[Pipeline][XeGPUToVC][MathToVC][ArithToVC][VectorLinearize] Move XeGPUToVC forward

[chencha3]

This PR moves XeGPUToVC (as well as MathToVC and ArithToVC) pass forward in the pipeline, such that it focuses on converting XeGPU ops into VC intrinsics and maintaining 2D/3D vector view using shapecast (via materialization). And updated VectorLinearize pass with support for loop ops, e.g. scf.for. This change also enables the removal of imex-remove-single-elem pass from current pipelines for XeTile/XeGPU integration tests

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?