diff options
| author | Craig Topper <craig.topper@intel.com> | 2019-08-01 18:48:57 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2019-08-01 18:48:57 +0000 |
| commit | 005cc423168196b2e0c7b39d5465744bad951bf3 (patch) | |
| tree | ae05fa0abb3d897e1707f8b921943d046a5d2f66 /llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp | |
| parent | 90b4388f5612f3088b15a351a0ad421f312fbabb (diff) | |
| download | bcm5719-llvm-005cc423168196b2e0c7b39d5465744bad951bf3.tar.gz bcm5719-llvm-005cc423168196b2e0c7b39d5465744bad951bf3.zip | |
[X86] Add some test cases for 512-bit truncate to 128-bits with min-legal-vector-width=0 and prefer-vector-width=256.
We currently split the 512 type, truncate each half to 128 bits,
concatenate them, and then truncate again. Probably better to
truncate each half to 64-bits and then concat the results
using vpunpcklqdq.
llvm-svn: 367600
Diffstat (limited to 'llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp')
0 files changed, 0 insertions, 0 deletions
