On Thu, Sep 27, 2018 at 07:38:20PM +0200, Jakub Jelinek wrote:
> task-reduction-5.C testcase still fails, need to fix up passing of the
> remapped original address properly even for C/C++ array reductions.
Fixed thusly, committed to gomp-5_0-branch.
2018-09-27 Jakub Jelinek <ja...@redhat.com>
* omp-low.c (lower_rec_input_clauses): Fix handling of
OMP_CLAUSE_REDUCTION_OMP_ORIG_REF for task array reductions.
libgomp/
* testsuite/libgomp.c++/task-reduction-5.C (main): Add forgotten
checks.
* testsuite/libgomp.c++/task-reduction-6.C: New test.
--- gcc/omp-low.c.jj 2018-09-27 18:26:31.960486678 +0200
+++ gcc/omp-low.c 2018-09-27 21:13:24.946076732 +0200
@@ -4096,36 +4096,51 @@ lower_rec_input_clauses (tree clauses, g
tree i2 = NULL_TREE, y2 = NULL_TREE;
tree body2 = NULL_TREE, end2 = NULL_TREE;
tree y3 = NULL_TREE, y4 = NULL_TREE;
- if (OMP_CLAUSE_REDUCTION_PLACEHOLDER (c) || is_simd)
+ if (task_reduction_needs_orig_p)
{
- y2 = create_tmp_var (ptype, NULL);
- gimplify_assign (y2, y, ilist);
- tree ref = build_outer_var_ref (var, ctx);
- /* For ref build_outer_var_ref already performs this. */
- if (TREE_CODE (d) == INDIRECT_REF)
- gcc_assert (omp_is_reference (var));
- else if (TREE_CODE (d) == ADDR_EXPR)
- ref = build_fold_addr_expr (ref);
- else if (omp_is_reference (var))
- ref = build_fold_addr_expr (ref);
- ref = fold_convert_loc (clause_loc, ptype, ref);
- if (OMP_CLAUSE_REDUCTION_PLACEHOLDER (c)
- && OMP_CLAUSE_REDUCTION_OMP_ORIG_REF (c))
+ tree ref = build4 (ARRAY_REF, ptr_type_node, tskred_avar,
+ size_int (task_reduction_cnt_full
+ + task_reduction_cntorig - 1),
+ NULL_TREE, NULL_TREE);
+ y3 = create_tmp_var (ptype, NULL);
+ gimplify_assign (y3, ref, ilist);
+ }
+ else if (OMP_CLAUSE_REDUCTION_PLACEHOLDER (c) || is_simd)
+ {
+ if (pass != 3)
{
- y3 = create_tmp_var (ptype, NULL);
- gimplify_assign (y3, unshare_expr (ref), ilist);
+ y2 = create_tmp_var (ptype, NULL);
+ gimplify_assign (y2, y, ilist);
}
- if (is_simd)
+ if (is_simd || OMP_CLAUSE_REDUCTION_OMP_ORIG_REF (c))
{
- y4 = create_tmp_var (ptype, NULL);
- gimplify_assign (y4, ref, dlist);
+ tree ref = build_outer_var_ref (var, ctx);
+ /* For ref build_outer_var_ref already performs this. */
+ if (TREE_CODE (d) == INDIRECT_REF)
+ gcc_assert (omp_is_reference (var));
+ else if (TREE_CODE (d) == ADDR_EXPR)
+ ref = build_fold_addr_expr (ref);
+ else if (omp_is_reference (var))
