-----Original Message-----
> Date: Tue, 30 Jan 2018 16:07:08 -0800
> From: Yongseok Koh <ys...@mellanox.com>
> To: jerin.ja...@caviumnetworks.com, jianbo....@arm.com
> CC: dev@dpdk.org, Yongseok Koh <ys...@mellanox.com>, sta...@dpdk.org
> Subject: [PATCH] eal/arm64: fix instrinsic for ARM64 NEON with GCC < 4.9
> X-Mailer: git-send-email 2.11.0
>
> vceqzq_u32() is being used by mlx5 PMD but added since gcc 4.9.
>
> Fixes: 570acdb1da8a ("net/mlx5: add vectorized Rx/Tx burst for ARM")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Yongseok Koh <ys...@mellanox.com>
Acked-by: Jerin Jacob <jerin.ja...@caviumnetworks.com>
> ---
> lib/librte_eal/common/include/arch/arm/rte_vect.h | 6 ++++++
> 1 file changed, 6 insertions(+)
>
> diff --git a/lib/librte_eal/common/include/arch/arm/rte_vect.h
> b/lib/librte_eal/common/include/arch/arm/rte_vect.h
> index 5cc34190f..2a18a6854 100644
> --- a/lib/librte_eal/common/include/arch/arm/rte_vect.h
> +++ b/lib/librte_eal/common/include/arch/arm/rte_vect.h
> @@ -78,6 +78,12 @@ vcopyq_laneq_u32(uint32x4_t a, const int lane_a,
> typedef uint64_t poly64_t;
> typedef uint64x2_t poly64x2_t;
> typedef uint8_t poly128_t __attribute__((vector_size(16), aligned(16)));
> +
> +static inline uint32x4_t
> +vceqzq_u32(uint32x4_t a)
> +{
> + return (a == 0);
> +}
> #endif
>
> /* NEON intrinsic vreinterpretq_u64_p128() is supported since GCC version 7
> */
> --
> 2.11.0
>
