How fast is your Java platform for number crunching?
Run it on your system now!
SciMark 2.0 is a Java benchmark for scientific and numerical computing. It measures several computational kernels and reports a composite score in approximate Mflops (Millions of floating point operations per second). You can run the benchmark directly from your browser, or download the class files and Java source codes to run SciMark 2.0 on a separate Java environment. Afterwards, you may want to submit the results to our database of existing scores.
|Find out about our new kernels, availability of source code and class files, new units of measurement for score results, and revamped automated submission system. You can also find out how to run our special LARGE version of SciMark 2.0 for out-of-cache problems.
|Run it Now
|Contains instructions on executing SciMark 2.0 and reporting results. You can compare with other platforms on a kernel-by-kernel basis to see how your environment performs on specific algorithms.
|SciMark 2.0 scores
|We keep an up-to-the minute list of contributed scores for various Java platforms. If you submit a score, our database is updated immediately.
|If you want to run SciMark 2.0 outside your browser, there is access to the class files as well as Java and C source codes.
|Find out about the design of SciMark 2.0, and why we built it. Includes details on kernels chosen for SciMark and how to get meaningful information about your Java platform from your benchmark scores.
|Here we keep a list of our most frequently asked questions.
|Links to other Java benchmarking projects and numerics-related sites for Java scientific computing.
|Find out about SciMark authors and major contributors. Includes general disclaimers and acknowledgments.
Commercial equipment and software is referred to on these pages in order to precisely document experimental measurements. Mention of these products does not imply recommendation or endorsement by the National Institute of Standards and Technology, nor does it imply that the products so identified are necessarily the best available for that purpose.