From: xuli <[email protected]>
This patch would like to support .SAT_ADD when IMM=-1.
Form1:
T __attribute__((noinline)) \
sat_s_add_imm_##T##_fmt_1##_##INDEX (T x) \
{ \
T sum = (UT)x + (UT)IMM; \
return (x ^ IMM) < 0 \
? sum \
: (sum ^ x) >= 0 \
? sum \
: x < 0 ? MIN : MAX; \
}
Take below form1 as example:
DEF_SAT_S_ADD_IMM_FMT_1(0, int8_t, uint8_t, -1, INT8_MIN, INT8_MAX)
Before this patch:
__attribute__((noinline))
int8_t sat_s_add_imm_int8_t_fmt_1_0 (int8_t x)
{
unsigned char x.0_1;
unsigned char _2;
unsigned char _3;
int8_t iftmp.1_4;
signed char _8;
unsigned char _9;
signed char _10;
<bb 2> [local count: 1073741824]:
x.0_1 = (unsigned char) x_5(D);
_3 = -x.0_1;
_10 = (signed char) _3;
_8 = x_5(D) & _10;
if (_8 < 0)
goto <bb 4>; [1.40%]
else
goto <bb 3>; [98.60%]
<bb 3> [local count: 434070867]:
_2 = x.0_1 + 255;
<bb 4> [local count: 1073741824]:
# _9 = PHI <_2(3), 128(2)>
iftmp.1_4 = (int8_t) _9;
return iftmp.1_4;
}
After this patch:
__attribute__((noinline))
int8_t sat_s_add_imm_int8_t_fmt_1_0 (int8_t x)
{
int8_t _4;
<bb 2> [local count: 1073741824]:
gimple_call <.SAT_ADD, _4, x_5(D), 255> [tail call]
gimple_return <_4>
}
The below test suites are passed for this patch:
1. The rv64gcv fully regression tests.
2. The x86 bootstrap tests.
3. The x86 fully regression tests.
Signed-off-by: Li Xu <[email protected]>
gcc/ChangeLog:
* match.pd: Add signed scalar SAT_ADD IMM form1 with IMM=-1 matching.
* tree-ssa-math-opts.cc (match_unsigned_saturation_add): Adapt function
name.
(match_saturation_add_with_assign): Match signed and unsigned SAT_ADD
with assign.
(math_opts_dom_walker::after_dom_children): Match imm=-1 signed SAT_ADD
with NOP_EXPR case.
---
gcc/match.pd | 19 ++++++++++++++++++-
gcc/tree-ssa-math-opts.cc | 30 +++++++++++++++++++++++++-----
2 files changed, 43 insertions(+), 6 deletions(-)
diff --git a/gcc/match.pd b/gcc/match.pd
index 98411af3940..a07dbb808d2 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3403,7 +3403,24 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(bit_xor:c @0 INTEGER_CST@3)) integer_zerop)
(signed_integer_sat_val @0)
@2)
- (if (wi::bit_and (wi::to_wide (@1), wi::to_wide (@3)) == 0))))
+ (if (wi::bit_and (wi::to_wide (@1), wi::to_wide (@3)) == 0)))
+
+(match (signed_integer_sat_add @0 @1)
+ /* T SUM = (T)((UT)X + (UT)-1);
+ SAT_S_ADD = (X ^ -1) < 0 ? SUM : (X ^ SUM) >= 0 ? SUM
+ : (x < 0) ? MIN : MAX */
+ (convert (cond^ (lt (bit_and:c @0 (nop_convert (negate (nop_convert @0))))
+ integer_zerop)
+ INTEGER_CST@2
+ (plus (nop_convert @0) integer_all_onesp@1)))
+ (with
+ {
+ unsigned precision = TYPE_PRECISION (type);
+ wide_int c1 = wi::to_wide (@1);
+ wide_int c2 = wi::to_wide (@2);
+ wide_int sum = wi::add (c1, c2);
+ }
+ (if (wi::eq_p (sum, wi::max_value (precision, SIGNED)))))))
/* Saturation sub for signed integer. */
(if (INTEGRAL_TYPE_P (type) && !TYPE_UNSIGNED (type))
diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
index 292eb852f2d..f6a1bea2002 100644
--- a/gcc/tree-ssa-math-opts.cc
+++ b/gcc/tree-ssa-math-opts.cc
@@ -4064,15 +4064,34 @@ build_saturation_binary_arith_call_and_insert
(gimple_stmt_iterator *gsi,
* _10 = -_9;
* _12 = _7 | _10;
* =>
- * _12 = .SAT_ADD (_4, _6); */
+ * _12 = .SAT_ADD (_4, _6);
+ *
+ * Try to match IMM=-1 saturation signed add with assign.
+ * <bb 2> [local count: 1073741824]:
+ * x.0_1 = (unsigned char) x_5(D);
+ * _3 = -x.0_1;
+ * _10 = (signed char) _3;
+ * _8 = x_5(D) & _10;
+ * if (_8 < 0)
+ * goto <bb 4>; [1.40%]
+ * else
+ * goto <bb 3>; [98.60%]
+ * <bb 3> [local count: 434070867]:
+ * _2 = x.0_1 + 255;
+ * <bb 4> [local count: 1073741824]:
+ * # _9 = PHI <_2(3), 128(2)>
+ * _4 = (int8_t) _9;
+ * =>
+ * _4 = .SAT_ADD (x_5, -1); */
static void
-match_unsigned_saturation_add (gimple_stmt_iterator *gsi, gassign *stmt)
+match_saturation_add_with_assign (gimple_stmt_iterator *gsi, gassign *stmt)
{
tree ops[2];
tree lhs = gimple_assign_lhs (stmt);
- if (gimple_unsigned_integer_sat_add (lhs, ops, NULL))
+ if (gimple_unsigned_integer_sat_add (lhs, ops, NULL)
+ || gimple_signed_integer_sat_add (lhs, ops, NULL))
build_saturation_binary_arith_call_and_replace (gsi, IFN_SAT_ADD, lhs,
ops[0], ops[1]);
}
@@ -6363,7 +6382,7 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
break;
case PLUS_EXPR:
- match_unsigned_saturation_add (&gsi, as_a<gassign *> (stmt));
+ match_saturation_add_with_assign (&gsi, as_a<gassign *> (stmt));
match_unsigned_saturation_sub (&gsi, as_a<gassign *> (stmt));
/* fall-through */
case MINUS_EXPR:
@@ -6389,7 +6408,7 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
break;
case BIT_IOR_EXPR:
- match_unsigned_saturation_add (&gsi, as_a<gassign *> (stmt));
+ match_saturation_add_with_assign (&gsi, as_a<gassign *> (stmt));
match_unsigned_saturation_trunc (&gsi, as_a<gassign *> (stmt));
/* fall-through */
case BIT_XOR_EXPR:
@@ -6410,6 +6429,7 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
case NOP_EXPR:
match_unsigned_saturation_trunc (&gsi, as_a<gassign *> (stmt));
+ match_saturation_add_with_assign (&gsi, as_a<gassign *> (stmt));
break;
default:;
--
2.17.1