+ ref = build_fold_addr_expr (ref);
+ ref = fold_convert_loc (clause_loc, ptype, ref);
+ if (OMP_CLAUSE_REDUCTION_PLACEHOLDER (c)
+ && OMP_CLAUSE_REDUCTION_OMP_ORIG_REF (c))
+ {
+ y3 = create_tmp_var (ptype, NULL);
+ gimplify_assign (y3, unshare_expr (ref), ilist);
+ }
+ if (is_simd)
+ {
+ y4 = create_tmp_var (ptype, NULL);
+ gimplify_assign (y4, ref, dlist);
+ }
}
}
tree i = create_tmp_var (TREE_TYPE (v), NULL);
gimplify_assign (i, build_int_cst (TREE_TYPE (v), 0), ilist);
tree body = create_artificial_label (UNKNOWN_LOCATION);
gimple_seq_add_stmt (ilist, gimple_build_label (body));
- if (y2 && pass != 3)
+ if (y2)
{
i2 = create_tmp_var (TREE_TYPE (v), NULL);
gimplify_assign (i2, build_int_cst (TREE_TYPE (v), 0), dlist);
@@ -4170,7 +4185,7 @@ lower_rec_input_clauses (tree clauses, g
}
DECL_HAS_VALUE_EXPR_P (placeholder) = 0;
DECL_HAS_VALUE_EXPR_P (decl_placeholder) = 0;
- if (pass != 3)
+ if (y2)
{
x = lang_hooks.decls.omp_clause_dtor
(c, build_simple_mem_ref (y2));
@@ -4218,7 +4233,7 @@ lower_rec_input_clauses (tree clauses, g
g = gimple_build_cond (LE_EXPR, i, v, body, end);
gimple_seq_add_stmt (ilist, g);
gimple_seq_add_stmt (ilist, gimple_build_label (end));
- if (y2 && pass != 3)
+ if (y2)
{
g = gimple_build_assign (y2, POINTER_PLUS_EXPR, y2,
TYPE_SIZE_UNIT (TREE_TYPE (type)));
--- libgomp/testsuite/libgomp.c++/task-reduction-5.C.jj 2018-09-27
18:59:16.036667969 +0200
+++ libgomp/testsuite/libgomp.c++/task-reduction-5.C 2018-09-27
20:01:17.366563819 +0200
@@ -312,6 +312,9 @@ test (int n)
int
main ()
{
+ int c1 = S::cnt1, c2 = S::cnt2, c3 = S::cnt3;
test (1);
+ if (S::cnt1 + S::cnt2 - c1 - c2 != S::cnt3 - c3)
+ abort ();
return 0;
}
--- libgomp/testsuite/libgomp.c++/task-reduction-6.C.jj 2018-09-27
20:08:49.003006631 +0200
+++ libgomp/testsuite/libgomp.c++/task-reduction-6.C 2018-09-27
21:01:19.599216946 +0200
@@ -0,0 +1,341 @@
+extern "C" void abort ();
+
+struct S { S (); S (long int, long int); ~S (); static int cnt1, cnt2, cnt3;
long int s, t; };
+
+int S::cnt1;
+int S::cnt2;
+int S::cnt3;
+
+S::S ()
+{
+ #pragma omp atomic
+ cnt1++;
+}
+
+S::S (long int x, long int y) : s (x), t (y)
+{
+ #pragma omp atomic update
+ ++cnt2;
+}
+
+S::~S ()
+{
+ #pragma omp atomic
+ cnt3 = cnt3 + 1;
+ if (t < 3 || t > 9 || (t & 1) == 0)
+ abort ();
+}
+
+void
+bar (S *p, S *o)
+{
+ p->s = 1;
+ if (o->t != 5)
+ abort ();
+ p->t = 9;
