CUDA

Evidence (20)

• 8NVIDIA GenAI·10/7/2026product_launch
  NVIDIA and Microsoft launch RTX Spark for Windows AI agents

  NVIDIA and Microsoft announced new Windows PC hardware and software built for local AI agents, including Microsoft Execution Containers (MXC) for secure, persistent agent execution. They also introduced RTX Spark laptops and compact desktops that integrate the NVIDIA AI stack, Blackwell RTX GPUs, Grace CPUs, and up to 128GB of unified memory for running large models on-device.

• 7The New Stack·9/23/2026open_source
  Q.ANT releases open-source software for photonic AI chips

  Q.ANT has released the Q.ANT Native Computing Toolkit on GitHub, giving developers a simulator and software tools to write and test programs for its light-powered AI chips on standard computers. The kit supports Python and C, but real hardware access is still limited to select research sites, with cloud access expected in the coming months.

• 6Hugging Face Blog·9/23/2026framework_update
  How NVIDIA Warp and MJWarp Speed Up Robotics Simulation

  The article explains how MuJoCo Warp (MJWarp), built on NVIDIA Warp, moves compatible MuJoCo robotics simulations from CPU execution to large-batch GPU execution. It highlights a workflow that scales an SO-101 arm simulation to up to 2,048 parallel environments and describes validation and integration steps, without training a policy.

• 6NVIDIA GenAI·9/21/2026product_launch
  Five Companies Using NVIDIA AI for Clean Energy

  NVIDIA is highlighting five companies that are using its AI and accelerated computing stack to speed up clean-energy deployment, grid optimization, and power infrastructure planning. The examples span digital twins for interconnection, AI knowledge tools for nuclear operations, and battery-based off-grid power systems for AI data centers.

• 6Hacker News·9/17/2026open_source
  Bend language promises proof-checked AI code on CPU and GPU

  Bend is a new programming language and runtime that emphasizes fast compilation, parallel execution on CPUs and GPUs, and proof-based checks to prevent rule-breaking changes. The post highlights AGENTS.md guidance, a law/proof workflow, and claims that AI-generated code can be constrained to satisfy declared invariants before commit.

• 8Hacker News·9/16/2026product_launch
  NVIDIA adds native Rust GPU kernel programming

  NVIDIA announced CUDA Rust, allowing GPU kernels to be written in Rust and compiled natively to PTX. The rollout includes two paths: cuda-oxide for SIMT kernels on a nightly toolchain, and cutile-rs for tile-based programming on stable Rust, with planned interoperability across CUDA Rust, CUDA C++, and CUDA Python.

• 6Hacker News·9/13/2026open_source
  CUDA Compatibility Layer for AMD GPUs on Windows

  An open-source project aims to let CUDA-based applications run on AMD GPUs under Windows by translating CUDA calls to AMD-compatible GPU APIs. The repository has drawn strong attention on Hacker News, indicating interest in broader GPU software compatibility outside NVIDIA hardware. The effort is early-stage and primarily targets developers who want to run CUDA workloads on AMD systems.

• 7The New Stack·9/3/2026research
  Cut GPU inference cold start from 8 minutes to under a minute

  The article breaks down GPU inference startup into six phases and shows that cold-start time can be reduced substantially through configuration and platform changes. It reports that warm-node restarts can drop from 1.5-8 minutes to under 30 seconds, while fresh-node startups can fall from 8-15 minutes to about 5 minutes when using Amazon EKS Auto Mode and related optimizations.

• 4Hacker News·8/21/2026research
  How a GPU Reads Memory

  This article reverse-engineers the path a GPU global load takes on an RTX 4090, from register reads and warp scheduling through the load/store unit, coalescer, cache hierarchy, and memory controller. It uses timing experiments and SASS inspection to explain how a simple vector-add kernel moves data through the hardware for performance analysis.

• 3Hacker News·8/19/2026research
  Geometry and CUDA Used to Geolocate a Random Island

  A Hacker News post describes a human-written writeup of solving a geolocation challenge for an island resort photo using geometry and GPU-accelerated code. The author built a fingerprint from island positions and used OpenStreetMap coastline data plus heuristic filtering and CUDA-based computation to search for a matching island cluster.

