From: Pan Li <[email protected]>
This patch would like to try to match the the unsigned
SAT_MUL form 11, aka below
#define DEF_SAT_U_MUL_FMT_11(NT, WT) \
NT __attribute__((noinline)) \
sat_u_mul_##NT##_from_##WT##_fmt_11 (NT a, NT b) \
{ \
WT x = (WT)a * (WT)b; \
NT max = -1; \
bool overflow_p = x >= (WT)(max); \
return -(NT)(overflow_p) | (NT)x; \
}
while WT is uint128_t, uint64_t, uint32_t and uint16_t, and
NT is uint64_t, uint32_t, uint16_t or uint8_t.
gcc/ChangeLog:
* match-sat-alu.pd: Add pattern for unsigned scalar
SAT_MUL form 11.
Signed-off-by: Pan Li <[email protected]>
---
gcc/match-sat-alu.pd | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/gcc/match-sat-alu.pd b/gcc/match-sat-alu.pd
index 483c37b6d9f..6145a0c9948 100644
--- a/gcc/match-sat-alu.pd
+++ b/gcc/match-sat-alu.pd
@@ -548,7 +548,7 @@ along with GCC; see the file COPYING3. If not see
/* SAT_U_MUL (X, Y) = {
WT x = (WT)a * (WT)b;
NT max = -1;
- bool overflow_p = x > (WT)max;
+ bool overflow_p = x > (WT)max || x > (WT)(max - 1);
return -(NT)(overflow_p) | (NT)x;
} while WT is uint128_t, uint64_t, uint32_t, uint16_t,
and T is uint64_t, uint32_t, uint16_t, uint8_t. */
@@ -560,7 +560,12 @@ along with GCC; see the file COPYING3. If not see
unsigned prec = TYPE_PRECISION (type);
unsigned widen_prec = TYPE_PRECISION (TREE_TYPE (@3));
wide_int max = wi::mask (prec, false, widen_prec);
- bool c2_is_max_p = wi::eq_p (wi::to_wide (@2), max);
+
+ wide_int c2 = wi::to_wide (@2);
+ bool c2_is_max_p = wi::eq_p (c2, max);
+
+ wide_int c2_plus_one = wi::add (c2, wi::uhwi (1, widen_prec));
+ bool c2_plus_one_is_max_p = wi::eq_p (c2_plus_one, max);
}
- (if (c2_is_max_p)))))
+ (if (c2_is_max_p || c2_plus_one_is_max_p)))))
)
--
2.43.0