Match: Support SAT_TRUNC variant NARROW_CLIP

This patch tries to add support for a variant of SAT_TRUNC where
negative numbers are clipped to 0 instead of NARROW_TYPE_MAX_VALUE.
This form is seen in x264, aka

UT clip (T a)
{
  return a & (UT)(-1) ? (-a) >> 31 : a;
}

Where sizeof(UT) < sizeof(T)

I'm unable to get the SAT_TRUNC pattern to appear on x86_64, however it
does appear when building for riscv as seen below:

Before this patch:
  <bb 3> [local count: 764504183]:
  # i_21 = PHI <i_14(8), 0(15)>
  # vectp_x.10_54 = PHI <vectp_x.10_55(8), x_10(D)(15)>
  # vectp_res.20_66 = PHI <vectp_res.20_67(8), res_11(D)(15)>
  # ivtmp_70 = PHI <ivtmp_71(8), _69(15)>
  _72 = .SELECT_VL (ivtmp_70, POLY_INT_CST [4, 4]);
  _1 = (long unsigned int) i_21;
  _2 = _1 * 4;
  _3 = x_10(D) + _2;
  ivtmp_53 = _72 * 4;
  vect__4.12_57 = .MASK_LEN_LOAD (vectp_x.10_54, 32B, { -1, ... }, _56(D), _72, 0);
  vect_x.13_58 = VIEW_CONVERT_EXPR<vector([4,4]) unsigned int>(vect__4.12_57);
  vect__38.15_60 = -vect_x.13_58;
  vect__15.16_61 = VIEW_CONVERT_EXPR<vector([4,4]) int>(vect__38.15_60);
  vect__16.17_62 = vect__15.16_61 >> 31;
  mask__29.14_59 = vect_x.13_58 > { 255, ... };
  vect__17.18_63 = VEC_COND_EXPR <mask__29.14_59, vect__16.17_62, vect__4.12_57>;
  vect__18.19_64 = (vector([4,4]) unsigned char) vect__17.18_63;
  _4 = *_3;
  _5 = res_11(D) + _1;
  x.0_12 = (unsigned int) _4;
  _38 = -x.0_12;
  _15 = (int) _38;
  _16 = _15 >> 31;
  _29 = x.0_12 > 255;
  _17 = _29 ? _16 : _4;
  _18 = (unsigned char) _17;
  .MASK_LEN_STORE (vectp_res.20_66, 8B, { -1, ... }, _72, 0, vect__18.19_64);
  i_14 = i_21 + 1;
  vectp_x.10_55 = vectp_x.10_54 + ivtmp_53;
  vectp_res.20_67 = vectp_res.20_66 + _72;
  ivtmp_71 = ivtmp_70 - _72;
  if (ivtmp_71 != 0)
    goto <bb 8>; [89.00%]
  else
    goto <bb 17>; [11.00%]

After this patch:

 <bb 3> [local count: 764504183]:
  # i_21 = PHI <i_14(8), 0(15)>
  # vectp_x.10_68 = PHI <vectp_x.10_69(8), x_10(D)(15)>
  # vectp_res.15_75 = PHI <vectp_res.15_76(8), res_11(D)(15)>
  # ivtmp_79 = PHI <ivtmp_80(8), _78(15)>
  _81 = .SELECT_VL (ivtmp_79, POLY_INT_CST [4, 4]);
  _1 = (long unsigned int) i_21;
  _2 = _1 * 4;
  _3 = x_10(D) + _2;
  ivtmp_67 = _81 * 4;
  vect__4.12_71 = .MASK_LEN_LOAD (vectp_x.10_68, 32B, { -1, ... }, _70(D), _81, 0);
  vect_patt_37.13_72 = MAX_EXPR <{ 0, ... }, vect__4.12_71>;
  vect_patt_39.14_73 = .SAT_TRUNC (vect_patt_37.13_72);
  _4 = *_3;
  _5 = res_11(D) + _1;
  x.0_12 = (unsigned int) _4;
  _38 = -x.0_12;
  _15 = (int) _38;
  _16 = _15 >> 31;
  _29 = x.0_12 > 255;
  _17 = _29 ? _16 : _4;
  _18 = (unsigned char) _17;
  .MASK_LEN_STORE (vectp_res.15_75, 8B, { -1, ... }, _81, 0, vect_patt_39.14_73);
  i_14 = i_21 + 1;
  vectp_x.10_69 = vectp_x.10_68 + ivtmp_67;
  vectp_res.15_76 = vectp_res.15_75 + _81;
  ivtmp_80 = ivtmp_79 - _81;
  if (ivtmp_80 != 0)
    goto <bb 8>; [89.00%]
  else
    goto <bb 17>; [11.00%]

gcc/ChangeLog:

	* match.pd: New NARROW_CLIP variant for SAT_TRUNC.
	* tree-vect-patterns.cc (gimple_unsigned_integer_narrow_clip):
	Add new decl for NARROW_CLIP.
	(vect_recog_sat_trunc_pattern): Add NARROW_CLIP check.

Signed-off-by: Edwin Lu <ewlu@rivosinc.com>

0 files changed, 0 insertions, 0 deletions