Vorion: A RISC-V GPU with Hardware-Accelerated 3D Gaussian Rendering and Training

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Yipeng, Yang, Mengtian, Lo, Chieh-pu, Kulkarni, Jaydeep P.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909915925184512
author Wang, Yipeng
Yang, Mengtian
Lo, Chieh-pu
Kulkarni, Jaydeep P.
author_facet Wang, Yipeng
Yang, Mengtian
Lo, Chieh-pu
Kulkarni, Jaydeep P.
contents 3D Gaussian Splatting (3DGS) has recently emerged as a foundational technique for real-time neural rendering, 3D scene generation, volumetric video (4D) capture. However, its rendering and training impose massive computation, making real-time rendering on edge devices and real-time 4D reconstruction on workstations currently infeasible. Given its fixed-function nature and similarity with traditional rasterization, 3DGS presents a strong case for dedicated hardware in the graphics pipeline of next-generation GPUs. This work, Vorion, presents the first GPGPU prototype with hardware-accelerated 3DGS rendering and training. Vorion features scalable architecture, minimal hardware change to traditional rasterizers, z-tiling to increase parallelism, and Gaussian/pixel-centric hybrid dataflow. We prototype the minimal system (8 SIMT cores, 2 Gaussian rasterizer) using TSMC 16nm FinFET technology, which achieves 19 FPS for rendering. The scaled design with 16 rasterizers achieves 38.6 iterations/s for training.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vorion: A RISC-V GPU with Hardware-Accelerated 3D Gaussian Rendering and Training
Wang, Yipeng
Yang, Mengtian
Lo, Chieh-pu
Kulkarni, Jaydeep P.
Hardware Architecture
Graphics
3D Gaussian Splatting (3DGS) has recently emerged as a foundational technique for real-time neural rendering, 3D scene generation, volumetric video (4D) capture. However, its rendering and training impose massive computation, making real-time rendering on edge devices and real-time 4D reconstruction on workstations currently infeasible. Given its fixed-function nature and similarity with traditional rasterization, 3DGS presents a strong case for dedicated hardware in the graphics pipeline of next-generation GPUs. This work, Vorion, presents the first GPGPU prototype with hardware-accelerated 3DGS rendering and training. Vorion features scalable architecture, minimal hardware change to traditional rasterizers, z-tiling to increase parallelism, and Gaussian/pixel-centric hybrid dataflow. We prototype the minimal system (8 SIMT cores, 2 Gaussian rasterizer) using TSMC 16nm FinFET technology, which achieves 19 FPS for rendering. The scaled design with 16 rasterizers achieves 38.6 iterations/s for training.
title Vorion: A RISC-V GPU with Hardware-Accelerated 3D Gaussian Rendering and Training
topic Hardware Architecture
Graphics
url https://arxiv.org/abs/2511.16831