[PATCH 1/2] Add support for IVOPT

[Richard Biener]

On Wed, May 15, 2019 at 4:40 AM <kugan.vivekanandarajah@linaro.org> wrote:
>
> From: Kugan Vivekanandarajah <kugan.vivekanandarajah@linaro.org>
>
> gcc/ChangeLog:
>
> 2019-05-15  Kugan Vivekanandarajah  <kugan.vivekanandarajah@linaro.org>
>
>         PR target/88834
>         * tree-ssa-loop-ivopts.c (get_mem_type_for_internal_fn): Handle
>         IFN_MASK_LOAD_LANES and IFN_MASK_STORE_LANES.
>         (find_interesting_uses_stmt): Likewise.
>         (get_alias_ptr_type_for_ptr_address): Likewise.
>         (add_iv_candidate_for_use): Add scaled index candidate if useful.
>
> Change-Id: I8e8151fe2dde2845dedf38b090103694da6fc9d1
> ---
>  gcc/tree-ssa-loop-ivopts.c | 60 +++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 59 insertions(+), 1 deletion(-)
>
> diff --git a/gcc/tree-ssa-loop-ivopts.c b/gcc/tree-ssa-loop-ivopts.c
> index 9864b59..115a70c 100644
> --- a/gcc/tree-ssa-loop-ivopts.c
> +++ b/gcc/tree-ssa-loop-ivopts.c
> @@ -2451,11 +2451,13 @@ get_mem_type_for_internal_fn (gcall *call, tree *op_p)
>    switch (gimple_call_internal_fn (call))
>      {
>      case IFN_MASK_LOAD:
> +    case IFN_MASK_LOAD_LANES:
>        if (op_p == gimple_call_arg_ptr (call, 0))
>         return TREE_TYPE (gimple_call_lhs (call));
>        return NULL_TREE;
>
>      case IFN_MASK_STORE:
> +    case IFN_MASK_STORE_LANES:
>        if (op_p == gimple_call_arg_ptr (call, 0))
>         return TREE_TYPE (gimple_call_arg (call, 3));
>        return NULL_TREE;
> @@ -2545,7 +2547,7 @@ find_interesting_uses_stmt (struct ivopts_data *data, gimple *stmt)
>           return;
>         }
>
> -      /* TODO -- we should also handle address uses of type
> +      /* TODO -- we should also handle all address uses of type
>
>          memory = call (whatever);
>
> @@ -2553,6 +2555,27 @@ find_interesting_uses_stmt (struct ivopts_data *data, gimple *stmt)
>
>          call (memory).  */
>      }
> +  else if (is_gimple_call (stmt))
> +    {
> +      gcall *call = dyn_cast <gcall *> (stmt);
> +      if (call

that's testing things twice, just do

       else if (gcall *call = dyn_cast <gcall *> (stmt))
         {
...

no other comments besides why do you need _LANES handling here where
the w/o _LANES handling didn't need anything.

> +         && gimple_call_internal_p (call)
> +         && (gimple_call_internal_fn (call) == IFN_MASK_LOAD_LANES
> +             || gimple_call_internal_fn (call) == IFN_MASK_STORE_LANES))
> +       {
> +         tree *arg = gimple_call_arg_ptr (call, 0);
> +         struct iv *civ = get_iv (data, *arg);
> +         tree mem_type = get_mem_type_for_internal_fn (call, arg);
> +         if (civ && mem_type)
> +           {
> +             civ = alloc_iv (data, civ->base, civ->step);
> +             record_group_use (data, arg, civ, stmt, USE_PTR_ADDRESS,
> +                               mem_type);
> +             return;
> +           }
> +       }
> +    }
> +
>
>    if (gimple_code (stmt) == GIMPLE_PHI
>        && gimple_bb (stmt) == data->current_loop->header)
> @@ -3500,6 +3523,39 @@ add_iv_candidate_for_use (struct ivopts_data *data, struct iv_use *use)
>      basetype = sizetype;
>    record_common_cand (data, build_int_cst (basetype, 0), iv->step, use);
>
> +  /* Compare the cost of an address with an unscaled index with the cost of
> +    an address with a scaled index and add candidate if useful. */
> +  if (use != NULL && use->type == USE_PTR_ADDRESS)
> +    {
> +      struct mem_address parts = {NULL_TREE, integer_one_node,
> +                                 NULL_TREE, NULL_TREE, NULL_TREE};
> +      poly_uint64 temp;
> +      poly_int64 fact;
> +      bool speed = optimize_loop_for_speed_p (data->current_loop);
> +      poly_int64 poly_step = tree_to_poly_int64 (iv->step);
> +      machine_mode mem_mode = TYPE_MODE (use->mem_type);
> +      addr_space_t as = TYPE_ADDR_SPACE (TREE_TYPE (use->iv->base));
> +
> +      fact = GET_MODE_SIZE (GET_MODE_INNER (TYPE_MODE (use->mem_type)));
> +      parts.index = integer_one_node;
> +
> +      if (fact.is_constant ()
> +         && can_div_trunc_p (poly_step, fact, &temp))
> +       {
> +         /* Addressing mode "base + index".  */
> +         rtx addr = addr_for_mem_ref (&parts, as, false);
> +         unsigned cost = address_cost (addr, mem_mode, as, speed);
> +         tree step = wide_int_to_tree (sizetype,
> +                                       exact_div (poly_step, fact));
> +         parts.step = wide_int_to_tree (sizetype, fact);
> +         /* Addressing mode "base + index << scale".  */
> +         addr = addr_for_mem_ref (&parts, as, false);
> +         unsigned new_cost = address_cost (addr, mem_mode, as, speed);
> +         if (new_cost < cost)
> +           add_candidate (data, size_int (0), step, true, NULL);
> +       }
> +    }
> +
>    /* Record common candidate with constant offset stripped in base.
>       Like the use itself, we also add candidate directly for it.  */
>    base = strip_offset (iv->base, &offset);
> @@ -7112,6 +7168,8 @@ get_alias_ptr_type_for_ptr_address (iv_use *use)
>      {
>      case IFN_MASK_LOAD:
>      case IFN_MASK_STORE:
> +    case IFN_MASK_LOAD_LANES:
> +    case IFN_MASK_STORE_LANES:
>        /* The second argument contains the correct alias type.  */
>        gcc_assert (use->op_p = gimple_call_arg_ptr (call, 0));
>        return TREE_TYPE (gimple_call_arg (call, 1));
> --
> 2.7.4
>