diff options
| author | Adam Nemet <anemet@apple.com> | 2015-01-14 01:31:17 +0000 |
|---|---|---|
| committer | Adam Nemet <anemet@apple.com> | 2015-01-14 01:31:17 +0000 |
| commit | 63a951eb1c59a1f4e4a66278ce1a322867700109 (patch) | |
| tree | b891eaad399cfe2c567785072f2c7799921c710f /llvm/lib/CodeGen | |
| parent | a5a0f5766a3585a9aff56babe270baa064e7b2f5 (diff) | |
| download | bcm5719-llvm-63a951eb1c59a1f4e4a66278ce1a322867700109.tar.gz bcm5719-llvm-63a951eb1c59a1f4e4a66278ce1a322867700109.zip | |
[AVX512] Add FP unpack intrinsics
These are implemented with __builtin_shufflevector just like AVX.
We have some tests on the LLVM side to assert that these shufflevectors do
indeed generate the corresponding unpck instruction.
Part of <rdar://problem/17688758>
llvm-svn: 225922
Diffstat (limited to 'llvm/lib/CodeGen')
0 files changed, 0 insertions, 0 deletions
