llvm-project

ac47d8c2 - [msan] Handle Arm NEON BFloat16 multiply-add to single-precision (#178510)

[msan] Handle Arm NEON BFloat16 multiply-add to single-precision (#178510) aarch64.neon.bfmlalb/t perform dot-products after zeroing out the odd/even-indexed values. We handle these by generalizing handleVectorDotProductIntrinsic() and (mis-)using getPclmulMask().