Metraipolis › archive › dc_fdf9d290222e
Co-Fabric: Breaking Host-Domain Boundaries for Unified xPU Interconnection — arXiv:2609.25560
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25560
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T14:37:22.203Z
- SHA-256 of the archived text
0f435d36f0becc69f3bc91ad34790c3afc4c641d83f0019be8391cc11ec37f65- Stable URL of this page
https://metraipolis.com/documento/dc_fdf9d290222e
How to cite
Co-Fabric: Breaking Host-Domain Boundaries for Unified xPU Interconnection — arXiv:2609.25560 — arXiv (en), https://arxiv.org/abs/2609.25560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdf9d290222e (Metraipolis archive dc_fdf9d290222e, sha256 0f435d36f0becc69f3bc91ad34790c3afc4c641d83f0019be8391cc11ec37f65)
BibTeX
@misc{dcfdf9d290222e,
title = {Co-Fabric: Breaking Host-Domain Boundaries for Unified xPU Interconnection — arXiv:2609.25560},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25560},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdf9d290222e; sha256 0f435d36f0becc69f3bc91ad34790c3afc4c641d83f0019be8391cc11ec37f65},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large-model parameters have grown beyond the capacity of a single xPU, dispersing across multiple xPUs spanning distinct host domains, where xPU-to-xPU communication dominates overall system efficiency. Existing scale-up interconnect remains inadequate: network-based solutions built on Ethernet--such as RoCE (RDMA over Converged Ethernet)--introduce specific message-semantics and protocol-stack characteristics, and rely on fragmented per-host addressing, while conventional host-based fabrics are confined to a single host domain and lack cross-host unified addressing. This paper presents Co-Fabric, a bus-based interconnect that, unlike conventional bus designs, breaks host-domain boundaries to deliver unified xPU interconnection for scale-up superpods. Co-Fabric makes three contributions: a streamlined four-layer protocol stack achieving nanosecond-scale processing latency with native reliability; a cross-domain scaling and P2P mechanism that routes using port identifiers embedded in the packet header; and a unified address space built on shadow-device auto-enumeration. On a 64-xPU 3D-Mesh system, Co-Fabric cuts inter-node communication latency by over 50% and improves bandwidth by 2-5x over RoCE, accelerating DeepSeek R1 inference by 30%-80%. Moreover, since its streamlined four-layer protocol stack and higher data-communication efficiency reduce protocol and processing overhead relative to the Ethernet-based RoCE stack, Co-Fabric cuts the cost and power of the interconnect itself by up to 80% and 5%, respectively. These results demonstrate Co-Fabric's advantage for AI computing centers. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-23 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.25560 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:47:35.192Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).