#GPUcomputing
CUDA.jl 6.4 is here 🚀

🟢 Improved NVIDIA Jetson support
🟢 Compiled GPU code caching for faster TTFX
🟢 CUDA 13.4 support
🟢 LLVM 23 upgrade

See what's new → juliagpu.org/post/2026-09...

#JuliaLang #CUDA #GPUComputing
CUDA.jl 6.4: NVIDIA Jetson support, and compiled code caching ⋅ JuliaGPU
juliagpu.org
September 21, 2026 at 7:59 PM
CUDA.jl v5.6 & 5.7 bring major improvements! Async CUBLAS calls, a Julia-level caching allocator, and optimized #GPU memory usage—faster & more efficient computing. Upgrade now! juliagpu.org/post/2025-03... #JuliaLang #CUDA #GPUComputing #HPC
March 20, 2025 at 4:31 PM
Small changes, massive speed gains. 🚀

The Array API standard is transforming Python performance, enabling 50x speedups by moving libraries like scikit-learn and SciPy to the GPU.

Mateusz Sokół breaks down the latest benchmarks: buff.ly/ycoUlvD

#GPUComputing #PythonProgramming #Innovation
April 23, 2026 at 10:05 AM
Metal.jl 1.6 adds support for Apple’s MPSGraph, enabling better matrix operations and paving the way for advanced #GPU #workflows on M1/M2. Dive into the new capabilities and explore what’s next for Metal.jl. juliagpu.org/post/2025-05...
#JuliaLang #GPUComputing #MPSGraph #OpenSource #ML
June 24, 2025 at 3:23 PM
🧪Curious about high performance across GPUs? Our new paper benchmarks a parallel FSI code on CUDA, SYCL & OpenMP across top systems. See Aristotle Martin present it at #ISC2025 on June 11, 10:45 in Hamburg!

#HPC #GPUcomputing #PerformancePortability
June 10, 2025 at 8:52 PM
CUDA.jl 5.8 adds broadcasting for CuSparseVector, support for CUDA 12.9, and key library updates—making it easier to write efficient, element-wise #GPU operations in Julia without sacrificing clarity or #performance. juliagpu.org/post/2025-05... #JuliaLang #CUDA #GPUcomputing #programming
June 3, 2025 at 7:21 PM
Show HN: Agentic CUDA Kernel Optimizer
Discussion | hackernews | Author: bertaye

#GPUComputing
Show HN: Agentic CUDA Kernel Optimizer
A langgraph based workflow with a C++ CUDA suite to optimize CUDA kernels - bertaye/agentic-cuda-optimizer
github.com
September 25, 2026 at 11:45 AM
Oceananigans.jl uses Julia and #GPU magic to build high-fidelity, scalable ocean #simulations from scratch. With kernel fusion, adaptive numerics, and communication-light solvers, it's setting a new standard in #performance. hackernoon.com/from-code-to... #JuliaLang #GPUComputing #ClimateTech #HPC
From Code to Currents: Julia and GPU Magic Transform Ocean Modeling Efficiency | HackerNoon
Oceananigans.jl leverages Julia for advanced ocean simulations, combining GPU-optimized WENO schemes with efficient barotropic solvers to boost climate modeling
hackernoon.com
April 1, 2025 at 4:41 PM
Write once. Run across #CPUs and #GPUs from different vendors. See how JACC.jl enables portable parallel Julia code from one codebase in a live ORNL #webinar. juliahub.com/videos/build...

#julialang #HPC #GPUComputing
Build Portable CPU/GPU Code in Julia with Minimal Effort - Video | JuliaHub
Build portable CPU/GPU code in Julia with JACC.jl. Learn vendor-neutral parallel computing from a single codebase for modern HPC workflows.
juliahub.com
July 30, 2026 at 6:03 PM
fatbin tools for object files
tech_blogs_redplait_blogspot_com | Author: redp

#GPUComputing
fatbin tools for object files
Yesterday, I needed to patch CUBIN inside object file, and my fb failed to do it. Let's check why: file bobhash32.o bobhash32.o: ELF 64-bit...
redplait.blogspot.com
September 24, 2026 at 1:45 PM
Julia’s GPU-accelerated ODE solvers deliver 20–100× speedups over JAX and PyTorch. In this talk, Chris Rackauckas explains the GPU architecture choices behind the gains—and where they matter most.
youtu.be/ZSFfv2cckx0

#JuliaLang #GPUComputing #SciML #HPC #ScientificComputing
Chris Rackauckas-Why Julia_s GPU-Accelerated ODE Solvers are 20x-100x Faster than Jax and PyTorch
YouTube video by PyData
youtu.be
February 6, 2026 at 6:14 PM
Meet the team (Bernardo de Souza and Christoph Riplinger) at the #NVIDIA Atomistic Simulation Summit 2026 and learn more about fast GPU-accelerated calculations with #ORCA via #cuEST and about #SURFF.

