The manufacturing process is down to 32nm now with the Bulldozer CPUs compared to that of Phenom II which is 45nm. This entails that due to the smaller architecture, it should be both cooler running and it should use less power. With that in mind, it should also mean that overclocking headroom is increased. Lets take a look at what the results say...

In order to make sure that our results were comparable to the Phenom II sample we have, we had to limit the CPU multiplier to 11.5x on both CPUs. The AMD Phenom II 955 which we have can only go to around 3.8GHz before it becomes unstable and no amount of voltage tweaking could get any more out of the system. It is most likely due to it being a C2 revision as the C3 revised chips overclocked much better. Our AMD Bulldozer FX-8120 sample on the other hand is capable of 4.5GHz, fully stable, and it will run anything we throw at it. So, improved overclocking definitely is there, as expected.

Below is an image of the two CPU-Z shots of each chip, side by side. This is what configuration we are going to be running for this review.



Lets talk overclocking. In terms of how easy it was to overclock either CPU, they were both just as easy as each other. We were able to get an extra 4MHz out of the CPU bus with the AMD Bulldozer FX-8120 but this is as far as it would go. It is most likely down to a motherboard limitation and/or CPU limitation as they are pushing the chipset and CPU extremely hard at this point. So it is fair to say that the overclocking being slightly better is most likely down to the CPUs rather than the design.

The AMD Phenom II range of quad cores were known to start to hit thermal and voltage limitations once they hit the 4 or 4.2GHz barrier with the later C3 revisions of chips flying off of the shelves. So, to be able to take eight cores to 4.5GHz with less voltage is some achievement. However, will the increase in speed and double the amount of cores translate into a large performance increase? Lets find out...