Re: [PATCH v2] Vect: Support IFN SAT_SUB for unsigned vector int

[Richard Biener <richard.guenther@gmail.com>]

On Thu, Jun 6, 2024 at 8:26 AM <pan2.li@intel.com> wrote:
>
> From: Pan Li <pan2.li@intel.com>
>
> This patch would like to support the .SAT_SUB for the unsigned
> vector int.  Given we have below example code:
>
> void
> vec_sat_sub_u64 (uint64_t *out, uint64_t *x, uint64_t *y, unsigned n)
> {
>   for (unsigned i = 0; i < n; i++)
>     out[i] = (x[i] - y[i]) & (-(uint64_t)(x[i] >= y[i]));
> }
>
> Before this patch:
> void
> vec_sat_sub_u64 (uint64_t *out, uint64_t *x, uint64_t *y, unsigned n)
> {
>   ...
>   _77 = .SELECT_VL (ivtmp_75, POLY_INT_CST [2, 2]);
>   ivtmp_56 = _77 * 8;
>   vect__4.7_59 = .MASK_LEN_LOAD (vectp_x.5_57, 64B, { -1, ... }, _77, 0);
>   vect__6.10_63 = .MASK_LEN_LOAD (vectp_y.8_61, 64B, { -1, ... }, _77, 0);
>
>   mask__7.11_64 = vect__4.7_59 >= vect__6.10_63;
>   _66 = .COND_SUB (mask__7.11_64, vect__4.7_59, vect__6.10_63, { 0, ... });
>
>   .MASK_LEN_STORE (vectp_out.15_71, 64B, { -1, ... }, _77, 0, _66);
>   vectp_x.5_58 = vectp_x.5_57 + ivtmp_56;
>   vectp_y.8_62 = vectp_y.8_61 + ivtmp_56;
>   vectp_out.15_72 = vectp_out.15_71 + ivtmp_56;
>   ivtmp_76 = ivtmp_75 - _77;
>   ...
> }
>
> After this patch:
> void
> vec_sat_sub_u64 (uint64_t *out, uint64_t *x, uint64_t *y, unsigned n)
> {
>   ...
>   _76 = .SELECT_VL (ivtmp_74, POLY_INT_CST [2, 2]);
>   ivtmp_60 = _76 * 8;
>   vect__4.7_63 = .MASK_LEN_LOAD (vectp_x.5_61, 64B, { -1, ... }, _76, 0);
>   vect__6.10_67 = .MASK_LEN_LOAD (vectp_y.8_65, 64B, { -1, ... }, _76, 0);
>
>   vect_patt_37.11_68 = .SAT_SUB (vect__4.7_63, vect__6.10_67);
>
>   .MASK_LEN_STORE (vectp_out.12_70, 64B, { -1, ... }, _76, 0, vect_patt_37.11_68);
>   vectp_x.5_62 = vectp_x.5_61 + ivtmp_60;
>   vectp_y.8_66 = vectp_y.8_65 + ivtmp_60;
>   vectp_out.12_71 = vectp_out.12_70 + ivtmp_60;
>   ivtmp_75 = ivtmp_74 - _76;
>   ...
> }
>
> The below test suites are passed for this patch
> * The x86 bootstrap test.
> * The x86 fully regression test.
> * The riscv fully regression tests.

OK.

Richard.

