[RalfJung]

The current docs seem just wrong -- k is the mask, it has the wrong size to be the source of the output bits. The implementation is simd_select_bitmask(k, ..., a) and the last a means that that's what is used where k is 0.

[rustbot]

r? @davidtwco

rustbot has assigned @davidtwco.
They will have a look at your PR within the next two weeks and either review your PR or reassign to another reviewer.

Use r? to explicitly pick a reviewer

Why was this reviewer chosen?

The reviewer was selected based on:

• Owners of files modified in this PR: @Amanieu, @adamgemmell, @davidtwco, @folkertdev
• @Amanieu, @adamgemmell, @davidtwco, @folkertdev expanded to Amanieu, adamgemmell, davidtwco, folkertdev
• Random selection from Amanieu, adamgemmell, davidtwco, folkertdev

[RalfJung]

That CI failure looks unrelated to my PR.

(This repo would benefit a lot from pinning the nightly rustc, to avoid PRs getting held up by unrelated breakage.)

[folkertdev]

We just fixed that CI issue