diff options
| author | Richard Sandiford <richard.sandiford@arm.com> | 2019-01-07 16:00:52 +0000 |
|---|---|---|
| committer | Richard Sandiford <rsandifo@gcc.gnu.org> | 2019-01-07 16:00:52 +0000 |
| commit | 18fd43b95264a7244b50fd34cf983f4d78c208dc (patch) | |
| tree | 172176ce412363181232105e2e60d4016975e8a3 /gcc | |
| parent | e002afaa8e01395110c77de18bb7e0fa030ba019 (diff) | |
| download | gcc-18fd43b95264a7244b50fd34cf983f4d78c208dc.zip gcc-18fd43b95264a7244b50fd34cf983f4d78c208dc.tar.gz gcc-18fd43b95264a7244b50fd34cf983f4d78c208dc.tar.bz2 | |
Fix ICE in get_initial_defs_for_reduction (PR 88567)
The use of "j" in:
init = permute_results[number_of_vectors - j - 1];
was out-of-sync with the new flat loop structure. Now that all that
reversing is gone, we can just use the result of duplicate_and_interleave
directly.
The other cases shouldn't be affected by postponing the insertion
of ctor_seq, since gimple_build* appends to the seq without clearing
it first (unlike some of the gimplify routines).
The ICE is already covered by gcc.dg/vect/pr63379.c.
2019-01-07 Richard Sandiford <richard.sandiford@arm.com>
gcc/
PR middle-end/88567
* tree-vect-loop.c (get_initial_defs_for_reduction): Pass the
output vector directly to duplicate_and_interleave instead of
going through a temporary. Postpone insertion of ctor_seq to
the end of the loop.
From-SVN: r267652
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/ChangeLog | 8 | ||||
| -rw-r--r-- | gcc/tree-vect-loop.c | 18 |
2 files changed, 15 insertions, 11 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 0aad583..c236588 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,11 @@ +2019-01-07 Richard Sandiford <richard.sandiford@arm.com> + + PR middle-end/88567 + * tree-vect-loop.c (get_initial_defs_for_reduction): Pass the + output vector directly to duplicate_and_interleave instead of + going through a temporary. Postpone insertion of ctor_seq to + the end of the loop. + 2019-01-07 Richard Earnshaw <rearnsha@arm.com> PR target/86891 diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index 6dafb86..afbf9a9 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -4103,7 +4103,6 @@ get_initial_defs_for_reduction (slp_tree slp_node, unsigned int group_size = stmts.length (); unsigned int i; struct loop *loop; - auto_vec<tree, 16> permute_results; vector_type = STMT_VINFO_VECTYPE (stmt_vinfo); @@ -4138,6 +4137,7 @@ get_initial_defs_for_reduction (slp_tree slp_node, bool constant_p = true; tree_vector_builder elts (vector_type, nunits, 1); elts.quick_grow (nunits); + gimple_seq ctor_seq = NULL; for (j = 0; j < nunits * number_of_vectors; ++j) { tree op; @@ -4163,7 +4163,6 @@ get_initial_defs_for_reduction (slp_tree slp_node, if (number_of_places_left_in_vector == 0) { - gimple_seq ctor_seq = NULL; tree init; if (constant_p && !neutral_op ? multiple_p (TYPE_VECTOR_SUBPARTS (vector_type), nunits) @@ -4189,16 +4188,11 @@ get_initial_defs_for_reduction (slp_tree slp_node, else { /* First time round, duplicate ELTS to fill the - required number of vectors, then cherry pick the - appropriate result for each iteration. */ - if (vec_oprnds->is_empty ()) - duplicate_and_interleave (&ctor_seq, vector_type, elts, - number_of_vectors, - permute_results); - init = permute_results[number_of_vectors - j - 1]; + required number of vectors. */ + duplicate_and_interleave (&ctor_seq, vector_type, elts, + number_of_vectors, *vec_oprnds); + break; } - if (ctor_seq != NULL) - gsi_insert_seq_on_edge_immediate (pe, ctor_seq); vec_oprnds->quick_push (init); number_of_places_left_in_vector = nunits; @@ -4207,6 +4201,8 @@ get_initial_defs_for_reduction (slp_tree slp_node, constant_p = true; } } + if (ctor_seq != NULL) + gsi_insert_seq_on_edge_immediate (pe, ctor_seq); } |