Intel Core i5-661 Clarkdale Processor Review – Westmere debuts

Testing power consumption has become just as important and relevant in recent years as judging performance of these processors.  And unfortunately, testing power consumption has also become a lot more complex than it used to be.  Where as we used to just simply test and idle and a load configuration from the wall, new advancements in multiple-core processors, changes in how power planes are controlled on these CPUs and software complications give us a bit more to think about in our power testing.

With the same discrete graphics setup, the Clarkdale CPU uses about the same power as Lynnfield at idle.  Removing the GTX 285 and using just the IGP on the Core i5-661 takes us much lower – to just 82w!

Under a full load, the Clarkdale part uses just a little less juice than the Core i5-750 processor.  Even though we have two fewer cores than the Core i5-750 obviously the addition of the IGP logic has kept power consumption at a similar level.  Without the NVIDIA GPU the entire system was operating around 120 watts, which is impressive.

Performance per Watt Measurements

Now I want to evaluate how the different processors tested here relate to each other in terms of performance per watt.  To do this I took the load power consumption of each processor and divided it into the benchmark result to create a new metric like Hz/watt (for Euler3D) or FPS/watt for the games. 

In terms of performance per watt in CB10, the Core i5-661 is not very efficient and is only beating out the Phenom X4 and the Core 2 E8500.  However, where the Clarkdale CPU does shine is after utilizing the IGP – performance stays nearly the same (in non-gaming tests only of course) but power consumption drops considerably.  This improves our performance / watt rating well above any other system. 

Of course, this isn’t completely fair.  We could always have put a GeForce 220 in the system with the Core i7-860 and dramatically lower its power consumption to get similar results.

The same is seen here, though it takes the removal of the GTX 285 to make it competitive.

Ouch – the results don’t really get any better here with Handbrake as the only system it is better than is the AMD Phenom X4 part when we use the discrete graphics.  Once we use the Intel HD Graphics though, it becomes the most efficient system tested. 

Here you can see that the IGP actually makes the Core i5-661 far and away the most efficient compute scenario.