Documentation Update for NCCL

[tharittk]

Ongoing update - in parallel to NCCL implementation PR (#130)

Tasks

• Update README mentioning the possibility to use NCCL instead of MPI for distributed cupy arrays, updating the install, example and tests sections with NCCL-related commands
• Update index.rst similar to README to reflect new NCCL engine
• Update gpu.rst documenting the new env variable (NCCL_PYLOPS_MPI), adding NCCL to the example, and perhaps consider adding a table like in https://pylops.readthedocs.io/en/stable/gpu.html to document what features are supported in NCCL and what are not, eg the missing support for complex numbers (this can also serve as a live roadmap for you work, as we progress we should see more and more features being supported by both MPI and NCCL)

[mrava87]

Just left a few comments on what you have done so far, this needs much more to be ready but hopefully with the checklist that I put in the description of the PR you will have a easier life to navigate the documentation and add bits related to NCCL

[mrava87]

Very good work @tharittk, I left some additional mostly stylistic comments... once you have address them, I think for now this is already a very good improvement to the documentation to include NCCL related stuff and we can continue revising it as we progress with the code development 🚀

[mrava87]

@tharittk this looks great to me!

@rohanbabbar04 you want to have a look or shall I go ahead and merge?

[rohanbabbar04]

Yup, looks good, I am going to approve this.
@tharittk, once the merge conflicts are fixed, it is good to go. I have fixed the linting with flake8 in this PR #134, so no need to change the setup.cfg.