+}
+
+static inline void
+baz (S *o, S *i)
+{
+ if (o->t != 5 || i->t != 9)
+ abort ();
+ o->s *= i->s;
+}
+
+#pragma omp declare reduction (+: S : omp_out.s += omp_in.s) initializer
(omp_priv (0, 3))
+#pragma omp declare reduction (*: S : baz (&omp_out, &omp_in)) initializer
(bar (&omp_priv, &omp_orig))
+
+S as[2] = { { 0, 7 }, { 0, 7 } };
+S (&a)[2] = as;
+S bs[7] = { { 9, 5 }, { 11, 5 }, { 1, 5 }, { 1, 5 }, { 1, 5 }, { 13, 5 }, {
15, 5 } };
+S (&b)[7] = bs;
+S es[3] = { { 5, 7 }, { 0, 7 }, { 5, 7 } };
+S (&e)[3] = es;
+S fs[5] = { { 6, 7 }, { 7, 7 }, { 0, 7 }, { 0, 7 }, { 9, 7 } };
+S (&f)[5] = fs;
+S gs[4] = { { 1, 7 }, { 0, 7 }, { 0, 7 }, { 2, 7 } };
+S (&g)[4] = gs;
+S hs[3] = { { 0, 7 }, { 1, 7 }, { 4, 7 } };
+S (&h)[3] = hs;
+S ks[4][2] = { { { 5, 7 }, { 6, 7 } }, { { 0, 7 }, { 0, 7 } }, { { 0, 7 }, {
0, 7 } }, { { 7, 7 }, { 8, 7 } } };
+S (&k)[4][2] = ks;
+S *ss;
+S *&s = ss;
+S (*ts)[2];
+S (*&t)[2] = ts;
+
+void
+foo (int &n, S *&c, S *&d, S (&m)[3], S *&r, S (&o)[4], S *&p, S (&q)[4][2])
+{
+ int i;
+ for (i = 0; i < 2; i++)
+ #pragma omp task in_reduction (+: a, c[:2]) in_reduction (*: b[2 * n:3 *
n], d[0:2]) \
+ in_reduction (+: o[n:n*2], m[1], k[1:2][:], p[0], f[2:2]) \
+ in_reduction (+: q[1:2][:], g[n:n*2], e[1], h[0], r[2:2]) \
+ in_reduction (*: s[1:2], t[2:2][:])
+ {
+ a[0].s += 7;
+ a[1].s += 17;
+ b[2].s *= 2;
+ b[4].s *= 2;
+ c[0].s += 6;
+ d[1].s *= 2;
+ e[1].s += 19;
+ f[2].s += 21;
+ f[3].s += 23;
+ g[1].s += 25;
+ g[2].s += 27;
+ h[0].s += 29;
+ k[1][0].s += 31;
+ k[2][1].s += 33;
+ m[1].s += 19;
+ r[2].s += 21;
+ r[3].s += 23;
+ o[1].s += 25;
+ o[2].s += 27;
+ p[0].s += 29;
+ q[1][0].s += 31;
+ q[2][1].s += 33;
+ s[1].s *= 2;
+ t[2][0].s *= 2;
+ t[3][1].s *= 2;
+ if ((e[1].t != 7 && e[1].t != 3) || (h[0].t != 7 && h[0].t != 3)
+ || (m[1].t != 7 && m[1].t != 3) || (p[0].t != 7 && p[0].t != 3))
+ abort ();
+ for (int z = 0; z < 2; z++)
+ if ((a[z].t != 7 && a[z].t != 3) || (c[z].t != 7 && c[z].t != 3)
+ || (d[z].t != 5 && d[z].t != 9) || (f[z + 2].t != 7 && f[z + 2].t
!= 3)
+ || (g[z + 1].t != 7 && g[z + 1].t != 3) || (r[z + 2].t != 7 && r[z
+ 2].t != 3)
+ || (s[z + 1].t != 5 && s[z + 1].t != 9) || (o[z + 1].t != 7 && o[z
+ 1].t != 3)
+ || (k[z + 1][0].t != 7 && k[z + 1][0].t != 3) || (k[z + 1][1].t !=
7 && k[z + 1][1].t != 3)
+ || (q[z + 1][0].t != 7 && q[z + 1][0].t != 3) || (q[z + 1][1].t !=
