HN Showcase
Back to browse
GitHub Repository

GPU-Native Programming Language. 4.5 MB binary. Any GPU. Zero dependencies.

5 stars

OctoFlow – A GPU-native programming language

by mr_octopus·Feb 19, 2026·3 points·4 comments
Visit ProjectView on HN

AI Analysis

●●●●GemZero to OneWizardryBig Brain

GPU-first language where CPU handles only I/O, shipping as single 2.2MB binary.

Strengths
  • •Genuine architectural inversion: GPU as primary execution target, not accelerated afterthought—rethinks data flow
  • •Self-hosted compiler (compiled by itself) with 51-module stdlib and Vulkan multi-vendor support shows completeness rare for 0.83.0
  • •Zero dependencies + single binary distribution removes deployment friction entirely
Weaknesses
  • •Extremely early (0.83.0, 4 commits); ecosystem immature—no package manager, external library bindings unclear
  • •Vulkan requirement excludes older GPUs and non-graphics-capable accelerators (TPUs, NPUs)
Target Audience

GPU compute researchers, ML engineers, numerical computing specialists

Similar To

CUDA C · OpenCL · Julia (GPU subset)

Post Description

I built a general-purpose programming language where the GPU is the primary execution target, not an afterthought.

Most languages treat GPU as "write a kernel, dispatch it, copy results back." OctoFlow flips it — data lives on the GPU by default. The CPU handles I/O and nothing else.

let a = gpu_fill(1.0, 10000000) let b = gpu_scale(a, 2.0) let c = gpu_add(a, b) print("sum: {gpu_sum(c)}")

10 million elements. Data never leaves VRAM between operations.

It's early — there's a lot to improve — but it works today and I'd love feedback from people who try it.

What you can do right now:

- GPU compute with arrays up to 10M+ elements - Statistical analysis, ML (regression, clustering, neural net primitives) - CSV/JSON data processing, HTTP client - Stream pipelines for image processing - Interactive REPL with GPU access - Import from 51 stdlib modules across 11 domains

What you need: any GPU with a Vulkan driver and the 2.2 MB binary. That's it.

I've been working on this solo and would genuinely appreciate people kicking the tires. What works, what breaks, what's missing — all useful.

https://github.com/octoflow-lang/octoflow

Similar Projects