# Radiant Foam Rendering on a Graph Processor

arXiv: https://arxiv.org/abs/2601.04382 · HTML: https://mlsanity.com/paper/2601.04382/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM](https://mlsanity.com/paper/2312.02126/) (2023)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction](https://mlsanity.com/paper/2402.17427/) (2024)
- [Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra](https://mlsanity.com/paper/2304.09987/) (2023)
- [Triangle Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2505.19175/) (2025)
- [Dissecting the Graphcore IPU Architecture via Microbenchmarking](https://mlsanity.com/paper/1912.03413/) (2019)
- [RT-NeRF: Real-Time On-Device Neural Radiance Fields Towards Immersive AR/VR Rendering](https://mlsanity.com/paper/2212.01120/) (2022)
- [Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering](https://mlsanity.com/paper/2412.04459/) (2024)
- [LinPrim: Linear Primitives for Differentiable Volumetric Rendering](https://mlsanity.com/paper/2501.16312/) (2025)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [Bundle Adjustment on a Graph Processor](https://mlsanity.com/paper/2003.03134/) (2020)
- [GCC: A 3DGS Inference Architecture with Gaussian-Wise and Cross-Stage Conditional Processing](https://mlsanity.com/paper/2507.15300/) (2025)
- [Tetrahedron Splatting for 3D Generation](https://mlsanity.com/paper/2406.01579/) (2024)
- [Graphcore C2 Card performance for image-based deep learning application: A Report](https://mlsanity.com/paper/2002.11670/) (2020)
- [Triangle Splatting+: Differentiable Rendering with Opaque Triangles](https://mlsanity.com/paper/2509.25122/) (2025)
- [Harnessing Manycore Processors with Distributed Memory for Accelerated Training of Sparse and Recurrent Models](https://mlsanity.com/paper/2311.04386/) (2023)
- [FlexNeRFer: A Multi-Dataflow, Adaptive Sparsity-Aware Accelerator for On-Device NeRF Rendering](https://mlsanity.com/paper/2505.06504/) (2025)
- [Towards Neural Path Tracing in SRAM](https://mlsanity.com/paper/2305.20061/) (2023)
- [Efficient 3D Gaussian Splatting with Axis-Shared Rasterization and Order-independent Transmittance](https://mlsanity.com/paper/2506.07069/) (2025)

## Built on by (most cited first, 1 of 1)

- [Rendering 3D Gaussians on a Graph Processor](https://mlsanity.com/paper/2607.15951/) (2026)

## Abstract (arXiv)

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.