diff options
| author | Arnold Schwaighofer <aschwaighofer@apple.com> | 2013-07-11 15:21:55 +0000 |
|---|---|---|
| committer | Arnold Schwaighofer <aschwaighofer@apple.com> | 2013-07-11 15:21:55 +0000 |
| commit | 11eb51e23935e22e1cb7b346c45713e8c9169c84 (patch) | |
| tree | 5a2fd7b42be639e60baad696a2a46aae78f2ceb1 /tools/llvm-ar | |
| parent | 12fa02841ca1f2115d38aadd3e5d7afe08c65337 (diff) | |
| download | llvm-11eb51e23935e22e1cb7b346c45713e8c9169c84.tar.gz llvm-11eb51e23935e22e1cb7b346c45713e8c9169c84.tar.bz2 llvm-11eb51e23935e22e1cb7b346c45713e8c9169c84.tar.xz | |
LoopVectorize: Vectorize all accesses in address space zero with unit stride
We can vectorize them because in the case where we wrap in the address space the
unvectorized code would have had to access a pointer value of zero which is
undefined behavior in address space zero according to the LLVM IR semantics.
(Thank you Duncan, for pointing this out to me).
Fixes PR16592.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186088 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'tools/llvm-ar')
0 files changed, 0 insertions, 0 deletions