Simon Pilgrim 15a31389b2 [X86][AVX] LowerBUILD_VECTOR - reduce 256/512-bit build vectors with zero/undef upper elements + pad. ...

As discussed on D92645, we don't do a good job of recognising when we don't require the full width of a ymm/zmm build vector because the upper elements are undef/zero.

This commit allows us to make use of implicit zeroing of upper elements with AVX instructions, which we emulate in DAG with a INSERT_SUBVECTOR into the bottom of a undef/zero vector of the original type.

This exposed a limitation in getTargetConstantBitsFromNode which didn't extract bits from INSERT_SUBVECTORs of different element widths which I've included as well to prevent a couple of regressions.

2020-12-15 10:11:38 +00:00

6.2 KiB

Raw Blame History

View Raw