8129

A File System Using GPU-Accelerated File-wise Reliability Scheme

Chien-Kai Tseng, Shang-Chieh Lin, Yarsun Hsu
Department of Electrical Engineering, National Tsing Hua University, HsinChu, Taiwan, R.O.C
International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA’12), 2012

@article{tseng2012file,

   title={A File System Using GPU-Accelerated File-wise Reliability Scheme},

   author={Tseng, C.K. and Lin, S.C. and Hsu, Y.},

   year={2012}

}

Download Download (PDF)   View View   Source Source   

2034

views

This work revises the original file-wise reliability scheme to cope with larger pages in storage devices nowadays, and implements it as a file system prototype: CRSFS. There are four layers in CRSFS: GPU primitive for Cauchy Reed-Solomon (CRS) coding, CrystalGPU framework, CRS coding layer and AFS FUSE layer. CRSFS provides GPU acceleration on the CRS encoding/decoding operations by using the CUDA program: GPU primitive for CRS coding. Besides, it is integrated with FUSE (Filesystem in Userspace) framework and Rx (extended remote procedure call) protocol in AFS FUSE layer to provide high flexibility on storage system configurations. Hence, most programs can benefit from it without rewriting their read/write operations. Finally, it’s shown that with the help of GPU acceleration, there are up to 24.5x performance gains compared to the CPU counterpart in AFS FUSE layer. The speed of CRS encoding/decoding operations is no longer the performance bottleneck.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: