# CUDA Published articles for CUDA. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Translating CUDA Tile Operations from Python to Rust Using Agentic AI DevFeed: [Translating CUDA Tile Operations from Python to Rust Using Agentic AI]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-09-16T16:28:59Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [CUDA Tile](), [Rust](), [Agent Skill](), [Artificial Intelligence](), [AI Agent](), [GPU](), [benchmarking](), [Compiler]() Tags: [agent-skill](), [agentic-ai](), [agentic-ai-generative-ai](), [ai-agent](), [benchmarking](), [cuda](), [cuda-tile](), [cutile](), [developer-tools-techniques](), [gpu](), [mixture-of-experts-moe](), [python](), [rust]() ### AI overview This NVIDIA developer article explains a multi-agent workflow for translating cuTile Python and Triton-TileIR GPU kernels into cuTile Rust. The team ported 24 public TileGym operators, covering about 40 kernels, and achieved 99.5% of cuTile Python performance on average, with correctness and performance checks at each stage. ### Source excerpt cuTile Rust (cutile-rs) is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to... ## OpenVDB Introduces SIMD Framework With Some 2~4x Performance Improvements DevFeed: [OpenVDB Introduces SIMD Framework With Some 2~4x Performance Improvements]() Original publisher: [Read original article]() Author: Michael Larabel Published: 2026-09-16T10:05:23Z Content type: news Language: en Sources: [Phoronix]() Topics: [Data structures](), [Tooling](), [x86](), [releases](), [cudnn](), [Open Source]() Tags: [avx](), [command-line](), [cuda](), [data](), [data-structure](), [desktop-linux](), [github](), [kernels](), [linux-benchmarking](), [linux-hardware-benchmarks](), [linux-hardware-reviews](), [linux-how-to](), [linux-performance](), [linux-server-benchmarks](), [open-source-graphics](), [performance](), [phoronix](), [phoronix-test-suite](), [release](), [ubuntu-benchmarks](), [ubuntu-hardware](), [x86]() ### AI overview OpenVDB 13.1 introduces a SIMD framework using Agner Fog's VectorClass Library for explicit x86 vectorization up to AVX-512. Adapted point transfer algorithms reportedly achieve 2x to 4x performance improvements on modern AVX-512 x86_64 CPUs. The release also includes NanoVDB CUDA resource-management and kernel improvements, plus updates to vdb_tool. ### Source excerpt OpenVDB is the sparse volume data structure and tooling library maintained by the Academy Software Foundation. OpenVDB in turn is used by various CGI software for dealing with sparse volumetric data such as Houdini, RenderMan, and Cinema 4D to the open-source Blender. It's even won an Academy Award for technical achievement while now in 2026 it's finally establishing a SIMD framework for better leveraging modern x86 ISA capabilities... ## NVIDIA Adds CUDA-Q Logical for Fault-Tolerant Quantum Application Design DevFeed: [NVIDIA Adds CUDA-Q Logical for Fault-Tolerant Quantum Application Design]() Original publisher: [Read original article]() Author: Harold Fritts Published: 2026-09-15T16:47:58Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [CUDA](), [Quantum Computing](), [Nvidia](), [Orchestration](), [Open Source](), [Algorithm]() Tags: [ai](), [algorithm](), [applications](), [cuda](), [enterprise](), [nvidia](), [open-source](), [orchestration](), [quantum]() ### AI overview NVIDIA added CUDA-Q Logical to its open-source CUDA-Q platform for designing applications on fault-tolerant quantum computers. Early-access reports say Fermilab reduced an algorithm design cycle from five months to three weeks, while Iceberg Quantum modeled a Diraq spin-qubit architecture using about 150,000 physical qubits for 1,000 logical qubits. ### Source excerpt NVIDIA has added CUDA-Q Logical to its open-source CUDA-Q platform, an orchestration layer for building applications that run on fault-tolerant quantum computers, and it arrives with two numbers that are interesting. Fermilab says the tool cut a fault-tolerant algorithm design cycle from five months to three weeks, and Iceberg Quantum used it to show that The post NVIDIA CUDA-Q Logical