[ET-VK] Changing all conv 2d pw ints from uint16 to int since it slightly improves perf. (#7566)

* [ET-VK] Adding a common utility function to calculate 3d output position based on unique index.

Pull Request resolved: https://github.com/pytorch/executorch/pull/7522

This diff adds an indexing utils header file used in Vulkan backend of Executorch. The header file includes functions for converting a global index to u16 indices based on input sizes.
ghstack-source-id: 260707858
@exported-using-ghexport

Differential Revision: [D67821941](https://our.internmc.facebook.com/intern/diff/D67821941/)

* [ET-VK] Adding batch processing in x axis to conv2d dw shader by caching input texel for reuse.

Pull Request resolved: https://github.com/pytorch/executorch/pull/7526

This diff adds batch processing in the x axis to the conv2d dw shader by reusing input texel overlapping between consecutive tiles. The changes include modifying the glsl code for the conv2d dw output tile, adding a new parameter to the yaml file, and modifying the Convolution.cpp file to use the new parameter.
ghstack-source-id: 260707856

Differential Revision: [D67868671](https://our.internmc.facebook.com/intern/diff/D67868671/)

* [ET-VK] Changing all conv 2d pw ints from uint16 to int since it slightly improves perf.

Pull Request resolved: https://github.com/pytorch/executorch/pull/7545

This diff changes all integers in conv 2d pw op shader from uint16 to int in the Vulkan backend of Executorch. The change is made to improve performance since the shader does not appear to be register bound.
ghstack-source-id: 260707857

Differential Revision: [D67906023](https://our.internmc.facebook.com/intern/diff/D67906023/)

---------

Co-authored-by: Vivek Trivedi <5340687+trivedivivek@users.noreply.github.com>