[XeTileToXeGPU] Add generic lowering pattern for Xetile elementwise o…

[mshahneo]

…ps (arith, math dialect ops).

Allows Arith/math dialect pre/post-ops to be decomposed (blocked and updated).

Add a generic element-wise conversion pattern that can tackle all operations. It removes multiple patterns necessary to handle different kind of ops. It also supports passing attributes (e.g., fastmath).

Add support for all the operations in Arith dialect.

Please review these guidelines to help with the review process:

• Have you provided a meaningful PR description?
• Have you added a test, a reproducer, or a reference to an issue with a reproducer?
• Have you tested your changes locally for CPU and GPU devices?
• Have you made sure that new changes do not introduce compiler warnings?
• If this PR is a work in progress, are you filing the PR as a draft?
• Have you organized your commits logically and ensured each can be built by itself?

[nbpatel]

LGTM