Debuts With a 7x Fermilab Speedup and a 10x Cut in Diraq's Qubit Estimate appeared first on StorageReview.com. ## High-Throughput Structure Prediction with BioNeMo Inference Runtime DevFeed: [High-Throughput Structure Prediction with BioNeMo Inference Runtime]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-09-10T15:00:00Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI, ML & Data Engineering]() Tags: [bionemo](), [cuda](), [cuda-graphs](), [data-center-cloud](), [data-science](), [drug-discovery](), [gpu](), [healthcare-life-sciences](), [how-to](), [hpc-scientific-computing](), [inference](), [integration](), [kernels](), [model](), [models](), [node](), [nvidia](), [python](), [pytorch](), [resource](), [scale](), [simulation-modeling-design](), [tokenization](), [torch](), [tutorial](), [workflow]() ### AI overview A tutorial on using NVIDIA BioNeMo Inference Runtime to accelerate biomolecular structure-prediction models on GPUs. It covers the end-to-end Boltz2 workflow, PyTorch integration, input requirements, and Ray-based single-node throughput scaling. ### Source excerpt Biomolecular structure prediction is now often run at proteome scale, where the goal is to move an entire worklist through the pipeline efficiently. NVIDIA... ## CUDA Toolkit 13.4 Adds Windows on Arm Support and Greater Control over Shared GPUs DevFeed: [CUDA Toolkit 13.4 Adds Windows on Arm Support and Greater Control over Shared GPUs]() Original publisher: [Read original article]() Author: Jonathan Bentz Published: 2026-09-09T20:24:12Z Content type: release Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [CUDA](), [GPU](), [NVLink](), [Orchestration]() Tags: [cli](), [cuda](), [cuda-tile](), [developer-tools-techniques](), [gpu](), [nsight-tools-compute](), [nvidia](), [nvlink](), [release](), [simulation-modeling-design](), [top-stories](), [windows]() ### AI overview CUDA Toolkit 13.4 adds Windows on Arm support, preview support for the NVIDIA Rubin GPU architecture, and new GPU-sharing controls through MPS V3. It also introduces CUDA Compute Fabric Transport for data movement across NVIDIA NVLink fabric. ### Source excerpt Every NVIDIA CUDA Toolkit release adds functionality and performance improvements that help developers get more from NVIDIA GPUs and the broader NVIDIA software... ## Introducing CUDA Rust: Two Tracks for Writing GPU Kernels DevFeed: [Introducing CUDA Rust: Two Tracks for Writing GPU Kernels]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-09-08T12:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [GPU](), [Code generation](), [toolchain](), [C++]() Tags: [c-plus-plus](), [cuda](), [cuda-tile](), [data-science](), [developer-tools-techniques](), [dynamo](), [gpu](), [kernels](), [nemo-retriever](), [open-source](), [programming-languages-compilers](), [rust](), [toolchains]() ### AI overview NVIDIA introduces CUDA Rust for writing GPU kernels natively in Rust and compiling them to PTX. The article explains the SIMT and Tile programming tracks, recommends Tile as the default, and describes cuda-oxide's Rust-based code-generation path. ### Source excerpt In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains, and... ## Cut GPU inference cold start from 8 minutes to less than a minute DevFeed: [Cut GPU inference cold start from 8 minutes to less than a minute]() Original publisher: [Read original article]() Author: Sajjan Gundapuneedi Published: 2026-09-03T18:30:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [GPU](), [Inference](), [model-deployment](), [Amazon Elastic Kubernetes Service](), [CUDA](), [Optimization](), [Amazon S3](), [Kubernetes]() Tags: [ai-infrastructure](), [amazon-eks](), [aws-marketplace](), [cpu](), [cuda](), [gpu](), [inference](), [kubernetes](), [large-language-models](), [optimization](), [post-contributed](), [s3](), [sponsor-aws-marketplace](), [sponsored-post-contributed]() ### AI overview The article measures GPU model startup from pod creation to the first inference response and identifies six sequential phases. It reports that CUDA kernel recompilation dominates startup for a 64 GB model, while S3 