> gcc/ChangeLog:
>
>         * match.pd: Add new form for vector mode recog.
>         * tree-vect-patterns.cc (gimple_unsigned_integer_sat_sub): Add
>         new match func decl;
>         (vect_recog_build_binary_gimple_call): Extract helper func to
>         build gcall with given internal_fn.
>         (vect_recog_sat_sub_pattern): Add new func impl to recog .SAT_SUB.
>
> Signed-off-by: Pan Li <pan2.li@intel.com>
> ---
>  gcc/match.pd              | 14 +++++++
>  gcc/tree-vect-patterns.cc | 85 ++++++++++++++++++++++++++++++++-------
>  2 files changed, 84 insertions(+), 15 deletions(-)
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 7c1ad428a3c..ebc60eba8dc 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -3110,6 +3110,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
>   (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
>        && types_match (type, @0, @1))))
>
> +/* Unsigned saturation sub, case 3 (branchless with gt):
> +   SAT_U_SUB = (X - Y) * (X > Y).  */
> +(match (unsigned_integer_sat_sub @0 @1)
> + (mult:c (minus @0 @1) (convert (gt @0 @1)))
> + (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> +      && types_match (type, @0, @1))))
> +
> +/* Unsigned saturation sub, case 4 (branchless with ge):
> +   SAT_U_SUB = (X - Y) * (X >= Y).  */
> +(match (unsigned_integer_sat_sub @0 @1)
> + (mult:c (minus @0 @1) (convert (ge @0 @1)))
> + (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> +      && types_match (type, @0, @1))))
> +
>  /* x >  y  &&  x != XXX_MIN  -->  x > y
>     x >  y  &&  x == XXX_MIN  -->  false . */
>  (for eqne (eq ne)
> diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc
> index 81e8fdc9122..cef901808eb 100644
> --- a/gcc/tree-vect-patterns.cc
> +++ b/gcc/tree-vect-patterns.cc
> @@ -4488,6 +4488,32 @@ vect_recog_mult_pattern (vec_info *vinfo,
>  }
>
>  extern bool gimple_unsigned_integer_sat_add (tree, tree*, tree (*)(tree));
> +extern bool gimple_unsigned_integer_sat_sub (tree, tree*, tree (*)(tree));
> +
> +static gcall *
> +vect_recog_build_binary_gimple_call (vec_info *vinfo, gimple *stmt,
> +                                    internal_fn fn, tree *type_out,
> +                                    tree op_0, tree op_1)
> +{
> +  tree itype = TREE_TYPE (op_0);
> +  tree vtype = get_vectype_for_scalar_type (vinfo, itype);
> +
> +  if (vtype != NULL_TREE
> +    && direct_internal_fn_supported_p (fn, vtype, OPTIMIZE_FOR_BOTH))
> +    {
> +      gcall *call = gimple_build_call_internal (fn, 2, op_0, op_1);
> +
> +      gimple_call_set_lhs (call, vect_recog_temp_ssa_var (itype, NULL));
> +      gimple_call_set_nothrow (call, /* nothrow_p */ false);
> +      gimple_set_location (call, gimple_location (stmt));
> +
> +      *type_out = vtype;
> +
> +      return call;
> +    }
> +
> +  return NULL;
> +}
>
>  /*
>   * Try to detect saturation add pattern (SAT_ADD), aka below gimple:
> @@ -4510,27 +4536,55 @@ vect_recog_sat_add_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo,
>    if (!is_gimple_assign (last_stmt))
>      return NULL;
>
> -  tree res_ops[2];
> +  tree ops[2];
>    tree lhs = gimple_assign_lhs (last_stmt);
>
> -  if (gimple_unsigned_integer_sat_add (lhs, res_ops, NULL))
> +  if (gimple_unsigned_integer_sat_add (lhs, ops, NULL))
>      {
> -      tree itype = TREE_TYPE (res_ops[0]);
> -      tree vtype = get_vectype_for_scalar_type (vinfo, itype);
> -
> -      if (vtype != NULL_TREE
> -       && direct_internal_fn_supported_p (IFN_SAT_ADD, vtype,
> -                                          OPTIMIZE_FOR_BOTH))
> +      gcall *call = vect_recog_build_binary_gimple_call (vinfo, last_stmt,
> +                                                        IFN_SAT_ADD, type_out,
> +                                                        ops[0], ops[1]);
> +      if (call)
>         {
> -         *type_out = vtype;
> -         gcall *call = gimple_build_call_internal (IFN_SAT_ADD, 2, res_ops[0],
> -                                                   res_ops[1]);
> +         vect_pattern_detected ("vect_recog_sat_add_pattern", last_stmt);
> +         return call;
> +       }
> +    }
> +
> +  return NULL;
> +}
>
> -         gimple_call_set_lhs (call, vect_recog_temp_ssa_var (itype, NULL));
> -         gimple_call_set_nothrow (call, /* nothrow_p */ false);
> -         gimple_set_location (call, gimple_location (last_stmt));
> +/*
> + * Try to detect saturation sub pattern (SAT_ADD), aka below gimple:
> + *   _7 = _1 >= _2;
> + *   _8 = _1 - _2;
> + *   _10 = (long unsigned int) _7;
> + *   _9 = _8 * _10;
> + *
> + * And then simplied to
> + *   _9 = .SAT_SUB (_1, _2);
> + */
>
> -         vect_pattern_detected ("vect_recog_sat_add_pattern", last_stmt);
> +static gimple *
> +vect_recog_sat_sub_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo,
> +                           tree *type_out)
> +{
> +  gimple *last_stmt = STMT_VINFO_STMT (stmt_vinfo);
> +
> +  if (!is_gimple_assign (last_stmt))
> +    return NULL;
> +
> +  tree ops[2];
> +  tree lhs = gimple_assign_lhs (last_stmt);
> +
> +  if (gimple_unsigned_integer_sat_sub (lhs, ops, NULL))
> +    {
> +      gcall *call = vect_recog_build_binary_gimple_call (vinfo, last_stmt,
> +                                                        IFN_SAT_SUB, type_out,
> +                                                        ops[0], ops[1]);
> +      if (call)
> +       {
> +         vect_pattern_detected ("vect_recog_sat_sub_pattern", last_stmt);
>           return call;
>         }
>      }
> @@ -6999,6 +7053,7 @@ static vect_recog_func vect_vect_recog_func_ptrs[] = {
>    { vect_recog_divmod_pattern, "divmod" },
>    { vect_recog_mult_pattern, "mult" },
>    { vect_recog_sat_add_pattern, "sat_add" },
> +  { vect_recog_sat_sub_pattern, "sat_sub" },
>    { vect_recog_mixed_size_cond_pattern, "mixed_size_cond" },
>    { vect_recog_gcond_pattern, "gcond" },
>    { vect_recog_bool_pattern, "bool" },
> --
> 2.34.1
>