Re: [dpdk-dev] [PATCH] net/mlx5: add vectorized Rx

[Thomas Monjalon <thomas@monjalon.net>]

28/05/2017 17:40, Yongseok Koh:
> Vectorized Rx API for x86 is added.
> 
> Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
> ---
>  drivers/net/mlx5/Makefile      |   1 +
>  drivers/net/mlx5/mlx5_defs.h   |   6 +
>  drivers/net/mlx5/mlx5_ethdev.c |   8 +
>  drivers/net/mlx5/mlx5_rxq.c    |  39 +++-
>  drivers/net/mlx5/mlx5_rxtx.c   | 485 +++++++++++++++++++++++++++++++++++++++++
>  drivers/net/mlx5/mlx5_rxtx.h   |  10 +
>  6 files changed, 548 insertions(+), 1 deletion(-)

It would be probably clearer to have a specific file for
Rx/Tx on SSE. So it would be compiled only for x86.

> --- a/drivers/net/mlx5/Makefile
> +++ b/drivers/net/mlx5/Makefile
> @@ -60,6 +60,7 @@ CFLAGS += -D_DEFAULT_SOURCE
>  CFLAGS += -D_XOPEN_SOURCE=600
>  CFLAGS += $(WERROR_FLAGS)
>  CFLAGS += -Wno-strict-prototypes
> +CFLAGS += -msse4.1
>  LDLIBS += -libverbs
[...]
> --- a/drivers/net/mlx5/mlx5_ethdev.c
> +++ b/drivers/net/mlx5/mlx5_ethdev.c
> @@ -723,7 +723,11 @@ mlx5_dev_supported_ptypes_get(struct rte_eth_dev *dev)
>  
>         };
>  
> +#ifdef MLX5_VECTORIZED_RX
> +       if (dev->rx_pkt_burst == mlx5_rx_burst_vec)
> +#else
>         if (dev->rx_pkt_burst == mlx5_rx_burst)
> +#endif
>                 return ptypes;
>         return NULL;
>  }

Can we avoid an #ifdef here?
We should check SSE support at runtime with rte_cpu_get_flag_enabled().