Matt Warren takes a look at how to measure, what to measure and how get the best performance from .NET code, considering examples from the Roslyn codebase and StackOverflow (the product).
Sylvan Clebsch talks about using Pony for fintech to build high-performance tools. Pony is a new actor-model statically typed language, compiled AOT, with a GC and a data-race free type system.
John Oliver takes a look at both G1 and Shenandoah, explaining how they work, what are their limitations, providing tuning advice. He also looks at recent and future changes to garbage collection.
Monica Beckwith talks about G1 pause (young and mixed) composition, G1's remembered sets and collection set and G1's concurrent marking algorithm, providing performance tuning advice.
Gil Tene provides an in-depth overview of Latency and Response Time Characterization, including proven methodologies for measuring, reporting, and investigating latencies, including pitfalls to avoid.
Charlie Hunt explains the three performance attributes of throughput, latency and (memory) footprint and how each of these are influenced in terms of JVM garbage collection.
This talk looks at where Java has come from and where it is going, including some of the things that may be in Java 9 such as Jigsaw, the sun.* changes, the G1 garbage collector, and VarHandles.
Rick Hudson discusses the motivation, performance, and technical challenges of Go's low latency concurrent GC and why the approach fits Go well.
Yehuda Katz introduces Rust: the ownership system, automatic memory management which guarantees at compile time that a program will never segfault, making Rust code resilient against memory leaks.
Rifat Shahriyar, Steve Blackburn, Kathryn McKinley show that conservative garbage collectors using Immix can be as performant and sometimes even faster than generational GCs.
Gil Tene introduces org.ObjectLayout and StructuredArray, the APIs and design considerations that allow Java JDKs to match C on data structure access speeds.
The session covers various GC tuning techniques, in particular focusing on tuning large scale JVM deployments and showing how to optimally size a platform for enhanced memory consumption.