gcc/libgomp/testsuite/libgomp.c/scan-17.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

91 lines
2.0 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);
float r = 1.0f, a[1024], b[1024];
__attribute__((noipa)) void
foo (float *a, float *b)
{
#pragma omp for simd reduction (inscan, *:r)
for (int i = 0; i < 1024; i++)
{
b[i] = r;
#pragma omp scan exclusive(r)
r *= a[i];
}
}
__attribute__((noipa)) float
bar (void)
{
float s = -__builtin_inff ();
#pragma omp parallel for simd reduction (inscan, max:s)
for (int i = 0; i < 1024; i++)
{
b[i] = s;
#pragma omp scan exclusive(s)
s = s > a[i] ? s : a[i];
}
return s;
}
int
main ()
{
float s = 1.0f;
for (int i = 0; i < 1024; ++i)
{
if (i < 80)
a[i] = (i & 1) ? 0.25f : 0.5f;
else if (i < 200)
a[i] = (i % 3) == 0 ? 2.0f : (i % 3) == 1 ? 4.0f : 1.0f;
else if (i < 280)
a[i] = (i & 1) ? 0.25f : 0.5f;
else if (i < 380)
a[i] = (i % 3) == 0 ? 2.0f : (i % 3) == 1 ? 4.0f : 1.0f;
else
switch (i % 6)
{
case 0: a[i] = 0.25f; break;
case 1: a[i] = 2.0f; break;
case 2: a[i] = -1.0f; break;
case 3: a[i] = -4.0f; break;
case 4: a[i] = 0.5f; break;
case 5: a[i] = 1.0f; break;
default: a[i] = 0.0f; break;
}
b[i] = -19.0f;
asm ("" : "+g" (i));
}
#pragma omp parallel
foo (a, b);
if (r * 16384.0f != 0.125f)
abort ();
float m = -175.25f;
for (int i = 0; i < 1024; ++i)
{
if (b[i] != s)
abort ();
else
b[i] = -231.75f;
s *= a[i];
a[i] = m - ((i % 3) == 1 ? 2.0f : (i % 3) == 2 ? 4.0f : 0.0f);
m += 0.75f;
}
if (bar () != 592.0f)
abort ();
s = -__builtin_inff ();
for (int i = 0; i < 1024; ++i)
{
if (b[i] != s)
abort ();
if (s < a[i])
s = a[i];
}
return 0;
}