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. In our labs, this option was observed to give performance lift typically between … Continue reading
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 some applications and heap configurations we saw up to a 2.5X performance improvement. … Continue reading
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 tuning reference poster: http://blogs.amd.com/developer/2011/07/12/apache-hadoop-performance-tuning-methodologies-and-best-practices-%E2%80%93-a-downloadable-reference-guide/ This week I made a pleasant discovery that would … Continue reading
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 might be able to take advantage of the (potentially huge) compute performance of … Continue reading
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 task. Apart from the nature and implementation of Hadoop jobs, the hardware, network … Continue reading
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 compatible workloads on a GPU. Although OpenCL™ bindings for Java already exist (JOCL/JOpenCL), … Continue reading
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 ones that also throw and catch exceptions as part of their flow control. We’ve … Continue reading
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 in the JVM to recover if the code cache of compiled Java methods … Continue reading
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 another collection. And we saw that there could be a significant performance difference … Continue reading
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 methods in inner classes. Let’s recap. Here is a method which launches … Continue reading
