[PATCH] D37680: [X86][SSE] Add support for X86ISD::PACKSS to ComputeNumSignBitsForTargetNode

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

In https://reviews.llvm.org/D37680#866273, @delena wrote:

> I want to suggest a test case without intrinsic:


Done - I added vselect_packss_v16i32 / vselect_packss_v16i64 cases as well. Interestingly avx512vl gets caught in an infinite loop on vselect_packss_v16i32, with/without this patch -  I'll raise a bug.


Repository:
  rL LLVM

https://reviews.llvm.org/D37680