Raspberry Pi - Java Virtual Machine Benchmarks

I have recently been performing some benchmarks of the various Java Virtual Machines available on the Raspberry Pi ARM11 platform and thought I would share the results.  I used this test suite:  http://dacapobench.org/

Thanks to forum member chrisg on the Raspberry Pi forums who posted these benchmarks results for the previous Debian "Squeeze" image.  The results listed below for the OpenJDK are taken directly from chrisg's post.  I also ran these same tests on my Pi with Debian "Squeeze" and received very similar (maybe slightly higher) results.  

The following JVMs are represented:

• Oracle SE 7 JDK (7u6)
• Oracle SE 7 Embedded JRE (7u4) 
• OpenJDK Zero VM (6u18)
• OpenJDK Cacao VM (6u18)

The following chart includes all the tests performed and the resulting time in milliseconds that each test took to complete.  Obviously the lower number the better :-) 

I included a TOTAL line that sums up all the test results in minutes for each test case for rough comparisons, but please note that it does not compensate for the time missing from failed tests.

The test results are charted below for a visual representation.

 

I was particularly interested in the performance between the two available Oracle JVMs.  The results (as expected) were almost negligible.  The graph below illustrates the results of the two Oracle JVMs. 

* Raspberry Pi is a trademark of the Raspberry Pi foundation.
* Oracle and Java are registered trademarks of Oracle.

Comments

[Paul H]

Cool. I've been looking for something like this for a while. It would be cool to know how things stack up when oracle release the hard float jre.

[Robert Savage]

@Paul H

I attended JavaOne and the Oracle team confirmed that a hard-float version was in the works, but of course could not provide any estimated timeline when to expect a release. I'm not sure the performance gain will be all that significant unless you are crunching numbers or displaying a GUI app. But it will be nice to be able to use the main Raspian distribution. I hope to be able to update these test results when the hard-float supported JDK is finally released.

Thanks,
Robert

[mike]

Could you please benchmark the JDK8 preview with runs on raspberry pi (hardfloat)
http://www.savagehomeautomation.com/raspi-jdk8
THX Mike

[gowsalya]

Thank you for your information. It very nice article.
Java Training in Pune

[Hadoop admin training in pune]

Your article is too good and informative. I am searching For article related and I get exact article i am thankful to you for sharing such a helpful article.

Hadoop admin training in pune

[Anamika]

Thanks for sharing with us. I just loved your way of presentation. I enjoyed reading this .Thanks for sharing and keep writing. It is good to read blogs like this.
Rubix Research

[German classes In Chennai]

thanks for sharing me valid information and a useful blogs

[mihax83101]

This is a cockfight-related betting site that is legal in various countries of the world including the Philippines. This virtual gaming site is quite popular among people. The WPC2029 updates are regularly given on the WPC 2029 Facebook page.9
wpc2029

[gawes83833]

You can grab this benefit of regular updates by visiting the Facebook page after getting yourself registered with the website of WPC. At the time of registration, you will come across all the regulations and rules of the WPC 2029.

[types of packaging]

Glass packaging is a popular option for products like perfumes, cosmetics, and beverages due to its transparency, durability, and ability to preserve product quality. Glass is non-reactive, meaning it does not interact with the contents of the package, ensuring that the product’s flavor, aroma, and appearance remain intact.

[Convenience of packaged goods]

The convenience of packaged goods refers to the ease and convenience that packaged products provide to consumers. Packaged goods come in a variety of sizes and shapes that are easy to handle and transport, making them convenient for consumers to purchase and use.

[Deepaverma]

Machine learning (ML) is a subset of artificial intelligence (AI) that involves the development of algorithms that enable computers to learn from and make predictions or decisions based on data. Instead of being explicitly programmed for every task, ML algorithms build models based on sample data, known as training data, to make data-driven predictions or decisions.

Key Concepts in Machine Learning
Types of Machine Learning:
Supervised Learning: The algorithm is trained on a labeled dataset, meaning that each training example is paired with an output label. Common tasks include classification and regression.
Example: Predicting house prices based on features like size, location, and number of bedrooms.
Unsupervised Learning: The algorithm works on unlabeled data and tries to find hidden patterns or intrinsic structures in the input data. Common tasks include clustering and association.
Example: Grouping customers into different segments based on purchasing behavior.
Semi-supervised Learning: Combines a small amount of labeled data with many unlabeled data during training. It falls between supervised and unsupervised learning.
Reinforcement Learning: The algorithm learns by interacting with an environment, receiving rewards or penalties for actions, and aims to maximize cumulative rewards.
Example: Training a robot to navigate a maze.