Skip to main content
GameDev.net gamedev.net

GPUOpen

10 items across game development

10 results

News

Temporally stable generative illumination with a one-step diffusion model

AMD GPUOpen details a one-step latent diffusion approach for real-time global illumination that aims to keep lighting stable without iterative denoising passes. For graphics programmers, the pitch is...

AMD GPUOpen ·
graphics global-illumination diffusion-model real-time-rendering gpuopen
News

AMD FSR plugin updated for Unreal Engine 5.8

AMD GPUOpen says its updated AMD FSR Unreal Engine plugin now supports Unreal Engine 5.8, bringing ML-powered upscaling and frame generation into the latest UE branch. The update also extends …

AMD GPUOpen ·
unreal engine 58 upscaling frame generation gpuopen radeon rx 7000
News

Lightweight attention-based indirect illumination

AMD GPUOpen details a lightweight attention-based neural GI model that reconstructs off-screen indirect illumination from reflective shadow maps. The pitch is practical for teams chasing better...

AMD GPUOpen ·
graphics global-illumination neural-rendering gpuopen lighting
News

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

AMD GPUOpen details MiniDXNN v0.4.0, adding DirectX 12 SM 6.10 linear algebra support, input encodings, and neural texture compression. The update also ships a real-time GUI for training and...

AMD GPUOpen ·
gpuopen directx 12 shader model 610 neural texture compression graphics programming
News

GPU view-adaptive crack-free subdivision of Bézier surfaces

AMD GPUOpen details a GPU work-graph approach for view-adaptive, crack-free subdivision of bicubic Bézier surfaces. The technique cuts triangle counts sharply while keeping output on par with...

AMD GPUOpen ·
gpuopen graphics tessellation bézier surfaces gpu work graphs
News

Post-mortem GPU crash debugging with LLMs

AMD has wired its GPU crash analysis pipeline into an LLM-friendly MCP server, letting agents turn a single prompt into post-mortem root-cause analysis and fix suggestions. For graphics teams, that...

AMD GPUOpen ·
gpuopen gpu debugging crash analysis graphics programming
News

WMMA guide for AMD RDNA 4 architecture GPUs - part 3

AMD’s RDNA 4 WMMA guide shows a practical way to do in-register matrix transpose without touching memory, using an identity-matrix trick. For graphics and compute programmers, that’s a nice latency...

AMD GPUOpen ·
rdna 4 wmma gpu compute matrix transpose llamacpp
News

WMMA guide for AMD RDNA 4 architecture GPUs - part 2

AMD’s RDNA 4 WMMA guidance gets practical here: fuse the matrix ops so you double the K dimension and unlock 128-bit loads for FP8/INT8. The payoff is better memory bandwidth …

AMD GPUOpen ·
gpuopen rdna 4 wmma gemm int8