This fixes the case where we try to fold a read from an
array initalizer and happen to cross the boundary of
multiple CTORs which isn't really supported. For the
interesting cases like the testcase we actually handle
the folding by encoding the whole initializer.
Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed.
2020-07-10 Richard Biener <rguent...@suse.de>
PR tree-optimization/96133
* gimple-fold.c (fold_array_ctor_reference): Do not
recurse to folding a CTOR that does not fully cover the
asked for object.
* gcc.dg/torture/pr96133.c: New testcase.
---
gcc/gimple-fold.c | 11 +++++++++--
gcc/testsuite/gcc.dg/torture/pr96133.c | 16 ++++++++++++++++
2 files changed, 25 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/torture/pr96133.c
diff --git a/gcc/gimple-fold.c b/gcc/gimple-fold.c
index 41b84ba3bb3..dfda6db5e96 100644
--- a/gcc/gimple-fold.c
+++ b/gcc/gimple-fold.c
@@ -6875,10 +6875,17 @@ fold_array_ctor_reference (tree type, tree ctor,
SIZE to the size of the accessed element. */
inner_offset = 0;
type = TREE_TYPE (val);
- size = elt_size.to_uhwi () * BITS_PER_UNIT;
+ size = elt_sz * BITS_PER_UNIT;
}
+ else if (size && access_index < CONSTRUCTOR_NELTS (ctor) - 1
+ && TREE_CODE (val) == CONSTRUCTOR
+ && (elt_sz * BITS_PER_UNIT - inner_offset) < size)
+ /* If this isn't the last element in the CTOR and a CTOR itself
+ and it does not cover the whole object we are requesting give up
+ since we're not set up for combining from multiple CTORs. */
+ return NULL_TREE;
- *suboff += (access_index * elt_size * BITS_PER_UNIT).to_uhwi ();
+ *suboff += access_index.to_uhwi () * elt_sz * BITS_PER_UNIT;
return fold_ctor_reference (type, val, inner_offset, size, from_decl,
suboff);
}
diff --git a/gcc/testsuite/gcc.dg/torture/pr96133.c
b/gcc/testsuite/gcc.dg/torture/pr96133.c
new file mode 100644
index 00000000000..8d051ce2913
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr96133.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+
+typedef int T;
+static const T a[2][3] = { { 1, 2, 3 }, { 4, 5, 6 } };
+typedef T v2 __attribute__((vector_size(2*sizeof(T))));
+
+int
+main()
+{
+ const T *p = &a[0][2];
+ v2 x = *(const v2 *)p;
+ T z = x[1];
+ if (z != 4)
+ __builtin_abort ();
+ return 0;
+}
--
2.26.2
