Bend is a newly introduced programming language that compiles to native code, runs on multiple CPU cores or GPUs without manual threading, and includes a built-in proof checker similar to Lean and Rocq. Developers can write rules in a LAWS.bend file, and Bend will refuse to accept any AI-generated code change that violates those rules, checking each change in about a second. Its creators demonstrate this by showing an AI agent attempt to break a game's win condition, which Bend blocks until the AI produces a compliant fix.
bend-lang.com
· 2026-09-17
Nvidia announced it is extending CUDA to support GPU kernels written natively in Rust, compiled directly to PTX rather than wrapped around another language. The move covers both the existing SIMT model used in CUDA C++ and Python, and the newer Tile programming model, with development continuing into 2027.
developer.nvidia.com
· 2026-09-16
Nvidia has introduced the RTX Pro 5500 Blackwell Workstation Edition, a professional graphics card built on the same GB202 die as the GeForce RTX 5090 and offering similar CUDA core counts and performance. The key difference is memory: the RTX Pro 5500 carries 84GB of GDDR7, 2.6 times more than the RTX 5090, positioning it between the existing RTX Pro 5000 and RTX Pro 6000 in Nvidia's professional lineup.
tomshardware.com
· 2026-09-14
An independent developer known as Speedstu built a PowerShell-based toolkit that combines ZLUDA with AMD's HIP/ROCm SDK, allowing CUDA-only applications to run on AMD GPUs in Windows without dual-booting or virtual machines. The setup successfully mapped CUDA's driver API and libraries like cuBLAS, cuSPARSE, and cuFFT to AMD equivalents, and was tested by training a small reinforcement-learning model on a Radeon RX 9060 XT using unmodified CUDA code.
tomshardware.com
· 2026-09-14
Developers behind the ZLUDA project have released a reproducible stack combining ZLUDA v6-preview.69 with AMD's HIP SDK 6.4, allowing CUDA-targeted Windows applications, including LibTorch-based machine learning workloads, to run on AMD hardware. The setup has been validated specifically on the Radeon RX 9060 XT (gfx1200), where core CUDA libraries like cuBLAS and cuFFT passed checks and a PPO reinforcement learning network completed training over 65,536 timesteps.
github.com
· 2026-09-13
A technical blog post walks through building a custom attention kernel for Nvidia's Blackwell B200 GPU entirely from scratch, using CUDA and some PTX code. Through a 14-step progression of optimizations illustrated with 60 diagrams, the kernel reaches 94.4% of FlashAttention-4's performance on 4K, 8K, and 16K sequence shapes, and is demonstrated by plugging it into a video-generation model.
iaroslavelistratov.github.io
· 2026-09-02
A day after DLSS 5's nvngx_dlssnr.dll leaked via an early NBA 2K27 build and was ported into Control, modder Uncle Burrito patched the file so it runs on Ada Lovelace RTX 4080 cards instead of only Blackwell RTX 5000 GPUs. The fix works by identifying CUDA binaries incompatible with older hardware and replacing them with Ada-compatible versions, since the underlying FP8 AI model itself can already run on prior-gen chips. Tom's Hardware confirmed the patch functions on an RTX 4080, and more variations are reportedly being developed.
tomshardware.com
· 2026-08-28
OpenAI revealed its first custom AI chip, called Jalapeño, claiming it delivers industry-leading speed and efficiency for inference workloads. The chip, co-developed with Broadcom, is set to be deployed in OpenAI's own infrastructure by year-end, with two more generations already in development.
cnbc.com
· 2026-08-26
Nvidia is working to extend CUDA compatibility beyond x86-64 and aarch64 to RISC-V CPUs, according to a Hot Chips 2026 presentation. The company laid out strict hardware requirements, including RVA23 compliance, adherence to RISC-V server SoC and platform specs, ACPI support, and PCIe coherency, to ensure CUDA runs efficiently rather than falling back on lowest-common-denominator code.
chipsandcheese.com
· 2026-08-24
GoKawiil