7 && q[z + 1][1].t != 3)
+ || (t[z + 2][0].t != 5 && t[z + 2][0].t != 9) || (t[z + 2][1].t !=
5 && t[z + 2][1].t != 9))
+ abort ();
+ for (int z = 0; z < 3; z++)
+ if (b[z + 2].t != 5 && b[z + 2].t != 9)
+ abort ();
+ }
+}
+
+void
+test (int &n)
+{
+ S cs[2] = { { 0, 7 }, { 0, 7 } };
+ S (&c)[2] = cs;
+ S ps[3] = { { 0, 7 }, { 1, 7 }, { 4, 7 } };
+ S (&p)[3] = ps;
+ S qs[4][2] = { { { 5, 7 }, { 6, 7 } }, { { 0, 7 }, { 0, 7 } }, { { 0, 7 }, {
0, 7 } }, { { 7, 7 }, { 8, 7 } } };
+ S (&q)[4][2] = qs;
+ S sb[4] = { { 5, 5 }, { 1, 5 }, { 1, 5 }, { 6, 5 } };
+ S tb[5][2] = { { { 9, 5 }, { 10, 5 } }, { { 11, 5 }, { 12, 5 } }, { { 1, 5
}, { 1, 5 } }, { { 1, 5 }, { 1, 5 } }, { { 13, 5 }, { 14, 5 } } };
+ S ms[3] = { { 5, 7 }, { 0, 7 }, { 5, 7 } };
+ S os[4] = { { 1, 7 }, { 0, 7 }, { 0, 7 }, { 2, 7 } };
+ s = sb;
+ t = tb;
+ #pragma omp parallel
+ #pragma omp single
+ {
+ S ds[] = { { 1, 5 }, { 1, 5 } };
+ S (&d)[2] = ds;
+ S (&m)[3] = ms;
+ S rs[5] = { { 6, 7 }, { 7, 7 }, { 0, 7 }, { 0, 7 }, { 9, 7 } };
+ S (&r)[5] = rs;
+ S (&o)[4] = os;
+ #pragma omp taskgroup task_reduction (+: a, c) task_reduction (*: b[2 *
n:3 * n], d) \
+ task_reduction (+: e[1], f[2:2], g[n:n*2], h[0],
k[1:2][0:2]) \
+ task_reduction (+: o[n:n*2], m[1], q[1:2][:], p[0],
r[2:2]) \
+ task_reduction (*: t[2:2][:], s[1:n + 1])
+ {
+ int i;
+ for (i = 0; i < 4; i++)
+ #pragma omp task in_reduction (+: a, c) in_reduction (*: b[2 * n:3 *
n], d) \
+ in_reduction (+: o[n:n*2], q[1:2][:], p[0], m[1],
r[2:2]) \
+ in_reduction (+: g[n:n * 2], e[1], k[1:2][:], h[0],
f[2:2]) \
+ in_reduction (*: s[1:2], t[2:2][:])
+ {
+ int j;
+ a[0].s += 2;
+ a[1].s += 3;
+ b[2].s *= 2;
+ f[3].s += 8;
+ g[1].s += 9;
+ g[2].s += 10;
+ h[0].s += 11;
+ k[1][1].s += 13;
+ k[2][1].s += 15;
+ m[1].s += 16;
+ r[2].s += 8;
+ s[1].s *= 2;
+ t[2][1].s *= 2;
+ t[3][1].s *= 2;
+ if ((e[1].t != 7 && e[1].t != 3) || (h[0].t != 7 && h[0].t != 3)
+ || (m[1].t != 7 && m[1].t != 3) || (p[0].t != 7 && p[0].t != 3))
+ abort ();
+ for (int z = 0; z < 2; z++)
+ if ((a[z].t != 7 && a[z].t != 3) || (c[z].t != 7 && c[z].t != 3)
+ || (d[z].t != 5 && d[z].t != 9) || (f[z + 2].t != 7 && f[z +
2].t != 3)
+ || (g[z + 1].t != 7 && g[z + 1].t != 3) || (r[z + 2].t != 7 &&
r[z + 2].t != 3)
+ || (s[z + 1].t != 5 && s[z + 1].t != 9) || (o[z + 1].t != 7 &&
o[z + 1].t != 3)
+ || (k[z + 1][0].t != 7 && k[z + 1][0].t != 3) || (k[z + 1][1].t
