diff mbox series

[01/11] Match: Support form 1 for vector signed integer SAT_TRUNC

Message ID 20241014111058.1033886-1-pan2.li@intel.com
State New
Headers show
Series [01/11] Match: Support form 1 for vector signed integer SAT_TRUNC | expand

Commit Message

Li, Pan2 Oct. 14, 2024, 11:10 a.m. UTC 
From: Pan Li <pan2.li@intel.com>

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

Form 1:
  #define DEF_VEC_SAT_S_TRUNC_FMT_1(NT, WT, NT_MIN, NT_MAX)             \
  void __attribute__((noinline))                                        \
  vec_sat_s_trunc_##NT##_##WT##_fmt_1 (NT *out, WT *in, unsigned limit) \
  {                                                                     \
    unsigned i;                                                         \
    for (i = 0; i < limit; i++)                                         \
      {                                                                 \
        WT x = in[i];                                                   \
        NT trunc = (NT)x;                                               \
        out[i] = (WT)NT_MIN <= x && x <= (WT)NT_MAX                     \
	  ? trunc                                                       \
	  : x < 0 ? NT_MIN : NT_MAX;                                    \
      }                                                                 \
  }

DEF_VEC_SAT_S_TRUNC_FMT_1(int32_t, int64_t, INT32_MIN, INT32_MAX)

Before this patch:
  48   │   _87 = .SELECT_VL (ivtmp_85, POLY_INT_CST [2, 2]);
  49   │   ivtmp_64 = _87 * 8;
  50   │   vect_x_14.10_67 = .MASK_LEN_LOAD (vectp_in.8_65, 64B, { -1, ... }, _87, 0);
  51   │   vect_trunc_15.21_78 = (vector([2,2]) int) vect_x_14.10_67;
  52   │   _61 = VIEW_CONVERT_EXPR<vector([2,2]) unsigned long>(vect_x_14.10_67);
  53   │   _32 = _61 >> 63;
  54   │   vect_patt_52.16_73 = (vector([2,2]) int) _32;
  55   │   vect__46.17_74 = VIEW_CONVERT_EXPR<vector([2,2]) unsigned int>(vect_patt_52.16_73);
  56   │   vect__47.18_75 = -vect__46.17_74;
  57   │   vect__21.19_76 = VIEW_CONVERT_EXPR<vector([2,2]) int>(vect__47.18_75);
  58   │   vect_x.11_68 = VIEW_CONVERT_EXPR<vector([2,2]) unsigned long>(vect_x_14.10_67);
  59   │   vect__5.12_69 = vect_x.11_68 + { 2147483648, ... };
  60   │   mask__34.13_70 = vect__5.12_69 > { 4294967295, ... };
  61   │   _25 = .COND_XOR (mask__34.13_70, vect__21.19_76, { 2147483647, ... }, vect_trunc_15.21_78);
  62   │   ivtmp_80 = _87 * 4;
  63   │   .MASK_LEN_STORE (vectp_out.23_81, 32B, { -1, ... }, _87, 0, _25);
  64   │   vectp_in.8_66 = vectp_in.8_65 + ivtmp_64;
  65   │   vectp_out.23_82 = vectp_out.23_81 + ivtmp_80;
  66   │   ivtmp_86 = ivtmp_85 - _87;

After this patch:
  38   │   _77 = .SELECT_VL (ivtmp_75, POLY_INT_CST [2, 2]);
  39   │   ivtmp_65 = _77 * 8;
  40   │   vect_x_14.10_68 = .MASK_LEN_LOAD (vectp_in.8_66, 64B, { -1, ... }, _77, 0);
  41   │   vect_patt_53.11_69 = .SAT_TRUNC (vect_x_14.10_68);
  42   │   ivtmp_70 = _77 * 4;
  43   │   .MASK_LEN_STORE (vectp_out.12_71, 32B, { -1, ... }, _77, 0, vect_patt_53.11_69);
  44   │   vectp_in.8_67 = vectp_in.8_66 + ivtmp_65;
  45   │   vectp_out.12_72 = vectp_out.12_71 + ivtmp_70;
  46   │   ivtmp_76 = ivtmp_75 - _77;

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: Refine matching for vector signed SAT_TRUNC form 1.

Signed-off-by: Pan Li <pan2.li@intel.com>
---
 gcc/match.pd | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/gcc/match.pd b/gcc/match.pd
index 2ab76f9d055..36195d0c920 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3493,7 +3493,9 @@  DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
    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)
+	(bit_xor:c (nop_convert?
+		    (negate (nop_convert? (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)))