https://gcc.gnu.org/g:e21a8d9ec63464b2c8301f882a3a04ac59b01fcd
commit r15-4168-ge21a8d9ec63464b2c8301f882a3a04ac59b01fcd
Author: Pan Li <pan2...@intel.com>
Date: Thu Oct 3 16:06:08 2024 +0800
Match: Support form 3 and form 4 for scalar signed integer SAT_SUB
This patch would like to support the form 3 and form 4 of the scalar signed
integer SAT_SUB. Aka below example:
Form 3:
#define DEF_SAT_S_ADD_FMT_3(T, UT, MIN, MAX) \
T __attribute__((noinline)) \
sat_s_add_##T##_fmt_3 (T x, T y) \
{ \
T sum; \
bool overflow = __builtin_add_overflow (x, y, &sum); \
return overflow ? x < 0 ? MIN : MAX : sum; \
}
Form 4:
#define DEF_SAT_S_SUB_FMT_4(T, UT, MIN, MAX) \
T __attribute__((noinline)) \
sat_s_sub_##T##_fmt_4 (T x, T y) \
{ \
T minus; \
bool overflow = __builtin_sub_overflow (x, y, &minus); \
return !overflow ? minus : x < 0 ? MIN : MAX; \
}
DEF_SAT_S_ADD_FMT_3(int8_t, uint8_t, INT8_MIN, INT8_MAX);
Before this patch:
4 │ __attribute__((noinline))
5 │ int8_t sat_s_sub_int8_t_fmt_3 (int8_t x, int8_t y)
6 │ {
7 │ signed char _1;
8 │ signed char _2;
9 │ int8_t _3;
10 │ __complex__ signed char _6;
11 │ _Bool _8;
12 │ signed char _9;
13 │ signed char _10;
14 │ signed char _11;
15 │
16 │ ;; basic block 2, loop depth 0
17 │ ;; pred: ENTRY
18 │ _6 = .SUB_OVERFLOW (x_4(D), y_5(D));
19 │ _2 = IMAGPART_EXPR <_6>;
20 │ if (_2 != 0)
21 │ goto <bb 4>; [50.00%]
22 │ else
23 │ goto <bb 3>; [50.00%]
24 │ ;; succ: 4
25 │ ;; 3
26 │
27 │ ;; basic block 3, loop depth 0
28 │ ;; pred: 2
29 │ _1 = REALPART_EXPR <_6>;
30 │ goto <bb 5>; [100.00%]
31 │ ;; succ: 5
32 │
33 │ ;; basic block 4, loop depth 0
34 │ ;; pred: 2
35 │ _8 = x_4(D) < 0;
36 │ _9 = (signed char) _8;
37 │ _10 = -_9;
38 │ _11 = _10 ^ 127;
39 │ ;; succ: 5
40 │
41 │ ;; basic block 5, loop depth 0
42 │ ;; pred: 3
43 │ ;; 4
44 │ # _3 = PHI <_1(3), _11(4)>
45 │ return _3;
46 │ ;; succ: EXIT
47 │
48 │ }
After this patch:
4 │ __attribute__((noinline))
5 │ int8_t sat_s_sub_int8_t_fmt_3 (int8_t x, int8_t y)
6 │ {
7 │ int8_t _3;
8 │
9 │ ;; basic block 2, loop depth 0
10 │ ;; pred: ENTRY
11 │ _3 = .SAT_SUB (x_4(D), y_5(D)); [tail call]
12 │ return _3;
13 │ ;; succ: EXIT
14 │
15 │ }
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 case 3 matching pattern for signed SAT_SUB.
Signed-off-by: Pan Li <pan2...@intel.com>
Diff:
---
gcc/match.pd | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/gcc/match.pd b/gcc/match.pd
index ba83f0f29e61..d50b732bc86b 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3388,6 +3388,19 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(bit_xor:c (negate (convert (lt @0 integer_zerop))) max_value))
(if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type))))
+/* Signed saturation sub, case 3:
+ Z = .SUB_OVERFLOW (X, Y)
+ SAT_S_SUB = IMAGPART_EXPR (Z) != 0 ? (-(T)(X < 0) ^ MAX) : REALPART_EXPR
(Z);
+
+ The T and UT are type pair like T=int8_t, UT=uint8_t. */
+(match (signed_integer_sat_sub @0 @1)
+ (cond^ (ne (imagpart (IFN_SUB_OVERFLOW@2 @0 @1)) integer_zerop)
+ (bit_xor:c (negate (convert (lt @0 integer_zerop)))
+ max_value)
+ (realpart @2))
+ (if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
/* 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)
