…49930)

This PR is cleanup only. There are no feature changes or bug fixes.

We create a TunableOp context manager for setting up and cleanup. We re-write TunableOp unit tests in terms of this context manager. Ultimately reduces the amount of copy-paste code.

Pull Request resolved: pytorch#149930
Approved by: https://github.com/jeffdaily

(cherry picked from commit 45b1173)

…ytorch#150142)

Improvements to unit tests and warnings for unsupported cases in offline tuning. Here are more details:
- Previously we only compared the OpSig for the untuned vs. tuned entries. This was not strict enough so we now compare OpSig+ParamSig.
- The main offline and online UTs are now stricter to make sure we exercise the code paths for the four combinations of transA and transB.
- Offline tuning does not support some tensor shapes. Emit warning and skip tuning.

Pull Request resolved: pytorch#150142
Approved by: https://github.com/jeffdaily

Co-authored-by: Jeff Daily <jeff.daily@amd.com>
(cherry picked from commit ca2ffc2)

…rch#150463)

This PR fixes two race conditions that occur when UT tests are run:
- In a particular order within a single shard.
- Concurrently in multiple shards. Each test now gets a unique filename that depends on the test name.

There were two other minor improvements to the UTs:
- matmul_offline_mgpu could occasionally fail if run on 8 GPUs. Criteria was relaxed.
- bmm_tunableop_rocm checks that the rotating buffer is not zero. Otherwise, the test is not useful.

Additionally, several UTs took over 1 minute to run. Their duration was reduced by a combination of setting max tuning iterations to one, setting the rotating buffer size to zero, and/or reducing the matrix dimensions.

Pull Request resolved: pytorch#150463
Approved by: https://github.com/jeffdaily

(cherry picked from commit d0026fa)

This PR adds support for submatrices in offline tuning for:
- GEMM
- GEMM and bias
- ScaledGEMM
- Batch Strided GEMM

New UTs to cover submatrices. Submatrices for strided batch API is not part of this PR and will be done seperately.

There is also a bug fix for offline tuning for full matrix for GEMM and bias in the `NT` case. Offline and online UTs were updated to cover this corner case.

To improve code readability, swapped definition of transA and transB.

Pull Request resolved: pytorch#151138
Approved by: https://github.com/jeffdaily

(cherry picked from commit f6c1cf0)

Fixes TunableOp ScaledGEMM regression for rowwise scaling caused by this pytorch#147548

Credit goes to @mawong-amd for fix.

Pull Request resolved: pytorch#152403
Approved by: https://github.com/jeffdaily

(cherry picked from commit ece1658)