Very exciting for me. I submitted two panels.
What every programmer should know about memory
An unconference style tribute to Ulrich Drepper's paper of the same name (http://goo.gl/EoiZE). Come find out what a cache line is and why you should care. Go under the hood of CC-NUMA architectures and find out what it takes to provide cache coherency in the face of a variety synchronization primitives and memory models. Learn about the Java memory model and the upcoming C++11x memory model. Discuss the various tradeoffs between single-thread performance and multi-thread scalability associated with CC-NUMA architectures.
Tools for scaling out instead of scaling up
The popularity of scale out architectures has led to the development of a new generation of tools for building distributed systems. Distributed agreement protocols, databases, filesystems, and map-reduce frameworks provide the scalable, fault-tolerant, and highly available building blocks necessary to develop scalable applications and services. In this session Ariel Weisberg, Software Engineer @ VoltDB leads a series of as yet unknown panelists in providing an overview of the new tools on the block by describing the problem each tools solves and how they solve it. We will be discussing Hadoop, ZooKeeper, Dynamo (Riak, Voltdemort, and Cassandra), MongoDB, and VoltDB.
I am looking for panelists!
I am supposed to have a committed panelists by July 8th with a 340x420 head shot and an 80 word profile for each panelist. Presumably they start printing schedules at that point. Late comers are still welcome as the content of the panel is the most important thing.
The content of the panels is fungible and highly fungible in the case of "Tools for scaling out instead of scaling up." I want to focus the on the strengths and experience of the panelists.
If you know anyone who would be interested in attending PAX and PAX dev with experience in these areas please put them in touch with me. email@example.com