In this solutions track talk, sponsored by Azul Systems, Gil Tene discusses common pitfalls encountered in measuring and characterizing latency, and ways to address them using some new open source tools.
Jonathan Worthington explains how invokedynamic works, how he has been using it while porting the Rakudo Perl 6 compiler to the JVM, and its performance impact.
Hosted by Erik Meijer, who runs the Cloud Programmability Team at Microsoft, the panelists answer questions on C/C++ and Java performance, contrasting the virtues of native vs. managed code.
Limin Fu introduces Dao, a lightweight and optionally typed programming language having a LLVM-based JIT compiler optimized for numeric computation, and a Clang-based tool generating Dao bindings for C/C++ libraries.
Gil Tene examines the core issues that have historically kept Java environments from performing well in low latency environments and how it can perform now without trade-offs and compromises.
Brandon Benvie introduces Continuum, what it does, how it works, and why it's useful. Continuum maintains compatibility with all popularly used JS engines in use today (IE8, modern browsers, Node.js).
Luke Daley introduces Ratpack, a micro web framework inspired by Ruby's Sinatra, built on Netty, Guice and Guava.
Alex Gaynor explains how he solved the usual Ruby VM speed problems with Topaz, a high performance VM built on the same technologies that power PyPy.
Antoni Batchelli introduces VMFest, a PalletOps project used to turn VirtualBox into a lightweight cloud provider, good for developing cloud automation.
Roman Gonzalez and Tavis Rudd discuss techniques for shortening the ClojureScript development cycle by using the same codebase for clj and cljs and automatically running tests on the JVM.
The panelists discuss the future of the JVM in the context of parallelism and high concurrency of tomorrow’s thousands of cores.
Timothy Baldridge presents clojure-py2, a compiler written in Clojure that uses LLVM for code generation.