help-octave
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

benchmark 1.6 results


From: Francesco Potorti`
Subject: benchmark 1.6 results
Date: Mon, 15 Apr 96 12:33 MET

Here is a new table of results of many machines octave runs on.  The
most notable error of the previous table was the ranking of the Sun
Ultra 1, which really is at the top.

benchmark 1.5 contains a programming error that makes it fail under
very unlikely conditions.  If you experience a runtime error just try
to rerun it.  Or else you can download a more reliable version
(benchmark 1.6) from <URL:ftp://fly.cnuce.cnr.it/pub/benchmark.m>.
The tests are the same as before, so the results are fully comparable.

If you run benchmark on your machine send the results to me:  I will
add them to this table and will post it when it grows significantly.

Octave benchmark bm 1.6
                                 inv   schur lsode fft2  for   index
octave-1.1.1
[11] Linux/486dx-33              0.22  0.18  0.49  0.18  0.44   0.28
[15] DECstation 3100             0.22  0.23  0.49  0.33  0.43   0.32
[8]  Sun Sparc IPX4/50           0.40  0.39  0.44  0.42  0.38   0.41
[9]  Linux/486dx2-66             0.33  0.32  0.69  0.30  0.57   0.42
[2]  Sun Sparc2                  0.40  0.41  0.49  0.51  0.38   0.43
[12] OS2/486dx2-66               0.42  0.34  0.80  0.38  0.67   0.49
[8]  HP9000/710/50               0.92  1.04  0.44  1.14  0.32   0.69
[13] Sun Sparc5/70               0.74  0.89  0.79  0.91  0.63   0.78
[8]  Sun Sparc10/super51         0.65  0.69  0.99  0.96  0.98   0.84
[8]  Sun Sparc4/microII          0.81  0.91  0.85  0.95  0.73   0.85
[8]  Sun Sparc10/super20         0.89  0.88  0.83  0.85  0.82   0.85
[8]  Sun Sparc10/super30         0.99  0.94  0.89  0.99  0.88   0.94
[8]  Sun Sparc10/super40         1.00  1.00  1.00  1.00  1.00   1.0
[8]  Sun Sparc10/super41         1.12  1.17  1.03  1.03  1.01   1.1
[8]  HP9000/750/66               1.51  2.12  0.87  1.59  0.61   1.2
[8]  Sun Sparc20/super50         1.41  1.33  1.26  1.39  1.22   1.3
[13] Sun Sparc20/51              1.42  1.46  1.11  1.38  1.29   1.3
[6]  Linux/Pentium 90            1.23  1.23  1.91  0.87  1.71   1.3
[5]  Linux/Pentium 100           1.48  1.30  1.84  0.91  1.76   1.4
[8]  Sun Sparc20/super61         1.62  1.67  1.37  1.42  1.22   1.5
[7]  Irix 5.3/R8000 75/90        1.76  1.27  1.81  1.78  1.53   1.6
[8]  SGI Indigo 2XL              1.69  1.34  2.17  1.45  1.95   1.7
[13] Sun Sparc20/71              1.87  1.68  1.92  2.00  1.66   1.8
[7]  Irix/R8000                  2.07  1.53  2.17  2.14  1.91   1.9
[14] Linux/Pentium 133           1.81  2.43  2.37  1.44  2.22   2.0
[8]  Sun Sparc20/hyper125        1.82  2.76  1.92  1.98  1.87   2.0
[8]  HP9000/735/99               2.26  3.90  1.37  2.73  0.94   2.0
[4]  IBM RS6000/590              4.28  4.62  1.27  3.83  0.91   2.5
[1]  DEC Alpha 2100              3.84  3.54  2.80  3.58  2.37   3.2
[8]  Sun Ultra 1                 3.23  3.87  3.39  3.35  2.97   3.3

octave ss-960323
[10] Sun Sparc 10/50             1.00  1.00  1.00  1.00  1.00   1.0
[10] Sun UltraSparc 167          3.55  3.70  2.54  3.13  2.44   3.0
[10] DEC Alpha 400               3.51  6.53  1.74  4.26  1.50   3.0

[1]  Francesco Potorti` <address@hidden>
[2]  Evan Thomas <address@hidden>
[3]  Jarle Brinchmann <address@hidden>
[4]  John L Daschbach <address@hidden>
[5]  Michael Smolsky <address@hidden>
[6]  Jim Van Zandt <address@hidden>
[7]  Przemek Klosowski <address@hidden>
[8]  Matthias Roessler <address@hidden>
[9]  "Gisle J. Torvetj|nn" <address@hidden>
[10] Rick Niles <address@hidden>
[11] Carl Wilhelm Welin <address@hidden>
[12] Nils Naumann <address@hidden>
[13] Vinayak Dutt <address@hidden>
[14] Guido Masarotto <address@hidden>
[15] Heber Farnsworth <address@hidden>


reply via email to

[Prev in Thread] Current Thread [Next in Thread]