[metal] Add Metal codegen handlers for load, store, and mask_to

[aditvenk]

Stacked PRs:

• [metal] Auto-cap threadgroup size via CuteND/CuteFlattenedTileStrategy #1855
• Add backend-agnostic lane loop APIs to tile strategies #1798
• [metal] Add elementwise kernel tests #1796
• Add Metal test job to CI test matrix #1862
• [metal] Add MSL AST walker for Python-to-C++ translation #1794
• Add Backend.post_process_function_def hook #1851
• ->[metal] Add Metal codegen handlers for load, store, and mask_to #1854

---

[metal] Add Metal codegen handlers for load, store, and mask_to

Add @_decorators.codegen handlers for the Metal backend:

• load("metal"): delegates to PointerIndexingStrategy.codegen_load
• store("metal"): delegates to PointerIndexingStrategy.codegen_store
• _mask_to("metal"): applies tile masks via IfExp

[jansel]

Is there test coverage for this?

[aditvenk]

• [metal] Add MSL walker, 3D launcher, and copy kernel tests [metal] Add MSL AST walker for Python-to-C++ translation #1794

In follow-up PR in the stack: #1794 (copy kernels)
and #1796 (elementwise operators)