http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46886
Jakub Jelinek <jakub at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |rakdver at gcc dot gnu.org,
| |spop at gcc dot gnu.org
--- Comment #1 from Jakub Jelinek <jakub at gcc dot gnu.org> 2011-01-18
17:00:29 UTC ---
Seems one extra incorrect iteration is added after GOMP_parallel_end:
<bb 16>:
D.1592_69 = D.1591_183 * 4;
<bb 17>:
# D.1592_15 = PHI <0(15), D.1592_69(16)>
D.1749_71 = (<unnamed-unsigned:64>) D.1592_15;
D.1750_72 = MAX_EXPR <D.1749_71, 1>;
D.1751_73 = __builtin_malloc (D.1750_72);
D.1594_74 = (void * restrict) D.1751_73;
D.1898_232 = (<unnamed-unsigned:64>) D.1591_183;
D.1899_233 = D.1591_183 >= 0;
D.1900_234 = D.1898_232 > 199;
D.1901_235 = D.1899_233 && D.1900_234;
if (D.1901_235 != 0)
goto <bb 18>;
else
goto <bb 19>;
<bb 18>:
.paral_data_store.64.D.1910 = D.1578_1;
.paral_data_store.64.D.1911 = D.1594_74;
.paral_data_store.64.D.1912 = D.1898_232;
__builtin_GOMP_parallel_start (build._loopfn.1, &.paral_data_store.64, 2);
build._loopfn.1 (&.paral_data_store.64);
__builtin_GOMP_parallel_end ();
ivtmp.60_247 = D.1898_232;
S.7_248 = (integer(kind=8)) ivtmp.60_247;
D.1755_249 = *D.1578_1[S.7_248];
MEM[(real(kind=4)[0:] *)D.1594_74][S.7_248] = D.1755_249;
S.7_251 = S.7_248 + 1;
ivtmp.60_252 = ivtmp.60_247 + 1;
S.7_248 is equal to the number of ints allocated, so stores after the end of
malloced area. The loop is initially:
loop_4 (header = 18, latch = 19, niter = , upper_bound = 9223372036854775808,
estimate = 9223372036854775808)
{
bb_18 (preds = {bb_17 bb_19 }, succs = {bb_20 bb_19 })
{
<bb 18>:
# S.7_7 = PHI <0(17), S.7_80(19)>
# .MEM_152 = PHI <.MEM_182(17), .MEM_185(19)>
if (S.7_7 > D.1586_64)
goto <bb 20>;
else
goto <bb 19>;
}
bb_19 (preds = {bb_18 }, succs = {bb_18 })
{
<bb 19>:
# VUSE <.MEM_152>
D.1755_79 = *D.1578_1[S.7_7];
# .MEM_185 = VDEF <.MEM_152>
MEM[(real(kind=4)[0:] *)D.1594_74][S.7_7] = D.1755_79;
S.7_80 = S.7_7 + 1;
goto <bb 18>;
}
}
and try_get_loop_niter computes niter->niter as (<unnamed-unsigned:64>)
D.1591_183. On:
__attribute__((noinline, noclone)) void
foo (int *__restrict__ p, int *__restrict__ q, int n)
{
int i;
for (i = 0; i < n; i++)
p[i] = q[i];
}
int
main (void)
{
int *p = __builtin_calloc (1024, sizeof (int));
int *q = __builtin_calloc (1024, sizeof (int));
foo (p, q, 1024);
return 0;
}
try_get_loop_niter instead computes niter->niter as n - 1 (which is strange to
me), but then it works even with the extra iteration added after
GOMP_parallel_end (as that iteration is done with iv set to n - 1).
