@inproceedings{f566ca8b2edf4e39828ee7112d67d5f6,
title = "BAASH: Lightweight, efficient, and reliable blockchain-As-A-service for HPC systems",
abstract = "Distributed resiliency becomes paramount to alleviate the growing costs of data movement and I/Os while preserving the data accuracy in HPC systems. This paper proposes to adopt blockchain-like decentralized protocols to achieve such distributed resiliency. The key challenge for such an adoption lies in the mismatch between blockchain s targeting systems (e.g., shared-nothing, loosely-coupled, TCP/IP stack) and HPC s unique design on storage subsystems, resource allocation, and programming models. We present BAASH, Blockchain-As-A-Service for HPC, deployable in a plug-n-play fashion. BAASH bridges the HPC-blockchain gap with two key components: (i) Lightweight consensus protocols for the HPC s shared-storage architecture, (ii) A new fault-Tolerant mechanism compensating for the MPI to guarantee the distributed resiliency. We have implemented a prototype system and evaluated it with more than two million transactions on a 500-core HPC cluster. Results show that the prototype of the proposed techniques signi?cantly outperforms vanilla blockchain systems and exhibits strong reliability with MPI.",
keywords = "Blockchain, Fault tolerance, HPC, MPI, Reproducibility, Resilience",
author = "Mamun, {Abdullah Al} and Feng Yan and Dongfang Zhao",
note = "Funding Information: This work is supported in part by the following grants: National Science Foundation CCF-1756013, IIS-1838024, and CAREER-2048044. Publisher Copyright: {\textcopyright} 2021 IEEE Computer Society. All rights reserved.; 33rd International Conference for High Performance Computing, Networking, Storage and Analysis: Science and Beyond, SC 2021 ; Conference date: 14-11-2021 Through 19-11-2021",
year = "2021",
month = nov,
day = "14",
doi = "10.1145/3458817.3476155",
language = "English (US)",
series = "International Conference for High Performance Computing, Networking, Storage and Analysis, SC",
publisher = "IEEE Computer Society",
booktitle = "Proceedings of SC 2021",
}