Ananyev, Konstantin <konstantin.ananyev@intel.com>
> Cc: dev@dpdk.org; Chaeyong Chong <cychong@samsung.com>; stable@dpdk.org
> Subject: [PATCH] mk: Detect AVX2 capability based on the target CPU architecture
> 
> From: Chaeyong Chong <cychong@samsung.com>
> 
> AVX2 support check should be based on the target CPU architecure.
> For this, -march option should be $(RTE_MACHINE) instead of core-avx2.

I don't really think it should.
The purpose is to build an AVX2 function even for 'default' target.
Then at runtime proper version of the code (SSE/AVX2/etc) could be selected.
So NACK.
Konstantin

> 
> Cc: stable@dpdk.org
> 
> Signed-off-by: Chaeyong Chong <cychong@samsung.com>
> ---
>  lib/librte_acl/Makefile | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/lib/librte_acl/Makefile b/lib/librte_acl/Makefile
> index ea5edf00a..c756eaeb2 100644
> --- a/lib/librte_acl/Makefile
> +++ b/lib/librte_acl/Makefile
> @@ -44,7 +44,7 @@ ifeq ($(findstring RTE_MACHINE_CPUFLAG_AVX2,$(CFLAGS)),RTE_MACHINE_CPUFLAG_AVX2)
>  	CC_AVX2_SUPPORT=1
>  else
>  	CC_AVX2_SUPPORT=\
> -	$(shell $(CC) -march=core-avx2 -dM -E - </dev/null 2>&1 | \
> +	$(shell $(CC) -march=$(RTE_MACHINE) -dM -E - </dev/null 2>&1 | \
>  	grep -q AVX2 && echo 1)
>  	ifeq ($(CC_AVX2_SUPPORT), 1)
>  		ifeq ($(CONFIG_RTE_TOOLCHAIN_ICC),y)
> --
> 2.18.0

           reply	other threads:[~2018-07-22  9:20 UTC|newest]

Thread overview: expand[flat|nested]  mbox.gz  Atom feed
 [parent not found: <20180721145342.6503-1-cychong@gmail.com>]

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=2601191342CEEE43887BDE71AB977258DF51920C@irsmsx105.ger.corp.intel.com \
    --to=konstantin.ananyev@intel.com \
    --cc=cychong@gmail.com \
    --cc=cychong@samsung.com \
    --cc=dev@dpdk.org \
    --cc=stable@dpdk.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).