Intel Westmere 32nm Launch & Clarkdale Core i5-661 CPU Review

Packaging & Chips


We can expect Clarkdale chips to ship in the same packaging design that was unveiled with Lynnfield. The Pentium G6000 series will obviously have its Pentium logo.


For Clarkdale, Intel has re-used the tiny & puny stock cooler that they had included with Lynnfield. It is a typical Intel design, featuring an aluminium body with an integrated copper core, and push-pins as the mounting system. This cooler was downright mediocre at cooling Lynnfield under heavy load, but perhaps it will be a little better with the cooler running Clarkdale chips. As you can see, there is a huge size difference between the Clarkdale/Lynnfield cooler and the one that ships with Bloomfield Core i7-900 series processors. We will definitely be testing to see how well this cooler manages to cool our i5-661 with both the CPU and GPU at full load.


If you mistake this chip for a Lynnfield-based one, we don't blame you. Externally, Clarkdale and Lynnfield are absolutely identical. This is not a big surprise though, as they do both use the same LGA1156 package. Needless to say that our chip is an engineering sample, and thus the stepping code is different from what you will find in the retail channel. The core itself is identical though.


As per the LGA1156 socket name, those are 1156 contact points, a decrease from the LGA1366 Core i7 900 series, but still a huge increase from the 775 that are found on all Core 2 models. The layout of the micro SMD resistors is very interesting because it mimics the layout of the actual core, which you can see on the next page.


When placed side-by-side, you can clearly see how much smaller the Clarkdale chip is compared to the Bloomfield. Why is the Bloomfield's LGA1366 package so big? Well, it was designed with future headroom in mind, specifically larger six-core and maybe even eight-core dies. It is also worth noting that the Clarkdale chip is actually exactly the same size as the venerable Core 2 Duo/Quad.


As usual, the CPU core speed is derived by a multiplier times bus speed formula. Since the FSB is no longer present, the bus speed in question is the base clock (BCLK), which has a stock frequency of 133MHz. As mentioned above, although our chip is an engineering sample it is manufactured with the final retail stepping, so it will perform the same as the chips you will be able to buy in the retail channel.

On Bloomfield and Lynnfield, the integrated memory controller (IMC) and the L3 cache operate on a seperate frequency called the Uncore clock (NB frequency in CPU-Z), which is derived by the uncore multiplier times the BCLK. However, the IMC is not part of the the CPU die on Clarkdale, it is integrated into the GPU die. The L3 cache remains part of the CPU though. On our i5-661 sample the integrated memory controller was running at 1600Mhz (12X), while the L3 cache was operating 2400Mhz (18X). The QPI frequency was set to 6384Mhz (48X).

Now let’s take an in-depth look at the Westmere microarchitecture (aka 32nm Nehalem) upon which these Clarkdale processors are based.