From: Pan Li <pan2...@intel.com>

This patch would like to support the form 4 of the scalar signed
integer SAT_TRUNC.  Aka below example:

Form 4:
  #define DEF_SAT_S_TRUNC_FMT_4(NT, WT, NT_MIN, NT_MAX) \
  NT __attribute__((noinline))                          \
  sat_s_trunc_##WT##_to_##NT##_fmt_4 (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_4(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_4 (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 + 128;
  20   │   if (_2 > 254)
  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_4 (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 4 matching pattern for signed SAT_TRUNC.

Signed-off-by: Pan Li <pan2...@intel.com>
---
 gcc/match.pd | 1 +
 1 file changed, 1 insertion(+)

diff --git a/gcc/match.pd b/gcc/match.pd
index 5e20651c8ce..6bd515fdd87 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3488,6 +3488,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   }
   (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_2))
+        || (wi::eq_p (int_cst_1, offset) && wi::eq_p (int_cst_2, limit_2))
         || (wi::eq_p (int_cst_1, itype_max) && wi::eq_p (int_cst_2, limit_1)))
        && wi::eq_p (int_cst_3, otype_max))))))
 
-- 
2.43.0

Reply via email to