Re: [PATCH 20/55] target/arm: Implement MVE VDUP

[Richard Henderson]

On 6/7/21 9:57 AM, Peter Maydell wrote:
> +#define DO_VDUP(OP, ESIZE, TYPE, H)                                     \
> +    void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t val)     \
> +    {                                                                   \
> +        TYPE *d = vd;                                                   \
> +        uint16_t mask = mve_element_mask(env);                          \
> +        unsigned e;                                                     \
> +        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
> +            uint64_t bytemask = mask_to_bytemask##ESIZE(mask);          \
> +            d[H(e)] &= ~bytemask;                                       \
> +            d[H(e)] |= (val & bytemask);                                \
> +        }                                                               \
> +        mve_advance_vpt(env);                                           \
> +    }
> +
> +DO_VDUP(vdupb, 1, uint8_t, H1)
> +DO_VDUP(vduph, 2, uint16_t, H2)
> +DO_VDUP(vdupw, 4, uint32_t, H4)

Hmm.  I think the masking should be done at either uint32_t or uint64_t.  Doing 
it byte-by-byte is wasteful.

Whether you want to do the replication in tcg (I can export gen_dup_i32 from 
tcg-op-gvec.c) and have one helper, or do the replication here e.g.

static void do_vdup(CPUARMState *env, void *vd, uint64_t val);
void helper(mve_vdupb)(CPUARMState *env, void *vd, uint32_t val)
{
    do_vdup(env, vd, dup_const(MO_8, val));
}


r~