Re: Antwort: Re: compare SP-wide node with a p610 standalone conc erning performance [Virus checked]

From: Green, Simon (Simon.Green_at_EU.ALTRIA.COM)
Date: 04/29/05

  • Next message: fmu_at_OERAG.DE: "Antwort: Re: compare SP-wide node with a p610 standalone concerning perfor mance [Virus checked]" 
    Date:         Fri, 29 Apr 2005 15:55:30 +0200
To: aix-l@Princeton.EDU

    Simply multiply rPerf by 20 to get ROLTP. That's dreadfully inaccurate -
    more so as the architectural differences increase - but it's good enough for
    a quick estimate. Note that 20 is a very dodgy value to use for this but it
    makes the mental arithmetic easy. 

    --
Simon Green
Altria ITSC Europe s.a.r.l.
AIX-L Archive at https://new-lists.princeton.edu/listserv/aix-l.html
New to AIX? http://publib-b.boulder.ibm.com/redbooks.nsf/portals/UNIX
N.B. Unsolicited email from vendors will not be appreciated.
Please post all follow-ups to the list.
-----Original Message-----
From: IBM AIX Discussion List [mailto:aix-l@Princeton.EDU] On Behalf Of
fmu@OERAG.DE
Sent: 29 April 2005 14:38
To: aix-l@Princeton.EDU
Subject: Antwort: Re: compare SP-wide node with a p610 standalone concerning
performance [Virus checked]
Hi Holger,
where you find this information?
I show in the IBM performance report. But for the 332MHz wide node I find
only ROLTP-values and for the p610 only rPerf-values. I cannot compare
this...
  • Next message: fmu_at_OERAG.DE: "Antwort: Re: compare SP-wide node with a p610 standalone concerning perfor mance [Virus checked]"