tree-optimization/110742 - fix latent issue with permuting existing vectors
Checks
Commit Message
When we materialize a layout we push edge permutes to constant/external
defs without checking we can actually do so. For externals defined
by vector stmts rather than scalar components we can't.
Bootstrapped and tested on x86_64-unknown-linux-gnu.
OK?
Thanks,
Richard.
PR tree-optimization/110742
* tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
Do not materialize an edge permutation in an external node with
vector defs.
(vect_slp_analyze_node_operations_1): Guard purely internal
nodes better.
* g++.dg/torture/pr110742.C: New testcase.
---
gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
gcc/tree-vect-slp.cc | 8 +++--
2 files changed, 53 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C
new file mode 100644
@@ -0,0 +1,47 @@
+// { dg-do compile }
+
+struct HARD_REG_SET {
+ HARD_REG_SET operator~() const {
+ HARD_REG_SET res;
+ for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
+ res.elts[i] = ~elts[i];
+ return res;
+ }
+ HARD_REG_SET operator&(const HARD_REG_SET &other) const {
+ HARD_REG_SET res;
+ for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
+ res.elts[i] = elts[i] & other.elts[i];
+ return res;
+ }
+ unsigned long elts[4];
+};
+typedef const HARD_REG_SET &const_hard_reg_set;
+inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
+ unsigned long bad = 0;
+ for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
+ bad |= (x.elts[i] & ~y.elts[i]);
+ return bad == 0;
+}
+inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
+ unsigned long bad = 0;
+ for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
+ bad |= x.elts[i];
+ return bad == 0;
+}
+extern HARD_REG_SET rr[2];
+extern int t[2];
+extern HARD_REG_SET nn;
+static HARD_REG_SET mm;
+void setup_reg_class_relations(void) {
+ HARD_REG_SET intersection_set, union_set, temp_set2;
+ for (int cl2 = 0; cl2 < 2; cl2++) {
+ temp_set2 = rr[cl2] & ~nn;
+ if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
+ mm = rr[0] & nn;
+ if (hard_reg_set_subset_p(mm, intersection_set))
+ if (!hard_reg_set_subset_p(mm, temp_set2) ||
+ hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
+ t[cl2] = 0;
+ }
+ }
+}
@@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
return result;
if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
- || SLP_TREE_DEF_TYPE (node) == vect_external_def)
+ || (SLP_TREE_DEF_TYPE (node) == vect_external_def
+ && (to_layout_i == 0
+ /* We can't permute vector defs. */
+ || SLP_TREE_VEC_DEFS (node).is_empty ())))
{
/* If the vector is uniform or unchanged, there's nothing to do. */
if (to_layout_i == 0 || vect_slp_tree_uniform_p (node))
@@ -5944,7 +5947,8 @@ vect_slp_analyze_node_operations_1 (vec_info *vinfo, slp_tree node,
calculated by the recursive call). Otherwise it is the number of
scalar elements in one scalar iteration (DR_GROUP_SIZE) multiplied by
VF divided by the number of elements in a vector. */
- if (!STMT_VINFO_DATA_REF (stmt_info)
+ if (SLP_TREE_CODE (node) != VEC_PERM_EXPR
+ && !STMT_VINFO_DATA_REF (stmt_info)
&& REDUC_GROUP_FIRST_ELEMENT (stmt_info))
{
for (unsigned i = 0; i < SLP_TREE_CHILDREN (node).length (); ++i)