weight downloads dominate for a 203 GB model. Configuration and platform changes reduced warm-node startup times by 80-93%, with additional cold-node improvements requiring Amazon EKS Auto Mode. ### Source excerpt We instrumented the full path from pod creation to first inference response on a GPU node running a 70B-class model. The post Cut GPU inference cold start from 8 minutes to less than a minute appeared first on The New Stack. ## The Modern CUDA Toolbox in Practice: A Step-by-Step Optimization Walkthrough DevFeed: [The Modern CUDA Toolbox in Practice: A Step-by-Step Optimization Walkthrough]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-09-02T17:15:57Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [CUDA](), [Optimization](), [GPU](), [toolchain](), [debug](), [Instrumentation](), [Algorithms]() Tags: [algorithms](), [benchmark](), [cuda](), [debug](), [developer-tools-techniques](), [gpu](), [how-to](), [image-processing](), [instrumentation](), [memory](), [optimization]() ### AI overview A step-by-step CUDA optimization walkthrough that improves an image-processing pipeline with debugging, benchmarking, optimized algorithms, GPU memory management, pinned transfers, streams, and asynchronous transfers. ### Source excerpt NVIDIA CUDA remains the foundation of GPU-accelerated computing, powering everything from scientific simulations to large-scale AI training. But writing... ## Fast model loading for AI inference on Amazon EKS DevFeed: [Fast model loading for AI inference on Amazon EKS]() Original publisher: [Read original article]() Author: Sajjan Gundapuneedi Published: 2026-09-01T15:48:15Z Content type: article Language: en Sources: [Containers]() Topics: [Inference Performance](), [Amazon Elastic Kubernetes Service](), [Amazon S3](), [Language models]() Tags: [advanced-300](), [ai](), [ai-inference](), [amazon-eks](), [amazon-elastic-kubernetes-service](), [best-practices](), [cuda](), [gpu](), [inference](), [kubernetes](), [language-models](), [pytorch](), [s3](), [sglang](), [startup](), [vllm]() ### AI overview The article analyzes cold-start delays for AI inference pods on Amazon EKS. It finds that startup bottlenecks vary by model size: torch.compile dominates for smaller models, while loading weights from S3 to GPU memory dominates for larger models. Configuration changes to Run:ai Model Streamer reduce model-loading time on repeat launches. ### Source excerpt When you scale AI inference on Amazon EKS, every new pod must load model weights into GPU memory before serving traffic. We investigated where cold-start time goes and found two configuration-only changes to Run:ai Model Streamer that cut model startup time by 80-93% on subsequent launches, with no code changes. ## How to Train a Cross-Embodiment Robot Navigation Policy with AI Agents DevFeed: [How to Train a Cross-Embodiment Robot Navigation Policy with AI Agents]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-08-26T20:05:06Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Artificial Intelligence](), [Reinforcement learning](), [codex](), [coding](), [Simulation and Design](), [CUDA]() Tags: [agent](), [agentic-ai-generative-ai](), [ai](), [ai-agent](), [ai-agents](), [architecture](), [codex](), [coding](), [cuda](), [development](), [evaluation](), [framework](), [nvidia](), [omniverse](), [physical-ai](), [reinforcement-learning](), [robotics](), [simulation-modeling-design](), [skills](), [testing](), [training](), [tutorial](), [workflow]() ### AI overview This tutorial presents an agent-driven COMPASS workflow for training and evaluating cross-embodiment robot navigation policies. It covers asset preparation, smoke testing, residual reinforcement learning, checkpoint evaluation, runtime integration, and optional reconstructed environments using NVIDIA Omniverse NuRec. ### Source excerpt Navigation enables a robot to turn perception and motion into purposeful autonomy. Unlike locomotion, which produces stable movement, navigation must be used to... ## Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo DevFeed: [Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-08-25T20:57:54Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Large Language Model](), [Inference](), [model-deployment](), [Nvidia](), [Optimization](), [CUDA](), [Processes](), [GPU](), [NCCL](), [sglang]() Tags: [agentic-ai-generative-ai](), [cuda](), [cuda-x](), [data-science](), [deployment](), [developer-tools-techniques](), [gpu](), [inference](), [llm](), [models](), [nccl](), [nvidia](), [optimization](), [process]() ### AI overview This article explains NVIDIA Dynamo's shadow engine recovery for LLM inference. A fully initialized shadow engine shares weights with the active engine and takes over after a process failure, reducing recovery from a 283-second cold restart to 7.3 seconds in the described two-worker deployment. ### Source excerpt When an LLM engine process fails, the standard recovery path involves a cold restart. This requires loading weights into HBM from storage, compiling kernels,... ## CUDA Python 1.0: Stable APIs, One Foundation, Full Platform Access DevFeed: [CUDA Python 1.0: Stable APIs, One Foundation, Full Platform Access]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-08-25T15:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [CUDA](), [Python](), [GPU](), [C++](), [toolchain](), [PyTorch](), [RAPIDS](), [releases]() Tags: [c-plus-plus](), [cuda](), [data-science](), [developer-tools-techniques](), [gpu](), [numba](), [python](), [pytorch](), [rapids](), [release](), [toolchain]() ### AI overview CUDA Python 1.0 makes the CUDA platform accessible from Python through stable, versioned components, including runtime access, low-level CUDA C API bindings, parallel algorithms, component discovery, and NVIDIA math libraries. The release establishes a shared foundation for Python GPU libraries and introduces semantic-versioning commitments for public APIs. ### Source excerpt For years, a Python developer who needed a GPU had two realistic choices: Learn NVIDIA CUDA C++ well enough to write an extension, set up a build toolchain, and... ## Hot Chips 2026: CUDA Targets RISC-V DevFeed: [Hot Chips 2026: CUDA Targets RISC-V]() Original publisher: [Read original article]() Author: Chester Lam Published: 2026-08-24T16:49:25Z Content type: article Language: en Sources: [Chips and Cheese]() Topics: [CUDA](), [RISC-V](), [Nvidia](), [GPU](), [Software]() Tags: [cache](), [cuda](), [framework](), [gpu](), [nvidia](), [pcie](), [risc-v](), [software](), [uefi]() ### AI overview The article reports that Nvidia is exploring support for CUDA on RISC-V CPUs. It describes requirements including RVA23, server SoC and platform specifications, RISC-V ACPI support, vector extensions, and PCIe coherency to support reliable and efficient GPU compute. ### Source excerpt CUDA is the most important software framework in the GPU compute world, and Nvidia is looking at supporting CUDA on RISC-V. Terms and conditions may apply. ## How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit DevFeed: [How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-08-18T18:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [ALCHEMI](), [AI-assisted coding](), [Agent Skills](), [PyTorch](), [CUDA](), [GPU](), [Python](), [AI Development]() Tags: [agent-skills](), [agentic-ai-generative-ai](), [ai-agent](), [ai-coding](), [alchemi](), [coding](), [computational-chemistry-materials-science](), [compute](), [cuda](), [developer-tools-techniques](), [featured](), [gpu](), [python](), [pytorch](), [simulation-modeling-design]() ### AI overview This article presents an end-to-end workflow for using AI coding agents with NVIDIA ALCHEMI Toolkit to build GPU-accelerated atomistic materials simulations. It explains how ALCHEMI agent skills and reference files provide API knowledge, describes the Python, PyTorch, CUDA and NVIDIA GPU environment, and reports validation across 45 generated pipelines. ### Source excerpt Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the... ## NVIDIA JetPack 7.2.1 Adds Agentic Video Skills and T3000 Emulation DevFeed: [NVIDIA JetPack 7.2.1 Adds Agentic Video Skills and T3000 