Match: Support form 2 for scalar signed integer SAT_TRUNC

This patch would like to support the form 2 of the scalar signed
integer SAT_TRUNC.  Aka below example:

Form 2:
  #define DEF_SAT_S_TRUNC_FMT_2(NT, WT, NT_MIN, NT_MAX) \
  NT __attribute__((noinline))                          \
  sat_s_trunc_##WT##_to_##NT##_fmt_2 (WT x)             \
  {                                                     \
    NT trunc = (NT)x;                                   \
    return (WT)NT_MIN < x && x < (WT)NT_MAX             \
      ? trunc                                           \
      : x < 0 ? NT_MIN : NT_MAX;                        \
  }

DEF_SAT_S_TRUNC_FMT_2(int8_t, int16_t, INT8_MIN, INT8_MAX)

Before this patch:
   4   │ __attribute__((noinline))
   5   │ int8_t sat_s_trunc_int16_t_to_int8_t_fmt_2 (int16_t x)
   6   │ {
   7   │   int8_t trunc;
   8   │   unsigned short x.0_1;
   9   │   unsigned short _2;
  10   │   int8_t _3;
  11   │   _Bool _7;
  12   │   signed char _8;
  13   │   signed char _9;
  14   │   signed char _10;
  15   │
  16   │ ;;   basic block 2, loop depth 0
  17   │ ;;    pred:       ENTRY
  18   │   x.0_1 = (unsigned short) x_4(D);
  19   │   _2 = x.0_1 + 127;
  20   │   if (_2 > 253)
  21   │     goto <bb 4>; [50.00%]
  22   │   else
  23   │     goto <bb 3>; [50.00%]
  24   │ ;;    succ:       4
  25   │ ;;                3
  26   │
  27   │ ;;   basic block 3, loop depth 0
  28   │ ;;    pred:       2
  29   │   trunc_5 = (int8_t) x_4(D);
  30   │   goto <bb 5>; [100.00%]
  31   │ ;;    succ:       5
  32   │
  33   │ ;;   basic block 4, loop depth 0
  34   │ ;;    pred:       2
  35   │   _7 = x_4(D) < 0;
  36   │   _8 = (signed char) _7;
  37   │   _9 = -_8;
  38   │   _10 = _9 ^ 127;
  39   │ ;;    succ:       5
  40   │
  41   │ ;;   basic block 5, loop depth 0
  42   │ ;;    pred:       3
  43   │ ;;                4
  44   │   # _3 = PHI <trunc_5(3), _10(4)>
  45   │   return _3;
  46   │ ;;    succ:       EXIT
  47   │
  48   │ }

After this patch:
   4   │ __attribute__((noinline))
   5   │ int8_t sat_s_trunc_int16_t_to_int8_t_fmt_2 (int16_t x)
   6   │ {
   7   │   int8_t _3;
   8   │
   9   │ ;;   basic block 2, loop depth 0
  10   │ ;;    pred:       ENTRY
  11   │   _3 = .SAT_TRUNC (x_4(D)); [tail call]
  12   │   return _3;
  13   │ ;;    succ:       EXIT
  14   │
  15   │ }

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: Add case 2 matching pattern for signed SAT_TRUNC.

Signed-off-by: Pan Li <pan2.li@intel.com>

1 files changed, 13 insertions, 8 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index 8a7569c..754c1f3 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3461,7 +3461,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   }
   (if (wi::eq_p (trunc_max, int_cst_1) && wi::eq_p (max, int_cst_2))))))
 
-/* Signed saturation truncate, case 1, sizeof (WT) > sizeof (NT).
+/* Signed saturation truncate, case 1 and case 2, sizeof (WT) > sizeof (NT).
    SAT_S_TRUNC(X) = (unsigned)X + NT_MAX + 1  > Unsigned_MAX ? (NT)X.  */
 (match (signed_integer_sat_trunc @0)
  (cond^ (gt (plus:c (convert@4 @0) INTEGER_CST@1) INTEGER_CST@2)
@@ -3471,17 +3471,22 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
       && !TYPE_UNSIGNED (TREE_TYPE (@0)) && TYPE_UNSIGNED (TREE_TYPE (@4)))
  (with
   {
-   unsigned itype_precision = TYPE_PRECISION (TREE_TYPE (@0));
-   unsigned otype_precision = TYPE_PRECISION (type);
-   wide_int offset = wi::uhwi (HOST_WIDE_INT_1U << (otype_precision - 1), itype_precision);
-   wide_int trunc_max = wi::mask (otype_precision, false, itype_precision);
-   wide_int max = wi::mask (otype_precision - 1, false, otype_precision);
+   unsigned itype_prec = TYPE_PRECISION (TREE_TYPE (@0));
+   unsigned otype_prec = TYPE_PRECISION (type);
+   wide_int offset = wi::uhwi (HOST_WIDE_INT_1U << (otype_prec - 1),
+			       itype_prec); // Aka 128 for int8_t
+   wide_int limit_0 = wi::mask (otype_prec, false, itype_prec); // Aka 255
+   wide_int limit_1 = wi::uhwi ((HOST_WIDE_INT_1U << otype_prec) - 3,
+				itype_prec); // Aka 253
+   wide_int otype_max = wi::mask (otype_prec - 1, false, otype_prec);
+   wide_int itype_max = wi::mask (otype_prec - 1, false, itype_prec);
    wide_int int_cst_1 = wi::to_wide (@1);
    wide_int int_cst_2 = wi::to_wide (@2);
    wide_int int_cst_3 = wi::to_wide (@3);
   }
-  (if (wi::eq_p (int_cst_1, offset) && wi::eq_p (int_cst_2, trunc_max)
-       && wi::eq_p (int_cst_3, max))))))
+  (if (((wi::eq_p (int_cst_1, offset) && wi::eq_p (int_cst_2, limit_0))
+	 || (wi::eq_p (int_cst_1, itype_max) && wi::eq_p (int_cst_2, limit_1)))
+       && wi::eq_p (int_cst_3, otype_max))))))
 
 /* x >  y  &&  x != XXX_MIN  -->  x > y
    x >  y  &&  x == XXX_MIN  -->  false . */