Managing scalable direct storage accesses for GPUs

Zhou, Yirui (Eric)

Permalink

https://hdl.handle.net/2142/129995 Copy

Description

Title

Managing scalable direct storage accesses for GPUs

Author(s)

Zhou, Yirui (Eric)

Issue Date

2025-07-25

Director of Research (if dissertation) or Advisor (if thesis)

Huang, Jian

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• File System
• GPU

Abstract

As we shift from CPU-centric computing to GPU-accelerated computing for supporting intelligent data processing at scale, the storage bottleneck has been exacerbated. To bypass the host CPU and alleviate unnecessary data movements, modern GPUs enable direct storage access to SSDs (i.e., GPUDirect Storage). However, current GPUDirect Storage solutions still rely on the host file system to manage the storage device, direct storage accesses are still bottlenecked by the host. This thesis proposes a GPU-orchestrated file system (GoFS) for scaling the direct storage accesses for GPU programs, by fully offloading the storage management to the GPU. As GoFS provides POSIX API and manages core filesystem structures in GPU memory, it can execute both control path and data path without host CPU involvement. To enable highly concurrent direct storage accesses, GoFS rethinks the design and implementation of core filesystem structures with various optimization techniques, such as scalable data indexing, fine-grained per-SM (streaming multiprocessor) block management, and zero-copy I/O accesses, by carefully exploring the GPU-accelerated computing paradigm. GoFS preserves the essential filesystem properties such as crash consistency, and it is compatible with existing host-based file systems like F2FS. GoFS does not require changes to the on-disk filesystem organization, therefore, the host and GPU can manage the SSD in a coordinated fashion, and maintain the data consistency in a primary/secondary mode. GoFS develops based on F2FS using 7.9K lines of codes with CUDA programming. We examine its efficiency on an A100 GPU. The experiments with various GPU-based applications show that GoFS outperforms state-of-the-art storage access solutions for GPUs by 1.61× on average.

Graduation Semester

2025-08

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/129995

Copyright and License Information

Copyright 2025 Yirui (Eric) Zhou

Owning Collections