!= 7 && k[z + 1][1].t != 3)
+ || (q[z + 1][0].t != 7 && q[z + 1][0].t != 3) || (q[z + 1][1].t
!= 7 && q[z + 1][1].t != 3)
+ || (t[z + 2][0].t != 5 && t[z + 2][0].t != 9) || (t[z + 2][1].t
!= 5 && t[z + 2][1].t != 9))
+ abort ();
+ for (int z = 0; z < 3; z++)
+ if (b[z + 2].t != 5 && b[z + 2].t != 9)
+ abort ();
+ for (j = 0; j < 2; j++)
+ #pragma omp task in_reduction (+: a, c[:2]) \
+ in_reduction (*: b[2 * n:3 * n], d[n - 1:n + 1]) \
+ in_reduction (+: e[1], f[2:2], g[n:n*2], h[0],
k[1:2][:2]) \
+ in_reduction (+: m[1], r[2:2], o[n:n*2], p[0],
q[1:2][:2]) \
+ in_reduction (*: s[n:2], t[2:2][:])
+ {
+ m[1].s += 6;
+ r[2].s += 7;
+ q[1][0].s += 17;
+ q[2][0].s += 19;
+ a[0].s += 4;
+ a[1].s += 5;
+ b[3].s *= 2;
+ b[4].s *= 2;
+ f[3].s += 18;
+ g[1].s += 29;
+ g[2].s += 18;
+ h[0].s += 19;
+ s[2].s *= 2;
+ t[2][0].s *= 2;
+ t[3][0].s *= 2;
+ S *cp = c;
+ S *dp = d;
+ S *rp = r;
+ S *pp = p;
+ if ((e[1].t != 7 && e[1].t != 3) || (h[0].t != 7 && h[0].t != 3)
+ || (m[1].t != 7 && m[1].t != 3) || (p[0].t != 7 && p[0].t !=
3))
+ abort ();
+ for (int z = 0; z < 2; z++)
+ if ((a[z].t != 7 && a[z].t != 3) || (c[z].t != 7 && c[z].t != 3)
+ || (d[z].t != 5 && d[z].t != 9) || (f[z + 2].t != 7 && f[z
+ 2].t != 3)
+ || (g[z + 1].t != 7 && g[z + 1].t != 3) || (r[z + 2].t != 7
&& r[z + 2].t != 3)
+ || (s[z + 1].t != 5 && s[z + 1].t != 9) || (o[z + 1].t != 7
&& o[z + 1].t != 3)
+ || (k[z + 1][0].t != 7 && k[z + 1][0].t != 3) || (k[z +
1][1].t != 7 && k[z + 1][1].t != 3)
+ || (q[z + 1][0].t != 7 && q[z + 1][0].t != 3) || (q[z +
1][1].t != 7 && q[z + 1][1].t != 3)
+ || (t[z + 2][0].t != 5 && t[z + 2][0].t != 9) || (t[z +
2][1].t != 5 && t[z + 2][1].t != 9))
+ abort ();
+ for (int z = 0; z < 3; z++)
+ if (b[z + 2].t != 5 && b[z + 2].t != 9)
+ abort ();
+ foo (n, cp, dp, m, rp, o, pp, q);
+ r[3].s += 18;
+ o[1].s += 29;
+ o[2].s += 18;
+ p[0].s += 19;
+ c[0].s += 4;
+ c[1].s += 5;
+ d[0].s *= 2;
+ e[1].s += 6;
+ f[2].s += 7;
+ k[1][0].s += 17;
+ k[2][0].s += 19;
+ }
+ r[3].s += 8;
+ o[1].s += 9;
+ o[2].s += 10;
+ p[0].s += 11;
+ q[1][1].s += 13;
+ q[2][1].s += 15;
+ b[3].s *= 2;
+ c[0].s += 4;
+ c[1].s += 9;
+ d[0].s *= 2;
+ e[1].s += 16;
+ f[2].s += 8;
+ }
+ }
+ if (d[0].s != 1LL << (8 + 4)
+ || d[1].s != 1LL << 16
+ || m[0].s != 5
+ || m[1].s != 19 * 16 + 6 * 8 + 16 * 4
+ || m[2].s != 5
+ || r[0].s != 6
+ || r[1].s != 7
