projects / gcc.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 7705dfd) | patch
re PR tree-optimization/61403 (An opportunity for x86 gcc vectorizer (~40% gain))
authorJakub Jelinek <jakub@redhat.com>
Fri, 3 Oct 2014 18:16:09 +0000 (20:16 +0200)
committerJakub Jelinek <jakub@gcc.gnu.org>
Fri, 3 Oct 2014 18:16:09 +0000 (20:16 +0200)
commit76e06b73eeb9c3c01a6e360825454e1810c96b55
tree2c961bb0d0ad39f2f4cb513d06c39347a9bd3159tree
parent7705dfd11ffaabc5eeb7e7da66e138258a6594eacommit | diff
re PR tree-optimization/61403 (An opportunity for x86 gcc vectorizer (~40% gain))

PR tree-optimization/61403
* config/i386/i386.c (expand_vec_perm_palignr): Fix a spelling
error in comment.  Also optimize 256-bit vectors for AVX2
or AVX (floating vectors only), provided the first permutation
can be performed in one insn.

* gcc.dg/torture/vshuf-32.inc: Add a new test 29.

Co-Authored-By: Uros Bizjak <ubizjak@gmail.com>
From-SVN: r215866
gcc/ChangeLog diff | blob | history
gcc/config/i386/i386.c diff | blob | history
gcc/testsuite/ChangeLog diff | blob | history
gcc/testsuite/gcc.dg/torture/vshuf-32.inc diff | blob | history