1f52d1a8b5
* omp-low.c (struct omp_context): Add for_simd_scan_phase member. (maybe_lookup_ctx): Add forward declaration. (omp_find_scan): Likewise. Walk into body of simd if composited with worksharing loop. (scan_omp_simd_scan): New function. (scan_omp_1_stmt): Call it. (lower_rec_simd_input_clauses): Don't create rvar nor rvar2 if ctx->for_simd_scan_phase. (lower_rec_input_clauses): Do much less work for inscan reductions in ctx->for_simd_scan_phase is_simd regions. (lower_omp_scan): Set is_simd also on simd constructs composited with worksharing loop, unless ctx->for_simd_scan_phase. Never emit a sorry message. Don't change GIMPLE_OMP_SCAN stmts into nops and emit their body after in simd constructs composited with worksharing loop. (lower_omp_for_scan): Handle worksharing loop composited with simd. * c-c++-common/gomp/scan-4.c: Don't expect sorry message. * testsuite/libgomp.c/scan-11.c: New test. * testsuite/libgomp.c/scan-12.c: New test. * testsuite/libgomp.c/scan-13.c: New test. * testsuite/libgomp.c/scan-14.c: New test. * testsuite/libgomp.c/scan-15.c: New test. * testsuite/libgomp.c/scan-16.c: New test. * testsuite/libgomp.c/scan-17.c: New test. * testsuite/libgomp.c/scan-18.c: New test. * testsuite/libgomp.c++/scan-9.C: New test. * testsuite/libgomp.c++/scan-10.C: New test. * testsuite/libgomp.c++/scan-11.C: New test. * testsuite/libgomp.c++/scan-12.C: New test. * testsuite/libgomp.c++/scan-13.C: New test. * testsuite/libgomp.c++/scan-14.C: New test. * testsuite/libgomp.c++/scan-15.C: New test. * testsuite/libgomp.c++/scan-16.C: New test. From-SVN: r273157
120 lines
2.1 KiB
C
120 lines
2.1 KiB
C
// { dg-require-effective-target size32plus }
|
|
// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
|
|
// { 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;
|
|
|
|
__attribute__((noipa)) void
|
|
foo (int *a, int *b, int &r)
|
|
{
|
|
#pragma omp for simd if (0) reduction (inscan, +:r) nowait
|
|
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 = q;
|
|
q = 0;
|
|
#pragma omp parallel
|
|
#pragma omp for simd simdlen(1) reduction (inscan, +:s) nowait
|
|
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, int &r)
|
|
{
|
|
#pragma omp parallel for simd reduction (inscan, +: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 = q;
|
|
q = 0;
|
|
#pragma omp parallel for simd reduction (inscan, +: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, r);
|
|
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, r);
|
|
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 ();
|
|
}
|
|
}
|