Intel Ivy Bridge-E Core i7-4960X IPC and OCing Review

We debut Intel's next $1000 Extreme Desktop processor, the Core i7-4960X, this time with Ivy Bridge architecture and a couple of extra cores thrown in for good measure. It is a beast of a CPU for those that can actually harness its power and bandwidth, but how much better is it than Sandy Bridge-E and Haswell at the same clocks?

continued...

Synthetic Benchmarks

Synthetic benchmarks are not the best way to evaluate a processor's true value, but to ignore these would be a mistake if you are an enthusiast. While lacking much real world experience value, we know that these tried and true methods will pull back the curtain on an architecture that is simply lacking when it comes to computing basics.

Again, these data points represent equal clocks on all processors compared: 4.5GHz locked processor clock; 1866MHz memory clock with 9-10-9-27-2T timing.

SiSoft Sandra 2013

Article Image

As we hopefully expected, our Core i7-4960X has come out on top here, but by very little. The almost two year old Core i7-3930K processor is nipping at the heels of our new Intel flagship. Sandra CPU Arithmetic benchmark is very multi-threaded and reaches into all the resources the processors have to offer and of course this is reflected in our slimmer 4C/8T Haswell and Ivy Bridge Instructions Per Second (IPS).

Article Image

Again we are glad to see the Ivy Bridge-E come out on top here, but it is by very little. Surely this points to an ever slightly more efficient memory controller. The Ivy Bridge-E and Sandy Bridge-E parts have a four channel memory controller, compared to the Haswell and Ivy Bridge's two channel memory controller. All in all though, the 48.85GBps score is one of the highest we have ever seen at the 1866MHz memory speed.

Hyper Pi

Article Image

While Hyper Pi is a program capable of testing multi-threaded processors abilities to calculate pi out to millions of places, we will be using it in a single-threaded configuration to look at per core IPC.

Keep in mind here that a lower score is better as it is how many seconds it took for the pi calculation to the millionth place. Our new Ivy Bridge-E does again beat out its Sandy Bridge-E predecessor, but as you might have guessed it does not outrun the new Haswell architecture. Our slimmer and trimmer Ivy Bridge desktop processor also is a hair bit faster than the Ivy Bridge-E.

wPrime

Article Image

While "prime" is in the name of this synthetic benchmark, this benchmark actually calculates square roots. It aims to also be a "perfectly threaded" benchmark, and we of course allow it to reach into all of our multi-threaded processors' resources.

Again this is a timed benchmark so a lower score is better. Our flagship Ivy Bridge-E again takes the crown, but only by a very slight margin. The rest of our processors score as expected with almost perfect scaling as is expected with this synthetic.