RFR: 8349138: Optimize Math.copySign API for Intel e-core targets [v2]

[Jatin Bhateja]

On Mon, 3 Feb 2025 14:36:54 GMT, Quan Anh Mai <qamai at openjdk.org> wrote:

> Could you instead do this by trying to transform `AndI(MoveF2I(x), MoveF2I(y))` into `AndF(x, y)` instead?

@merykitty , this patch does not break existing IR invariants as multiple targets already emit efficient instruction sequences for it, we have just improved upon the x86-backed implementation.
![image](https://github.com/user-attachments/assets/61845793-ca3a-4ad2-8ee8-210f8a1bc60d)


Introducing another new IR "AndF" will again need changes in auto-vectorization.

-------------

PR Comment: https://git.openjdk.org/jdk/pull/23386#issuecomment-2632973584