QCon10Years
Conference:March 7-9, 2016
Workshops:March 10-11, 2016
Sign up to be informed when registration opens for QCon London 2017 (3/6 - 3/10)

Track: Close to the Metal

Location:

  • Churchill, G flr.

Day of week:

  • Tuesday

Writing efficient code is becoming ever more important. CPU cores are not getting significantly faster with each generation, all the action is now in the memory subsystems, buses, and networks. Efficiency plays a major role in reducing energy consumption in data centres and on mobile devices.

The Close to the Metal track is all about how we get back to writing efficient code. Code with mechanical sympathy, code we measure, but also code that is easy to reason about. We'll cover things like cache-efficient algorithms, concurrency that scales, and how to efficiently utilise our platforms.

Track Host:
Martin Thompson
High Performance & Low Latency Specialist
Martin is a Java Champion with over 2 decades of experience building complex and high-performance computing systems. He is most recently known for his work on Aeron and SBE. Previously at LMAX he was the co-founder and CTO when he created the Disruptor. Prior to LMAX Martin worked for Betfair, three different content companies wrestling with the world largest product catalogues, and was a lead on some of the most significant C++ and Java systems of the 1990s in the automotive and finance domains. He blogs at mechanical-sympathy.blogspot.com, and can be found giving training courses on performance and concurrency when he is not cutting code to make systems better.
10:35am - 11:25am

by Martin Thompson
High Performance & Low Latency Specialist
The quest for low-latency with concurrent Java

Concurrent programming with locks is hard. Concurrent programming without locks can be really hard. Concurrent programming with relaxed memory ordering and predictable latency is said to be only for wizards. This talk focuses on a decade long quest to discover algorithms which provide very high throughput while keeping latency low and predictable. Additionally, these algorithms and data structures need to provide real-time telemetry on how a system is performing via non-blocking operations...

11:50am - 12:40pm

by Maciej Maciejewski
Senior Software Engineer @Intel
How Will Persistent Memory Change Software Design?

Byte-addressable Persistent Memory, in the form of a DIMM, is an emerging technology expected to soon have a dramatic and disruptive impact on server software. Usage of persistent memory as a storage replacement attached directly to a memory controller, requires a different approach to data handling within the kernel and applications that use it.

In this talk we will examine the primary differences between persistent memory, storage devices, and regular DRAM. We shall present how...

1:40pm - 2:30pm

by Monica Beckwith
Led the performance effort for Java's G1 Garbage Collector
Game of Performance: A Song of JIT and GC

In this session attendees will learn about various JIT Compiler and Runtime optimizations in OpenJDK HotSpot as well as the inner workings of Garbage Collectors (GC) in OpenJDK HotSpot. The optimizations covered in this talk will have a common theme of "optimizing for the metal"

2:55pm - 3:45pm

by Gil Tene
CTO and co-founder @AzulSystems
Understanding Hardware Transactional Memory

Hardware Transactional Memory (HTM) is here. Again. It has finally become a common feature in commodity server hardware platforms. But what will we do with it? This session will explore the underlying mechanics that power HTM on current platforms, focusing on things developers need to understand when contemplating the use of HTM in new and existing code. We will discuss and demonstrate new speculative and optimistic locking mechanisms enabled by HTM, cover benefits and limitations, and...

4:10pm - 5:00pm

by Richard Kasperowski
Author of The Core Protocols: A Guide to Greatness

Open Space
Open Space Close to the metal
5:25pm - 6:15pm

by David Riddoch
Leads the development of the Solarflare Open Onload IP stack
Much Faster Networking

The bandwidth available on our network links has been growing much more rapidly than the performance of our CPU cores. In response, the host network stack has seen a great deal of innovation.

This session will cover the technologies that make very high performance networking possible on commodity servers and networks, with a special focus on kernel bypass technologies including sockets acceleration and NFV (Network Functions Virtualization).

These techniques give user-space...

Tracks

Covering innovative topics

Monday, 7 March

Tuesday, 8 March

Wednesday, 9 March

FULL SCHEDULE

Conference for Professional Software Developers

Follow QCon

Contact

Menu

QCons around the World

Qcon