Implement fp16 x fp8, bf16 x fp8, fp8 x fp16, and fp8 x bf16 for the V3 pipeline

[SamiAario-AMD]

Proposed changes

Implement fp16 x fp8, bf16 x fp8, fp8 x fp16, and fp8 x bf16 for the V3 pipeline. To make this work, we unify some of the type conversions needed into a templated class DetermineWarpPrecType, and we template-parameterize get_awarp_dstr_encoding of the block GEMM with NumAccessA. The latter is so that we can generate tile distribution encodings during compile time that are compatible with a new function load_tile_transpose_convert that we introduce, which is used for transposed loading and converting of tiles.

This PR depends on this other PR which has not been merged already: #3505
The changes introduced by this other PR are also in this one.
For this reason, this PR is opened as a draft.

Checklist

Please put an x into the boxes that apply. You can also fill these out after creating the PR. If you're not sure, please don't hesitate to ask.

• I have added tests relevant to the introduced functionality, and the unit tests are passing locally
• I have added the test to REGRESSION_TESTS list defined at the top of CMakeLists.txt in tests/CMakeLists.txt, IF the test takes more than 30 seconds to run.
• I have added inline documentation which enables the maintainers with understanding the motivation
• I have removed the stale documentation which is no longer relevant after this pull request
• (If this change is user-facing) I have added release notes which provide the end users with a brief summary of the improvement from this pull request
• I have run clang-format on all changed files
• Any dependent changes have been merged

Discussion

If this is a relatively large or complex change, feel free to start a discussion by explaining why you chose the solution you did and what alternatives you considered