I did it!...I just configured and ordered a Athlon Dual Core from CyberPowerSystems

[lilboy716]

1+1=2 is the marketing scheme

2 is always better than 1 right?

that's why intel has "duo" & "solo"

from what i've heard, there are 2 versions of the duo core, one has based on prescott, and the other is based on the pentium m.

Quote from nononsense:

The only good answer to all this is benchmarking. I have not done this for the dualcore chips, but from intensive testing of dual processors under non-server loads, it's quite frustrating to see that total processor load almost never exceeds 50%. In my experience, the OS and driver processes you are alluding to indeed run on the other processor but constitute typically only a fraction of your application loads.

I simply never came across a competent explanation as to why a dual core should be better in all this. This is simply marketeering, now that chip manufacturers ran into the wall of physical limitations. They absolutely want the ignorant to think that indeed 1 + 1 = 2.

 

[dcraig]

Quote from nononsense:

The only good answer to all this is benchmarking. I have not done this for the dualcore chips, but from intensive testing of dual processors under non-server loads, it's quite frustrating to see that total processor load almost never exceeds 50%. In my experience, the OS and driver processes you are alluding to indeed run on the other processor but constitute typically only a fraction of your application loads.

I simply never came across a competent explanation as to why a dual core should be better in all this. This is simply marketeering, now that chip manufacturers ran into the wall of physical limitations. They absolutely want the ignorant to think that indeed 1 + 1 = 2.

Yes 1 + 1 != 2,

but 1 + 1 == 2 - a bit

Where 'a bit' has to do with bus contention, memory contention and so forth. The size of the 'bit' depends on system architecture which is why Opteron with hyperchannel beats Xeon in multi CPU configurations.

It is simply not true that the operating system and device drivers run on one CPU ( unless the device driver is pretty shabby). If you don't believe me, look up the role of spin locks in the Linux kernel.

The problems with extracting the potential performance from 2+ CPUs lie in the design of the application software. If it distibutes its work over independently scheduable threads or processes it will receive the benefit. Otherwise it won't. If the application is constricted by disk throughput then any number of CPUs wont make much difference.

Dual core is not just marketing hype (though as always, hype is not in short supply).

 

[nononsense]

Quote from dcraig:


The problems with extracting the potential performance from 2+ CPUs lie in the design of the application software.

That's what I've been saying a long time. For most of today's garden variety (including trading) applications, you'll find that:
1 + 1 = 1 + possibly a very meager little chunck.
I only look at benchmark figures. The above holds for most of what I am running here.

In this sense, a lot has changed in the CPU world since the manufacturers hit the physics wall.

Before we get at the suggested 1 + 1 = nearly 2 for typical user loads, this may take quite a bit of time. NO MORE EASY SPEED SCALE UPS since the dual stuff hit us.