Jingning Tang developed and enhanced benchmarking and usability features across the ROCm/triton, ROCm/aiter, and intel-xpu-backend-for-triton repositories, focusing on GPU performance analysis and hardware compatibility. Using Python and C++, Tang refactored the plot layout command-line interface in ROCm/triton to improve argument parsing and maintainability. In ROCm/aiter, Tang created a GEMM A8W8 benchmarking script that automates input generation and performance parsing for Triton. For intel-xpu-backend-for-triton, Tang expanded the MI300 benchmarking suite to support new data types and cross-architecture compatibility, enabling more robust performance evaluation and facilitating collaboration across teams working with diverse GPU hardware.