[dpdk-dev] [PATCH 1/6] eal: introduce zmm type for AVX 512-bit

[Jerin Jacob]

On Mon, Mar 9, 2020 at 6:14 PM Vladimir Medvedkin
<vladimir.medvedkin at intel.com> wrote:
>
> New data type to manipulate 512 bit AVX values.
>
> Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin at intel.com>
> ---
>  lib/librte_eal/common/include/arch/x86/rte_vect.h | 20 ++++++++++++++++++++
>  1 file changed, 20 insertions(+)
>
> diff --git a/lib/librte_eal/common/include/arch/x86/rte_vect.h b/lib/librte_eal/common/include/arch/x86/rte_vect.h
> index df5a607..09f30e6 100644
> --- a/lib/librte_eal/common/include/arch/x86/rte_vect.h
> +++ b/lib/librte_eal/common/include/arch/x86/rte_vect.h
> @@ -90,6 +90,26 @@ __extension__ ({                 \
>  })
>  #endif /* (defined(__ICC) && __ICC < 1210) */
>
> +#ifdef __AVX512F__
> +
> +typedef __m512i zmm_t;
> +
> +#define        ZMM_SIZE        (sizeof(zmm_t))
> +#define        ZMM_MASK        (ZMM_SIZE - 1)
> +
> +typedef union rte_zmm {
> +       zmm_t    z;
> +       ymm_t    y[ZMM_SIZE / sizeof(ymm_t)];
> +       xmm_t    x[ZMM_SIZE / sizeof(xmm_t)];
> +       uint8_t  u8[ZMM_SIZE / sizeof(uint8_t)];
> +       uint16_t u16[ZMM_SIZE / sizeof(uint16_t)];
> +       uint32_t u32[ZMM_SIZE / sizeof(uint32_t)];
> +       uint64_t u64[ZMM_SIZE / sizeof(uint64_t)];
> +       double   pd[ZMM_SIZE / sizeof(double)];

Are we missing __attribute__((aligned(64))) here?

> +} rte_zmm_t;

IMO, Due to legacy reason, we have selected  rte_xmm_t, rte_ymm_t for
128 and 256 operations in public APIs[1]

# Not sure where xmm_t and ymm_t and new zmm_t come from? Is this name
x86 arch-specific? If so,
why not give the more generic name rte_512i_t or something?
# Currently, In every arch file, we are repeating the definition for
rte_xmm_t, Why not make, this generic definition
in common file. ie.  rte_zmm_t or rte_512i_t definition in common
file(./lib/librte_eal/common/include/generic/rte_vect.h)
# Currently ./lib/librte_eal/common/include/generic/rte_vect.h has
defintion for rte_vXsY_t for vector representation, would that
be enough for public API? Do we need to new type?


[1]
rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4],
uint32_t defv)


> +
> +#endif /* __AVX512F__ */
> +
>  #ifdef __cplusplus
>  }
>  #endif
> --
> 2.7.4
>