cv

AI Framework Engineer

INTEL CORPORATION

Yudong Si have been an AI Frameworks Engineer (Triton Compiler) at the Intel since 2022, contributed to several impactful projects, involving Triton Compiler, Triton XPU backend, XeTLA, PyTorch, and Torchbench.

CUDA Test Development Software Engineer

NVIDIA CORPORATION

Interned as a CUDA Test Development Engineer at NVIDIA.

Master

Tongji University

Integrated circuit engineering

Bachelor

Nantong University

Electronic information engineering

Third Prize of the 17th National Post-Graduate Mathematic Contest in Modeling

China Academic Degrees & Graduate Education Development Center (CDGDC)

Campus Scholarship

Nantong University

Detection and identification method and device for fatigue driving

RGB-LED Touch Control Experimental System for Automobile Based on Configuration Design

According to the needs of the undergraduate experiment course of electronic science and technology,an RGB-LED touch control experiment system for automobile based on configuration design is developed.The system is oriented to automotive electronic applications,using the serial screen as the operating terminal,and the Kinetis EA series MCU as the system microcontroller.The touch commands of the human-machine interface of the serial screen are designed by configuration,the data are sent to the microcontroller through the serial port for analysis,finally forwarded to the pulse width modulation(PWM)constant current module through the LIN protocol port.Then the system outputs the three primary color channel drive signals with different duty cycles to realize the dimming and color adjustment of RGB-LED

Touch device for automobile atmosphere lamp and implementation method

intel/intel-xpu-backend-for-triton

Intel® XPU Backend for Triton, a new Triton backend for Intel GPUs. Intel® XPU Backend for Triton* is a out of tree backend module for Triton used to provide best-in-class performance and productivity on any Intel GPUs for PyTorch and standalone usage.*

• AI
• MLIR
• Compiler
• Triton

pytorch/pytorch

We built a CI/CD pipeline on AWS Xeon instances using Jenkins to automatically collect, test, and publish PyTorch Inductor CPU performance data – accelerating Intel’s optimization efforts for PyTorch.

• AI Infrastructures

TorchBench

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

• AI Infrastructures