On Thu, Sep 26, 2024 at 2:25 PM <pan2...@intel.com> wrote:
>
> From: Pan Li <pan2...@intel.com>
>
> This patch would like to support the form 2 of the scalar signed
> integer SAT_SUB. Aka below example:
>
> Form 2:
> #define DEF_SAT_S_SUB_FMT_2(T, UT, MIN, MAX) \
> T __attribute__((noinline)) \
> sat_s_sub_##T##_fmt_1 (T x, T y) \
> { \
> T minus = (UT)x - (UT)y; \
> if ((x ^ y) >= 0 || (minus ^ x) >= 0) \
> return minus; \
> return x < 0 ? MIN : MAX; \
> }
>
> DEF_SAT_S_SUB_FMT_2(int8_t, uint8_t, INT8_MIN, INT8_MAX)
>
> Before this patch:
> 4 │ __attribute__((noinline))
> 5 │ int8_t sat_s_sub_int8_t_fmt_2 (int8_t x, int8_t y)
> 6 │ {
> 7 │ int8_t minus;
> 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 _15;
> 19 │
> 20 │ ;; basic block 2, loop depth 0
> 21 │ ;; pred: ENTRY
> 22 │ x.0_1 = (unsigned char) x_7(D);
> 23 │ y.1_2 = (unsigned char) y_8(D);
> 24 │ _3 = x.0_1 - y.1_2;
> 25 │ minus_9 = (int8_t) _3;
> 26 │ _4 = x_7(D) ^ y_8(D);
> 27 │ _5 = x_7(D) ^ minus_9;
> 28 │ _15 = _4 & _5;
> 29 │ if (_15 >= 0)
> 30 │ goto <bb 4>; [42.57%]
> 31 │ else
> 32 │ goto <bb 3>; [57.43%]
> 33 │ ;; succ: 4
> 34 │ ;; 3
> 35 │
> 36 │ ;; basic block 3, loop depth 0
> 37 │ ;; pred: 2
> 38 │ _11 = x_7(D) < 0;
> 39 │ _12 = (signed char) _11;
> 40 │ _13 = -_12;
> 41 │ _14 = _13 ^ 127;
> 42 │ ;; succ: 4
> 43 │
> 44 │ ;; basic block 4, loop depth 0
> 45 │ ;; pred: 2
> 46 │ ;; 3
> 47 │ # _6 = PHI <minus_9(2), _14(3)>
> 48 │ return _6;
> 49 │ ;; succ: EXIT
> 50 │
> 51 │ }
>
> After this patch:
> 4 │ __attribute__((noinline))
> 5 │ int8_t sat_s_sub_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_SUB (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.
OK.
Richard.
> gcc/ChangeLog:
>
> * match.pd: Add case 2 matching pattern for signed SAT_SUB.
>
> Signed-off-by: Pan Li <pan2...@intel.com>
> ---
> gcc/match.pd | 14 ++++++++++++++
> 1 file changed, 14 insertions(+)
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 63f7f3142c4..3baf209350b 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -3372,6 +3372,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> @2)
> (if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type))))
>
> +/* Signed saturation sub, case 2:
> + T minus = (T)((UT)X - (UT)Y);
> + SAT_S_SUB = (X ^ Y) & (X ^ minus) < 0 ? (-(T)(X < 0) ^ MAX) : minus;
> +
> + The T and UT are type pair like T=int8_t, UT=uint8_t. */
> +(match (signed_integer_sat_sub @0 @1)
> + (cond^ (ge (bit_and:c (bit_xor:c @0 @1)
> + (bit_xor @0 (nop_convert@2 (minus (nop_convert @0)
> + (nop_convert @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 truncate, case 1, sizeof (WT) > sizeof (NT).
> SAT_U_TRUNC = (NT)x | (NT)(-(X > (WT)(NT)(-1))). */
> (match (unsigned_integer_sat_trunc @0)
> --
> 2.43.0
>