• 5Hacker News·8/15/2026research
  Auto-research with Codex delivers a 232x faster QR kernel

  A Hacker News post describes how the author used Codex in GPU Mode to iteratively optimize a batched square QR decomposition kernel for a contest. The final solution achieved a 232x speedup over the baseline and ranked 12th out of 183 participants, highlighting agent-assisted kernel tuning and auto-research workflows.

• 8The New Stack·8/10/2026breakthrough
  EKS speeds up multi-gigabyte container image pulls

  The article describes how large ML inference container images on Amazon EKS were taking several minutes to pull, delaying pod readiness and leaving GPUs idle. By reworking the image pull pipeline to better use available network, storage, and compute resources, the team reduced multi-gigabyte pulls to seconds; the improvements are now available by default in EKS Auto Mode and were contributed upstream to containerd and the SOCI snapshotter.

• 8NVIDIA GenAI·7/22/2026open_source
  NVIDIA Open Sources GPU-Accelerated Medical Physics Simulation Framework

  NVIDIA has open sourced Medical Physics Simulation, a GPU-accelerated framework within Isaac for Healthcare for simulating anatomy-device interactions, sensor inputs, and difficult edge-case scenarios. The framework is designed to help medical robotics teams train, test, and evaluate policies in simulation before moving to hardware-heavy validation.

• 7Hacker News·7/14/2026product_launch
  Spectral Compute Pushes a CUDA-Free Path for Non-NVIDIA GPUs

  The article covers Spectral Compute’s effort to make CUDA-style GPU programming work on non-NVIDIA hardware, potentially reducing dependence on NVIDIA’s software stack. The Hacker News discussion reflects interest in whether a credible alternative can emerge for developers and HPC users who want broader hardware compatibility.

• 4Hacker News·7/5/2026product_launch
  OpenPrinter launches a repairable, refillable compact printer

  OpenPrinter is a compact printer/plotter designed to be fully repairable, use refillable ink cartridges, and reduce consumables waste. It supports both roll paper and standard sheets, works with CUPS across major operating systems, and can be assembled as a kit or purchased ready to use.

• 7Hacker News·6/30/2026open_source
  ZLUDA 6 adds PhysX, Blender texture support, and better Windows compatibility

  ZLUDA has released version 6, a new major update for its project that enables unmodified CUDA applications to run on non-NVIDIA GPUs. The update adds pre-alpha 32-bit PhysX support, basic texture support that also enables Blender, and improved Windows handling for performance libraries and loaders.

• 4Hacker News·6/29/2026research
  A Deep Dive Into What Happens When a CUDA Kernel Runs

  This article traces a simple CUDA vector-add program from source code through compilation and GPU execution, explaining how nvcc, PTX, and SASS fit into the pipeline. It also describes low-level runtime details such as warps, device memory access, and the mechanisms used to launch and complete the kernel on an RTX 4090.

• 8NVIDIA GenAI·6/2/2026product_launch
  NVIDIA Adds Agentic AI Support to Jetson Edge Platform

  NVIDIA announced JetPack 7.2 and NemoClaw support for Jetson at COMPUTEX, bringing agentic AI capabilities to edge devices. The update adds Yocto support, CUDA 13 on Jetson Orin, MIG on Jetson Thor, and performance gains for Jetson AGX Orin 32GB, while enabling deployment of agentic workflows for robotics, inspection, and industrial automation.

• 4Hugging Face Blog·5/29/2026framework_update
  A Beginner’s Guide to torch.profiler in PyTorch

  Hugging Face Blog introduces the first part of a series on profiling in PyTorch, focused on helping beginners read profiler traces and understand how Python calls map to CPU and CUDA activity. The article explains how to use torch.profiler, interpret its tables and traces, and observe what changes when torch.compile is applied.

• 7Hugging Face Blog·2/13/2026open_source
  Claude and Codex Gain CUDA Kernel Writing Skill

  Hugging Face introduced an agent skill that teaches coding agents how to write production CUDA kernels and integrate them with PyTorch-based projects. The blog says Claude and Codex were used to generate working kernels for a diffusers pipeline and a transformers model, including bindings and benchmarks end to end.