https://gcc.gnu.org/g:a7eaf7d5edb194bae0d7d9bc3d20bb5730be57d8
commit r15-3569-ga7eaf7d5edb194bae0d7d9bc3d20bb5730be57d8
Author: Pan Li <pan2...@intel.com>
Date: Tue Sep 3 15:39:16 2024 +0800
Match: Support form 2 for scalar signed integer .SAT_ADD
This patch would like to support the form 2 of the scalar signed
integer .SAT_ADD. Aka below example:
Form 2:
#define DEF_SAT_S_ADD_FMT_2(T, UT, MIN, MAX) \
T __attribute__((noinline)) \
sat_s_add_##T##_fmt_2 (T x, T y) \
{ \
T sum = (UT)x + (UT)y; \
\
if ((x ^ y) < 0 || (sum ^ x) >= 0) \
return sum; \
\
return x < 0 ? MIN : MAX; \
}
DEF_SAT_S_ADD_FMT_2(int8_t, uint8_t, INT8_MIN, INT8_MAX)
We can tell the difference before and after this patch if backend
implemented the ssadd<m>3 pattern similar as below.
Before this patch:
4 │ __attribute__((noinline))
5 │ int8_t sat_s_add_int8_t_fmt_2 (int8_t x, int8_t y)
6 │ {
7 │ int8_t sum;
8 │ unsigned char x.0_1;
9 │ unsigned char y.1_2;
10 │ unsigned char _3;
11 │ signed char _4;
12 │ signed char _5;
13 │ int8_t _6;
14 │ _Bool _11;
15 │ signed char _12;
16 │ signed char _13;
17 │ signed char _14;
18 │ signed char _22;
19 │ signed char _23;
20 │
21 │ ;; basic block 2, loop depth 0
22 │ ;; pred: ENTRY
23 │ x.0_1 = (unsigned char) x_7(D);
24 │ y.1_2 = (unsigned char) y_8(D);
25 │ _3 = x.0_1 + y.1_2;
26 │ sum_9 = (int8_t) _3;
27 │ _4 = x_7(D) ^ y_8(D);
28 │ _5 = x_7(D) ^ sum_9;
29 │ _23 = ~_4;
30 │ _22 = _5 & _23;
31 │ if (_22 >= 0)
32 │ goto <bb 4>; [42.57%]
33 │ else
34 │ goto <bb 3>; [57.43%]
35 │ ;; succ: 4
36 │ ;; 3
37 │
38 │ ;; basic block 3, loop depth 0
39 │ ;; pred: 2
40 │ _11 = x_7(D) < 0;
41 │ _12 = (signed char) _11;
42 │ _13 = -_12;
43 │ _14 = _13 ^ 127;
44 │ ;; succ: 4
45 │
46 │ ;; basic block 4, loop depth 0
47 │ ;; pred: 2
48 │ ;; 3
49 │ # _6 = PHI <sum_9(2), _14(3)>
50 │ return _6;
51 │ ;; succ: EXIT
52 │
53 │ }
After this patch:
4 │ __attribute__((noinline))
5 │ int8_t sat_s_add_int8_t_fmt_2 (int8_t x, int8_t y)
6 │ {
7 │ int8_t _6;
8 │
9 │ ;; basic block 2, loop depth 0
10 │ ;; pred: ENTRY
11 │ _6 = .SAT_ADD (x_7(D), y_8(D)); [tail call]
12 │ return _6;
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 the form 2 of signed .SAT_ADD matching.
Signed-off-by: Pan Li <pan2...@intel.com>
Diff:
---
gcc/match.pd | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/gcc/match.pd b/gcc/match.pd
index bc6a83b47fb0..a664be5fe238 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3207,6 +3207,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type)
&& types_match (type, @0, @1))))
+/* Signed saturation add, case 2:
+ T sum = (T)((UT)X + (UT)Y)
+ SAT_S_ADD = (X ^ sum) & !(X ^ Y) >= 0 ? sum : (-(T)(X < 0) ^ MAX);
+
+ The T and UT are type pair like T=int8_t, UT=uint8_t. */
+(match (signed_integer_sat_add @0 @1)
+ (cond^ (ge (bit_and:c (bit_xor @0 (nop_convert@2 (plus (nop_convert @0)
+ (nop_convert @1))))
+ (bit_not (bit_xor:c @0 @1)))
+ integer_zerop)
+ @2
+ (bit_xor:c (negate (convert (lt @0 integer_zerop))) max_value))
+ (if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type))))
+
/* Unsigned saturation sub, case 1 (branch with gt):
SAT_U_SUB = X > Y ? X - Y : 0 */
(match (unsigned_integer_sat_sub @0 @1)
