惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

aimingoo的专栏
aimingoo的专栏
Engineering at Meta
Engineering at Meta
有赞技术团队
有赞技术团队
博客园_首页
Apple Machine Learning Research
Apple Machine Learning Research
Vercel News
Vercel News
G
Google Developers Blog
Blog — PlanetScale
Blog — PlanetScale
IT之家
IT之家
MongoDB | Blog
MongoDB | Blog
Y
Y Combinator Blog
B
Blog
The GitHub Blog
The GitHub Blog
M
MIT News - Artificial intelligence
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Stack Overflow Blog
Stack Overflow Blog
C
Check Point Blog
Microsoft Azure Blog
Microsoft Azure Blog
D
DataBreaches.Net
I
InfoQ
Recent Announcements
Recent Announcements
阮一峰的网络日志
阮一峰的网络日志
腾讯CDC
H
Help Net Security

HN's home page

Rainbow Query Language | Hacker News Exec into Node via Kubectl An AI native hedge fund The Seven-Action Documentation Model | Hacker News Package Manager for Kubectl Plugins Tongan Castaways | Hacker News Tech overlords plan for conscious AI to conquer the cosmos. What could go wrong? Data Breach Disclosure Lag Is Getting Worse How LLMs Work | Hacker News I Dropped PRDs for Shape Up Go Experiments Explained | Hacker News FCA's Palantir deal could expose UK financial data to Trump's US, critics fear WebXR BCI for Neural-Adaptive Avatar Control in Mixed Reality The first murder conviction via DNA analysis Tom Interviews Theo de Raadt of the OpenBSD Project (2019) [video] Show HN: Replace shell commands with bun shell typescript scripts Quay.io Is Down | Hacker News AI driven analysis of brokerage account fees in the UK Bill Gates Spent Years Crafting His Image. Now It's Cracking Using LLMs to secure source code Wi-Fi 8 in the Lab [video] The household battery revolution that could change energy bills and the world Is Python Becoming Pinyin? | Hacker News Livia – Executive Assistant | Hacker News FindMyPipe – Query Apple Find My from Linux for AI Agents Show HN: Agent skill for creating product launch videos with Remotion RecruitMyself – AI job search copilot for resumes and applications AI coding agents and the erosion of system understanding The 'Resting' Generation and South Korea's Youth Recession AMD Computex 2026: 10 Years of AM4, AM5 Support Through 2029
Show HN: Matrix Engine WGPU – focus on mobile]
zla · 2026-06-18 · via HN's home page

Hi ,

I made 'MatrixEngineWgpu' webgpu engine in javascript ("The Beast" i added alias ;) ). Objective is full support for all browsers (with webgpu support) specially mobile browsers. I use vanilla js thats very important in context of performance. 2 years ago it was classic programming (without ai) but i involved ai in last 6 months. Thats not main subject.

I see in last yeasr that quality of web games are catastrophic even in promo videos i see buggy moments. Almost every webGPU examples or graphics+physics are very pure or not runnable on mobile devices. Theres also opinion that web can't produce high quality/performance app. Thats not true and that's i wanna to prove. My GraphicsCard is 13 years old and thats good when you make optimised stuff.

What is characteristics for "The Beast" in dev zone:

  - Every feature is tested on mobile device and balanced to be on "edge". Must pass mobile render.
  - On linkedin i see every day some new features doned in one of major engines and i imitates/integrate intro project.
  - What ever i can do i avoid ai asking (i keep control under code) also AI never gives BEST solution on begin. I need sometimes 2-3 phases of optimisation. Some optimisations concepts i learned from ai.
  - Usually engines give best quallty - matrix engine is downgraded by default in the name of performance.
  - Must be easy to use

 
 This is not full list but generally all main featureas are here,

  Done list []

 Draw loop per pipeline not per mesh (PipelineManager) with share material. Power optimisation.
 Support for 3D objects and scene transformations.
 Ammo.js, cannonES, matterJS && Jolt Physics libs integration (app<->bridge<->worker). Physics use webworkers by default.
 Networking with Kurento/OpenVidu/Own middleware Nodejs -> frontend.
 Bloom post processing.
 HZB post processing.
 Scene Culling feature.
 Based on the shadowMapping sample from webgpu-samples.
 Web GUI(online) Editor [app exec graph] with Visual Scripting (Named: FlowCodexVertex).
 Web GUI(online) Editor [shader graph] with Visual Scripting (Named: FlowCodexShader).
 Dynamic shadow cast (done also for skinned meshes).
 VertexShader displacment (done also for skinned meshes), nice for water effect.
 Basic flow for AI Graph Generator - Simple tasks passed for now with ollama platform. Open account/open-source/free-service-quota.
 ProceduralMesh objectScene entity with options for vertex morph - Shadows following morph blend.


 Interest feature : 
  - All physics engines runs in worker by default
  - I added visual scripting (app level & shader level)
  - AI tool for generating app graphs

 Source: https://github.com/zlatnaspirala/matrix-engine-wgpu
 Demos: https://maximumroulette.com/apps/webgpu/examples.html

 Enjoy and star if you like it !