[ROCm] Add ROCm tuning config to block gemm and Re-tune for AMD Radeon Graphics

[BruceXcluding]

Motivation

Add ROCm block gemm tuning configs

Modifications

Modify config tunings for AMD Radeon Graphics

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.

[BruceXcluding]

cc @HaiShaw

[HaiShaw]

@BruceXcluding LGTM, do we notice performance regression on MI300X?

[fsx950223]

Device names in the config seems wrong.

[BruceXcluding]

Device names in the config seems wrong.

This is not used by MI300X

[fsx950223]

Device names in the config seems wrong.

This is not used by MI300X

It's a general device name for amd gpus. Mi308 config may mix with other gpu config.

[BruceXcluding]

Device names in the config seems wrong.

This is not used by MI300X

It's a general device name for amd gpus. Mi308 config may mix with other gpu config.

Actually not, but you may manually modify the device name or re-tune for local machine.