SEARCH
ISTC-CC NEWSLETTER
RESEARCH HIGHLIGHTS
Ling Liu's SC13 paper "Large Graph Processing Without the Overhead" featured by HPCwire.
ISTC-CC provides a listing of useful benchmarks for cloud computing.
Another list highlighting Open Source Software Releases.
Second GraphLab workshop should be even bigger than the first! GraphLab is a new programming framework for graph-style data analytics.
ISTC-CC Abstract
Scalable, High Performance Ethernet Forwarding Lookup
9th International Conference on emerging Networking Experiments and Technologies (CoNEXT), December 2013.
Dong Zhou, Bin Fan, Hyeontaek Lim, Michael Kaminsky*, David G. Andersen
Carnegie Mellon University
*Intel Labs
This poster will describe a new Ethernet forwarding lookup architecture that enables the simple construction of switches that can contain tens of millions of forwarding entries. The core design is based upon recent work on concurrent multi-reader cuckoo hashing [1] to create fast and memory-efficient lookup tables. This work has two primary benefits: First, it suggests that were a need for such scale to arise—whether for flat addressing or for more extreme uses such as content-based networking— such huge-scale tables could be practically constructed. Second, as a pragmatic byproduct, the technique allows storing several hundred thousand forwarding entries entirely in fast L3 CPU cache, facilitating the construction of high-throughput software-based switches.
FULL PAPER: pdf