All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jerin Jacob <jerin.jacob@caviumnetworks.com>
To: Thomas Monjalon <thomas@monjalon.net>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
	"yskoh@mellanox.com" <yskoh@mellanox.com>,
	"shahafs@mellanox.com" <shahafs@mellanox.com>,
	"ferruh.yigit@intel.com" <ferruh.yigit@intel.com>,
	"bruce.richardson@intel.com" <bruce.richardson@intel.com>,
	"konstantin.ananyev@intel.com" <konstantin.ananyev@intel.com>,
	"christian.ehrhardt@canonical.com"
	<christian.ehrhardt@canonical.com>,
	"justin.parus@microsoft.com" <justin.parus@microsoft.com>
Subject: Re: [PATCH] net/mlx5: restrict workaround of gcc AVX512F bug
Date: Tue, 13 Nov 2018 05:12:23 +0000	[thread overview]
Message-ID: <20181113051210.GA18506@jerin> (raw)
In-Reply-To: <20181113000122.12594-1-thomas@monjalon.net>

-----Original Message-----
> Date: Tue, 13 Nov 2018 01:01:22 +0100
> From: Thomas Monjalon <thomas@monjalon.net>
> To: dev@dpdk.org
> Cc: yskoh@mellanox.com, shahafs@mellanox.com, ferruh.yigit@intel.com,
>  bruce.richardson@intel.com, konstantin.ananyev@intel.com,
>  christian.ehrhardt@canonical.com, justin.parus@microsoft.com
> Subject: [dpdk-dev] [PATCH] net/mlx5: restrict workaround of gcc AVX512F bug
> X-Mailer: git-send-email 2.19.0
> 
> +/*
> + * GCC bug workaround for rte_memcpy broken when optimized for AVX512.
> + * Details are in https://bugs.dpdk.org/show_bug.cgi?id=97
> + * AVX512F is disabled for affected functions (calling mlx5_tx_complete).
> + */
> +#if defined(__clang__) || defined(__INTEL_COMPILER)

Probably you need to add check here for non x86 as no-avx512f valid only
for x86.

➜ [ctest] $ cat target.c 
void __attribute__((target("no-avx512f"))) test_fn(void)
{

}

int main(void)
{
	test_fn();
}

➜ [ctest] $ aarch64-linux-gnu-gcc -Wall target.c 
target.c:5:1: error: pragma or attribute 'target("no-avx512f")' is not
valid
 {
 ^
➜ [ctest] $ gcc -Wall target.c 
➜ [ctest] $ 


> +#define MLX5_WORKAROUND_GCC_BUG_AVX512F
> +#else
> +#define MLX5_WORKAROUND_GCC_BUG_AVX512F __attribute__((target("no-avx512f")))
> +#endif
> +

      parent reply	other threads:[~2018-11-13  5:12 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-13  0:01 [PATCH] net/mlx5: restrict workaround of gcc AVX512F bug Thomas Monjalon
2018-11-13  0:14 ` Stephen Hemminger
2018-11-13  0:30   ` Thomas Monjalon
2018-11-13  5:12 ` Jerin Jacob [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=20181113051210.GA18506@jerin \
    --to=jerin.jacob@caviumnetworks.com \
    --cc=bruce.richardson@intel.com \
    --cc=christian.ehrhardt@canonical.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=justin.parus@microsoft.com \
    --cc=konstantin.ananyev@intel.com \
    --cc=shahafs@mellanox.com \
    --cc=thomas@monjalon.net \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.