Top all-time · #29
NVIDIA Developer
Company blog · developer.nvidia.com/blogaihardware
NVIDIA Developer is the company blog at developer.nvidia.com, writing about ai and hardware. Since 2009, 723 different Hacker News readers have linked it 1,118 times, most often “Nvidia releases open-source GPU kernel modules”. It is still writing: the last post was on 2026-10-30, and you can follow it by feed.
Most-linked posts?
- /gpudirect15 people · 15 mentions · first linked 2016-06-13
- Nvidia releases open-source GPU kernel modules14 people · 14 mentions · first linked 2022-05-11
- /blog/gpudirect-storage/11 people · 13 mentions · first linked 2020-09-13
- Nvidia Research: Maxine (AI Video Compression using ⅒th of bandwidth of H.264)11 people · 12 mentions · first linked 2020-10-05
- Designing Arithmetic Circuits with Deep Reinforcement Learning10 people · 10 mentions · first linked 2022-07-08
- Jetson Nano Developer Kit10 people · 10 mentions · first linked 2019-09-20
- Nvidia announces native GPU programming in Rust9 people · 9 mentions · first linked 2026-09-08
- /cuda-fortran8 people · 9 mentions · first linked 2017-10-15
- /ai-video-compression8 people · 8 mentions · first linked 2021-04-24
- GPU Accelerated Path Rendering7 people · 8 mentions · first linked 2015-09-17
What Hacker News says?
Public post by nVidia: https://developer.nvidia.com/blog/nvidia-releases-open-sourc...
Comment linking /blog/nvidia-releases-open-source-gpu-kernel-modules/
on “Nvidia releases open-source GPU kernel modules”Submitted Nvidia releases open-source GPU kernel modules as a story · 2410 points
HN discussionOk, we've changed to that from https://developer.nvidia.com/blog/nvidia-releases-open-sourc... above. Thanks! Edit: ok, changed back
Comment linking /blog/nvidia-releases-open-source-gpu-kernel-modules/
on “Nvidia releases open-source GPU kernel modules”Submitted Nvidia announces native GPU programming in Rust as a story · 970 points
HN discussionAll of the major cloud providers offer grants for public research https://www.amazon.science/research-awards https://edu.google.com/intl/ALL_us/programs/credits/research https://www.microsoft.com/en-us/azure-academic-research/ NVIDIA offers discounts https://developer.nvidia.com/education-pricing eg. for Australia, the National Computing Infrastructure allows researchers to reserve time on: - 160 nodes each containi…
Comment linking /education-pricing
on “Open source AI is the path forward”Submitted NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules as a story · 881 points
HN discussionLooking at the conversations almost 24 hours after posting the IP, licensing, ecosystem, political, and overall business aspects of this have been discussed to death. Oddly for Hacker News there has been little discussion of the potential technical aspects of this acquisition. Pure speculation (of course)... To me (from a tech standpoint) this acquisition centers around three things we already know about Nvidia: - N…
Comment linking /gpudirect
on “Nvidia to Acquire Arm for $40B”Submitted Nvidia Opens CUDA Platform, Releases Compiler Source Code as a story · 302 points
HN discussionOpenCL up to 3.0 is ostensibly supported: https://developer.nvidia.com/blog/nvidia-is-now-opencl-3-0-c... I don't think bits like the GSP firmware will ever be open-sourced, but the opportunity to write better OpenCL drivers has always existed. Some of Nvidia's other proprietary driver backends (eg. GBM, Vulkan) are also decently neglected, but mostly out of disuse rather than malice. I don't think any of these thin…
Comment linking /blog/nvidia-is-now-opencl-3-0-conformant/
on “Nvidia agrees to acquire Hugging Face for $13B”Submitted Valve's GDC Talk: Porting Source to Linux [pdf] as a story · 221 points
HN discussionAs a lover of ray/path tracing I'm obligated to point out: rasterisation gets its efficiency by amortising the cost of per-triangle setup over many pixels. This more or less forces you to do fixed-resolution rendering; it's very efficient at this, which is why even today with hardware RT, rasterisation remains the fastest and most power-efficient way to do visibility processing (under certain conditions). However, t…
Comment linking /vrworks/graphics/variablerateshading
on “Steam Frame”Submitted Ray Tracing Gems II available as free download as a story · 220 points
HN discussionBy the way... There is a nice old good article about making real time stereograms. https://developer.nvidia.com/gpugems/gpugems/part-vi-beyond-...
