From: Pan Li <pan2...@intel.com>
This patch would like to support the form 3 of the vector signed
integer .SAT_ADD. Aka below example:
Form 3:
#define DEF_VEC_SAT_S_ADD_FMT_3(T, UT, MIN, MAX) \
void __attribute__((noinline)) \
vec_sat_s_add_##T##_fmt_3 (T *out, T *op_1, T *op_2, unsigned limit) \
{ \
unsigned i; \
for (i = 0; i < limit; i++) \
{ \
T x = op_1[i]; \
T y = op_2[i]; \
T sum; \
bool overflow = __builtin_add_overflow (x, y, &sum); \
out[i] = overflow ? x < 0 ? MIN : MAX : sum; \
} \
}
DEF_VEC_SAT_S_ADD_FMT_3(int8_t, uint8_t, INT8_MIN, INT8_MAX)
Before this patch:
40 │ # ivtmp.7_34 = PHI <0(3), ivtmp.7_30(7)>
41 │ _26 = op_1_12(D) + ivtmp.7_34;
42 │ x_29 = MEM[(int8_t *)_26];
43 │ _1 = op_2_14(D) + ivtmp.7_34;
44 │ y_24 = MEM[(int8_t *)_1];
45 │ _9 = .ADD_OVERFLOW (y_24, x_29);
46 │ _7 = IMAGPART_EXPR <_9>;
47 │ if (_7 != 0)
48 │ goto <bb 6>; [50.00%]
49 │ else
50 │ goto <bb 5>; [50.00%]
51 │ ;; succ: 6
52 │ ;; 5
53 │
54 │ ;; basic block 5, loop depth 1
55 │ ;; pred: 4
56 │ _42 = REALPART_EXPR <_9>;
57 │ _2 = out_17(D) + ivtmp.7_34;
58 │ MEM[(int8_t *)_2] = _42;
59 │ ivtmp.7_27 = ivtmp.7_34 + 1;
60 │ if (_13 != ivtmp.7_27)
61 │ goto <bb 7>; [89.00%]
62 │ else
63 │ goto <bb 8>; [11.00%]
64 │ ;; succ: 7
65 │ ;; 8
66 │
67 │ ;; basic block 6, loop depth 1
68 │ ;; pred: 4
69 │ _38 = x_29 < 0;
70 │ _39 = (signed char) _38;
71 │ _40 = -_39;
72 │ _41 = _40 ^ 127;
73 │ _33 = out_17(D) + ivtmp.7_34;
74 │ MEM[(int8_t *)_33] = _41;
75 │ ivtmp.7_25 = ivtmp.7_34 + 1;
76 │ if (_13 != ivtmp.7_25)
After this patch:
77 │ _94 = .SELECT_VL (ivtmp_92, POLY_INT_CST [16, 16]);
78 │ vect_x_13.9_81 = .MASK_LEN_LOAD (vectp_op_1.7_79, 8B, { -1, ... },
_94, 0);
79 │ vect_y_15.12_85 = .MASK_LEN_LOAD (vectp_op_2.10_83, 8B, { -1, ... },
_94, 0);
80 │ vect_patt_49.13_86 = .SAT_ADD (vect_x_13.9_81, vect_y_15.12_85);
81 │ .MASK_LEN_STORE (vectp_out.14_88, 8B, { -1, ... }, _94, 0,
vect_patt_49.13_86);
82 │ vectp_op_1.7_80 = vectp_op_1.7_79 + _94;
83 │ vectp_op_2.10_84 = vectp_op_2.10_83 + _94;
84 │ vectp_out.14_89 = vectp_out.14_88 + _94;
85 │ ivtmp_93 = ivtmp_92 - _94;
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: Add optional nop_convert for signed SAT_ADD case 4.
Signed-off-by: Pan Li <pan2...@intel.com>
---
gcc/match.pd | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/gcc/match.pd b/gcc/match.pd
index 940292d0d49..c271a8e4c9d 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3246,7 +3246,9 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
SAT_S_ADD = IMAGPART_EXPR (Z) != 0 ? (-(T)(X < 0) ^ MAX) : sum; */
(match (signed_integer_sat_add @0 @1)
(cond^ (ne (imagpart (IFN_ADD_OVERFLOW:c@2 @0 @1)) integer_zerop)
- (bit_xor:c (negate (convert (lt @0 integer_zerop))) max_value)
+ (bit_xor:c (nop_convert?
+ (negate (nop_convert? (convert (lt @0 integer_zerop)))))
+ max_value)
(realpart @2))
(if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type)
&& types_match (type, @0, @1))))
--
2.43.0
