O-Matrix Performance
O-Matrix has been designed from the ground up for accuracy and high-performance. The O-Matrix environment enables you to both prototype designs and perform large
scale analysis within the integrated environment. O-Matrix has been built using highly optimized C/C++, FORTRAN, and assembly code to provide optimal execution
performance. The linear algebra routines in O-Matrix are based on the algorithms from BLAS, LINPACK, and LAPACK to provide robust, accurate solutions.
Overall, O-Matrix is the fastest matrix computation package we have tested.
- SciViews
The following benchmark is a courtesy of Stefen Steinhaus' Number Crunching Report
|
Benchmark
|
O-Matrix 5.8
|
O-Matrix 5.7
|
Matlab
7.01
|
|
400x400 random
matrix^1000
|
0.062
|
0.151
|
0.110
|
|
Eigenvalues of 300x300
random matrix
|
0.386
|
0.396
|
0.516
|
|
Inverse of 500x500
random matrix
|
0.130
|
0.182
|
0.198
|
|
500000 sorted values
|
0.157
|
0.182
|
0.182
|
|
800x800 Toeplitz matrix
|
0.047
|
0.068
|
0.187
|
|
Cholesky decomposition,
500x500 matrix
|
0.026
|
0.031
|
0.031
|
|
500x500 cross product
matrix
|
0.078
|
0.093
|
0.063
|
|
FFT over 100000 values
|
0.078
|
0.089
|
0.052
|
|
Gaussian error function
over 500x500 matrix
|
0.010
|
0.255
|
0.193
|
|
Gamma function over
600x600 matrix
|
0.189
|
0.781
|
0.265
|
|
Linear regression over
500x500 matrix
|
0.052
|
0.068
|
0.078
|
All timings are in seconds. - Run on a 2.26 GHz Pentium 4. All calculations performed with double-precision values
You may download the M-File benchmark. (To run Matlab compatible m-files in O-Matrix, press the lightning bolt icon
on the toolbar, change the 'Files of type' drop down to 'Mlmode File Type,' and select the file.) Note that you must install the O-Matrix MFile Compatibility Library to run the Matlab-based benchmarks available. See Why Users are Choosing O-Matrix for a more detailed product comparison of O-Matrix and Matlab.
The following benchmark is a courtesy of SciViews.org.
|
Benchmark
|
O-Matrix 5.8
|
O-Matrix 5.7
|
Matlab 7.01
|
|
Creation, Transpose, Deformation of a 1500x1500 Matrix
|
0.365
|
0.365
|
0.328
|
|
Determinant of a 650x650 Random Matrix
|
0.109
|
0.193
|
0.125
|
|
Calculation of 750,000 Fibonacci Numbers
|
0.442
|
0.453
|
1.200
|
|
Creation of a 2500x2500 Hilbert Matrix
|
0.474
|
0.255
|
0.562
|
|
Grand Common Divisors of 70,000 Pairs
|
0.260
|
0.178
|
0.370
|
|
Escoufier's Method on a 37x37 Matrix
|
0.454
|
NA
|
0.813
|
|
All timings are in seconds. - Run on a 2.26 GHz Pentium 4
All calculations performed with double-precision values
|
Back to O-Matrix Main Page.
|
