Eliminating Hidden Serialization in Multi-Node Megakernel Communication

TL;DR

Perseus introduces techniques to eliminate serialization bottlenecks in multi-node Megakernel communication for Mixture-of-Experts inference, significantly improving performance by reducing fence overhead and NIC stalls.

Contribution

It presents Perseus, a novel approach that removes hidden serialization in RDMA transports, enabling faster multi-node MoE inference performance.

Findings

Perseus achieves up to 10.3× end-to-end speedup on proxy-based transports.

Perseus matches or exceeds GPU-direct performance by up to 1.2×.

Serialization, not transport choice, limits multi-node Megakernel performance.

Abstract

Recent megakernel designs for Mixture-of-Experts (MoE) inference fuse expert computation with fine-grained, GPU-initiated communication into a single persistent GPU kernel, and outperform collective-based MoE on a single node by overlapping data transfer with compute at tile granularity. This benefit does not carry over cleanly to multi-node inference, where experts span many nodes connected by an RDMA fabric. Communication-bound MoE models regress by up to $10\times$ on 8 nodes, and the regression worsens with node count. We trace this regression to hidden serialization in proxy-based RDMA transports. The ordering requirement between each tile transfer and its completion signal forces a fence that drains the NIC pipeline, and its cost grows with the number of concurrent transfers. As a result, models whose per-expert compute is too small to absorb this inflated network latency expose communication on the critical path. We present \emph{Perseus}, which eliminates this serialization through two techniques. \emph{Decoupled signaling} batches fences at per-destination granularity, reducing fence count by $8\times$. \emph{NIC-side ordering} replaces proxy stalls with hardware fence flags, so the proxy never blocks. On proxy-based transports, Perseus achieves up to 10.3$\times$ end-to-end speedup. Perseus on IBRC matches or exceeds IBGDA GPU-direct by up to 1.2$\times$, which shows that serialization, rather than the choice between proxy-based and GPU-direct transport, is what bounds multi-node megakernel performance.