论文标题
Baash：在高性能计算系统上启用区块链即服务
BAASH: Enabling Blockchain-as-a-Service on High-Performance Computing Systems
论文作者
论文摘要
管理区块链的最先进方法是处理在共享环境中的交易块。 Although blockchains have the potential to provide various services for high-performance computing (HPC) systems, HPC will not be able to embrace blockchains before the following two missing pieces become available: (i) new consensus protocols being aware of the shared-storage architecture in HPC, and (ii) new fault-tolerant mechanisms compensating for HPC's programming model---the message passing interface (MPI)---that is vulnerable for类似区块链的工作负载。为此，我们设计了一套针对HPC平台精心设计的新的共识协议，并设计了一个新的容错子系统，以补偿由错误的MPI流程引起的故障。建立在新协议和耐故障机制的基础上，在500核HPC群集上实施了200万笔交易，并评估了原型系统，显示出$ 6 \ times $，$ 12 \ tims $，$ 75 \ $ 75 \倍的$ $ $ $ $ $ $ $ $比HyperLdeger，Ethereum和Parity分别高。
The state-of-the-art approach to manage blockchains is to process blocks of transactions in a shared-nothing environment. Although blockchains have the potential to provide various services for high-performance computing (HPC) systems, HPC will not be able to embrace blockchains before the following two missing pieces become available: (i) new consensus protocols being aware of the shared-storage architecture in HPC, and (ii) new fault-tolerant mechanisms compensating for HPC's programming model---the message passing interface (MPI)---that is vulnerable for blockchain-like workloads. To this end, we design a new set of consensus protocols crafted for the HPC platforms and a new fault-tolerance subsystem compensating for the failures caused by faulty MPI processes. Built on top of the new protocols and fault-tolerance mechanism, a prototype system is implemented and evaluated with two million transactions on a 500-core HPC cluster, showing $6\times$, $12\times$, and $75\times$ higher throughput than Hyperldeger, Ethereum, and Parity, respectively.
