0ad7981cb4
PR libgomp/91530 * testsuite/libgomp.c/scan-11.c: Add -msse2 option for sse2_runtime targets. * testsuite/libgomp.c/scan-12.c: Likewise. * testsuite/libgomp.c/scan-13.c: Likewise. * testsuite/libgomp.c/scan-14.c: Likewise. * testsuite/libgomp.c/scan-15.c: Likewise. * testsuite/libgomp.c/scan-16.c: Likewise. * testsuite/libgomp.c/scan-17.c: Likewise. * testsuite/libgomp.c/scan-18.c: Likewise. * testsuite/libgomp.c/scan-19.c: Likewise. * testsuite/libgomp.c/scan-20.c: Likewise. * testsuite/libgomp.c++/scan-9.C: Likewise. * testsuite/libgomp.c++/scan-10.C: Likewise. * testsuite/libgomp.c++/scan-11.C: Likewise. * testsuite/libgomp.c++/scan-12.C: Likewise. * testsuite/libgomp.c++/scan-14.C: Likewise. * testsuite/libgomp.c++/scan-15.C: Likewise. * testsuite/libgomp.c++/scan-13.C: Likewise. Use sse2_runtime instead of i?86-*-* x86_64-*-* as target for scan-tree-dump-times. * testsuite/libgomp.c++/scan-16.C: Likewise. From-SVN: r274947
122 lines
2.3 KiB
C
122 lines
2.3 KiB
C
/* { dg-require-effective-target size32plus } */
|
|
/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
|
|
/* { dg-additional-options "-msse2" { target sse2_runtime } } */
|
|
/* { dg-additional-options "-mavx" { target avx_runtime } } */
|
|
/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
|
|
|
|
extern void abort (void);
|
|
int r, a[1024], b[1024];
|
|
|
|
#pragma omp declare reduction (foo: int: omp_out += omp_in) initializer (omp_priv = 0)
|
|
|
|
__attribute__((noipa)) void
|
|
foo (int *a, int *b)
|
|
{
|
|
#pragma omp for simd reduction (inscan, foo:r) simdlen (1)
|
|
for (int i = 0; i < 1024; i++)
|
|
{
|
|
r += a[i];
|
|
#pragma omp scan inclusive(r)
|
|
b[i] = r;
|
|
}
|
|
}
|
|
|
|
__attribute__((noipa)) int
|
|
bar (void)
|
|
{
|
|
int s = 0;
|
|
#pragma omp parallel
|
|
#pragma omp for simd reduction (inscan, foo:s)
|
|
for (int i = 0; i < 1024; i++)
|
|
{
|
|
s += 2 * a[i];
|
|
#pragma omp scan inclusive(s)
|
|
b[i] = s;
|
|
}
|
|
return s;
|
|
}
|
|
|
|
__attribute__((noipa)) void
|
|
baz (int *a, int *b)
|
|
{
|
|
#pragma omp parallel for simd reduction (inscan, foo:r)
|
|
for (int i = 0; i < 1024; i++)
|
|
{
|
|
r += a[i];
|
|
#pragma omp scan inclusive(r)
|
|
b[i] = r;
|
|
}
|
|
}
|
|
|
|
__attribute__((noipa)) int
|
|
qux (void)
|
|
{
|
|
int s = 0;
|
|
#pragma omp parallel for simd if (simd: 0) reduction (inscan, foo:s)
|
|
for (int i = 0; i < 1024; i++)
|
|
{
|
|
s += 2 * a[i];
|
|
#pragma omp scan inclusive(s)
|
|
b[i] = s;
|
|
}
|
|
return s;
|
|
}
|
|
|
|
int
|
|
main ()
|
|
{
|
|
int s = 0;
|
|
for (int i = 0; i < 1024; ++i)
|
|
{
|
|
a[i] = i;
|
|
b[i] = -1;
|
|
asm ("" : "+g" (i));
|
|
}
|
|
#pragma omp parallel
|
|
foo (a, b);
|
|
if (r != 1024 * 1023 / 2)
|
|
abort ();
|
|
for (int i = 0; i < 1024; ++i)
|
|
{
|
|
s += i;
|
|
if (b[i] != s)
|
|
abort ();
|
|
else
|
|
b[i] = 25;
|
|
}
|
|
if (bar () != 1024 * 1023)
|
|
abort ();
|
|
s = 0;
|
|
for (int i = 0; i < 1024; ++i)
|
|
{
|
|
s += 2 * i;
|
|
if (b[i] != s)
|
|
abort ();
|
|
else
|
|
b[i] = -1;
|
|
}
|
|
r = 0;
|
|
baz (a, b);
|
|
if (r != 1024 * 1023 / 2)
|
|
abort ();
|
|
s = 0;
|
|
for (int i = 0; i < 1024; ++i)
|
|
{
|
|
s += i;
|
|
if (b[i] != s)
|
|
abort ();
|
|
else
|
|
b[i] = -25;
|
|
}
|
|
if (qux () != 1024 * 1023)
|
|
abort ();
|
|
s = 0;
|
|
for (int i = 0; i < 1024; ++i)
|
|
{
|
|
s += 2 * i;
|
|
if (b[i] != s)
|
|
abort ();
|
|
}
|
|
return 0;
|
|
}
|