[dpdk-dev] [PATCH] mk: disable SCHED_VECTOR in the default config

Christian Ehrhardt christian.ehrhardt at canonical.com
Thu Dec 3 08:46:41 CET 2015


Hi Thomas,
no it is not fixed by that commit.
Even with it applied the remaining include subsequently at
rte_vect.h:67 pulls in x86intrin.h which still ends up including
smmintrin.h.
Long story short is that the mentioned issues like the following still occur:

/usr/lib/gcc/x86_64-linux-gnu/5/include/smmintrin.h:67:1: error:
inlining failed in call to always_inline ‘_mm_testz_si128’: target
specific option mismatch
 _mm_testz_si128 (__m128i __M, __m128i __V)

So I'd ask to still disable CONFIG_RTE_SCHED_VECTOR in the default
config via my patch.
Kind Regards,
Christian

On Wed, Dec 2, 2015 at 11:14 PM, Thomas Monjalon
<thomas.monjalon at 6wind.com> wrote:
> Hi,
>
> 2015-12-01 16:13, Christian Ehrhardt:
>> As it causes issues when building with RTE_MACHINE=default due to SSE4.x
>> requirements and in other discussions was so far rated "lightly tested and
>> doesn't provide really significant performance improvement" let us disable
>> that in the default config.
>> (=> http://dpdk.org/ml/archives/dev/2015-November/029067.html)
>
> Is your issue fixed with the following patch?
> http://dpdk.org/browse/dpdk/commit/?id=1985903e4454
>


More information about the dev mailing list