lkml.org 
[lkml]   [1996]   [Apr]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: When you post a benchmark, please explain the units
Date
> When you do so, please describe the units in which each test is calibrated,
> at least briefly. A number of us have no particular acquaintance with the
> tests you've posted, be they from Byte, OSF, or whatever.
>
> It would also be helpful to provide URL's which point to the particular
> place from which you've extracted the source, or your source if you
> originated the benchmark.
>
> Please take the time to ensure that your posting is not noise for a large
> number of readers.

Unless otherwise stated, bigger numbers are better.

This should do because the numbers are relative.
I have different hardware than you do, so I could even
scale my results by an arbitrary number and it shouldn't
matter at all. There can be no calibration because there
is no standard PC, and even then individual machines vary.

The purpose is to answer "Are we gaining or losing?".


\
 
 \ /
  Last update: 2005-03-22 13:36    [W:0.055 / U:0.916 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site