iiinova — where your digital self keeps evolving

Zino @zino2201.bsky.social · 11/09/2026

I just dropped a new blog post about my renderer: zino2201.substack.com/p/how-sparse... I would love feedback about my writing style, I'm still not sure about it :)

zino2201.substack.com

How sparse resources helped my GPU-driven renderer memory usage

NOTE: This blog post assumes knowledge of GPU programming, GPU-driven rendering, D3D12 and systems programming.

281

Reposted by Zino

Arseny Kapoulkine @zeux.io · 08/12/2025

After nine years of development, meshoptimizer has reached its first major version, 1.0! This release focuses on improvements in clusterization and simplification as well as stabilization. Here's a release announcement with more details on past, present and future; please RT! meshoptimizer.org/v1

meshoptimizer.org

🐇 meshoptimizer v1.0

Mesh optimization library that makes meshes smaller and faster to render

924975

Zino @zino2201.bsky.social · 16/09/2025

Are there engines or apps out there that uses vulkan as their sole gfx API /RHI and provide homemade vk implementations for other backends/platforms (with homemade extensions too) ?

000

Zino @zino2201.bsky.social · 16/09/2025

So it seems like a miracle happend in Win11 24H2. UpdateTileMappings() doesn't seems as unpredictable and slow on NVidia. I only did simple tests though, with buffers and not giga textures.

110

Reposted by Zino

Jendrik Illner @jendrikillner.bsky.social · 03/03/2025

Graphics Programming weekly - Issue 381 - March 2nd, 2025 www.jendrikillner.com/post/graphic...

08524

Zino @zino2201.bsky.social · 26/01/2025

ajmmertens.medium.com/why-it-is-ti... This resonate with me a lot, recently I am prototyping on a game that involves a lot of data-driven logic and relationships between entities, factions, resources etc... Seeing this world has a database, a flat array of entities with relationships to each other

ajmmertens.medium.com

Why it is time to start thinking of games as databases

How do we build games that can be understood by intelligent agents? An in-depth overview of the tech that could one day make this a…

150

Zino @zino2201.bsky.social · 24/01/2025

TIL MSVC only apply NRVO when using using /O2, /std:c++20 or later, /permissive- or /Zc:nrvo. We were wondering why a copy constructor was called when returning from a function and the return value was not constructed as part of the return statement. devblogs.microsoft.com/cppblog/impr...

devblogs.microsoft.com

Improving Copy and Move Elision - C++ Team Blog

With Visual Studio 2022 version 17.4 Preview 3, we’ve significantly increased the number of situations where we do copy or move elision and given users more control over whether these transformations ...

120

Zino @zino2201.bsky.social · 22/01/2025

21 yo... why is time accelerating ?

000

Reposted by Zino

Morten Vassvik @vassvik.bsky.social · 17/11/2024

Let's wrap up this lovely week with a nice technical post This is the "case study" from my Masterclass at GPC, where I apply a series of optimizations to improve the effective bandwidth of a 3x3x3 blur (a proxy for a huge set of operations on volumetric data) Check ALT text for (a lot of) context.

A table showing the experimental results of applying 6 different compute shader versions of a simple 3x3x3 box blur on a 512x512x512 texture using either GL_R16F or GL_R32F internal format for storage for a eight different GPUs spanning several GPU architectures and vendors.

The upper table shows the absolute effective bandwidth (measured as the sum of total bytes read and written divided by execution time), whereas the lower table shows the effective bandwidth relative to the theoretical bandwidth as a percentage.

Each row corresponds to a specific shader variant (except for the "theoretical" row, which displays the theoretical bandwidth according to the GPU specification), and each column corresponds to a specific GPU. The color coding is per column in the upper table, and it's a single color coding on the entire lower table.

Each version will be explained in detail in the subsequent posts.

Version 6 applies uses half precision floating point for the shared memory cache, and the relevant extension does not exist in the Intel drivers for Windows. Likewise this version is not applied to the GL_R32F internal format benchmarks since that would destroy the precision of the backing format anyway.

The code was written and initially tested on a desktop 4090 (the first column), which naturally skews the results a bit since everything was evaluated and tested on that GPU. Had I used another GPU I might have picked slightly different compromises, and the results would have been slightly different.

One interesting observation is that the RTX 4000 series (Ada Lovelace architecture) significantly overperform everything else, with 7900 XTX (RDNA3) slightly behind. A large part of these overwhelmingly efficient results is due to the massive caches these devices sport (72 MiB on the desktop 4090, 64 MiB on the laptop 4090, etc.), which really helps reach peak bandwidth a lot easier.

