# MiniDXNN v0.4.0: Interactive neural texture compression on DirectX 12

DevFeed: [MiniDXNN v0.4.0: Interactive neural texture compression on DirectX 12](<https://devfeed.tech/articles/minidxnn-v0-4-0-interactive-neural-texture-compression-on-directx-12-15043.md>)

Original publisher: [Read original article](<https://gpuopen.com/learn/minidxnn-v040-interactive-neural-texture-compression/>)

Author: Takahiro Harada; Sho Ikeda

Published: 2026-08-13T14:30:00Z

Content type: release

Language: en

Sources: [AMD GPUOpen](<https://devfeed.tech/sources/amd-gpuopen.md>)

Topics: [Compression](<https://devfeed.tech/topics/compression.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [mlp](<https://devfeed.tech/topics/mlp.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [GUI](<https://devfeed.tech/topics/gui.md>), [shaders](<https://devfeed.tech/topics/shaders.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [agility-sdk](<https://devfeed.tech/tags/agility-sdk.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [compression](<https://devfeed.tech/tags/compression.md>), [directx](<https://devfeed.tech/tags/directx.md>), [driver](<https://devfeed.tech/tags/driver.md>), [getting-started](<https://devfeed.tech/tags/getting-started.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-open-sdks](<https://devfeed.tech/tags/gpu-open-sdks.md>), [gpu-open-tools](<https://devfeed.tech/tags/gpu-open-tools.md>), [gpuopen-sdks](<https://devfeed.tech/tags/gpuopen-sdks.md>), [gpuopen-tools](<https://devfeed.tech/tags/gpuopen-tools.md>), [graphics-apis](<https://devfeed.tech/tags/graphics-apis.md>), [gui](<https://devfeed.tech/tags/gui.md>), [inference](<https://devfeed.tech/tags/inference.md>), [maths](<https://devfeed.tech/tags/maths.md>), [memory](<https://devfeed.tech/tags/memory.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [microsoft-agility-sdk](<https://devfeed.tech/tags/microsoft-agility-sdk.md>), [microsoft-directx](<https://devfeed.tech/tags/microsoft-directx.md>), [ml](<https://devfeed.tech/tags/ml.md>), [mlp](<https://devfeed.tech/tags/mlp.md>), [neural](<https://devfeed.tech/tags/neural.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [product-release](<https://devfeed.tech/tags/product-release.md>), [quick-start](<https://devfeed.tech/tags/quick-start.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [shaders](<https://devfeed.tech/tags/shaders.md>), [technical-article](<https://devfeed.tech/tags/technical-article.md>), [technical-articles](<https://devfeed.tech/tags/technical-articles.md>), [tools](<https://devfeed.tech/tags/tools.md>)

## AI overview

MiniDXNN v0.4.0 is an open-source library for GPU-accelerated MLP inference and training on DirectX 12. The release adds D3D12 Linear Algebra support, input encoding for neural texture compression, and a real-time GUI application for training and visualizing texture representations.

## Source excerpt

MiniDXNN v0.4.0 introduces D3D12 Linear Algebra (SM 6.10) support, input encodings and neural texture compression, plus a real-time GUI app that trains and visualizes GPU-accelerated MLPs on DirectX® 12.