Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ucbvax!ucsd!sdcsvax!ucsdhub!hp-sdd!hplabs!hpda!hpcuhb!hp-ses!hpcc01!hpwrce!howeird
From: howeird@hpwrce.HP.COM (Howard Stateman)
Newsgroups: comp.lang.postscript
Subject: Re: Postscript Benchmarks
Message-ID: <980004@hpwrce.HP.COM>
Date: 10 Apr 89 16:13:52 GMT
References: <1273@esunix.UUCP>
Organization: Ye Olde Salt Mines
Lines: 32

>However, the real point of this message is benchmarks.  We would like to
>benchmark the various printers to see which is faster.  Has anyone written a
>postscript benchmark?  Does anyone have any ideas as to what they think
>should be tested by such a benchmark.

I haven't written a benchmark, but I have used Pagemaker to give me an
idea of what kinds of things print faster/slower on a single Postscript
and HP PCL printer. So as a starting point, I'd say you want to try
three basic benchmarks:

1. Make a full-page scanned image. This is usually the most memory-intensive
   kind of page, especially if you use Gray Scale imaging from a color
   photograph. 
2. Try normal text, 10 or 12 point, Helvetica or Times Roman, something
   which doesn't take much memory or page description processing. Compose
   a 10-page letter, because one page won't give you enough of a benchmark
   to really tell the difference between printers.
3. Try a page of line drawings (such as a cartoon) or headlines (fonts
   which are between 36 and 72 point). This will test the mid-range
   of memory use.

Hope this helps.

-------------------------------------------------------------------
Howard Stateman, Hewlett-Packard Response Center, Mountain View, CA
howeird@hpwrc.HP.COM      or     hplabs!hpwrc!howeird
My opinions are not necessarily those of anyone or anything else
--------------------------------------------------------------------
Sysop of the Anatomically Correct BBS (415) 364-3739
"Nothing can be said so correctly that it cannot be twisted."
                                               - Spinoza
--------------------------------------------------------------------