A Decentralized Blockchain with Near Optimal Throughput and Latency
, University of Toronto
Date: Friday, May 17, 2019
Time: 1:00 PM to 2:00 PM
Location: 7th Floor G Tower Lounge
Event Type: Seminar
Host: Martin Rinard, MIT-CSAIL
Contact: Mary McDavitt, 6172539620, email@example.com
Speaker URL: None
TALK: A Decentralized Blockchain with Near Optimal Throughput and Latency
I will present Conflux, a scalable and decentralized blockchain system that
achieves near-optimal throughput and latency, with respect to underlying P2P
gossip network bandwidth and propagation delay.
Conflux operates with a novel consensus protocol which optimistically processes
concurrent blocks without discarding any as forks and adaptively assigns
weights to blocks based on their topologies in the Conflux ledger structure
(called Tree-Graph). The adaptive weight mechanism enables Conflux to detect
and thwart liveness attack by automatically switching between a fast mode in
normal scenarios and a structured mode to ensure consensus progress during
We evaluated Conflux on Amazon EC2 clusters with up to 12k full nodes. The
consensus protocol of Conflux achieves a block throughput of 9.38Mbps with
20Mbps network bandwidth limit per node. On a combined workload of payment
transactions and Ethereum history transactions, the end-to-end system of
Conflux achieves the throughput of up to 3480 transactions per second while
confirming transactions under one minute.
Fan Long is an Assistant Professor at University of Toronto. His research interests include programming language, systems security, software engineering, and blockchain. He is a recipient of ACM SIGSOFT Outstanding Dissertation Award and MIT Best Dissertation Award. He is also a co-Founder of Conflux, a project to build the next generation scalable, permission-less, and high performance blockchain.
Created by Mary McDavitt at Wednesday, May 15, 2019 at 12:15 PM.