Comment linking /gpugems/gpugems/part-vi-beyond-triangles/chapter-41-real-time-stereograms
on “I've acquired a new superpower”Submitted Nvidia Digits DevBox as a story · 193 points
HN discussionFeels to me like: https://www.gdcvault.com/play/1026182/ (which Nvidia has wrapped up in their RTXGI library: https://developer.nvidia.com/rtxgi ). The idea is to supplement basic irradiance probes with moment shadow maps, so you can efficiently calculate how much each pixel should be affected by each probe. This greatly reduces the light bleeding problem, which is the biggest downfall of irradiance probes. Nvidia u…
Comment linking /rtxgi
on “A first look at Unreal Engine 5”Submitted Nvidia Scientists Take Top Spots in 2021 Brain Tumor Segmentation Challenge as a story · 168 points
HN discussionToo bad. I'm always curious about gains in cross-platform target productivity. The dream being that you build a high fidelity game and just need to drag a slider down to create a build that runs at 30fps+ on the, for example, Switch. Of course what we normally see is a lot of work to port down games. A good example being all the work that went into getting Witcher 3 to run on the Switch: https://developer.nvidia.com…
Comment linking /gtc/2020/video/s22697
on “A first look at Unreal Engine 5”Submitted Deep Learning Courses as a story · 159 points
HN discussionCUDA features unified memory that is only limited by the bandwidth of your PCIe connector: https://developer.nvidia.com/blog/unified-memory-cuda-beginn... People have been tiling 24gb+ models on a single (or several) 3090/4090s for a while now.
Comment linking /blog/unified-memory-cuda-beginners/
on “Apple introduces M4 chip”Submitted Unifying the CUDA Python Ecosystem as a story · 147 points
HN discussionThis is so standard it's part of the tutorials now https://developer.nvidia.com/isaac/gr00t
Comment linking /isaac/gr00t
on “Genie 3: A new frontier for world models”Submitted Megatron-Turing NLG 530B, the World’s Largest Generative Language Model as a story · 116 points
HN discussionhttps://developer.nvidia.com/sites/default/files/akamai/game...
Comment linking /sites/default/files/akamai/gamedev/docs/Porting%20Source%20to%20Linux.pdf
on “SteamOS”Submitted Nvidia Hopper Architecture In-Depth as a story · 69 points
HN discussionOn top of that, Nvidia has provided a unified addressing abstraction over PCI for a looooong time via CUDA: https://developer.nvidia.com/blog/unified-memory-in-cuda-6/ Customers like Pixar could probably push this even further, with a more recent Nvidia rack and Mellanox networking. Networking a couple Mac Studios over Thunderbolt doesn't have a hope of competing, at that scale.
Comment linking /blog/unified-memory-in-cuda-6/
on “LLaMA now goes faster on CPUs”Submitted Nvidia robot reference platforms as a story · 67 points
HN discussionComputer science. This is a grad level topic probably. Nvidia literally wrote most of the textbooks in this field and you’d probably be taught using one of these anyway: https://developer.nvidia.com/cuda-books-archive “GPGPU Gems” is another “cookbook” sort of textbook that might be helpful starting out but you’ll want a good understanding of the SIMT model etc.
Comment linking /cuda-books-archive
on “Run CUDA, unmodified, on AMD GPUs”Submitted Solving Entry-Level Edge AI Challenges with Nvidia Jetson Orin Nano as a story · 65 points
HN discussion…yes it is? https://developer.nvidia.com/cuda-toolkit-archive
Comment linking /cuda-toolkit-archive
on “Run CUDA, unmodified, on AMD GPUs”Submitted Running Large-Scale Graph Analytics with Memgraph and Nvidia CuGraph Algorithms as a story · 59 points
HN discussion