+ || r[2].s != 21 * 16 + 7 * 8 + 8 * 4
+ || r[3].s != 23 * 16 + 18 * 8 + 8 * 4
+ || r[4].s != 9
+ || o[0].s != 1
+ || o[1].s != 25 * 16 + 29 * 8 + 9 * 4
+ || o[2].s != 27 * 16 + 18 * 8 + 10 * 4
+ || o[3].s != 2)
+ abort ();
+ if (e[1].t != 7 || h[0].t != 7 || m[1].t != 7 || p[0].t != 7)
+ abort ();
+ for (int z = 0; z < 2; z++)
+ if (a[z].t != 7 || c[z].t != 7 || d[z].t != 5 || f[z + 2].t != 7
+ || g[z + 1].t != 7 || r[z + 2].t != 7 || s[z + 1].t != 5 || o[z +
1].t != 7
+ || k[z + 1][0].t != 7 || k[z + 1][1].t != 7 || q[z + 1][0].t != 7 ||
q[z + 1][1].t != 7
+ || t[z + 2][0].t != 5 || t[z + 2][1].t != 5)
+ abort ();
+ for (int z = 0; z < 3; z++)
+ if (b[z + 2].t != 5)
+ abort ();
+ }
+ if (a[0].s != 7 * 16 + 4 * 8 + 2 * 4
+ || a[1].s != 17 * 16 + 5 * 8 + 3 * 4
+ || b[0].s != 9 || b[1].s != 11
+ || b[2].s != 1LL << (16 + 4)
+ || b[3].s != 1LL << (8 + 4)
+ || b[4].s != 1LL << (16 + 8)
+ || b[5].s != 13 || b[6].s != 15
+ || c[0].s != 6 * 16 + 4 * 8 + 4 * 4
+ || c[1].s != 5 * 8 + 9 * 4
+ || e[0].s != 5
+ || e[1].s != 19 * 16 + 6 * 8 + 16 * 4
+ || e[2].s != 5
+ || f[0].s != 6
+ || f[1].s != 7
+ || f[2].s != 21 * 16 + 7 * 8 + 8 * 4
+ || f[3].s != 23 * 16 + 18 * 8 + 8 * 4
+ || f[4].s != 9
+ || g[0].s != 1
+ || g[1].s != 25 * 16 + 29 * 8 + 9 * 4
+ || g[2].s != 27 * 16 + 18 * 8 + 10 * 4
+ || g[3].s != 2
+ || h[0].s != 29 * 16 + 19 * 8 + 11 * 4
+ || h[1].s != 1 || h[2].s != 4
+ || k[0][0].s != 5 || k[0][1].s != 6
+ || k[1][0].s != 31 * 16 + 17 * 8
+ || k[1][1].s != 13 * 4
+ || k[2][0].s != 19 * 8
+ || k[2][1].s != 33 * 16 + 15 * 4
+ || k[3][0].s != 7 || k[3][1].s != 8
+ || p[0].s != 29 * 16 + 19 * 8 + 11 * 4
+ || p[1].s != 1 || p[2].s != 4
+ || q[0][0].s != 5 || q[0][1].s != 6
+ || q[1][0].s != 31 * 16 + 17 * 8
+ || q[1][1].s != 13 * 4
+ || q[2][0].s != 19 * 8
+ || q[2][1].s != 33 * 16 + 15 * 4
+ || q[3][0].s != 7 || q[3][1].s != 8
+ || sb[0].s != 5
+ || sb[1].s != 1LL << (16 + 4)
+ || sb[2].s != 1LL << 8
+ || sb[3].s != 6
+ || tb[0][0].s != 9 || tb[0][1].s != 10 || tb[1][0].s != 11 || tb[1][1].s
!= 12
+ || tb[2][0].s != 1LL << (16 + 8)
+ || tb[2][1].s != 1LL << 4
+ || tb[3][0].s != 1LL << 8
+ || tb[3][1].s != 1LL << (16 + 4)
+ || tb[4][0].s != 13 || tb[4][1].s != 14)
+ abort ();
+}
+
+int
+main ()
+{
+ int c1 = S::cnt1, c2 = S::cnt2, c3 = S::cnt3;
+ int n = 1;
+ test (n);
+ if (S::cnt1 + S::cnt2 - c1 - c2 != S::cnt3 - c3)
+ abort ();
+ return 0;
+}
Jakub
