Pretty good article at AnandTech about new 32nm
Clarksdale cpus. There will be a somewhat confusing myriad of different platform and CPU offerings available this year. A person will really need to consider current usage, needs, budget, and extent of "future-proof" they desire to land on the "right" combo of CPU & platform.
If looking at Clarksdale w/ Seti crunching in mind, this part of article is especially worth noting.
it’s not all rosy with Clarkdale unfortunately. Remember the memory controller that Nehalem so graciously integrated? Clarkdale kicks it off die again. The IMC is housed in the 45nm GMA die. It’s still on-package, but not on-die. The benefit is super fast memory access for the graphics core, but slower memory access for the CPU core. In fact, this is a derivative of the memory controller used in older Intel chipsets (e.g. P45/X48).........Latency is unfortunately hurt as a result. Access times can be longer than older LGA-775 processors thanks to this memory controller design being optimized for FSB architectures.....the on-package chipset is a derivative of the P45 lineage. It’s optimized for FSB architectures, not the QPI that connects the chipset to Clarkdale.
Processor L1 Latency L2 Latency L3 Latency
Intel Core i7-975 4 clocks 10 clocks 34 clocks
Intel Core i5-750 4 clocks 10 clocks 34 clocks
Intel Core i5-661 4 clocks 10 clocks 39 clocks
Phenom II X4 965 3 clocks 15 clocks 57 clocks
Intel Core 2 E8600 3 clocks 15 clocks
L1 and L2 cache latency is unchanged. Nehalem uses a 4-cycle L1 and a 10-cycle L2, and that’s exactly what we get with Clarkdale. L3 cache is a bit slower, which makes sense because the Core i5 661 has a lower un-core clock (1.66GHz vs. 2.66GHz for the high end Core i7s).
Processor Memory Latency Read Bandwidth Write Bandwidth Copy Bandwidth
Intel Core i7-975 45.5 ns 14379 MB/s 15424 MB/s 16291 MB/s
Intel Core i5-750 51.5 ns 15559 MB/s 12432 MB/s 15200 MB/s
Intel Core i5-661 76.4 ns 9796 MB/s 7599 MB/s 9354 MB/s
Phenom II X4 9600 52.3 ns 8425 MB/s 6811 MB/s 10145 MB/s
Intel Core 2 E8600 68.6 ns 7975 MB/s 7062 MB/s 7291 MB/s
Memory latency is about 76% higher than on Lynnfield. It’s also reflected in the memory bandwidth scores. While Lynnfield can manage over 15GB/s from its dual-channel memory controller, Clarkdale can’t break 10. Granted this is higher than the Core 2 platforms, but it’s not great.
What we’re looking at is a Nehalem-like CPU architecture coupled with a 45nm P45 chipset on-package. If anything was going to hurt Clarkdale’s performance, it’d be memory latency.
If planning to crunch Seti (or any DC project)
w/ Cuda or ATI-based GPU applications, pay real close attention to CPU, platform and total build costs between Penryn, i7 Bloomfield & Lynnfield, i5 Lynnfield, and i5 Clarksdale CPUs @ $149- $289 CPU price points.
Lots of Intel quad-core, and even 8-threaded options within that price-range.
Intel appears to be charging
quite a premium for their integrated GPU & Turbo feature in new i5.
A person can add a pretty nice entry/mid-level nVidia or ATI graphics card for equal or less $ than the cost difference for an upper echelon i5.
However, if considering a dual core Intel CPU, this i3 model appears to offer pretty good value for clock speed, # of threads & cache size for the $ when compared to similar clock and cache size of
Core 2 models. At 32nm, should also be pretty fun to OC.
Processor Core Clock Cores / Threads L3 Cache Max Turbo TDP Price
Intel Core i3-530
2.93GHz 2 / 4 4MB N/A 73W $113[/b]
Now, bring on those 6-core Westmeres!
