https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111683
Jakub Jelinek <jakub at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |rguenth at gcc dot gnu.org
--- Comment #14 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
It is indeed pcom.
Slightly better testcase which doesn't use double arithmetics but long long:
long long b[6] = { 3, 4, 5, 6, 7, 8 };
long long c[16];
typedef long long U __attribute__ ((vector_size(16), may_alias, aligned(1)));
typedef long long V __attribute__ ((vector_size(16), may_alias));
int
main ()
{
for (int f = 0; f < 6; f++)
{
*(U *) &c[f] = *(U *) &c[f] + (V) { b[f], b[f] };
*(U *) &c[f + 2] = *(U *) &c[f + 2] + (V) { b[f], b[f] };
}
if (c[1] != 7)
__builtin_abort ();
return 0;
}
And it doesn't need to be about vector types either, nor use any aligned(1)
loads/stores in the source:
int b[6] = { 3, 4, 5, 6, 7, 8 }, c[12];
int d[16] = { 0, 1, 3, 6, 10, 14, 12, 9, 5, 0, 0, 0 };
int
main ()
{
int i;
if (sizeof (int) * 2 != sizeof (long long))
return 0;
for (i = 0; i < 6; i++)
{
long long a;
__builtin_memcpy (&a, &c[i], sizeof (a));
a += (((long long) i) << (sizeof (int) * __CHAR_BIT__)) + i;
__builtin_memcpy (&c[i], &a, sizeof (a));
__builtin_memcpy (&a, &c[i + 2], sizeof (a));
a += (((long long) i) << (sizeof (int) * __CHAR_BIT__)) + i;
__builtin_memcpy (&c[i + 2], &a, sizeof (a));
}
if (__builtin_memcmp (&c[0], &d[0], sizeof (c)))
__builtin_abort ();
return 0;
}
On the last testcase the *.pcom change against previous dump is:
int main ()
{
+ unsigned long D__lsm1.7;
+ unsigned long D__lsm0.6;
long long int a;
int i;
int * _1;
@@ -21,18 +31,24 @@ int main ()
unsigned long _20;
sizetype _25;
sizetype _28;
+ unsigned long _33;
+ unsigned long _37;
unsigned int ivtmp_38;
unsigned int ivtmp_39;
<bb 2> [local count: 153437704]:
+ _37 = MEM <unsigned long> [(char * {ref-all})&c];
+ _33 = MEM <unsigned long> [(char * {ref-all})&c + 4B];
<bb 3> [local count: 920304121]:
# i_26 = PHI <i_23(7), 0(2)>
# ivtmp_39 = PHI <ivtmp_38(7), 6(2)>
+ # D__lsm0.6_34 = PHI <D__lsm1.7_35(7), _37(2)>
+ # D__lsm1.7_35 = PHI <D__lsm0.6_36(7), _33(2)>
_28 = (sizetype) i_26;
_9 = _28 * 4;
_1 = &c + _9;
- _12 = MEM <unsigned long> [(char * {ref-all})_1];
+ _12 = D__lsm0.6_34;
a_13 = (long long int) _12;
_19 = _28 * 4294967297;
_2 = (long long int) _19;
@@ -48,6 +64,7 @@ int main ()
_6 = _2 + a_18;
_20 = (unsigned long) _6;
MEM <unsigned long> [(char * {ref-all})_5] = _20;
+ D__lsm0.6_36 = _20;
i_23 = i_26 + 1;
ivtmp_38 = ivtmp_39 - 1;
if (ivtmp_38 != 0)
The data refs in the loop have access fns {0B, +, 4}_1 and {8B, +, 4}_1, so
within
the same iteration there is no overlap between the two, but because they are
actually
8 byte loads/stores, there is partial overlap between the adjacent iterations
in them that pcom doesn't take into account.
So, shall we somewhere punt for references with larger access sizes than their
DR_STEP?
Something else?
