The AMD vs Intel issue generally seems to relate to the amount of L2 cache on the CPU. Rosetta's application is much larger then many other BOINC projects. This means much of it is stored in L2 cache and so systems with small L2 caches are constantly running out to memory to get subroutines. This slows overall efficiency.

A X2 2.8ghz AMD only has a 2mb processor cache, the E8400 has a 6 mb processor cache. The bigger the processor cache, the more credit you are granted, especially for work units that are cache sensitive, like the Rosetta mini. The Intel core 2 Duo's are the way to go for building a crunching machine, and they use much less power and electricity than an AMD.

Though this theory works for Intel CPU's which use a memory controller on the motherboard, which introduces high latency for main memory accesses. AMD CPU's have an integrated memory controller which means memory accesses are much faster than Intel chips. Therefore reducing the need for a large cache, which
a) introduces latency itself if it is not neccesary, and
b) bumps up the cost of the CPU as cache memory is manufactured using SRAM which is very expensive.

Intel are moving away from this problem with their next gen Nehalam chips with the Quickpath design

t

guess i'll also have to consider the power supply thing if i want to put a x1950 into a Compaq...

The Penryn is not going to perform any better clock-to-clock wise then the actual core. // in rosetta

Hard to say, right now. Some apps show a few % improvement, others 0%. I think Penryns have some better memory management or something; we'll soon find out, at any rate.

But it's not going to be much, unless the Rosetta coders add SSE4 support (if it's even useful), which seems unlikely for some time.

Still the 12mb cache could come in handy; or would it be better to o/c the 2.5ghz/6mb part...???? : )

Intel Core 2 CPUs seem to do slightly better at Rosetta than AMD CPUs.

Is there actually any comparison by anyone for a Hz to Hz (or £€$) with granted credit. I suppose I could have a look is the big long list but if somebody has already done it, it's so much easier.



EDIT to add my 2 mins of checking

Taking near the 1000th RAC to remove all the Quad Cores
found

http://boinc.bakerlab.org/rosetta/show_host_detail.php?hostid=280878
Intel(R) Core(TM)2 CPU 6420 @ 2.13GHz
~48 credits per task

http://boinc.bakerlab.org/rosetta/show_host_detail.php?hostid=439791
AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ ( should be 2GHz)
~ 32 credit per task (34.5 adjusted to 2.13GHz)

Both using the same time length (~10,000 seconds)



Have to assume neither is overclocked beyond it's designated speed.
And this is a 2 minute look using the fist 2 nearest each other in RAC, lol.


So cost difference, ?

Increase in performance compared with other AMD products = 0
A AMD Fx processor will have the same performance and was releasead on... 2005?

They launcheg a (new? :/) processor...


http://game.amd.com/us-en/unlock_athlonblack.aspx

Things aren't quite good with amd...