AMD Helios is a GPU platform for AI with 432 GB of HBM4 memory and 40 PFLOPs of FP4 compute. This post presents an educational ladder of BF16 GEMM kernel implementations that progressively optimize for Helios's architectural features, including partitioned LDS, simplified cache hierarchy, and 32-thread waves.
In September 2026, NVIDIA announced native GPU programming support in Rust, enabling developers to write GPU kernels directly in Rust compiled to PTX. The move reflects Rust's growing adoption in AI systems infrastructure for its compile-time safety benefits. NVIDIA offers two programming models—SIMT and the newer Tile—with cuda-oxide providing a custom Rust compiler backend for kernel development.
A discussion on social.kernel.org about the volume of patches in seven stable Linux kernels, with participants noting that reviewing thousands of patches requires re-reviewing already-released code for backporting to older kernel branches.
In September 2026, NVIDIA announced CUDA Rust, enabling native GPU kernel programming in Rust compiled directly to PTX. The language supports two programming models: SIMT (traditional thread-based) and Tile (newer, architecture-agnostic), with cuda-oxide providing a custom rustc backend for compilation. NVIDIA is expanding Rust adoption across its AI systems stack including drivers and serving infrastructure.
In September 2026, NVIDIA announced CUDA Rust, enabling developers to write GPU kernels natively in Rust compiled to PTX. The announcement includes two programming tracks—SIMT and Tile—with cuda-oxide providing a custom rustc codegen backend that routes Rust code through MIR and LLVM to GPU compilation, while Tile is recommended for architecture-agnostic code.