On Thu, Nov 21, 2024 at 3:09 AM Li, Pan2 <pan2...@intel.com> wrote:
>
> Almost forgot this patch, kindly reminder.
OK.
Richard.
> Pan
>
> -----Original Message-----
> From: Li, Pan2 <pan2...@intel.com>
> Sent: Monday, November 11, 2024 4:44 PM
> To: gcc-patches@gcc.gnu.org
> Cc: richard.guent...@gmail.com; tamar.christ...@arm.com;
> juzhe.zh...@rivai.ai; kito.ch...@gmail.com; jeffreya...@gmail.com;
> rdapp....@gmail.com; Li, Pan2 <pan2...@intel.com>
> Subject: [PATCH v1 2/2] Match: Refactor the unsigned SAT_ADD match pattern
> [NFC]
>
> From: Pan Li <pan2...@intel.com>
>
> This patch would like to refactor the unsigned SAT_ADD pattern by:
> * Extract type check outside.
> * Extract common sub pattern.
> * Re-arrange the related match pattern forms together.
> * Remove unnecessary helper pattern matches.
>
> The below test suites are passed for this patch.
> * The rv64gcv fully regression test.
> * The x86 bootstrap test.
> * The x86 fully regression test.
>
> gcc/ChangeLog:
>
> * match.pd: Refactor sorts of unsigned SAT_ADD match pattern.
>
> Signed-off-by: Pan Li <pan2...@intel.com>
> ---
> gcc/match.pd | 109 +++++++++++++++++++++------------------------------
> 1 file changed, 45 insertions(+), 64 deletions(-)
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index af3272eac55..30000a76757 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -3086,14 +3086,6 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> || POINTER_TYPE_P (itype))
> && wi::eq_p (wi::to_wide (int_cst), wi::max_value (itype))))))
>
> -/* Unsigned Saturation Add */
> -/* SAT_ADD = usadd_left_part_1 | usadd_right_part_1, aka:
> - SAT_ADD = (X + Y) | -((X + Y) < X) */
> -(match (usadd_left_part_1 @0 @1)
> - (plus:c @0 @1)
> - (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> - && types_match (type, @0, @1))))
> -
> /* SAT_ADD = usadd_left_part_2 | usadd_right_part_2, aka:
> SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | (IMAGPART_EXPR <.ADD_OVERFLOW>
> != 0) */
> (match (usadd_left_part_2 @0 @1)
> @@ -3101,20 +3093,6 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> && types_match (type, @0, @1))))
>
> -/* SAT_ADD = usadd_left_part_1 | usadd_right_part_1, aka:
> - SAT_ADD = (X + Y) | -((type)(X + Y) < X) */
> -(match (usadd_right_part_1 @0 @1)
> - (negate (convert (lt (plus:c @0 @1) @0)))
> - (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> - && types_match (type, @0, @1))))
> -
> -/* SAT_ADD = usadd_left_part_1 | usadd_right_part_1, aka:
> - SAT_ADD = (X + Y) | -(X > (X + Y)) */
> -(match (usadd_right_part_1 @0 @1)
> - (negate (convert (gt @0 (plus:c @0 @1))))
> - (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> - && types_match (type, @0, @1))))
> -
> /* SAT_ADD = usadd_left_part_2 | usadd_right_part_2, aka:
> SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | (IMAGPART_EXPR <.ADD_OVERFLOW>
> != 0) */
> (match (usadd_right_part_2 @0 @1)
> @@ -3129,33 +3107,62 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> && types_match (type, @0, @1))))
>
> +(if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type))
> + (match (usadd_overflow_mask @0 @1)
> + /* SAT_U_ADD = (X + Y) | -(X > (X + Y)).
> + Overflow_Mask = -(X > (X + Y)). */
> + (negate (convert (gt @0 (plus:c @0 @1))))
> + (if (types_match (type, @0, @1))))
> + (match (usadd_overflow_mask @0 @1)
> + /* SAT_U_ADD = (X + Y) | -(X > (X + Y)).
