Category: AMD Java Labs

Oracle Java and AllocatePrefetchStyle for “Bulldozer” Processors

This blog describes an option, -XX:AllocatePrefetchStyle=0, that may help performance when using a Java 6 (or older) Oracle JVM and running on an AMD Bulldozer core processor.…

A new NUMA option for Windows® on the Hotspot JVM

Here we discuss a new option that AMD contributed to the Hotspot JVM that helps improve performance on some applications on NUMA systems running Windows® OS. On…

5 minutes work for up to 5% more Hadoop performance

Lately we have been working on studying and trying to improve the performance of Apache Hadoop. In the spring my coworker Shrinivas Joshi created a great Hadoop…

I don’t always write GPU code in Java but when I do I like to use Aparapi

The AMD JavaLabs team is proud to announce the open source release of our Aparapi project. Over 18 months ago we began to investigate how Java developers…

Apache Hadoop Performance-tuning Methodologies and Best Practices – a downloadable reference guide

Users who have deployed and tried tuning their Hadoop clusters for the first time will certainly attest to the fact that optimizing Hadoop clusters is a daunting…

AMD Releases Aparapi, a Java API for Expressing GPU Bound Data Parallel Algorithms

At JavaOne 2010, AMD announced the release of an alpha version of Aparapi, an API that enables Java developers to express data parallel workloads plus a runtime capable of running…

Java Performance when Debugging is Enabled

Earlier this year AMD, working with the Hotspot JVM team,  submitted a change to the OpenJDK to help the performance of Java applications which run with debugging enabled, in particular…

Better uptime for long running Java applications

In January 2010 we submitted a new change to OpenJDK to overcome a long standing problem in the HotSpot JVM, that is that there was no mechanism…

Java Generics Performance Puzzler Part 2

  In a previous blog, we looked at a microbenchmark where we were pulling an item from a collections class like an ArrayList and eventually putting it in…

Final Words

I have always been a little unhappy with the decision to overload the use of the ‘final’ keyword to enable local variables to be made available to…