413325

Zino @zino2201.bsky.social · 09/01/2025

Graphics programming changed my PoV about CPU architectures. I want to see a more ILP/SIMD approach to software. I saw some architectures having what's called SPM (scratchpad memory) which is similar to groupshared memory. Wonder what computing would look like if we went full VLIW early.

120

Zino @zino2201.bsky.social · 28/12/2024

The actor model is very elegant and message-passing in general always worked great for me to exchange data between threads. I would love to generalize my engine towards more actors, but I'm still skeptical about the overhead VS classical fibers/job graph with fine-grained locking (what I have).

010

Zino @zino2201.bsky.social · 19/12/2024

yea so I watched again some videos of threat interactive, I agree on some of his points, but no, nanite is not a perf disaster. no serious game developer will use something without evalutating its tradeoffs with its content. rendering avatar: the last frontier is not the same

340

Reposted by Zino

Culture Crave 🍿 @culturecrave.co · 17/12/2024

First look at Wakanda in 'Marvel 1943: The Rise of Hydra' It will be a playable location "We wanted to tell a globe-trotting story ... There are yet-to-be-revealed locations in between" (via EW)

953349

Zino @zino2201.bsky.social · 29/11/2024

(1/2) Anyone experimented or have resources about depth gradient based occlusion culling ? I wonder how it could looks in a meshlet renderer. This is how I see it: - Store (or compute ?) in your hierarchical depth buffer the gradients

130

Reposted by Zino

Harry Eccles @harryeccles.bsky.social · 28/11/2024

Repost if BlueSky is now your primary social media site.

5492205813164

Reposted by Zino

Lea - Newin AKA Shodan’s girlfriend @newincpp.bsky.social · 24/11/2024

I’m doing so much photomode in games and I don’t have my virtual gallery website anymore, so here is a thread. I will try to dump a game a day. Today Plague Tale: Requiem.

1152

Zino @zino2201.bsky.social · 27/11/2024

Follow up on that, I started writing the safe part of the bindings and I hit several issues due to the differences between C++ and Rust, specially around mutability. So yesterday I started writing a USDA parser... let's see where this goes

120

Zino @zino2201.bsky.social · 24/11/2024

yay I've been able to bind a small part of the OpenUSD api to Rust, only unsafe bindings for now

030

Zino @zino2201.bsky.social · 21/11/2024

I made the choice to drop out of uni to work in the video games industry as a engine programmer, but sometimes I wonder if I made the right choice. I'm still scared about diploma gatekeeping even though in video games it seems to be easier to enter with only a portfolio.

470

Reposted by Zino

Rami Ismail (رامي) @ramiismail.com · 21/11/2024

OK honestly though, Microsoft Flight Simulator 2024 is staggeringly beautiful? Everything about this feels like a massive upgrade. The EFB, the load transitions, the career mode, the flight model, the weather - it's all just An Enormous Step Up. Did not think it would blow my mind again, but damn.

91592

Zino @zino2201.bsky.social · 21/11/2024

oh! saw on UE5.5 that Nanite streaming pool use tiled/sparse resources if available, could they now be usable ? Atleast for buffers, i'm not yet interested into hw virtual textures

030

Zino @zino2201.bsky.social · 21/11/2024

Took a small trip to Japan in Flight Simulator 2024

Microsoft Flight Simulator 2024 landscape at sunrise with a clouded sky on a mountain with some vegetation. The sun is rising at the horizon showing orange colors piercing through the clouds.

081

Zino @zino2201.bsky.social · 19/11/2024

and now you can too ! :)

130

Reposted by Zino

Alan Wolfe @demofox.bsky.social · 14/05/2024

For folks that know me as "the blue noise guy", I've put together a 50 minute video that talks about many of the things I've learned in my ~decade long dive into noise and related topics - up to and including our latest paper published days ago at I3D. Enjoy! www.youtube.com/watch?v=teth...

515839

Reposted by Zino

Radek Paszkowski @artdev.bsky.social · 10/10/2024

If you want to learn about Mesh Shaders and understand where they can be used, and already are used, check out my talk from #dd2024: youtu.be/3EMdMD1PsgY?...

youtu.be

Radosław Paszkowski - Mesh Shaders - The Future of Rendering

YouTube video by Digital Dragons

1155

Zino @zino2201.bsky.social · 17/11/2024

(1/3) I'm currently doing a toy engine in Rust, so far I love the language. But I'm seriously considering switching back to C++ just so I can use the gigantic amount of libs/middleware for gamedev available. I'm tired of writing bindings, it is not as easy as using bindgen or autocxx.

