diff options
author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-06-17 14:26:10 +0000 |
---|---|---|
committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-06-17 14:26:10 +0000 |
commit | 454e6b9010fe0b266505fdfa9c85b574772b793f (patch) | |
tree | f95270e3e8f3041c0674f8eb897718800af44226 /lldb/packages/Python/lldbsuite/test/lldbtest.py | |
parent | 3c9391aad9eeefd4a5b4535931949a30898b79bc (diff) | |
download | bcm5719-llvm-454e6b9010fe0b266505fdfa9c85b574772b793f.tar.gz bcm5719-llvm-454e6b9010fe0b266505fdfa9c85b574772b793f.zip |
[X86][SSE] Prevent misaligned non-temporal vector load/store combines
For loads, pre-SSE41 we can't perform NT loads at all, and after that we can only perform vector aligned loads, so if the alignment is less than for a xmm we'll just end up using the regular unaligned vector loads anyway.
First step towards fixing PR42026 - the next step for stores will be to use SSE4A movntsd where possible and to avoid the stack spill on SSE2 targets.
Differential Revision: https://reviews.llvm.org/D63246
llvm-svn: 363564
Diffstat (limited to 'lldb/packages/Python/lldbsuite/test/lldbtest.py')
0 files changed, 0 insertions, 0 deletions