Deep Learning · Parallel Programming · Systems Optimization
- Studying: SystemVerilog, NPU Architecture Design, and Hardware-level Computation Acceleration.
- Building: Custom NPU (pccx) for LLM acceleration on FPGA — see pccx-FPGA-NPU-LLM-kv260.
- Researching: Conducting research and writing a paper on AI hardware acceleration.
- Learning: Parallel Programming (CUDA, OpenCL) & Operating Systems.
- Collaborating: SystemVerilog, Digital IC Design, and HW/SW Co-design projects.
For full project write-ups, blog posts, and papers → hwkim-dev.github.io/hwkim-dev
Email: k1h6w4@gmail.com