Emulation]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-08-11T19:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Jetson](), [SDKs](), [CUDA](), [GPU](), [AI Inference](), [Inference Performance](), [Latency](), [Low Latency](), [C++](), [Python](), [Artificial Intelligence](), [Automation]() Tags: [agentic-ai-generative-ai](), [ai-inference](), [automation](), [c-plus-plus](), [cuda](), [edge-computing](), [featured](), [gpu](), [inference](), [jetpack](), [jetson](), [latency](), [low-latency](), [nvidia](), [python](), [robotics](), [robotics-compute](), [sdks](), [video-analytics](), [video-codec-sdk]() ### AI overview NVIDIA JetPack 7.2.1 adds PyNvVideoCodec 2.2 support on Jetson Thor, enabling Python-based hardware video encoding and decoding with GPU-resident frames. It also introduces agentic video skills that turn developer goals into device inspection, configuration, execution, measurement, and evidence-driven codec workflows. ### Source excerpt Video is a core data path across NVIDIA Jetson applications, from robotics and intelligent video analytics to industrial automation, healthcare, media... ## Pulling multi-gigabyte container images in seconds on Amazon EKS DevFeed: [Pulling multi-gigabyte container images in seconds on Amazon EKS]() Original publisher: [Read original article]() Author: Sri Saran Balaji Vellore Rajakumar Published: 2026-08-10T16:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Amazon Elastic Kubernetes Service](), [container images](), [Machine learning](), [autoscaling](), [CUDA]() Tags: [ai-infrastructure](), [amazon-eks](), [autoscaling](), [aws-marketplace](), [container](), [container-images](), [containers](), [cuda](), [kubernetes](), [machine-learning](), [post-contributed](), [sponsor-aws-marketplace](), [sponsored-post-contributed]() ### AI overview This article explains how a production ML platform on Amazon EKS reduced multi-minute pulls of roughly 30 GB container images to seconds. Profiling found that software use of available hardware, rather than network bandwidth or the registry, was the main constraint; the resulting changes are available by default in EKS Auto Mode and were contributed upstream to containerd and the SOCI snapshotter. ### Source excerpt When the image is the bottleneck: Machine learning changed what a container image looks like. A typical application ships in The post Pulling multi-gigabyte container images in seconds on Amazon EKS appeared first on The New Stack. ## Run High-Performance Core Math at Scale with NVIDIA nvmath-python DevFeed: [Run High-Performance Core Math at Scale with NVIDIA nvmath-python]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-07-30T22:43:04Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Python](), [CUDA](), [math](), [GPU](), [NumPy](), [cpu](), [PyTorch](), [pip]() Tags: [agentic-ai-generative-ai](), [c-plus-plus](), [ci-cd](), [cpu](), [cuda](), [cuda-x](), [data-science](), [developer-tools-techniques](), [device-apis](), [featured](), [gpu](), [multi-gpu](), [nvidia](), [performance](), [python](), [pytorch](), [scale]() ### AI overview NVIDIA nvmath-python 1.0 provides a Pythonic interface to CUDA-X and NVPL math libraries, enabling optimized numerical operations on CPUs, CUDA GPUs, and distributed multi-GPU, multi-node systems. The article covers its sparse-tensor approach, flexible installation options, and interoperability with NumPy, CuPy, and PyTorch. ### Source excerpt NVIDIA nvmath-python is a library designed to bridge the gap between the Python scientific community and NVIDIA CUDA-X math libraries. It gives Python users... ## Advancing Semiconductor Innovation Across Materials Engineering and Manufacturing DevFeed: [Advancing Semiconductor Innovation Across Materials Engineering and Manufacturing]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-07-27T00:45:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Artificial Intelligence](), [CUDA](), [GPU](), [Optimization](), [Nvidia](), [Simulation and Design](), [Hardware]() Tags: [ai](), [computational-chemistry-materials-science](), [compute](), [cuda](), [cuda-x](), [data-center-cloud](), [engineering](), [featured](), [gpu](), [hardware](), [industrial-digitalization-digital-twin](), [manufacturing](), [nvidia](), [optimization](), [physics](), [production](), [simulation-modeling-design]() ### AI overview Applied Materials and NVIDIA are presented as combining materials engineering, semiconductor manufacturing, CUDA-X libraries, GPU-accelerated simulation, physics-based modeling, and AI-driven digital twins in an end-to-end digital development model. The approach spans atomic-scale materials discovery, process development, and factory optimization, with Ginestra used to connect material defects and properties to predicted device performance. ### Source excerpt As AI workloads increase, explosive compute demand is pushing the semiconductor industry to meet unprecedented performance targets. Even small delays can have... ## Debugging Ray Tracing Applications Using NVIDIA OptiX Toolkit DevFeed: [Debugging Ray Tracing Applications Using NVIDIA OptiX Toolkit]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-07-23T16:07:03Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [debugging](), [SDKs]() Tags: [api](), [cuda](), [debugging](), [developer-tools-techniques](), [errors](), [featured](), [gaming](), [github](), [gpu](), [nvidia](), [ray-tracing](), [ray-tracing-path-tracing](), [testing](), [validation]() ### AI overview The article explains how NVIDIA OptiX Toolkit debugging facilities help diagnose GPU ray-tracing application failures, including API error checking and device-side debug printing. ### Source excerpt NVIDIA OptiX ray tracing engine is an application framework for achieving optimal ray tracing performance on the GPU. Applications using OptiX can fail in ways... ## Building Faster Cryptography with Carryless Multiplication in NVIDIA CUDA 13.3 DevFeed: [Building Faster Cryptography with Carryless Multiplication in NVIDIA CUDA 13.3]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-07-15T17:37:12Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Cryptography]() Tags: [benchmark](), [cryptography](), [cuda](), [developer-tools-techniques](), [encryption](), [featured](), [gpu](), [hardware](), [nvidia](), [trustworthy-ai-cybersecurity](), [zero-knowledge]() ### AI overview NVIDIA CUDA 13.3 adds a carryless-multiplication PTX instruction for Ampere-and-newer GPUs. The article benchmarks GHASH and zero-knowledge sum-check workloads, describing substantial throughput gains and explaining binary extension-field arithmetic. ### Source excerpt For over fifteen years, x86 CPUs have shipped with a dedicated hardware instruction for carryless multiplication. It's a small but stubborn primitive that... ## Kernel Fusion in NVIDIA CUDA: Optimizing Memory Traffic and Launch Overhead DevFeed: [Kernel Fusion in NVIDIA CUDA: Optimizing Memory Traffic and Launch Overhead]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-07-10T16:41:03Z Content type: tutorial Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [GPU](), [C++]() Tags: [c-plus-plus](), [cuda](), [cuda-graphs](), [developer-tools-techniques](), [featured](), [gpu](), [kernel](), [launch](), [memory](), [nvidia](), [performance]() ### AI overview This tutorial explains CUDA kernel fusion for GPU optimization. Combining operations into one kernel keeps intermediate values in registers, reduces global-memory traffic, and avoids separate kernel launches; it also distinguishes this approach from CUDA Graphs. ### Source excerpt There are many ways to optimize code for GPUs. In this post, you'll learn how kernel fusion can improve memory bandwidth and reduce kernel launch overhead,... ## Accelerating End-to-End Co-Folding Performance with NVIDIA BioNeMo Agent Toolkit DevFeed: [Accelerating End-to-End Co-Folding Performance with NVIDIA BioNeMo Agent Toolkit]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-07-10T13:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI, ML & Data Engineering](), [cpu]() Tags: [agentic-ai-generative-ai](), [ai-agents](), [bionemo](), [cuda](), [developer-tools-techniques](), [drug-discovery](), [featured](), [gpu](), [healthcare-life-sciences](), [hpc-scientific-computing](), [inference](), [multi-gpu](), [nvidia](), [performance](), [simulation-modeling-design]() ### AI