#cuda-tile
LightNews LightNews
fronkongames.bsky.social
NVIDIA CUDA 13.3 Rolls Out CUDA Python 1.0, CUDA Tile For C++

#indiedev #gamedev #gamedevelopment #python #cuda #nvidia
NVIDIA CUDA 13.3 Rolls Out CUDA Python 1.0, CUDA Tile For C++ - Phoronix
NVIDIA-CUDA-13.3-Released
www.phoronix.com
May 28, 2026 at 7:11 PM
phoronix-poster.bsky.social
NVIDIA Releases CUDA 13.1 With New "CUDA Tile" Programming Model - https://www.phoronix.com/news/NVIDIA-CUDA-13.1
NVIDIA Releases CUDA 13.1 With New "CUDA Tile" Programming Model
NVIDIA just released CUDA 13.1 for what they claim is "the largest and most comprehensive update to the CUDA platform since it was invented two decades ago." The most notable addition with the CUDA 13.1 release is CUDA Tile as a new tile-based programming model...
www.phoronix.com
December 4, 2025 at 10:56 PM
phoronix-poster.bsky.social
NVIDIA CUDA Tile IR Open-Sourced - https://www.phoronix.com/news/NVIDIA-CUDA-Tile-IR-Open-Source
NVIDIA CUDA Tile IR Open-Sourced
As a wonderful Christmas gift to open-source fans, NVIDIA dropped their proprietary license on the CUDA Tile intermediate representation and has now made the IR open-source software...
www.phoronix.com
December 25, 2025 at 8:33 PM
sungkim.bsky.social
Nvidia's CUDA Tile

It's an array-based paradigm where the compiler automates mem movement, pipelining & tensor core utilization, making GPU programming easier & more portable.
December 6, 2025 at 1:22 AM
phoronix-poster.bsky.social
NVIDIA Hiring More LLVM Engineers To Work On CUDA Tile - https://www.phoronix.com/news/NVIDIA-More-Engineers-CUDA-Tile
NVIDIA Hiring More LLVM Engineers To Work On CUDA Tile
Last year NVIDIA announced the new CUDA Tile programming model as one of the biggest updates ever to the CUDA platform. CUDA Tile brings a virtual ISA for tile-based parallel programming and they subsequently open-sourced the CUDA Tile IR as an intermediate representation built atop LLVM's MLIR. Now they are looking to hire additional LLVM compiler engineers to help foster their CUDA Tile initiatives...
www.phoronix.com
April 13, 2026 at 3:54 PM
sungkim.bsky.social
Docs: developer.nvidia.com/cuda/tile
Repo: github.com/NVIDIA/cutil...
NVIDIA CUDA Tile
A tile-based GPU programming model that targets portability for NVIDIA Tensor Cores.
developer.nvidia.com
December 6, 2025 at 1:22 AM
meetingcpp.bsky.social
CUDA 13.2 Introduces Enhanced CUDA Tile Support and New Python Features
developer.nvidia.com/blog/cuda-13...
#cpp
#cplusplus
CUDA 13.2 Introduces Enhanced CUDA Tile Support and New Python Features | NVIDIA Technical Blog
CUDA 13.2 arrives with a major update: NVIDIA CUDA Tile is now supported on devices of compute capability 8.X architectures (NVIDIA Ampere and NVIDIA Ada), as well as 10.X, 11.X and 12.
developer.nvidia.com
March 13, 2026 at 10:31 AM
sungkim.bsky.social
Blog: developer.nvidia.com/blog/focus-o...
Focus on Your Algorithm—NVIDIA CUDA Tile Handles the Hardware | NVIDIA Technical Blog
With its largest advancement since the NVIDIA CUDA platform was invented in 2006, CUDA 13.1 is launching NVIDIA CUDA Tile. This exciting innovation introduces a virtual instruction set for tile-based…
developer.nvidia.com
December 6, 2025 at 1:26 AM
meetingcpp.bsky.social
NVIDIA CUDA 13.3 Enhances GPU Development with Tile Programming in C++, Compiler Autotuning, and Python Updates
developer.nvidia.com/blog/nvidia-...
#cpp
#cplusplus
NVIDIA CUDA 13.3 Enhances GPU Development with Tile Programming in C++, Compiler Autotuning, and Python Updates | NVIDIA Technical Blog
NVIDIA CUDA 13.3 brings new capabilities and performance optimizations to developers across the CUDA ecosystem. The launch of NVIDIA CUDA Tile programming in C++, enables high-level…
developer.nvidia.com
May 27, 2026 at 9:18 PM
derdreschi84.bsky.social
NVIDIA CUDA 13.3 Rolls Out CUDA Python 1.0, CUDA Tile For C++
#Linux
NVIDIA CUDA 13.3 Rolls Out CUDA Python 1.0, CUDA Tile For C++
www.phoronix.com
May 28, 2026 at 4:51 AM
buysellram.bsky.social
The Largest CUDA Update in 20 Years: CUDA 13.1 Reconstructs GPU Programming

