https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68136
Bug ID: 68136
Summary: missed tree-level optimization with redundant
computations
Product: gcc
Version: 6.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: enhancement
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ktkachov at gcc dot gnu.org
Target Milestone: ---
Take the testcase gcc.dg/ifcvt-3.c:
typedef long long s64;
int
foo (s64 a, s64 b, s64 c)
{
s64 d = a - b;
if (d == 0)
return a + c;
else
return b + d + c;
}
on aarch64 this produces the simplest possible:
foo:
add w0, w2, w0
ret
However, this is due to RTL-level ifconversion.
The final tree dump is the more complex:
foo (s64D.2694 aD.2695, s64D.2694 bD.2696, s64D.2694 cD.2697)
{
s64D.2694 dD.2700;
intD.7 _1;
unsigned int _5;
unsigned int _7;
unsigned int _8;
intD.7 _9;
unsigned int _10;
unsigned int _11;
unsigned int _13;
unsigned int _14;
intD.7 _15;
unsigned int _17;
;; basic block 2, loop depth 0, count 0, freq 10000, maybe hot
;; prev block 0, next block 3, flags: (NEW, REACHABLE)
;; pred: ENTRY [100.0%] (FALLTHRU,EXECUTABLE)
d_4 = a_2(D) - b_3(D);
if (d_4 == 0)
goto <bb 3>;
else
goto <bb 4>;
;; succ: 3 [39.0%] (TRUE_VALUE,EXECUTABLE)
;; 4 [61.0%] (FALSE_VALUE,EXECUTABLE)
;; basic block 3, loop depth 0, count 0, freq 3900, maybe hot
;; prev block 2, next block 4, flags: (NEW, REACHABLE)
;; pred: 2 [39.0%] (TRUE_VALUE,EXECUTABLE)
# RANGE [0, 4294967295]
_5 = (unsigned int) a_2(D);
# RANGE [0, 4294967295]
_7 = (unsigned int) c_6(D);
# RANGE [0, 4294967295]
_8 = _5 + _7;
_9 = (intD.7) _8;
goto <bb 5>;
;; succ: 5 [100.0%] (FALLTHRU,EXECUTABLE)
;; basic block 4, loop depth 0, count 0, freq 6100, maybe hot
;; prev block 3, next block 5, flags: (NEW, REACHABLE)
;; pred: 2 [61.0%] (FALSE_VALUE,EXECUTABLE)
# RANGE [0, 4294967295]
_10 = (unsigned int) b_3(D);
# RANGE [0, 4294967295]
_11 = (unsigned int) d_4;
# RANGE [0, 4294967295]
_13 = (unsigned int) c_6(D);
# RANGE [0, 4294967295]
_17 = _10 + _13;
# RANGE [0, 4294967295]
_14 = _11 + _17;
_15 = (intD.7) _14;
;; succ: 5 [100.0%] (FALLTHRU,EXECUTABLE)
;; basic block 5, loop depth 0, count 0, freq 10000, maybe hot
;; prev block 4, next block 1, flags: (NEW, REACHABLE)
;; pred: 3 [100.0%] (FALLTHRU,EXECUTABLE)
;; 4 [100.0%] (FALLTHRU,EXECUTABLE)
# _1 = PHI <_9(3), _15(4)>
# VUSE <.MEM_16(D)>
return _1;
;; succ: EXIT [100.0%]
}
It's probably a good idea to detect this earlier and produce a " return a + c;"
at the tree level
