Conference：ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)
CCF level：CCF A
Categories：Computer Architecture/Parallel and Distributed Computing/Storage Systems
Year：2024
Num：3
1
Title:
OsirisBFT: Say No to Task Replication for Scalable Byzantine Fault Tolerant Analytics
OsirisBFT：对可扩展拜占庭容错分析的任务复制说不
Authors:****
Key words:
Distributed Computing, Byzantine Fault Tolerance, Data Processing Systems, Resilient Systems
分布式计算、拜占庭容错、数据处理系统、弹性系统
Abstract:****
We present a verification-based Byzantine Fault Tolerant processing system, called OsirisBFT, for distributed task-parallel applications. OsirisBFT treats computation tasks differently from state update tasks, allowing the application to scale independently from number of expected failures. OsirisBFT captures application-specific verification semantics via generic verification operators and employs lightweight verification strategies with little coordination during graceful execution. Evaluation across multiple applications and workloads shows that OsirisBFT delivers high processing throughput and scalability compared to replicated processing. Importantly, the scalable nature of OsirisBFT enables it to reduce the performance gap compared to baseline with no fault tolerance by simply scaling out.
我们为分布式任务并行应用程序提出了一种基于验证的拜占庭容错处理系统，称为 OsirisBFT。OsirisBFT 将计算任务与状态更新任务区别对待，允许应用程序独立于预期故障数量进行扩展。OsirisBFT 通过通用验证运算符捕获特定于应用程序的验证语义，并在优雅的执行期间采用轻量级验证策略，几乎不需要协调。跨多个应用程序和工作负载的评估表明，与复制处理相比，OsirisBFT 提供了高处理吞吐量和可扩展性。重要的是，OsirisBFT 的可扩展性使其能够通过简单的扩展来减少与没有容错能力的baseline相比的性能差距。
The system is modeled as a pipeline with three steps: (i) input processes IP generate or ingest tasks and distribute them downstream; (ii) worker processes WP execute the tasks and output a sequence of records; and, (iii) output processes OP receive the results.
WP is divided into two sub-clusters: the execution cluster EP and the verifier clusters VP.
Pdf link:
https://dl.acm.org/doi/10.1145/3627535.3638468
2
Title:
POSTER: Accelerating High-Precision Integer Multiplication used in Cryptosystems with GPUs
海报：利用 GPU 加速密码系统中的高精度整数乘法运算
Authors:****
Key words:
GPU computing, big integer multiplication
GPU 计算、大整数乘法
Abstract:****
High-precision integer multiplication is crucial in privacy-preserving computational techniques but poses acceleration challenges on GPUs due to its complexity and the diverse bit lengths in cryptosystems. This paper introduces GIM, an efficient high-precision integer multiplication algorithm accelerated with GPUs. It employs a novel segmented integer multiplication algorithm that separates implementation details from bit length, facilitating code optimizations. We also present a computation diagram to analyze parallelization strategies, leading to a series of enhancements. Experiments demonstrate that this approach achieves a 4.47× speedup over the commonly used baseline.
高精度整数乘法在隐私保护计算技术中至关重要，但由于其复杂性和密码系统中不同的比特长度，给 GPU 的加速带来了挑战。本文介绍了利用 GPU 加速的高效高精度整数乘法算法 GIM。它采用了一种新颖的分段整数乘法算法，将实现细节与比特长度分开，便于优化代码。我们还提出了一种计算图，用于分析并行化策略，从而实现一系列改进。实验证明，与常用基线相比，这种方法的速度提高了 4.47 倍。
Pdf link:
https://dl.acm.org/doi/10.1145/3627535.3638495
3
Title:
POSTER: OCToPus: Semantic-aware Concurrency Control for Blockchain Transactions
海报：OCToPus：区块链交易的语义感知并发控制
Authors:****
Key words:
Blockchain, Concurrency Control, GPU
区块链、并发控制、GPU
Abstract:****
Many blockchain implementations offer APIs to send and receive money between accounts exclusively. In this paper, we introduce OCToPus, a deterministic concurrency control scheme that uses a semantic-aware fast path and a GPU-accelerated directed acyclic graph-based fallback path to parallelize the execution of a block aggressively.
许多区块链实现都提供了专门用于在账户之间发送和接收资金的 API。在本文中，我们介绍了一种确定性并发控制方案 OCToPus，它使用语义感知快速路径和基于 GPU 加速的有向无环图的回退路径来并行执行区块链。
Pdf link:
https://dl.acm.org/doi/10.1145/3627535.3638494
关注我们，持续接收区块链最新论文
洞察区块链技术发展趋势
Follow us to keep receiving the latest blockchain papers
Insight into Blockchain Technology Trends