[X86] Add a AVX512VBMI command line to min-legal-vector-width.ll. Always enable fast...
authorCraig Topper <craig.topper@intel.com>
Fri, 6 Sep 2019 21:49:01 +0000 (21:49 +0000)
committerCraig Topper <craig.topper@intel.com>
Fri, 6 Sep 2019 21:49:01 +0000 (21:49 +0000)
commit03936cb0f942a9a78220ffc25d2849f29a1c4511
tree866728324bf9c8d53d9763f0899d48199eb13d63
parenta31112e3576a5ae0b0959dd20a66d3689d8d9014
[X86] Add a AVX512VBMI command line to min-legal-vector-width.ll. Always enable fast-variable-shuffle

Trying to minimize the features we need to manipulate when this
is updated for D67259.

The VBMI is interesting because it enables some improved combining
for truncates.

I enabled fast-variable-shuffle because all the CPUs we're going
to add implicitly enable it. So they can share check lines.

llvm-svn: 371261
llvm/test/CodeGen/X86/min-legal-vector-width.ll