Match: Support .SAT_SUB with IMM op for form 1-4

This patch would like to support .SAT_SUB when one of the op
is IMM.  Aka below 1-4 forms.

Form 1:
 #define DEF_SAT_U_SUB_IMM_FMT_1(T, IMM) \
 T __attribute__((noinline))             \
 sat_u_sub_imm##IMM##_##T##_fmt_1 (T y)  \
 {                                       \
   return IMM >= y ? IMM - y : 0;        \
 }

Form 2:
  #define DEF_SAT_U_SUB_IMM_FMT_2(T, IMM) \
  T __attribute__((noinline))             \
  sat_u_sub_imm##IMM##_##T##_fmt_2 (T y)  \
  {                                       \
    return IMM > y ? IMM - y : 0;         \
  }

Form 3:
  #define DEF_SAT_U_SUB_IMM_FMT_3(T, IMM) \
  T __attribute__((noinline))             \
  sat_u_sub_imm##IMM##_##T##_fmt_3 (T x)  \
  {                                       \
    return x >= IMM ? x - IMM : 0;        \
  }

Form 4:
  #define DEF_SAT_U_SUB_IMM_FMT_4(T, IMM) \
  T __attribute__((noinline))             \
  sat_u_sub_imm##IMM##_##T##_fmt_4 (T x)  \
  {                                       \
    return x > IMM ? x - IMM : 0;         \
  }

Take below form 1 as example:

DEF_SAT_U_SUB_OP0_IMM_FMT_1(uint32_t, 11)

Before this patch:
   4   │ __attribute__((noinline))
   5   │ uint64_t sat_u_sub_imm11_uint64_t_fmt_1 (uint64_t y)
   6   │ {
   7   │   uint64_t _1;
   8   │   uint64_t _3;
   9   │
  10   │ ;;   basic block 2, loop depth 0
  11   │ ;;    pred:       ENTRY
  12   │   if (y_2(D) <= 11)
  13   │     goto <bb 3>; [50.00%]
  14   │   else
  15   │     goto <bb 4>; [50.00%]
  16   │ ;;    succ:       3
  17   │ ;;                4
  18   │
  19   │ ;;   basic block 3, loop depth 0
  20   │ ;;    pred:       2
  21   │   _3 = 11 - y_2(D);
  22   │ ;;    succ:       4
  23   │
  24   │ ;;   basic block 4, loop depth 0
  25   │ ;;    pred:       2
  26   │ ;;                3
  27   │   # _1 = PHI <0(2), _3(3)>
  28   │   return _1;
  29   │ ;;    succ:       EXIT
  30   │
  31   │ }

After this patch:
   4   │ __attribute__((noinline))
   5   │ uint64_t sat_u_sub_imm11_uint64_t_fmt_1 (uint64_t y)
   6   │ {
   7   │   uint64_t _1;
   8   │
   9   │ ;;   basic block 2, loop depth 0
  10   │ ;;    pred:       ENTRY
  11   │   _1 = .SAT_SUB (11, y_2(D)); [tail call]
  12   │   return _1;
  13   │ ;;    succ:       EXIT
  14   │
  15   │ }

The below test suites are passed for this patch:
1. The rv64gcv fully regression tests.
2. The x86 bootstrap tests.
3. The x86 fully regression tests.

gcc/ChangeLog:

	* match.pd: Add case 9 and case 10 for .SAT_SUB when one
	of the op is IMM.

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

diff --git a/gcc/match.pd b/gcc/match.pd
index cf359b0ec0f0dd490854d6813a64f36a2edb3e79..b2e7d61790dfc259765adad3478eb54946719bc2 100644 (file)
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3234,6 +3234,41 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
  (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
       && types_match (type, @0, @1))))
 
+/* Unsigned saturation sub with op_0 imm, case 9 (branch with gt):
+   SAT_U_SUB = IMM > Y  ? (IMM - Y) : 0.
+             = IMM >= Y ? (IMM - Y) : 0.  */
+(match (unsigned_integer_sat_sub @0 @1)
+ (cond^ (le @1 INTEGER_CST@2) (minus INTEGER_CST@0 @1) integer_zerop)
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+     && types_match (type, @1))
+ (with
+  {
+   unsigned precision = TYPE_PRECISION (type);
+   wide_int max = wi::mask (precision, false, precision);
+   wide_int c0 = wi::to_wide (@0);
+   wide_int c2 = wi::to_wide (@2);
+   wide_int c2_add_1 = wi::add (c2, wi::uhwi (1, precision));
+   bool equal_p = wi::eq_p (c0, c2);
+   bool less_than_1_p = !wi::eq_p (c2, max) && wi::eq_p (c2_add_1, c0);
+  }
+  (if (equal_p || less_than_1_p)))))
+
+/* Unsigned saturation sub with op_1 imm, case 10:
+   SAT_U_SUB = X > IMM  ? (X - IMM) : 0.
+             = X >= IMM ? (X - IMM) : 0.  */
+(match (unsigned_integer_sat_sub @0 @1)
+ (plus (max @0 INTEGER_CST@1) INTEGER_CST@2)
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+     && types_match (type, @1))
+ (with
+  {
+   unsigned precision = TYPE_PRECISION (type);
+   wide_int c1 = wi::to_wide (@1);
+   wide_int c2 = wi::to_wide (@2);
+   wide_int sum = wi::add (c1, c2);
+  }
+  (if (wi::eq_p (sum, wi::uhwi (0, precision)))))))
+
 /* Unsigned saturation truncate, case 1, sizeof (WT) > sizeof (NT).
    SAT_U_TRUNC = (NT)x | (NT)(-(X > (WT)(NT)(-1))).  */
 (match (unsigned_integer_sat_trunc @0)