https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101074
Bug ID: 101074
Summary: calloc result not treated as zeroed out
Product: gcc
Version: 11.1.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: msebor at gcc dot gnu.org
Target Milestone: ---
GCC folds malloc + bzero (or malloc + memset zero) to calloc and "knows" that
the returned memory is zeroed out. But it doesn't seem to understand that the
memory returned from a call specifically made to calloc is also zeroed out. In
the test case below both functions should be optimized equivalently but only
the first produces optimal code, the second is suboptimal.
$ cat z.c && gcc -O2 -S -Wall -fdump-tree-optimized=/dev/stdout z.c
struct A { int i; };
void* f (void)
{
struct A *p = __builtin_malloc (sizeof *p);
__builtin_memset (p, 0, sizeof *p);
if (p->i) // folded to false
__builtin_abort ();
return p;
}
void* g (void)
{
struct A *p = __builtin_calloc (1, sizeof *p);
if (p->i) // not folded
__builtin_abort ();
return p;
}
;; Function f (f, funcdef_no=0, decl_uid=1945, cgraph_uid=1, symbol_order=0)
void * f ()
{
struct A * p;
<bb 2> [local count: 1073741824]:
p_3 = __builtin_calloc (4, 1); [tail call]
return p_3;
}
;; Function g (g, funcdef_no=1, decl_uid=1949, cgraph_uid=2, symbol_order=1)
void * g ()
{
struct A * p;
int _1;
<bb 2> [local count: 1073741824]:
p_4 = __builtin_calloc (1, 4);
_1 = p_4->i;
if (_1 != 0)
goto <bb 3>; [0.00%]
else
goto <bb 4>; [100.00%]
<bb 3> [count: 0]:
__builtin_abort ();
<bb 4> [local count: 1073741824]:
return p_4;
}