llvm-project

344f5940 - [X86] combineTargetShuffle - fold (vzmovl (shift x, y)) -> (shift (vzmovl x), y) (#141579)

[X86] combineTargetShuffle - fold (vzmovl (shift x, y)) -> (shift (vzmovl x), y) (#141579) Move VZEXT_MOVL nodes up through shift nodes. We should be trying harder to move VZEXT_MOVL towards any associated SCALAR_TO_VECTOR nodes to make use of MOVD/Q implicit zeroing of upper elements. Fixes #141475