Keith Lea says, "I was sick of hearing people say Java was slow, when I know it’s pretty fast, so I took the benchmark code for C++ and Java from the now outdated Great Computer Language Shootout and ran the tests myself." The results are available on his web site at http://kano.net/javabench/ in an HTML document titled “The Java is Faster than C++ and C++ Sucks Unbiased Benchmark “
The benchmarks that were run include the old standards: Ackerman, Fibonacci, Hash2, Hash, Heapsort, Matrix, Method Call, Nested Loop, Object creation, Random gen, Sieve, String concatenation, Sum col, and Word count.
A data table and graph of the results are available at http://kano.net/javabench/data
JDJ wrote an article on the results. They offered to post additional results from anyone who runs benchmark tests - “JDJ has agreed to post online anyone else’s results as long as they use Java 1.4.2 or higher and any version of GCC that produces faster or equivalent code than the 3.3.1 I used. We encourage you to download the source and/or the binaries and perform the tests yourself, with your favorite compiler and on your favorite platform.“
http://sys-con.com/story/?storyid=45250&DE=1
I remember the great benchmark wars during the early years of the PC compiler and tools business. Borland ran ads with benchmark results comparing Pascal, C, and C++ compilers. It was great fun, but I always say “Beware of Benchmarks“ and what they show and don’t show. While benchmarks (synthetic or otherwise) show “real“ results, the actualy results in real applications can vary.
Post a Comment