Intel Core 2 on 45nm: Performance, Overclocking, Power Usage

CPU by piotke @ 2007-10-29

Intel is launching their successor the popular Conroe CPU, build on 45nm manufacturing process, it boasts reduced power consumption and has 50% more L2 cache. The first product out the door is a quad core beast dubbed QX9650. We take this new creation through its paces, comparing performance, power consumption and venturing into overclocking land, where sub zero cooling is the norm.

  • prev
  • next

Power usage and performance scaling

Performance scaling

We ran through the SuperPi 1M and Wprime 32 benchmark at different CPU speeds to get an idea what to expect if CPU speeds were to scale beyond speeds we were able to reach today.

Do note that these performance scaling charts give but a rough idea of how things will “play out”

Madshrimps (c)


SuperPi 1M at 5750Mhz can expect scores little under 8 seconds, it’ll take more than 6Ghz to go below 7 seconds though, and that’s still to be seen… as the prediction is being a bit optimistic on the results.

Madshrimps (c)


The Wprime 32 benchmark shows similar gain in performance as the frequency increases, although the difference is slightly lower compared to SuperPi, as the multi core performance doesn’t scale perfectly.

A look at the voltage vs frequency as we increased the vcore steadily by 0.05v we tested for maximum overclock:

Madshrimps (c)


At each 0.05v step we see a speed increase between 100~200Mhz, not too bad at all, since the default vcore is quite conservative, the potential for a faster edition of the QX9650 would only require a slightly higher default vcore.

Power usage

While we’ve been focusing on the performance benefits of the 45nm and extra L2 cache, there are those who like to keep an eye on the power consumption of their machine. While a single desktop will hardly make a difference in the large picture, a million dollar server park with hundreds of machines using a few percentage less per machine will show a difference at the end of the month.

So here’s what you can expect for full system usage with an ATI HD 2900 XT video card installed, please note that both CPU and VGA are loaded in this test:

Madshrimps (c)


At idle setting the difference between the Quad Core QX9650 and Dual Core E6850 is practically none existent. But even under load the difference is minimal, as expected with all cores enabled the QX9650 shows the highest numbers, but let’s be honest, 291Watt full system load with a Quad Core powered system and power hungry ATI VGA card is hardly “a lot”. The E6850 uses only ~20 watt less when under full load.

Comparing the single core vs multi core result shows us that the extra cores don’t take up that more power, between QX9650 SC vs MC there is only ~21W. Do note that the cores were disabled in Windows only; not through hardware or the BIOS.

So the new 45nm Yorkfield proves to be quite power friendly at intended voltage and frequency, let’s see what happens when we start to overclock, adding extra voltage along the way. We only stressed the CPU this time around; at default setting this gave a maximum system usage of 210 Watt.

Madshrimps (c)


It’s hard not the notice the discrepancy in this chart, at 3850Mhz using 1.65v the system is using close to 300 Watt, this was the highest air cooled stable speed we could reach with all 4 cores enabled. The next result is with the subzero cooling from Asetek. At 4050Mhz and 1.7v vcore the CPU is running much cooler, and somehow power usage goes down, dropping 35 Watt to 265. From that point forward it increases again, topping out at 386W at 4900Mhz with 2v vcore. Does anybody know what’s going here regarding the 3.8Ghz vs 4.05Ghz result?

Update: We received this answer from Intel, explaining the higher power usage at higher temperatures

Matty @ Intel:

Yes, the power consumption is reduced when the temperature of the processor is lowered.

There are many things that happen in a CPU when the temperature is changed and to elaborate further on the processor specific causes we have to look at the origin of the power consumption. We can divide the total consumed power into two main parts, static power (Ps) and dynamic power (Pd).

The static power consumption is what we usually call the leakage. In an ideal transistor, it should completely shut off the channel between the source-drain, gate-source and gate-drain. Transistors are far from ideal, and the current leaks between these parts and the substrate of the processor, and this is heavily dependent on the temperature.
For example, going from room temperature to 85C (~60C difference) increases the leakage power by a factor of more than 50. Thus, reducing the temperature with the same amount will make a huge impact on Ps.

Dynamic power consumption is emitted during the short amount of time that the transistor switches. Lower temperature reduces the resistance in the processor which results in shorter delay/faster switching of the transistors. Shorter delays and less noisy signals also reduce Pd.

