home *** CD-ROM | disk | FTP | other *** search
- Path: soap.news.pipex.net!pipex!usenet
- From: m.hendry@dial.pipex.com (Mathew Hendry)
- Newsgroups: comp.sys.amiga.misc
- Subject: Re: Speed: 68040 vs. 68060
- Date: Wed, 28 Feb 96 01:49:09
- Organization: Private node.
- Distribution: world
- Message-ID: <19960228.652C38.1B4E@ak138.du.pipex.com>
- References: <4foi00$60t@gondor.sdsu.edu> <3125E74D.3390@gih.no> <19960223.425E10.10CBD@an100.du.pipex.com> <19960225.7AF9790.E534@asd10-22.dial.xs4all.nl> <19960226.477570.1832@an174.du.pipex.com> <4grotj$8q3@serpens.rhein.de> <19960226.7B42F98.E8D9@asd06-03.dial.xs4all.nl> <19960226.43B8E8.EF50@ai038.du.pipex.com> <19960227.7AD21D0.FF6A@asd06-24.dial.xs4all.nl>
- NNTP-Posting-Host: ak138.du.pipex.com
- X-Newsreader: TIN [AMIGA 1.3 950726BETA PL0]
-
- Jeroen T. Vermeulen (jtv@xs4all.nl) wrote:
- : In article <19960226.43B8E8.EF50@ai038.du.pipex.com> m.hendry@dial.pipex.com (Mathew Hendry) writes:
- :
- : > : > >BTW, running the BYTEMarks in a multitasking environment is actually likely
- : > : > >to show the Amiga in a good light, because AmigaOS has much lower task
- : > : > >switching overheads than many other multitasking OSs...
- : > : >
- : > : > Right.
- : > :
- : > : Not necessarily in this case. What I meant is that the timing routines may
- : > : include time spent on other tasks.
- : >
- : > That's irrelevant. The intention is to see how long the algorithms take on a
- : > real system (in real time, not in CPU time). On a real system, running a real
- : > application, you will also have other tasks "stealing" CPU time, which
- : > increases the real time taken to complete a task.
- :
- : On a real system, you will usually want to do several things at the same time
- : (even if it's just for hiding I/O latencies). So whether or not a system is
- : multitasking is hardly irrelevant.
-
- I didn't say it was. The difficulty is that if you only measure the CPU time
- taken and not the real time, then you are effectively ignoring the fixed
- overheads present on that system, which could in some cases give a very
- distorted measure of real performance.
-
- These benchmarks were designed to test an OS / hardware combination. The
- documentation makes this very clear. Only measuring the CPU time taken would
- remove any consideration of the OS from the results.
-
- A more complete method would be to measure the time taken to complete the
- tasks in both CPU time _and_ real time. This would give an estimate of
- operating system overheads, as well as a measure of application performance.
-
- i.e. Operating system overhead = Real time taken - CPU time taken
-
- (assuming, of course, that the tests were carried out on a system otherwise
- unloaded by user tasks).
-
- Adding measurements of CPU time taken would sacrifice portability, though.
- AmigaOS, for example, has no built-in means of calculating it as far as I
- know, although numerous utilities such as Executive have been produced which
- implement such functions...
-
- [...]
-
- -- Mat.
-