add layernorm backward pass

[scxiao]

This PR is to add the backward pass to the layernorm op for the perf kernel of the amd rocm fork. The following changes are made:

• Added a backward pass of LayerNorm
• Enhanced the backward kernel to handle more input shapes
• Implemented Layernorm class following the standard interface
• Added unit tests to verify the backward kernel correctness.
• Added input shapes retrieved from model_config.json file

As for performance, the forward pass becomes slower, due to the following reasons:

• Added arguments "mean" and "rstd" and time needed to store results to these tensors
• The forward pass need time to create these two tensors
• The forward pass need time to backup a few tensors in the function "save_for_backward"
• If removing these two arguments, kernel ISA is the same as before

The core Triton is a small number of people, and we receive many PRs (thank
you!). To help us review your code more quickly, if you are a new
contributor (less than 3 PRs merged) we ask that you complete the following
tasks and include the filled-out checklist in your PR description.

Complete the following tasks before sending your PR, and replace [ ] with
[x] to indicate you have done them.

• I am not making a trivial change, such as fixing a typo in a comment.

• I have written a PR description following these
  rules.

• I have run pre-commit run --from-ref origin/main --to-ref HEAD.

• Select one of the following.

  • I have added tests.
    • /test for lit tests
    • /unittest for C++ tests
    • /python/test for end-to-end tests
  • This PR does not need a test because FILL THIS IN.

• Select one of the following.

  • I have not added any lit tests.
  • The lit tests I have added follow these best practices,
    including the "tests should be minimal" section. (Usually running Python code
    and using the instructions it generates is not minimal.)

[vgokhale]

Thanks Shucai!