[PATCH] D39720: [X86][AVX512] lowering kunpack intrinsic - llvm part

[Craig Topper via Phabricator via llvm-commits]

craig.topper added a comment.

I don't see any tests that produce kunpckbw after this change.



================
Comment at: lib/IR/AutoUpgrade.cpp:1048
+      uint64_t Shift = CI->getType()->getScalarSizeInBits() / 2;
+      uint64_t And = 0xFF;
+      if( Shift == 16) And = 0xFFFF;
----------------
Can this just be 

```
And = (1 << Shift) - 1;
```


https://reviews.llvm.org/D39720