Re: [dpdk-stable] patch 'mk: disable gcc AVX512F support' has been queued to LTS release 16.11.9

[Christian Ehrhardt <christian.ehrhardt@canonical.com>]

On Thu, Nov 8, 2018 at 7:01 PM Luca Boccassi <bluca@debian.org> wrote:
>
> Hi,
>
> FYI, your patch has been queued to LTS release 16.11.9
>
> Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
> It will be pushed if I get no objections before 11/10/18. So please
> shout if anyone has objections.
>
> Also note that after the patch there's a diff of the upstream commit vs the patch applied
> to the branch. If the code is different (ie: not only metadata diffs), due for example to
> a change in context or macro names, please double check it.
>
> Thanks.
>
> Luca Boccassi

Hi Luca,
please be aware of the still ongoing discussion on this patch, see
full thread around
http://mails.dpdk.org/archives/dev/2018-November/118121.html


> ---
> From 8dbda3ba255c6045ffe3eb73f1d8e1f67186c22b Mon Sep 17 00:00:00 2001
> From: Yongseok Koh <yskoh@mellanox.com>
> Date: Sat, 3 Nov 2018 01:06:32 +0000
> Subject: [PATCH] mk: disable gcc AVX512F support
>
> [ upstream commit 8d07c82b239f7782be0d3afbb626390e2cb0c8f5 ]
>
> This is a workaround to prevent a crash, which might be caused by
> optimization of newer gcc (7.3.0) on Intel Skylake.
>
> This disables AVX512F support of gcc by adding -mno-avx512f if it is
> disabled in DPDK (CONFIG_RTE_ENABLE_AVX512=n).
>
> This does not apply to the meson build as that doesn't have such an option
> but always enable AVX512F whenever supported.
>
> Bugzilla ID: 97
>
> Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
> ---
>  mk/rte.cpuflags.mk | 5 +++++
>  1 file changed, 5 insertions(+)
>
> diff --git a/mk/rte.cpuflags.mk b/mk/rte.cpuflags.mk
> index 8bbccb9ed..c7027a0fe 100644
> --- a/mk/rte.cpuflags.mk
> +++ b/mk/rte.cpuflags.mk
> @@ -91,6 +91,11 @@ endif
>
>  ifneq ($(filter $(AUTO_CPUFLAGS),__AVX512F__),)
>  CPUFLAGS += AVX512F
> +else
> +# disable AVX512F support of gcc as a workaround for Bug 97
> +ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y)
> +MACHINE_CFLAGS += -mno-avx512f
> +endif
>  endif
>
>  # IBM Power CPU flags
> --
> 2.19.1
>
> ---
>   Diff of the applied patch vs upstream commit (please double-check if non-empty:
> ---
> --- -   2018-11-08 17:59:30.124667578 +0000
> +++ 0003-mk-disable-gcc-AVX512F-support.patch   2018-11-08 17:59:30.048751011 +0000
> @@ -1,8 +1,10 @@
> -From 8d07c82b239f7782be0d3afbb626390e2cb0c8f5 Mon Sep 17 00:00:00 2001
> +From 8dbda3ba255c6045ffe3eb73f1d8e1f67186c22b Mon Sep 17 00:00:00 2001
>  From: Yongseok Koh <yskoh@mellanox.com>
>  Date: Sat, 3 Nov 2018 01:06:32 +0000
>  Subject: [PATCH] mk: disable gcc AVX512F support
>
> +[ upstream commit 8d07c82b239f7782be0d3afbb626390e2cb0c8f5 ]
> +
>  This is a workaround to prevent a crash, which might be caused by
>  optimization of newer gcc (7.3.0) on Intel Skylake.
>
> @@ -13,7 +15,6 @@
>  but always enable AVX512F whenever supported.
>
>  Bugzilla ID: 97
> -Cc: stable@dpdk.org
>
>  Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
>  ---
> @@ -21,12 +22,12 @@
>   1 file changed, 5 insertions(+)
>
>  diff --git a/mk/rte.cpuflags.mk b/mk/rte.cpuflags.mk
> -index 43ed84155..c3291b17a 100644
> +index 8bbccb9ed..c7027a0fe 100644
>  --- a/mk/rte.cpuflags.mk
>  +++ b/mk/rte.cpuflags.mk
> -@@ -68,6 +68,11 @@ endif
> +@@ -91,6 +91,11 @@ endif
> +
>   ifneq ($(filter $(AUTO_CPUFLAGS),__AVX512F__),)
> - ifeq ($(CONFIG_RTE_ENABLE_AVX512),y)
>   CPUFLAGS += AVX512F
>  +else
>  +# disable AVX512F support of gcc as a workaround for Bug 97
> @@ -34,8 +35,8 @@
>  +MACHINE_CFLAGS += -mno-avx512f
>  +endif
>   endif
> - endif
>
> + # IBM Power CPU flags
>  --
>  2.19.1
>


-- 
Christian Ehrhardt
Software Engineer, Ubuntu Server
Canonical Ltd