The Test

Performance-wise, the new Brisbane chips shouldn't be any different than their 90nm counterparts, but to make sure we benchmarked the new chip against our first 90nm X2 5000+. From a power consumption standpoint, we wanted to compare the new 65W 65nm chip to AMD's Energy Efficient and Energy Efficient Small Form Factor 90nm chips to see how the new process competes with the most efficient of AMD's CPUs that use the older, but more mature process. Unfortunately, we only have a 5000+ 65nm chip, so we can't say for certain what advantages Brisbane will hold at equivalent clocks to the EE/SFF parts.

For each benchmark we measured performance as well as average power consumption during the course of the benchmark, finally reporting performance per watt as one divided by the other.

CPU: Intel Core 2 Duo E6600 (2.40GHz/4MB)
AMD Athlon 64 X2 5000+ (2.6GHz/512KBx2)
AMD Athlon 64 X2 5000+ "Brisbane"
AMD Athlon 64 X2 EE 4600+ (2.4GHz/512KBx2)
AMD Athlon 64 X2 EE SFF 3800+ (2.0GHz/512KBx2)
Motherboard: eVGA NVIDIA nForce 680i
ASUS M2N32-SLI Deluxe
Chipset: nForce 680i
nForce 590 SLI
Chipset Drivers: NVIDIA 9.53
Hard Disk: Seagate 7200.9 300GB SATA
Memory: Corsair XMS2 DDR2-800 4-4-4-12 (1GB x 2)
Video Card: NVIDIA GeForce 8800 GTX
Video Drivers: NVIDIA ForceWare 97.44
Resolution: 1600 x 1200
OS: Windows XP Professional SP2

Before we get to the power consumption tests let's have a quick look at idle power consumption of these systems:

Power Consumption

Note that Cool 'n Quiet and EIST were enabled for all tests, but running at 1GHz the AMD CPUs at idle are able to draw much less power than the Intel system (which runs at an idle clock speed of 1.6GHz). Part of the increased power consumption for the E6600 may also be due to the 680i chipset vs. the 590 SLI used on the AMD systems, but we would need to compare both chipsets on a common CPU platform to be sure of that.

Regardless of the reasons, at idle, our Intel test platform consumes much more power than any of the AMD platforms. At the same time, the new 65nm Brisbane CPU doesn't really draw significantly less power than the 90nm cores at idle. Under load though, we've got a completely different story...

Index Media Encoding Performance & Power Consumption


View All Comments

  • mino - Friday, December 15, 2006 - link

    Read some paper on entropy.

    The problem in this discussion is most participants do not know what heat, electricity, work(i.e. in joule), work(i.e. inlogical one) means.

    Except for electromagnetic waves that leak badly shielded PC and the energy required to transfer the information out of the PC (by monitor and network cables) the energy(in form of electricity) consumed by the CP is completely changed to heat.

    In other words "focused" form of energy witch low entropy(electricity) is distributed to the environment and becomes an "unfocused" form of enegry, mostly heat. Also even the heat dispersed to the room is still partly focused in sense it still not spread to the whole universe.

    Hope this clears it for some.
  • mino - Friday, December 15, 2006 - link

    CP == PC Reply
  • smitty3268 - Thursday, December 14, 2006 - link

    I don't particularly know how transistors work (only the basics) but if a space heater isn't 100% efficient then why would a cpu be?

    Again, I could be wrong, but do you have any 3rd party info to support your claim?
  • Missing Ghost - Thursday, December 14, 2006 - link

    I think space heaters are 100% efficient, except maybe if there is a fan, then it could be 99.999%. Reply
  • smitty3268 - Thursday, December 14, 2006 - link

    If you can see something glowing, then at least part of the energy is producing visible light and not heat. Although now that you mention it, I think I heard that plain old light bulbs are fairly efficient heaters. Reply
  • smitty3268 - Thursday, December 14, 2006 - link


    The entire semiconductor industry is struggling with the heat of chips increasing exponentially as the number of transistors increase exponentially. Moving to new high-k materials that control leakage is one step of many towards making transistors run cooler. Because high-k gate dielectrics can be several times thicker, they reduce gate leakage by over 100 times, and therefore devices run cooler.

    This implies what I was saying, but perhaps the devices only run cooler because they require less power to begin with?
  • JarredWalton - Thursday, December 14, 2006 - link

    Heat density: less power in a smaller area can potentially run hotter (witness Prescott vs. Northwood P4). Except we're seeing the reverse here, so probably it's just a difference in chip/package design. There's no guarantee that the various chips are measured identically, meaning AMD could have changed temperature reporting with 65nm, and certainly the AMD vs. Intel numbers are not a direct comparison. I would put more weight on power numbers, personally. Reply
  • eRacer - Wednesday, December 20, 2006 - link

    In future Brisbane reviews could you check the Brisbane idle temperature to see if it appears to be somewhat accurate? Other previews and leaks show Brisbane idle temperatures in the 10C-15C range which is well below room temperature. Idle and load temps of Brisbane may actually be 15C higher than what is reported. Reply
  • Stereodude - Thursday, December 14, 2006 - link

    I was excluding the C2D from my comments. Sorry if that wasn't clear.

    If anything the die shrink should make the Brisbane run slightly hotter since the die is a little smaller. I can't come up with any good reason why one 65W processor runs cooler than another 65W processor given the same cooler and same size heat spreader. Maybe the heatspreaders aren't flat between all the AMD CPUs. The 35W AM2 processor definitely should have run cooler.
  • eRacer - Thursday, December 14, 2006 - link

    "As you can expect, AMD is pricing the 65nm chips in line with its 90nm offerings to encourage the transition. Die size and TDP have both gone down to 147 mm^2 and 65W across the line.

    Is 147 mm^2 accurate? That happens to be the same die size of 90-nm A64 X2 Manchester, and isn't much of a shrink from the current 183mm^2 512KBx2 Windsor cores. Some rumors had put it at ~125 mm^2.

Log in

Don't have an account? Sign up now