Saved in:
Bibliographic Details
Main Authors: Tuya, Zulkhuu, Alzugaray, Ignacio, Fry, Nicholas, Davison, Andrew J.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.04382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918282827661312
author Tuya, Zulkhuu
Alzugaray, Ignacio
Fry, Nicholas
Davison, Andrew J.
author_facet Tuya, Zulkhuu
Alzugaray, Ignacio
Fry, Nicholas
Davison, Andrew J.
contents Many emerging many-core accelerators replace a single large device memory with hundreds to thousands of lightweight cores, each owning only a small local SRAM and exchanging data via explicit on-chip communication. This organization offers high aggregate bandwidth, but it breaks a key assumption behind many volumetric rendering techniques: that rays can randomly access a large, unified scene representation. Rendering efficiently on such hardware therefore requires distributing both data and computation, keeping ray traversal mostly local, and structuring communication into predictable routes. We present a fully in-SRAM, distributed renderer for the Radiant Foam Voronoi-cell volumetric representation on the Graphcore Mk2 IPU(Intelligence Processing Unit), a many-core accelerator with tile-local SRAM and explicit inter-tile communication. Our system shards the scene across tiles and forwards rays between shards through a hierarchical routing overlay, enabling ray marching entirely from on-chip SRAM with predictable communication. On Mip-NeRF~360 scenes, the system attains near-interactive throughput of approximately 1 fps at 640x480 with image and depth map quality close to the original GPU-based Radiant Foam implementation, while keeping all scene data and ray state in on-chip SRAM. Beyond demonstrating feasibility, we analyze routing, memory, and scheduling bottlenecks that inform how future distributed-memory accelerators can better support irregular, data-movement-heavy rendering workloads.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04382
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Radiant Foam Rendering on a Graph Processor
Tuya, Zulkhuu
Alzugaray, Ignacio
Fry, Nicholas
Davison, Andrew J.
Graphics
Computer Vision and Pattern Recognition
Many emerging many-core accelerators replace a single large device memory with hundreds to thousands of lightweight cores, each owning only a small local SRAM and exchanging data via explicit on-chip communication. This organization offers high aggregate bandwidth, but it breaks a key assumption behind many volumetric rendering techniques: that rays can randomly access a large, unified scene representation. Rendering efficiently on such hardware therefore requires distributing both data and computation, keeping ray traversal mostly local, and structuring communication into predictable routes. We present a fully in-SRAM, distributed renderer for the Radiant Foam Voronoi-cell volumetric representation on the Graphcore Mk2 IPU(Intelligence Processing Unit), a many-core accelerator with tile-local SRAM and explicit inter-tile communication. Our system shards the scene across tiles and forwards rays between shards through a hierarchical routing overlay, enabling ray marching entirely from on-chip SRAM with predictable communication. On Mip-NeRF~360 scenes, the system attains near-interactive throughput of approximately 1 fps at 640x480 with image and depth map quality close to the original GPU-based Radiant Foam implementation, while keeping all scene data and ray state in on-chip SRAM. Beyond demonstrating feasibility, we analyze routing, memory, and scheduling bottlenecks that inform how future distributed-memory accelerators can better support irregular, data-movement-heavy rendering workloads.
title Radiant Foam Rendering on a Graph Processor
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.04382