140

Zino @zino2201.bsky.social · 16/11/2024

is there a Windows scheduler bible resource somewhere ? I was told about the Windows Internals books

000

Zino @zino2201.bsky.social · 08/11/2024

I wonder if in a high poly scene using visbuffer rendering shading into a gbuffer, having a vertex cache (like something implemented in Horizon Forbidden West) is worth it on modern consoles and GPUs vs blasting 3x vertex per pixel Has anyone benched both in the same scene ?

210

Zino @zino2201.bsky.social · 07/11/2024

1/9 Integrating a material system in your shaders is not easy. One obstacle you may encounter is that you have multiple vertex producers: static meshes, skinned meshes, particles, terrains, procgen meshes...

190

Zino @zino2201.bsky.social · 06/11/2024

Had a mystical bug on NV. Loading 4 texels per thread in a compute shader returned crazy values but not when loading 1 texel. The shader expects a Texture2D<uint2> but CPU-side it was created with the R32G32_FLOAT format, funny.

030

Reposted by Zino

Rebecca Fernandez O'Shea @rebeccafernandez.bsky.social · 29/10/2024

We are hiring at Nixxes for graphics and optimisation programmers. In my biased opinion we're a great bunch and the graphics/optimisation team is full of talented and caring people. We care about one another, the players and the games. Sounds trite, but it's true ❤️ #gamejobs www.nixxes.com/jobs/

nixxes.com

Jobs

24417

Reposted by Zino

Gabe Graziani @gabegraziani.bsky.social · 28/10/2024

Heads up for those looking to avoid Dragon Age: The Veilguard spoilers on Bsky! Also, please tag any potential narrative spoilers appropriately (hashtag DAspoilers should work). Be safe out there!

11814

Zino @zino2201.bsky.social · 28/10/2024

started replaying Stellaris, I wish one day to have a modern Stellaris with great graphics, would be so cool !!

010

Reposted by Zino

Erik Jansson @caffeineviking.net · 25/10/2024

Hello, World! It's cool to see so many rendering programmers here already! As a self-introduction and for those that haven't seen it on Twitter already, here's the talk that I did earlier this year at Digital Dragons re: the GPU-driven rendering in AW2! www.youtube.com/watch?v=EtX7...

youtube.com

Erik Jansson - GPU driven Rendering with Mesh Shaders in Alan Wake 2

YouTube video by Digital Dragons

16222

Reposted by Zino

Arseny Kapoulkine @zeux.io · 25/10/2024

meshoptimizer 0.22 is out! Featuring significant improvements to simplifier (attribute simplification, fewer topology restrictions, component pruning), new provoking vertex algorithm (thanks to John Hable), clusterization improvements & gltfpack size optimizations.

14915

Zino @zino2201.bsky.social · 25/10/2024

I think I have a good understanding of GPUs. Still, it amazes me seeing my GPU culls more than one million meshlets in less than one millisecond.

040

Zino @zino2201.bsky.social · 24/10/2024

RDNA really loves culling those primitives inside the mesh shader with a meshlet renderer

000

Reposted by Zino

Gijs Richard Kaerts @belgianrenderer.gijskaerts.com · 23/10/2024

Thought I'd share an old post I did which I still feel is pretty relevant today: Implementing a GPU-driven debug line renderer www.gijskaerts.com/wordpress/?p... Ever wanted to just draw debug primitives directly from a shader without CPU intervention? Look no further!

gijskaerts.com

Implementing a GPU-driven debug line renderer

I recently tweeted about some of the work I’m doing around GPU debugging tools (more specifically GPU-driven line rendering) in my home real-time rendering project. Since the tweet gained a g…

23610

Reposted by Zino

Jacco Bikker 🎦 @jbikker.bsky.social · 23/10/2024

Graphics moved to BlueSky? Great! While I work on the initial release of a fast, "C-with-classes", single-file BVH-builder / optimizer library, may I perhaps amuse you with some reading material on the subject: jacco.ompf2.com/2022/04/13/h... Comes with a github repo too! github.com/jbikker/bvh_...

05816

Zino @zino2201.bsky.social · 22/10/2024

Still shocked about the performance of vkd3d workgraph implementation vs NVidia and AMD drivers I hope this is because we need more adoption so drivers can iterate more on this. For now, workgraphs have a quite low occupancy :( github.com/HansKristian...

github.com

110