www.buysellram.com/blog/cuda-13...

#CUDA #CudaTile #Nvidia #GPU #GPUPrograming #CUDA131 #HPC #Blackwell #TileProgramming #DeveloperTools #GPUComputing
CUDA 13.1 Reinvents GPU Development — The Biggest Leap in Two Decades
CUDA 13.1 introduces the new CUDA Tile model, the biggest overhaul in 20 years, redefining GPU programming for AI, HPC, and future Blackwell GPUs
www.buysellram.com
December 8, 2025 at 3:12 PM
phoronix-poster.bsky.social
NVIDIA CUDA 13.3 Rolls Out CUDA Python 1.0, CUDA Tile For C++ - https://www.phoronix.com/news/NVIDIA-CUDA-13.3-Released
NVIDIA CUDA 13.3 Rolls Out CUDA Python 1.0, CUDA Tile For C++
NVIDIA on Tuesday released CUDA 13.3 as another significant advancement for their unified GPU programming stack for NVIDIA hardware...
www.phoronix.com
May 27, 2026 at 8:32 PM
phoronix.com.web.brid.gy
NVIDIA Releases CUDA 13.1 With New "CUDA Tile" Programming Model
NVIDIA just released CUDA 13.1 for what they claim is "the largest and most comprehensive update to the CUDA platform since it was invented two decades ago." The most notable addition with the CUDA 13.1 release is CUDA Tile as a new tile-based programming model...
www.phoronix.com
December 4, 2025 at 11:04 PM
hgpu.bsky.social
Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

#Triton #CUDA #CUBLAS #LLM #Performance #Package

hgpu.org?p=30763
Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs
NVIDIA’s CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Acce…
hgpu.org
May 3, 2026 at 9:01 PM
dragonxi.dev
env2torch) X:\torch4xi\env2torch\Scripts>python -m pip show cuda-tile
Name: cuda-tile
Version: 0.0.0a0
Sum: Zero version placeholder for cuda-tile
NVIDIA Kitmaker Team <compute_installer@nvidia.com>
License: Apache-2.0
Location: X:\torch4xi\env2torch\Lib\site-packages
Requires:
Required-by: tilegym
April 10, 2026 at 8:13 AM
enakat-it.bsky.social
TileGymがcuTile PythonからRustへの変換ツールを公開
エンジニアへの影響：既存のCUDAカーネルをRustへ移行し性能比99.5%を実現可能に
https://developer.nvidia.com/blog/translating-cuda-tile-operations-from-python-to-rust-using-agentic-ai/
Translating CUDA Tile Operations from Python to Rust Using Agentic AI | NVIDIA Technical Blog
cuTile Rust () is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to tile-based GPU kernels, it splits mutable outputs…
developer.nvidia.com
September 19, 2026 at 9:00 PM
juliahub.bsky.social
cuTile.jl brings NVIDIA’s tile-based GPU programming model to Julia, making high-performance CUDA kernel development simpler, more accessible, and more productive. juliahub.com/blog/cutile....
#JuliaLang #AIInfrastructure #HighPerformanceComputing #GPUComputing #DeveloperTools
cuTile.jl: Bringing NVIDIA's Tile-Based GPU Programming to Julia - Blog - JuliaHub
An early release of cuTile.jl, a Julia package that makes it possible to program CUDA GPUs using a tile-based abstraction by NVIDIA, is now available
juliahub.com
March 12, 2026 at 5:40 PM
camilleroux.com
NVIDIA introduit Rust natif pour écrire des kernels GPU, jusque-là réservés à C++ ou Python. Deux approches proposées : SIMT (cuda-oxide, MIR/LLVM vers PTX) pour contrôler chaque thread, ou Tile pour raiso...
https://developer.nvidia.com/blog/introducing-cuda-rust-two-tracks-for-writing-gpu-kernels/
Capture d'écran de code source Rust pour la programmation GPU, affichant des directives de compilation CUDA avec des paramètres de threads et des fonctions kernel, illustrant la prise en charge native de Nvidia pour Rust en programmation GPU.
September 17, 2026 at 2:00 PM
juliahub.bsky.social
Explore this recorded webinar to see how cuTile.jl brings NVIDIA’s CUDA Tile model to Julia for AI, linear algebra, and HPC workloads. juliahub.com/videos/cutil...

