Integrate axis mapping into naive matrix multiplication shaders (#5277)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/5277

## Context

Give similar treatment as https://github.com/pytorch/executorch/pull/5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability.

## Performance impact

Running the matrix multiplication operator benchmark, we can observe the following results:

| commit      | matmul_naive_texture3d_float | linear_naive_texture3d_float |
|-------------|------------------------------|------------------------------|
| master      | 6.53645                      | 6.98834                      |
| this commit | 6.61293                      | 6.34905                      |

Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency.

ghstack-source-id: 242452079
exported-using-ghexport

Reviewed By: jorgep31415

Differential Revision: D62518403

fbshipit-source-id: de873164fa6202b9b3312d1f62ff1dc2cec86db8