> + Overflow_Mask = -((X + Y) < X). */
> + (negate (convert (lt (plus:c @0 @1) @0)))
> + (if (types_match (type, @0, @1))))
> + (match (unsigned_integer_sat_add @0 @1)
> + /* SAT_U_ADD = (X + Y) | Overflow_Mask */
> + (bit_ior:c (plus:c @0 @1) (usadd_overflow_mask @0 @1))
> + (if (types_match (type, @0, @1))))
> + (match (unsigned_integer_sat_add @0 @1)
> + /* SAT_U_ADD = (X + Y) >= X ? (X + Y) : -1 */
> + (cond^ (ge (plus:c@2 @0 @1) @0) @2 integer_minus_onep)
> + (if (types_match (type, @0, @1))))
> + (match (unsigned_integer_sat_add @0 @1)
> + /* SAT_U_ADD = (X + Y) < X ? -1 : (X + Y) */
> + (cond^ (lt (plus:c@2 @0 @1) @0) integer_minus_onep @2)
> + (if (types_match (type, @0, @1))))
> + (match (unsigned_integer_sat_add @0 @1)
> + /* SAT_U_ADD = X <= (X + Y) ? (X + Y) : -1 */
> + (cond^ (le @0 (plus:c@2 @0 @1)) @2 integer_minus_onep)
> + (if (types_match (type, @0, @1))))
> + (match (unsigned_integer_sat_add @0 @1)
> + /* SAT_U_ADD = X > (X + Y) ? -1 : (X + Y) */
> + (cond^ (gt @0 (plus:c@2 @0 @1)) integer_minus_onep @2)
> + (if (types_match (type, @0, @1))))
> + (match (unsigned_integer_sat_add @0 @1)
> + /* SAT_U_ADD = (X + IMM) >= x ? (X + IMM) : -1 */
> + (plus (min @0 INTEGER_CST@2) INTEGER_CST@1)
> + (if (types_match (type, @0, @1))
> + (with
> + {
> + unsigned precision = TYPE_PRECISION (type);
> + wide_int cst_1 = wi::to_wide (@1);
> + wide_int cst_2 = wi::to_wide (@2);
> + wide_int max = wi::mask (precision, false, precision);
> + wide_int sum = wi::add (cst_1, cst_2);
> + }
> + (if (wi::eq_p (max, sum)))))))
> +
> /* We cannot merge or overload usadd_left_part_1 and usadd_left_part_2
> because the sub part of left_part_2 cannot work with right_part_1.
> For example, left_part_2 pattern focus one .ADD_OVERFLOW but the
> right_part_1 has nothing to do with .ADD_OVERFLOW. */
>
> -/* Unsigned saturation add, case 1 (branchless):
> - SAT_U_ADD = (X + Y) | - ((X + Y) < X) or
> - SAT_U_ADD = (X + Y) | - (X > (X + Y)). */
> -(match (unsigned_integer_sat_add @0 @1)
> - (bit_ior:c (usadd_left_part_1 @0 @1) (usadd_right_part_1 @0 @1)))
> -
> /* Unsigned saturation add, case 2 (branchless with .ADD_OVERFLOW):
> SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | -IMAGPART_EXPR <.ADD_OVERFLOW>
> or
> SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | (IMAGPART_EXPR <.ADD_OVERFLOW>
> != 0) */
> (match (unsigned_integer_sat_add @0 @1)
> (bit_ior:c (usadd_left_part_2 @0 @1) (usadd_right_part_2 @0 @1)))
>
> -/* Unsigned saturation add, case 3 (branch with ge):
> - SAT_U_ADD = (X + Y) >= x ? (X + Y) : -1. */
> -(match (unsigned_integer_sat_add @0 @1)
> - (cond^ (ge (usadd_left_part_1@2 @0 @1) @0) @2 integer_minus_onep))
> -
> -/* Unsigned saturation add, case 4 (branch with lt):
> - SAT_U_ADD = (X + Y) < x ? -1 : (X + Y). */
> -(match (unsigned_integer_sat_add @0 @1)
> - (cond^ (lt (usadd_left_part_1@2 @0 @1) @0) integer_minus_onep @2))
> -
> /* Unsigned saturation add, case 5 (branch with eq .ADD_OVERFLOW):
> SAT_U_ADD = REALPART_EXPR <.ADD_OVERFLOW> == 0 ? .ADD_OVERFLOW : -1. */
> (match (unsigned_integer_sat_add @0 @1)
> @@ -3168,32 +3175,6 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (cond^ (ne (imagpart (IFN_ADD_OVERFLOW:c @0 @1)) integer_zerop)
> integer_minus_onep (usadd_left_part_2 @0 @1)))
>
> -/* Unsigned saturation add, case 7 (branch with le):
> - SAT_ADD = x <= (X + Y) ? (X + Y) : -1. */
> -(match (unsigned_integer_sat_add @0 @1)
> - (cond^ (le @0 (usadd_left_part_1@2 @0 @1)) @2 integer_minus_onep))
> -
> -/* Unsigned saturation add, case 8 (branch with gt):
> - SAT_ADD = x > (X + Y) ? -1 : (X + Y). */
> -(match (unsigned_integer_sat_add @0 @1)
> - (cond^ (gt @0 (usadd_left_part_1@2 @0 @1)) integer_minus_onep @2))
> -
> -/* Unsigned saturation add, case 9 (one op is imm):
> - SAT_U_ADD = (X + 3) >= x ? (X + 3) : -1. */
> -(match (unsigned_integer_sat_add @0 @1)
> - (plus (min @0 INTEGER_CST@2) INTEGER_CST@1)
> - (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> - && types_match (type, @0, @1))
> - (with
> - {
> - unsigned precision = TYPE_PRECISION (type);
> - wide_int cst_1 = wi::to_wide (@1);
> - wide_int cst_2 = wi::to_wide (@2);
> - wide_int max = wi::mask (precision, false, precision);
> - wide_int sum = wi::add (cst_1, cst_2);
> - }
> - (if (wi::eq_p (max, sum))))))
> -
> /* Unsigned saturation add, case 10 (one op is imm):
> SAT_U_ADD = __builtin_add_overflow (X, 3, &ret) == 0 ? ret : -1. */
> (match (unsigned_integer_sat_add @0 @1)
> --
> 2.43.0
>
