Glad to have published my vibe Xe-Diagram

Link: https://xwang186.com/xe-diagram/ (also can be accessed thru blog menu)

Still in progress, but have finished some pages with details.

Architecture: Xe-HPG(A770)

Referred docs: https://www.x.org/docs/intel/ACM/

In progress/to be finished: GPU occupancy analysis view

But from the PRM, I don’t think hardware frontend information is included. I am planning to play safe on that and avoid to include any non-public information 😀

---

Updated – Fixed rendering pipelines and cleared some confusions

Added more detailed pages.

I have been spent quite long time with ChatGPT, on different topics. I am the 1% top user , without using any token api but just chat on web/app.

I have found it less meaningful to summarize “domain knowledge” into articles. This is a waste of time because AI agent can do 20x better than me.

Continue reading “Way I want to use blog” →

By Train from SAC

Introduction to NVDLA

The NVIDIA Deep Learning Accelerator (NVDLA) is an open-source hardware project designed to accelerate deep learning inference tasks. Its flexible, scalable architecture enables developers to implement AI acceleration on various platforms, from FPGAs to ASICs. By offering a complete stack of hardware and software, NVDLA has become a cornerstone for many projects in the AI hardware space, making it an invaluable tool for prototyping and development.

Continue reading “Revisit of my NVDLA adaption project in Novumind” →

as title. relief

Update 10/19: 1 week left

Everything done