Print local workgroup size (#3995)

Summary:
Pull Request resolved: https://github.com/pytorch/executorch/pull/3995

## Before
```
Kernel Name                             Workgroup Size             Duration (ns)
===========                             ==============               ===========
nchw_to_tensor_float_texture3d          {512, 672, 4}                   13848640
conv2d_pw_clamp_float                   {512, 672, 16}                 124203820
```

## After
```
Kernel Name                             Global Workgroup Size    Local Workgroup Size                 Duration (ns)
===========                             =====================    ====================                 =============
nchw_to_tensor_float_texture3d          {512, 672, 4}            {4, 4, 4}                                 13764816
conv2d_pw_clamp_float                   {512, 672, 16}           {4, 4, 4}                                124275060
```
ghstack-source-id: 230551342

bypass-github-export-checks
bypass-github-pytorch-ci-checks
bypass-github-executorch-ci-checks

Reviewed By: nathanaelsee

Differential Revision: D58476014

fbshipit-source-id: 6c916cb054bca666748949b932cf61e899f751ca