On 6/21/06, Yu Safin <[EMAIL PROTECTED]> wrote:
I am talking throughput here, not speed.
What would be the difference if your test fully saturates the 6 CPU's ? That would suggest the test is limited by the processing capacity right now. Less and/or slower CPUs will make it slower. If that's your application, a small z890 will not make you famous in a good way. Unless of course the CPU cycles are consumed by something completely unrelated to your experiment (e.g. some measurement program that does a busy wait to achieve exact timing measurements, or some java class that implements a wait by counting with very small steps). In that case your measurement is not very useful this way. Rob -- Rob van der Heij Velocity Software, Inc http://velocitysoftware.com/ ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
