This project is a small, high‑performance graphics engine core focused on SIMD math, fast batch transforms, a lightweight render pipeline, and a profiler. It aims for microsecond‑level kernels by using SIMD intrinsics, cache‑aligned data layouts, aggressive compiler optimizations, and batch processing to reduce per‑operation overhead.
Use it as a fast foundation for real‑time visualization, simulation prototypes, or compute‑heavy tasks like geometry processing, batch transforms, and performance benchmarking.