[llvm] [X86] Attempt to lower 512-bit shuffle(x,y) as concat(truncate(x),truncate(y)) (PR #117579)

[Simon Pilgrim via llvm-commits]

RKSimon wrote:

Sorry, I was rushing and too focused on the trunc-store case - I'll take another look

https://github.com/llvm/llvm-project/pull/117579