support L2Norm backward for GPU.

[zheng-da]

Description

(Brief description on what this PR is about)

Checklist

Essentials

Please feel free to remove inapplicable items for your PR.

• The PR title starts with [MXNET-$JIRA_ID], where $JIRA_ID refers to the relevant JIRA issue created (except PRs with tiny changes)
• Changes are complete (i.e. I finished coding on this PR)
• All changes have test coverage:
• Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
• Nightly tests are added for complicated/long-running ones (e.g. changing distributed kvstore)
• Build tests will be added for build configuration changes (e.g. adding a new build option with NCCL)
• Code is well-documented:
• For user-facing API changes, API doc string has been updated.
• For new C++ functions in header files, their functionalities and arguments are documented.
• For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
• Check the API doc at http://mxnet-ci-doc.s3-accelerate.dualstack.amazonaws.com/PR-$PR_ID/$BUILD_ID/index.html
• To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

[piiswrong]

Why didn't testing catch this? all tests in test_operator are automatically run again with gpu in test_operator_gpu

[zheng-da]

i was wondering about this as well. I'll look at the tests tomorrow.

[haojin2]

Should be FCompute<gpu> and FComputeEx<gpu>?

[szha]

@piiswrong I think we should get this fix in first. @zheng-da could you create an issue or something to keep track of the test issue?

[eric-haibin-lin]

I am still concerned that unit tests didn't catch this