gcc/libgomp/testsuite/libgomp.c++/scan-15.C
Jakub Jelinek 0ad7981cb4 re PR libgomp/91530 (Several libgomp.*/scan-* tests FAIL without avx_runtime)
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
2019-08-27 12:45:55 +02:00

123 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 "C" void abort ();
int r, a[1024], b[1024], q;
#pragma omp declare reduction (foo: int: omp_out += omp_in) initializer (omp_priv = 0)
__attribute__((noipa)) void
foo (int *a, int *b, int &r)
{
#pragma omp for simd reduction (inscan, foo:r)
for (int i = 0; i < 1024; i++)
{
b[i] = r;
#pragma omp scan exclusive(r)
r += a[i];
}
}
__attribute__((noipa)) int
bar (void)
{
int &s = q;
q = 0;
#pragma omp parallel
#pragma omp for simd reduction (inscan, foo:s) nowait
for (int i = 0; i < 1024; i++)
{
b[i] = s;
#pragma omp scan exclusive(s)
s += 2 * a[i];
}
return s;
}
__attribute__((noipa)) void
baz (int *a, int *b, int &r)
{
#pragma omp parallel for simd reduction (inscan, foo:r) if (simd: 0)
for (int i = 0; i < 1024; i++)
{
b[i] = r;
#pragma omp scan exclusive(r)
r += a[i];
}
}
__attribute__((noipa)) int
qux (void)
{
int &s = q;
q = 0;
#pragma omp parallel for simd reduction (inscan, foo:s)simdlen(1)
for (int i = 0; i < 1024; i++)
{
b[i] = s;
#pragma omp scan exclusive(s)
s += 2 * a[i];
}
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, r);
if (r != 1024 * 1023 / 2)
abort ();
for (int i = 0; i < 1024; ++i)
{
if (b[i] != s)
abort ();
else
b[i] = 25;
s += i;
}
if (bar () != 1024 * 1023)
abort ();
s = 0;
for (int i = 0; i < 1024; ++i)
{
if (b[i] != s)
abort ();
else
b[i] = -1;
s += 2 * i;
}
r = 0;
baz (a, b, r);
if (r != 1024 * 1023 / 2)
abort ();
s = 0;
for (int i = 0; i < 1024; ++i)
{
if (b[i] != s)
abort ();
else
b[i] = -25;
s += i;
}
if (qux () != 1024 * 1023)
abort ();
s = 0;
for (int i = 0; i < 1024; ++i)
{
if (b[i] != s)
abort ();
s += 2 * i;
}
}