overview The article describes NVIDIA BioNeMo Agent Toolkit accelerations for biomolecular co-folding workflows, focusing on faster MSA generation, inference, serving, and multi-GPU scaling for drug-discovery workloads. ### Source excerpt Biomolecular structure prediction and co-folding with models like OpenFold3 are now mainstream, large-scale workloads powering drug discovery and protein... ## Как проект из ШАДа попал в Spotlight статей на конференции ICML 2026 DevFeed: [Как проект из ШАДа попал в Spotlight статей на конференции ICML 2026]() Original publisher: [Read original article]() Author: mightyneighbor (Яндекс) Published: 2026-07-06T07:04:35Z Content type: article Language: ru Sources: [Яндекс - Как мы делаем Яндекс / Статьи]() Topics: [GPU](), [Graphs](), [Machine learning]() Tags: [2026](), [ai](), [cuda](), [gpu](), [graph](), [icml](), [icml-2026](), [ml](), [research](), [spotlight](), [tag-1e7f0701b819](), [tag-4004cf5948d3]() ### AI overview The article explains why graph neural networks underutilize modern GPUs: their irregular, sparse memory access patterns leave the hardware waiting for data. It describes a project that investigated the problem and produced three families of specialized GPU kernels. The resulting paper, "On Efficient Scaling of GNNs via IO-Aware Layer Implementations," was accepted to ICML 2026 as a Spotlight paper. ### Source excerpt Граф из миллионов вершин не загружает современную GPU на все 100%: видеокарта почти всё время не вычисляет, а ждёт загрузки данных из памяти. Графовые нейросети, или GNN, упираются в это давно: сами операции достаточно простые, но доступ к памяти нерегулярный и разреженный. И чем мощнее GPU, тем заметнее недостаточная её утилизация. Идея выросла из проектного курса в ШАДе. Толчком стало то, что один из самых популярных фреймворков для работы с графами, Deep Graph Library, на момент начала работы не обновлялся уже около года -- это знак того, что в области что-то застряло. Меня зовут Федя Великонивцев, я старший исследователь Yandex Research, руковожу группой, которая занимается эффективными вычислениями на GPU. На том курсе мы с коллегами -- Дарьей Фоминой из команды ML-инфраструктуры Яндекса, Вячеславом Ждановским из команды разработки инференса -- и студентами Даниилом Красильниковым, Алексеем Бойковым и Андреем Долговязовым взялись выяснить, почему графовые нейросети тормозят на современных GPU. Так появился проект, который мы оформили в отдельную статью -- On Efficient Scaling of GNNs via IO-Aware Layer Implementations. Её приняли на ICML-2026 со статусом Spotlight. Для контекста: из 23 918 поданных работ приняли 6 352 (26,6%), а Spotlight достался только 536 работам -- это 2,2% заявок с самыми высокими оценками программного комитета. Дальше расскажу, как мы прошли путь от этого вопроса до трёх семейств специализированных GPU-кернелов -- с парой неожиданных находок по дороге. Читать далее ## Designing GPU-Accelerated Query Engines with NVIDIA GQE DevFeed: [Designing GPU-Accelerated Query Engines with NVIDIA GQE]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-06-30T17:36:43Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [GPU](), [Databases](), [NCCL](), [CUDA](), [NVLink](), [Compression](), [IO](), [SQL](), [Parser](), [Streaming](), [Hardware](), [Open Source]() Tags: [accelerate](), [compression](), [cpu](), [cuda](), [cuda-x](), [data](), [data-analytics-processing](), [data-center-cloud](), [data-science](), [databases](), [featured](), [gpu](), [hardware](), [memory](), [nvidia](), [nvlink](), [performance](), [sql]() ### AI overview This article presents GQE, a reference architecture for executing SQL queries on GPUs. It explains how NVIDIA hardware and CUDA-X libraries address memory, I/O, data movement, decompression, and end-to-end performance challenges for large datasets. ### Source excerpt GPU-accelerated query engines are often constrained by memory and I/O bandwidth. NVIDIA hardware advances--including high bandwidth memory (HBM), NVIDIA... [Next page]()