gcc/libgomp/testsuite/libgomp.oacc-c-c++-common/reduction-flt.c
Chung-Lin Tang 2c71d454eb re PR middle-end/70895 (OpenACC: loop reduction does not work. Output is zero.)
2016-08-18  Chung-Lin Tang  <cltang@codesourcery.com>

	PR middle-end/70895
	gcc/
	* gimplify.c (omp_add_variable): Adjust/add variable mapping on
	enclosing parallel construct for reduction variables on OpenACC loop
	directives.

	gcc/testsuite/
	* gfortran.dg/goacc/loop-tree-1.f90: Add gimple scan-tree-dump test.
	* c-c++-common/goacc/reduction-1.c: Likewise.
	* c-c++-common/goacc/reduction-2.c: Likewise.
	* c-c++-common/goacc/reduction-3.c: Likewise.
	* c-c++-common/goacc/reduction-4.c: Likewise.

	libgomp/
	* testsuite/libgomp.oacc-fortran/reduction-7.f90: Add explicit
	firstprivate clauses.
	* testsuite/libgomp.oacc-fortran/reduction-6.f90: Remove explicit
	copy clauses.
	* testsuite/libgomp.oacc-c-c++-common/reduction-7.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-cplx-flt.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-flt.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/collapse-2.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/loop-red-wv-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/collapse-4.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/loop-red-v-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-cplx-dbl.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/loop-red-g-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/loop-red-gwv-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/loop-red-w-1.c: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/reduction-dbl.c: Likewise.

From-SVN: r239576
2016-08-18 14:46:19 +00:00

113 lines
1.9 KiB
C

/* Single float has 23 bits of fraction. */
#define FRAC (1.0f / (1 << 20))
typedef float Type;
int close_enough (Type a, Type b)
{
Type diff = a - b;
if (diff < 0)
diff = -diff;
return diff / a < FRAC;
}
#define N 100
static int __attribute__ ((noinline))
vector (Type ary[N], Type sum, Type prod)
{
Type tsum = 0, tprod = 1;
#pragma acc parallel vector_length(32) copyin(ary[0:N])
{
#pragma acc loop vector reduction(+:tsum) reduction (*:tprod)
for (int ix = 0; ix < N; ix++)
{
tsum += ary[ix];
tprod *= ary[ix];
}
}
if (!close_enough (sum, tsum))
return 1;
if (!close_enough (prod, tprod))
return 1;
return 0;
}
static int __attribute__ ((noinline))
worker (Type ary[N], Type sum, Type prod)
{
Type tsum = 0, tprod = 1;
#pragma acc parallel num_workers(32) copyin(ary[0:N])
{
#pragma acc loop worker reduction(+:tsum) reduction (*:tprod)
for (int ix = 0; ix < N; ix++)
{
tsum += ary[ix];
tprod *= ary[ix];
}
}
if (!close_enough (sum, tsum))
return 1;
if (!close_enough (prod, tprod))
return 1;
return 0;
}
static int __attribute__ ((noinline))
gang (Type ary[N], Type sum, Type prod)
{
Type tsum = 0, tprod = 1;
#pragma acc parallel num_gangs (32) copyin(ary[0:N])
{
#pragma acc loop gang reduction(+:tsum) reduction (*:tprod)
for (int ix = 0; ix < N; ix++)
{
tsum += ary[ix];
tprod *= ary[ix];
}
}
if (!close_enough (sum, tsum))
return 1;
if (!close_enough (prod, tprod))
return 1;
return 0;
}
int main (void)
{
Type ary[N], sum = 0, prod = 1;
for (int ix = 0; ix < N; ix++)
{
float frac = ix * (1.0f / 1024) + 1.0f;
ary[ix] = frac;
sum += ary[ix];
prod *= ary[ix];
}
if (vector (ary, sum, prod))
return 1;
if (worker (ary, sum, prod))
return 1;
if (gang (ary, sum, prod))
return 1;
return 0;
}