SwarmIO: Towards 100 Million IOPS SSD Emulation for Next-generation GPU-centric Storage Systems

TL;DR

SwarmIO is a high-performance SSD emulator designed for GPU-centric storage systems, achieving up to 40 million IOPS and enabling detailed evaluation of such systems' performance.

Contribution

It introduces a scalable, accurate SSD emulation framework tailored for GPU-initiated I/O, overcoming key challenges of existing emulators.

Findings

SwarmIO reaches 40 MIOPS performance, 303.9x faster than previous emulators.

Increasing SSD IOPS from 2.5 MIOPS to 40 MIOPS improves end-to-end speed by up to 9.7x.

Demonstrates practical utility through a vector search case study.

Abstract

GPU-initiated I/O has emerged as a key mechanism for achieving high-throughput storage access by leveraging massive GPU thread-level parallelism, while recent industry trends point toward SSDs optimized for ultra-high random-read IOPS. Together, these trends are enabling the emergence of IOPS-optimized, GPU-centric storage systems. Despite this momentum, no existing framework enables quantitative end-to-end evaluation of storage systems optimized for GPU-initiated I/O. While conventional SSD emulators provide a promising path toward end-to-end modeling in traditional storage systems, they face three key challenges in this GPU-centric setting: limited frontend scalability for ingesting massive request streams, high software overhead in emulating GPU-initiated I/O control and data paths, and excessive timing-model maintenance overhead at extremely high I/O request rates. We propose SwarmIO, an SSD emulator for massively parallel, GPU-centric storage. SwarmIO faithfully models IOPS-optimized SSDs at target performance levels of up to 40 MIOPS, achieving a 303.9x speedup over the state-of-the-art baseline SSD emulator under GPU-initiated I/O. We further demonstrate its utility through a vector search case study, showing that increasing SSD IOPS from 2.5 MIOPS to 40 MIOPS yields an average end-to-end speedup of up to 9.7x.