# Demystifying NVSHMEM: A System-Level Analysis on Symmetric Memory and Device-Initiated Operations in GPU Communication

arXiv: https://arxiv.org/abs/2606.05951 · HTML: https://mlsanity.com/paper/2606.05951/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2026.

## Built on by (most cited first, 4 of 4)

- [X-Stage: Modeling Post-Issue Backpressure in GPU Communication--Computation Fusion](https://mlsanity.com/paper/2607.23264/) (2026)
- [Mixture-of-Kittens: MoE Megakernel for NVL72s](https://mlsanity.com/paper/2609.36070/) (2026)
- [Purlin: Separating Orchestration from the Datapath of Collectives](https://mlsanity.com/paper/2609.36954/) (2026)
- [Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs](https://mlsanity.com/paper/2609.40093/) (2026)

## Abstract (arXiv)

NVSHMEM is NVIDIA's OpenSHMEM-based PGAS communication library for GPU clusters, enabling GPU-initiated, one-sided communication through symmetric memory. Despite its growing adoption, a system-level understanding of its design and behavior remains scattered across documentation, source code, and application experience. This paper presents a concise study of NVSHMEM's programming model, implementation, and performance characteristics, focusing on symmetric memory, one-sided operations, and device-side collectives. We also examine DeepEP as a case study of NVSHMEM in performance-critical sparse deep learning workloads. Our analysis shows that NVSHMEM pioneered a device-side symmetric-memory programming model that enables fine-grained GPU-driven communication and is important for approaching the hardware performance limit. Overall, this work defines NVSHMEM's role as a systems building block, highlights its design tradeoffs, and identifies opportunities for improving GPU communication runtimes.