#JuliaLang #GPUProgramming #CUDA #HPC #ScientificComputing
cuTile.jl for High-Performance Computing in Julia - Video - JuliaHub
Explore cuTile.jl in Julia to write high-performance GPU kernels for AI, linear algebra, and HPC using NVIDIA’s CUDA Tile model
juliahub.com
July 13, 2026 at 5:19 PM
yusukeohara.bsky.social
月刊連載
eetimes.itmedia.co.jp/ee/articles/...
担当者がCESに行ってて掲載がやや遅れました
NVIDIAがGroqを「事実上」買収　CUDA Tileが示す次の一手とは
2025年12月、GroqとNVIDIAが非独占的なテクノロジーライセンスの契約を結んだというニュースが発表された。これはNVIDIAによる、事実上のGroqの買収である。NVIDIAの狙いは何なのか。「CUDA」の課題や、新アーキテクチャ「CUDA Tile」の解説を交えて考えてみたい。
eetimes.itmedia.co.jp
January 19, 2026 at 3:39 AM
tech-trending.bsky.social
NVIDIAがGroqを「事実上」買収　CUDA Tileが示す次の一手とは
https://eetimes.itmedia.co.jp/ee/articles/2601/19/news051.html
NVIDIAがGroqを「事実上」買収　CUDA Tileが示す次の一手とは
2025年12月、GroqとNVIDIAが非独占的なテクノロジーライセンスの契約を結んだというニュースが発表された。これはNVIDIAによる、事実上のGroqの買収である。NVIDIAの狙いは何なのか。「CUDA」の課題や、新アーキテクチャ「CUDA Tile」の解説を交えて考えてみたい。
eetimes.itmedia.co.jp
January 20, 2026 at 2:41 AM
robertknight2.bsky.social
NVIDIA are experimenting with a safe Rust interface to CUDA Tile - www.youtube.com/watch?v=_b4I... (See 1:18:03). The whole presentation is worth a watch, especially around the balancing act of portability vs. predictable performance.
December 21, 2025 at 8:40 AM
rustaceans.bsky.social
NVIDIA Research open-sourced cutile-rs

>> cuTile-rs enables safe, idiomatic Rust GPU kernels with Rust ownership across host-GPU boundaries, using tile-based CUDA Tile IR for high-performance, data-race-free computing.

#rustlang #rust
June 19, 2026 at 7:50 AM
juliahub.bsky.social
March at JuliaHub: cuTile.jl brings NVIDIA’s CUDA Tile to Julia, Dyad 2.2 is here, and live Dyad workshops are coming to Europe. A strong month for modeling and scientific computing. juliahub.com/blog/march-2...
#JuliaHub #JuliaLang #Dyad #ScientificComputing #Simulation
March 2026 Newsletter: NVIDIA’s CUDA Tile in Julia & Dyad Live Workshops in Europe - Blog - JuliaHub
From the early release of cuTile.jl to hands-on Dyad modeling workshops in Europe, the March edition of our newsletter shares many glimpses from the world of Julia and JuliaHub
juliahub.com
March 18, 2026 at 4:02 PM
techpowerup.com
[PR] NVIDIA Announces CUDA Tile with CUDA 13.1
www.techpowerup.com
December 5, 2025 at 4:25 PM