rocm-systems/projects/rdc/CHANGELOG.md

Change Log for RDC

Full documentation for RDC is available at ROCm DataCenter Tool User Guide.

RDC for ROCm 7.0.0

Added

• More profiling and monitoring metrics, especially for AMD Instinct MI300 and newer GPUs.
• Advanced logging and debugging options, including new log levels and troubleshooting guidance.

Changed

• Completed migration from legacy ROCProfiler to ROCprofiler-SDK.
• Reorganized the configuration files internally and improved README/installation instructions.
• Updated metrics and monitoring support for the latest AMD data center GPUs.

Optimized

• Integration with ROCprofiler-SDK for performance metrics collection.
• Standalone and embedded operating modes, including streamlined authentication and configuration options.
• Support and documentation for diagnostic commands and GPU group management.
• RVS test integration and reporting.

RDC for ROCm 6.4.0

Added

• RDC policy feature
• Power and thermal throttling metrics
• RVS IET, PEBB, and memory bandwidth tests
• Link status
• RDC_FI_PROF_SM_ACTIVE metric

Changed

• Migrated from rocprofiler v1 to rocprofiler-sdk
• Improved README.md for better usability
• Moved rdc_options into share/rdc/conf/
• Fixed ABSL in clang18+

RDC for ROCm 6.3.0

Added

• RVS integration
• Real time logging for diagnostic command
• --version command
• XGMI_TOTAL_READ_KB and XGMI_TOTAL_WRITE_KB monitoring metrics

RDC for ROCm 6.2.0

• Added rocprofiler dmon metrics
• Added new ECC metrics
• Added ROCmValidationSuite diagnostic command
• Fully migrated to AMDSMI
  • Removed RASLIB dependency and blobs
  • Removed rocm_smi_lib dependency

RDC for ROCm 6.1.0

• Added --address flag to rdcd
• Upgraded from C++11 to C++17
• Upgraded gRPC

RDC for ROCm 5.5.0

• Added new profiling metrics for RDC dmon module.