Dynamically optimized environments present unique challenges for trading systems. Dynamic optimizations give us faster code, but can also bring temporary slowdowns, often at the worst possible times. After GC complaints, the most common issues we hear about in latency sensitive Java-based systems have to do with "warmup" behavior and de-optimization slowdowns. E.g. these seem to predictably hit trading systems just as the market opens, resulting in slow trades when speed matters most. In this talk, Gil Tene (CTO, Azul Systems) will provide an overview of JIT compiler optimization techniques and their impact on common slowdown scenarios. Gil will cover the technical issues behind such slowdowns, and discuss new techniques that may be used to avoid them, including the use of features specifically built to tame the JVM and improve behavior at market open.

Java is fast. Really fast. But the memory layout of objects and arrays is an area where Java still inherently lags (in speed) behind the C family of languages.

This session introduces org.ObjectLayout and StructuredArray, a new Java collection library and an array class designed specifically to enable JVMs to optimize memory layout for arrays of objects in a way that closely matches the performance behaviors of arrays of structs in C. org.ObjectLayout works on any JDK (version 6.0 and above), but when “intrinsified” in newer JDKs, it brings dead-reckoning and streaming speed to what is in essence an array of Java objects.

The presentation covers the APIs and design considerations behind them and explains the fundamentals behind logic that can allow Java JDKs to match C on data structure access speeds.

The panelists will discuss Java performance subjects, bringing their specific experiences to bear. The discussion will compare Java with other runtimes and languages, and debate recent and future Java-specific performance subjects.