I hope this explanation give you some clarity to the relation between power consumption and temperature. This can even be seen with air cooling: The power consumption is lower just after a load is applied compared to after a while when the temperature has levelled out, even though the load is the same.
  • prev
  • next
Comment from Sidney @ 2007/10/29
Reading other reviews, it would seem the engineering sample tested at [M] requires more vcore than others. 4Ghz quad would now be common speed; no bragging right unless you see 5Ghz.
Comment from jmke @ 2007/10/29
yes that seems to be the case, but no faulting engineering samples, they are supposed to run without fault at rated speeds with default vcore, which this QX9650 did
Comment from Kougar @ 2007/10/29
2.0v for 4.9GHz? Would have loved to see what that did to the power consumption figures for that CPU!

Regarding the discrepancy with your power chart, I think that has something to do with the physical properties of the chip design. I suspect that at very high frequencies there is a thermal threshold that once neared the leakage increases dramatically. After which it will quickly reach the point where the chip ceases to function or function stably since the increased leakage raises the heat, and the heat only further increases the transistor leakage in a self-fulfilling cycle. I don't have any real proof other than my own experiences with my Q6600...

I am curious, I notice from that CPUZ image the ES QX9650 uses 1.20v at 3GHz. My own Q6600 does the same... so how far can you drop the voltage and have the QX9650 remain stable at 3Ghz? I got a Q6600 down to 1.5v, but somewhere below that point my Q6600 will show errors. Gigabyte unfortunately lacks most of the FSB voltage tuning ASUS boards offer, as some members on the XS forums claim to have reached 1.10v for 2.5-2.8Ghz speeds for Kentsfields. Would be interesting to note what effect the smaller process size and change in transistor materials would have on this for Penryn.
Comment from jmke @ 2007/10/29
Quote:
Originally Posted by Kougar View Post
2.0v for 4.9GHz? Would have loved to see what that did to the power consumption figures for that CPU!
You can last chart on this page: http://www.madshrimps.be/?action=get...&articID=6 36
386W vs 210W stock
Comment from Kougar @ 2007/10/30
Ah, nice! I had completely missed that, staring me in the face. I guess I need to take more power measurements since the data I have on my Q6600 includes my video card...

Why not extend that same chart a bit more to the right though, and undervolt that puppy?
Comment from CFKane @ 2007/10/30
I'm a little surprised that you're talking about a discrepancy in the chart while you're mentioning the changed cooling solution in the same sentence. The die temperature is one of the most important factors for the CPU power consumption and if you switch to a solution which removes the heat more efficiently, you should expect reduced power draw even with a higher clock and voltage.

That's also the reason why the maximum current in the electrical specifications for CPUs significantly exceeds what you would get from dividing the TDP by the core voltage. It's given for the maximum die temperature, which you will (hopefully) never reach in a real world situation.

Bear that in mind when testing or comparing CPU power consumption: The room/case temperature and cooling solution have a major influence and the die temperature at a certain load is an interesting figure to report along the power draw (sadly missing in most reviews).
Comment from jmke @ 2007/10/30
Thank you CFKane for you post and welcome to the forums
since the temperature was the only large difference between the two settings we were not doubting that it was indeed the lower temperature which was causing the lower temps; but I've not seen any article on the web discussing this aspect of the power consumption... hence were a bit hesitant to include that statement.
Comment from jmke @ 2007/12/07
we also got word back from Intel explaining the power usage at different temperatures:

Quote:
Matty @ Intel:

Yes, the power consumption is reduced when the temperature of the processor is lowered.

There are many things that happen in a CPU when the temperature is changed and to elaborate further on the processor specific causes we have to look at the origin of the power consumption. We can divide the total consumed power into two main parts, static power (Ps) and dynamic power (Pd).

The static power consumption is what we usually call the leakage. In an ideal transistor, it should completely shut off the channel between the source-drain, gate-source and gate-drain. Transistors are far from ideal, and the current leaks between these parts and the substrate of the processor, and this is heavily dependent on the temperature.
For example, going from room temperature to 85C (~60C difference) increases the leakage power by a factor of more than 50. Thus, reducing the temperature with the same amount will make a huge impact on Ps.

Dynamic power consumption is emitted during the short amount of time that the transistor switches. Lower temperature reduces the resistance in the processor which results in shorter delay/faster switching of the transistors. Shorter delays and less noisy signals also reduce Pd.

I hope this explanation give you some clarity to the relation between power consumption and temperature. This can even be seen with air cooling: The power consumption is lower just after a load is applied compared to after a while when the temperature has levelled out, even though the load is the same.

 

reply