Match: Support more forms for the scalar unsigned .SAT_SUB

After we support the scalar unsigned form 1 and 2,  we would like
to introduce more forms include the branch and branchless.  There
are forms 3-10 list as below:

Form 3:
  #define SAT_SUB_U_3(T) \
  T sat_sub_u_3_##T (T x, T y) \
  { \
    return x > y ? x - y : 0; \
  }

Form 4:
  #define SAT_SUB_U_4(T) \
  T sat_sub_u_4_##T (T x, T y) \
  { \
    return x >= y ? x - y : 0; \
  }

Form 5:
  #define SAT_SUB_U_5(T) \
  T sat_sub_u_5_##T (T x, T y) \
  { \
    return x < y ? 0 : x - y; \
  }

Form 6:
  #define SAT_SUB_U_6(T) \
  T sat_sub_u_6_##T (T x, T y) \
  { \
    return x <= y ? 0 : x - y; \
  }

Form 7:
  #define SAT_SUB_U_7(T) \
  T sat_sub_u_7_##T (T x, T y) \
  { \
    T ret; \
    T overflow = __builtin_sub_overflow (x, y, &ret); \
    return ret & (T)(overflow - 1); \
  }

Form 8:
  #define SAT_SUB_U_8(T) \
  T sat_sub_u_8_##T (T x, T y) \
  { \
    T ret; \
    T overflow = __builtin_sub_overflow (x, y, &ret); \
    return ret & (T)-(!overflow); \
  }

Form 9:
  #define SAT_SUB_U_9(T) \
  T sat_sub_u_9_##T (T x, T y) \
  { \
    T ret; \
    T overflow = __builtin_sub_overflow (x, y, &ret); \
    return overflow ? 0 : ret; \
  }

Form 10:
  #define SAT_SUB_U_10(T) \
  T sat_sub_u_10_##T (T x, T y) \
  { \
    T ret; \
    T overflow = __builtin_sub_overflow (x, y, &ret); \
    return !overflow ? ret : 0; \
  }

Take form 10 as example:

SAT_SUB_U_10(uint64_t);

Before this patch:
uint8_t sat_sub_u_10_uint8_t (uint8_t x, uint8_t y)
{
  unsigned char _1;
  unsigned char _2;
  uint8_t _3;
  __complex__ unsigned char _6;

;;   basic block 2, loop depth 0
;;    pred:       ENTRY
  _6 = .SUB_OVERFLOW (x_4(D), y_5(D));
  _2 = IMAGPART_EXPR <_6>;
  if (_2 == 0)
    goto <bb 3>; [50.00%]
  else
    goto <bb 4>; [50.00%]
;;    succ:       3
;;                4

;;   basic block 3, loop depth 0
;;    pred:       2
  _1 = REALPART_EXPR <_6>;
;;    succ:       4

;;   basic block 4, loop depth 0
;;    pred:       2
;;                3
  # _3 = PHI <0(2), _1(3)>
  return _3;
;;    succ:       EXIT

}

After this patch:
uint8_t sat_sub_u_10_uint8_t (uint8_t x, uint8_t y)
{
  uint8_t _3;

;;   basic block 2, loop depth 0
;;    pred:       ENTRY
  _3 = .SAT_SUB (x_4(D), y_5(D)); [tail call]
  return _3;
;;    succ:       EXIT

}

The below test suites are passed for this patch:
1. The rv64gcv fully regression test with newlib.
2. The rv64gcv build with glibc.
3. The x86 bootstrap test.
4. The x86 fully regression test.

gcc/ChangeLog:

	* match.pd: Add more match for unsigned sat_sub.
	* tree-ssa-math-opts.cc (match_unsigned_saturation_sub): Add new
	func impl to match phi node for .SAT_SUB.
	(math_opts_dom_walker::after_dom_children): Try match .SAT_SUB
	for the phi node, MULT_EXPR, BIT_XOR_EXPR and BIT_AND_EXPR.

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

0 files changed, 0 insertions, 0 deletions