#CompChem #ChemSky #QuantumChemistry #GPUComputing #HPC #ML #FACCTs #MPIKofo
September 3, 2026 at 7:12 AM
🌟 Proud PI Moment! 🌟

Aristotle Martin crushed it at #SC24 with his talk — a highlight of the week! 🚀👏

📖 Missed it? Read the paper here: duke.is/sc24

If #GPUComputing, #Supercomputing, or scalable biological modeling excites you, let’s connect! 🧠💻
November 22, 2024 at 4:17 PM
An N-body #simulation with 262,000 particles running in real time in the browser using #WebGPU compute. This is wild. Built with #Claude 🤖 🌌
vislupus.github.io/ai-generated...
#AI #ClaudeCode #Opus46 #Tech #AICreation #Coding #AIEngineering #CreativeCoding #GPU #JavaScript #GPUComputing #vibecoding
February 14, 2026 at 10:46 AM
Explore #GPU acceleration in Julia’s #SciML! From ODEs to optimization, learn how SciML leverages GPUs for 20x-100x speedups over PyTorch & JAX. Watch the full talk now! youtu.be/PDGe2cEHWNk?... #JuliaLang #GPUComputing #juliacon
GPU Acceleration of Julia's SciML: ODEs, Optimization, and more | Smith, Smith | JuliaCon 2024
YouTube video by The Julia Programming Language
youtu.be
March 4, 2025 at 3:53 PM
𝗟𝗨𝗠𝗜 𝗛𝗮𝗰𝗸𝗮𝘁𝗵𝗼𝗻 (𝟭𝟮-𝟭𝟲/𝟬𝟱 𝗢𝘀𝗹𝗼): 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗲 𝗳𝗼𝗿 𝗔𝗠𝗗 𝗚𝗣𝗨𝘀!
Get free expert support to optimize your software LUMI-G!
🔹 Open to researchers, PhDs, postdocs & companies in LUMI/EuroHPC countries.
🔹 Apply before March 31: ssl.eventilla.com/hackathon2025

#LUMI #Hackathon #AMD #HPC #GPUComputing
February 24, 2025 at 6:07 PM
JACC v1.0 brings performance-portable parallelism to CPU & GPU computing with high-level APIs for arrays and execution. Born at Oak Ridge to turn DOE HPC research into practical tools for scientists.
github.com/JuliaGPU/JAC...

#JuliaLang #HPC #GPUComputing #OpenSource
GitHub - JuliaGPU/JACC.jl: CPU/GPU portable array, parallel_for/parallel_reduce in Julia for productive science. Funded by the US DOE Advanced Scientific Computing Research (ASCR).
CPU/GPU portable array, parallel_for/parallel_reduce in Julia for productive science. Funded by the US DOE Advanced Scientific Computing Research (ASCR). - JuliaGPU/JACC.jl
github.com
February 19, 2026 at 4:15 PM
#GPU #programming without vendor lock-in? Learn how KernelAbstractions.jl enables portable, high-performance GPU kernels in Julia—flexible, efficient & scalable. Watch now! juliahub.com/company/reso... #JuliaLang #GPUComputing #HPC #MachineLearning
Vendor-Neutral GPU Programming in Julia
Learn vendor-neutral GPU programming in Julia using KernelAbstractions.jl and array abstractions for efficient, portable, and flexible GPU code.
juliahub.com
March 10, 2025 at 4:46 PM
🚀 Szkolenie online: Introduction to Massively Parallel GPU Computing with CUDA!
📅 25 marca & 1 kwietnia, 15:00-18:00 CET
🤖 Naucz się programowania równoległego na GPU z użyciem CUDA!
Więcej informacji: cc.eurohpc.pl/index.php/sz...
#CUDA #HPC #GPUComputing #EuroCC #Superkomputery
March 14, 2025 at 9:56 AM
Georgia Tech, in collaboration with NVIDIA and the OpenACC organization, is hosting a virtual Open Hackathon from January 14 to January 30!

Learn more and register today: www.ai4opt.org/news-events/...

#Hackathon #Supercomputing #OpenACC #GPUComputing #GeorgiaTech
Georgia Tech Open Hackathon | Artificial Intelligence Institute for Advances in Optimization
www.ai4opt.org
January 8, 2025 at 6:01 PM
Where innovation meets learning, and students get a glimpse into the future of AI, GPU computing, and cutting-edge technology.

#NVIDIA #GalgotiasUniversity #DesignTogether #ArtificialIntelligence #Innovation #TechEducation #FutureReady #MachineLearning #GPUComputing #StudentInnovation
September 3, 2026 at 5:55 PM
🌊🐠 𝗡𝗲𝘄 𝗨𝘀𝗲𝗿 𝗦𝘁𝗼𝗿𝘆 𝗼𝘂𝘁! The team of Prof. Emmanuel Hanert at UCLouvain harnessed the power of GPU computing on the @lumi-supercomputer.eu to transform ocean modelling and conservation strategies 🌱🖥 💪💻
Read the story 👀🔗 www.enccb.be/USGreatBarri...
#LUMI #GPUComputing #GreatBarrierReef"
March 13, 2025 at 10:50 AM
NVIDIA DSX OS: modular operating system for AI factories

#AiInfrastructure #GpuComputing #Kubernetes
June 1, 2026 at 6:33 AM
Senior Applied AI Engineer @ Alembic.
Build GPU-resident systems delivering real-time causal analytics for Fortune 500 clients like NVIDIA.
🔧Python, GPUs, Causal AI, Graph Neural Networks
📍San Francisco
💰$182k–$207k
aihackerjobs.com/company/alem...
#AppliedAI #GPUComputing #Python #TechJobs
June 19, 2026 at 12:57 AM