More cores doesn't mean "faster" it means more processing ability.
In your example you compared a faster (3Ghz) Dual Core to a slower (2.53Ghz) Quad Core. In Practical Theory, the Quad Core can handle more requests per second than the Dual Core, but not twice as many requests... There is a factor of diminishing returns as you add more cores. =] On Wed, Apr 7, 2010 at 1:30 PM, John Foster <[email protected]> wrote: > > So I'm going to have to stick with 32 bit machines for a bit longer while > we find alternatives for some com's we're using that don't work on a 64 bit > platform. > > From my research It appears that request speed is directly correlated to > CPU clock, not number of cores, cache, or bus speed. > > Here are the average page load times from 3 different machines: > > 2x single core opteron 246 (2Ghz / core): 251ms > 2x Dual core Xeon 5160 (3Ghz / core): 196ms > 2x Quad core Xeon 5540 (2.53Ghz / core): 261ms > > We're running database servers on similar Xeon 5540 machines and the SQL > performance on those boxes if far better that what we would get with the > Opteron's or Xeon 5160's. > > Does anyone know why requests on the older generation xeon 5160 would be > 20% faster than the current generation 5540? Is the speed of a ColdFusion > app purely based on clock speed in anyone elses experience? > > Thx, > > John > > ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~| Want to reach the ColdFusion community with something they want? Let them know on the House of Fusion mailing lists Archive: http://www.houseoffusion.com/groups/cf-talk/message.cfm/messageid:332723 Subscription: http://www.houseoffusion.com/groups/cf-talk/subscribe.cfm Unsubscribe: http://www.houseoffusion.com/groups/cf-talk/unsubscribe.cfm
