Results of Single and Dual Processor Colt Matrix Benchmark

using the matrix package. For more explanations, on how to interpret and run benchmarks on your own boxes, see the documentation of class BenchmarkMatrix.

OS Linux Your config.
OS Config. Red Hat 6.1, Kernel 2.2.12-20smp  
HW 2 x PentiumIII@600 MHz, 512 MB, 32 KB L1, 2x256 KB L2 (lxplus012.cern.ch)  
VM IBMJDK1.3, Classic VM, build cxdev-20000502, jitc  
Performance here  

Here the result for the matrix matrix multiply with one thread and the parallel version with two threads.

Each operation is timed varying the following parameters

Methodology

Command line: java -Xmx400m cern.colt.matrix.bench.BenchmarkMatrix -file all

Below some results from an old version 1.0Beta4-1. Of historic interest only.

OS Linux Linux Linux Solaris
OS Config. Red Hat 6.1, Kernel 2.2.12-20 Red Hat 6.1, Kernel 2.2.12-20 Red Hat 6.1, Kernel 2.2.12-20 Solaris 2.6 (aka SunOS 5.6)
HW 1 x PentiumIII@600 MHz, 128 MB, 32 KB L1, 256 KB L2 (linuxosdev.cern.ch) 1 x PentiumIII@600 MHz, 128 MB, 32 KB L1, 256 KB L2 (linuxosdev.cern.ch) 1 x PentiumIII@600 MHz, 128 MB, 32 KB L1, 256 KB L2 (linuxosdev.cern.ch) Sun 450, 2 x Ultrasparc-II@400 MHz (1 CPU used), 256 MB, 32 KB L1, 4 MB L2 (shd70.cern.ch)
VM IBMJDK1.1.8 BlackdownJDK1.2.2RC3, Classic VM, native threads, sunwjit SunInpriseJDK1.2.2RC1, Classic VM (build 1.2.2-I, green threads, javacomp) SunJDK1.2.2, Classic VM
Performance here here here here