Apr 6 · 4 min read · The Myth: "C# is too slow for AI" For years, the narrative has been the same: if you want high-performance AI, you must use C++ or Python wrappers (like PyTorch/ONNX) that call into native kernels. Th
Join discussionMar 26 · 5 min read · Hi I am Duc Dao!Welcome to my blog : D Today, we’ll take a quick flash tour through High Performance Computing (HPC) and GPU programming. Sometimes, the most interesting things you learn don’t come fr
Join discussion
Jan 2 · 6 min read · C++ is renowned for its “zero-cost abstraction” philosophy, granting programmers near-direct control over hardware. However, this powerful control comes with significant responsibility — chief among them is resource management. Here, “resources” exte...
Join discussion
Nov 30, 2025 · 3 min read · 📝 Quick Summary: Tile Language (tile-lang) is a domain-specific language designed to streamline the development of high-performance GPU/CPU kernels. It uses a Pythonic syntax and builds upon the TVM compiler infrastructure, allowing developers to fo...
Join discussionOct 19, 2025 · 6 min read · On May 8, 2025, the enthusiasm at AWS Summit Bangalore was apparent. I knew I was going to have a thought-provoking day at the summit's Technical Edition as soon as I entered the KTPO Exhibition Center in Whitefield. Unexpectedly, one session would f...
Join discussion
