Match: Support form 1 for scalar signed integer SAT_TRUNC

This patch would like to support the form 1 of the scalar signed
integer SAT_TRUNC.  Aka below example:

Form 1:
  #define DEF_SAT_S_TRUNC_FMT_1(NT, WT, NT_MIN, NT_MAX) \
  NT __attribute__((noinline))                          \
  sat_s_trunc_##WT##_to_##NT##_fmt_1 (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_1(int64_t, int32_t, INT32_MIN, INT32_MAX)

Before this patch:
   4   │ __attribute__((noinline))
   5   │ int32_t sat_s_trunc_int64_t_to_int32_t_fmt_1 (int64_t x)
   6   │ {
   7   │   int32_t trunc;
   8   │   unsigned long x.0_1;
   9   │   unsigned long _2;
  10   │   int32_t _3;
  11   │   _Bool _7;
  12   │   int _8;
  13   │   int _9;
  14   │   int _10;
  15   │
  16   │ ;;   basic block 2, loop depth 0
  17   │ ;;    pred:       ENTRY
  18   │   x.0_1 = (unsigned long) x_4(D);
  19   │   _2 = x.0_1 + 2147483648;
  20   │   if (_2 > 4294967295)
  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 = (int32_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 = (int) _7;
  37   │   _9 = -_8;
  38   │   _10 = _9 ^ 2147483647;
  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   │ int32_t sat_s_trunc_int64_t_to_int32_t_fmt_1 (int64_t x)
   6   │ {
   7   │   int32_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 with pr116861-1.c failed.
* The x86 bootstrap test.
* The x86 fully regression test.

The failed pr116861-1.c ice will be fixed in underlying patch, as it
just trigger one existing bug.

gcc/ChangeLog:

	* match.pd: Add case 1 matching pattern for signed SAT_TRUNC.
	* tree-ssa-math-opts.cc (gimple_signed_integer_sat_trunc): Add
	new decl for signed SAT_TRUNC.
	(match_saturation_trunc): Add new func impl to try SAT_TRUNC
	pattern on phi node.
	(math_opts_dom_walker::after_dom_children): Add
	match_saturation_trunc for phi node iteration.

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

2 files changed, 83 insertions, 0 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index d50b732..6a924f4 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3461,6 +3461,28 @@ 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).
+   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)
+	(bit_xor:c (negate (convert (lt @0 integer_zerop))) INTEGER_CST@3)
+	(convert @0))
+ (if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type)
+      && !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);
+   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))))))
+
 /* x >  y  &&  x != XXX_MIN  -->  x > y
    x >  y  &&  x == XXX_MIN  -->  false . */
 (for eqne (eq ne)
diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
index 4584d8c..dad8428 100644
--- a/gcc/tree-ssa-math-opts.cc
+++ b/gcc/tree-ssa-math-opts.cc
@@ -4026,6 +4026,7 @@ extern bool gimple_unsigned_integer_sat_trunc (tree, tree*, tree (*)(tree));
 
 extern bool gimple_signed_integer_sat_add (tree, tree*, tree (*)(tree));
 extern bool gimple_signed_integer_sat_sub (tree, tree*, tree (*)(tree));
+extern bool gimple_signed_integer_sat_trunc (tree, tree*, tree (*)(tree));
 
 static void
 build_saturation_binary_arith_call (gimple_stmt_iterator *gsi, internal_fn fn,
@@ -4208,6 +4209,65 @@ match_unsigned_saturation_trunc (gimple_stmt_iterator *gsi, gassign *stmt)
     }
 }
 
+/*
+ * Try to match saturation truncate.
+ * Aka:
+ *   x.0_1 = (unsigned long) x_4(D);
+ *   _2 = x.0_1 + 2147483648;
+ *   if (_2 > 4294967295)
+ *     goto <bb 4>; [50.00%]
+ *   else
+ *     goto <bb 3>; [50.00%]
+ * ;;    succ:       4
+ * ;;                3
+ *
+ * ;;   basic block 3, loop depth 0
+ * ;;    pred:       2
+ *   trunc_5 = (int32_t) x_4(D);
+ *   goto <bb 5>; [100.00%]
+ * ;;    succ:       5
+ *
+ * ;;   basic block 4, loop depth 0
+ * ;;    pred:       2
+ *   _7 = x_4(D) < 0;
+ *   _8 = (int) _7;
+ *   _9 = -_8;
+ *   _10 = _9 ^ 2147483647;
+ * ;;    succ:       5
+ *
+ * ;;   basic block 5, loop depth 0
+ * ;;    pred:       3
+ * ;;                4
+ *   # _3 = PHI <trunc_5(3), _10(4)>
+ * =>
+ * _6 = .SAT_TRUNC (x_4(D));
+ */
+
+static void
+match_saturation_trunc (gimple_stmt_iterator *gsi, gphi *phi)
+{
+  if (gimple_phi_num_args (phi) != 2)
+    return;
+
+  tree ops[1];
+  tree phi_result = gimple_phi_result (phi);
+  tree type = TREE_TYPE (phi_result);
+
+  if ((gimple_unsigned_integer_sat_trunc (phi_result, ops, NULL)
+      || gimple_signed_integer_sat_trunc (phi_result, ops, NULL))
+      && direct_internal_fn_supported_p (IFN_SAT_TRUNC,
+					 tree_pair (type, TREE_TYPE (ops[0])),
+					 OPTIMIZE_FOR_BOTH))
+    {
+      gcall *call = gimple_build_call_internal (IFN_SAT_TRUNC, 1, ops[0]);
+      gimple_call_set_lhs (call, phi_result);
+      gsi_insert_before (gsi, call, GSI_SAME_STMT);
+
+      gimple_stmt_iterator psi = gsi_for_stmt (phi);
+      remove_phi_node (&psi, /* release_lhs_p */ false);
+    }
+}
+
 /* Recognize for unsigned x
    x = y - z;
    if (x > y)
@@ -6260,6 +6320,7 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
       /* The match_* may remove phi node.  */
       match_saturation_add (&gsi, psi.phi ());
       match_saturation_sub (&gsi, psi.phi ());
+      match_saturation_trunc (&gsi, psi.phi ());
     }
 
   for (gsi = gsi_after_labels (bb); !gsi_end_p (gsi);)