profiling with rocprofiler-sdk

[cj401-amd]

This PR is based on the PR for xla 0.6.0 ROCm/xla#302 and upstream PR openxla/xla#29769

rocprofiler-sdk integration for improved profiling with rocprofiler_force_configure() and annotations, support both time-based and step-based profiling,

• Keep roctracer(v1) for ROCm version < 6.3
• rocprofiler-sdk and roctracer are selected at compile time based on ROCm version guard
• Add unit tests for rocm_collector and rocm_tracer for v3 (ROCm version >= 6.3)
• still need to figure out how to add more stats related to kernel, e.g., kernel size, occupancy, DMA copy, etc.