AMD's 65nm Brisbane Core Previewed: The most energy efficient AMD CPU to date
by Anand Lal Shimpi on December 14, 2006 6:08 PM EST- Posted in
- CPUs
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 NVIDIA 9.35 |
| 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:
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...
Facebook
Twitter
RSS
63 Comments
View All Comments
Tilmitt - Thursday, December 14, 2006 - link
This "Performance per Watt" marketing bullshit has gone too far. Strange how Anandtech only started including it when Intel started marketing it insanely.To hell with performance per watt, give me performance.
Mantruch - Tuesday, December 19, 2006 - link
Indeed.. who give a sh*t about watt/performance, this is a desktop cpu not mobile...who sold this article to amd ? lol
Locutus465 - Saturday, December 16, 2006 - link
No... This was one of the major topics of discussion in the A64 v. P4 days as well, only AMD was enjoying Intel's current position. So Intel has a better chip right now, whats the big deal? This is why we like compitition.
Genx87 - Friday, December 15, 2006 - link
We didnt use to care about performance\watt in the consumer sector and left that to the professional arena. But ever since the power draw and heat of the consumer boxes started to rival professional level boxes it is good to see what you are getting.Gone are the days of a 250 watt PSU and a system that is passively cooled.
Frumious1 - Thursday, December 14, 2006 - link
Seems to me performance per watt is AMD's only leg to stand on right now (unless you just want to go with pure power draw). If you just look at performance AMD is even farther behind and that won't change until we see K8L, and maybe even that won't be enough. It's good to see lower temps and power requirements from AMD as it shows they're at least doing something other than sitting around bemoaning their fate. Intel already wins the marketing war, and now they're killing AMD on performance as well.Would have liked to see more CPUs for the comparison, though - like how about a 65nm 4600+ and 3800+ to see how they match up with the EE/EE SFF chips? Getting an E6300/6400 in as well would ahve been nice. Last, the use of an 8800 GTX is going to skew the "performance per watt" numbers, but it should still be consistent in this one set of benchmarks. As long as we don't get comparisons using other GPUs thrown in, it's probably the best you can do. Still would be nice to know how much power the CPU is really drawing on all these tests - probably less than 50W would be my bet.
yyrkoon - Thursday, December 14, 2006 - link
Intel won WHAT marketing war ? More like they won a battle, after losing many to their competitor, for around two years. Also, unless something has changed recently that I'm unaware of, AMD also leads in memory bandwidth, not that THAT much memory bandwidth translates into real world performance.I don't know which platform you like, and to be honest, I don't really care. However it would behoove us all, to realize that AMD, and Intel are both good companies, and if one were to go missing, we ALL would be in a much worse "market".
Frumious1 - Friday, December 15, 2006 - link
Right now, I prefer Intel. Oddly enough, though, I'm still running AMD Opteron 165 overclocked to 2.6 GHz, because it's fast enough. Better? Nope, but good enough. So I preferred AMD when they were ahead.My point about marketing is that Intel has always had the lead there - ALWAYS! How many AMD commercials do you see? A few, maybe. Intel floods the airwaves with adverts. Being better at marketing doesn't make your products superior, but if you own the mindshare of the common man it can make it damn hard for others to compete. Hell, with the junk that was Prescott (and the later NetBurst stuff), the fact that most corporations were still buying Intel says something, doesn't it? Yes, AMD made a lot of gains, but with Intel back in the lead those gains are eroding fast.
I for one hope K8L kicks some serious ass. HOPE. I remain unconvinced that AMD can close the gap and then some in the next 6 months. We shall see. Let's just hope it's not more of this Quad FX craziness. If I wanted two dual core AMD CPUs, I think I probably would have bought an Opteron 2xx setup a while back. Unbuffered RAM might improve performance a bit (5% or so?) but not enough to matter. As for octal core systems (dual quad core), don't make me laugh. That's great for the server market, and maybe even high end workstations, but on the desktop we're years away from being able to utilize/need that much CPU power.
Frumious1 - Friday, December 15, 2006 - link
Well, better a double post than to lose all that I typed. It looked like the post didn't go through, I luckily had it copied first, and after three refreshes I posted again. Naturally at that point both posts show up.yyrkoon - Saturday, December 16, 2006 - link
I don't know what current Intel CPUs memory bandwidth is, but at the time I checked my AM2 3800+ (single core) the closest thing was a core 2 duo at around 8-10GB/s bandwidth. After dropping the multiplier on my AM2 CPU, and increasing the "FSB" to 250MHZ, memory bandwidth on my 3800+ AM2 was over 11GB/s. I didn't test before hand, well maybe I did, but I don't recall what it was, so . . . I may have posted somewhere on the anandtech forums. Anyhow, I'm pretty sure its much more than 5% differences between the two, but like I said, it does not translate into real world performance, so it's pretty much moot.Frumious1 - Friday, December 15, 2006 - link
Right now, I prefer Intel. Oddly enough, though, I'm still running AMD Opteron 165 overclocked to 2.6 GHz, because it's fast enough. Better? Nope, but good enough. So I preferred AMD when they were ahead.My point about marketing is that Intel has always had the lead there - ALWAYS! How many AMD commercials do you see? A few, maybe. Intel floods the airwaves with adverts. Being better at marketing doesn't make your products superior, but if you own the mindshare of the common man it can make it damn hard for others to compete. Hell, with the junk that was Prescott (and the later NetBurst stuff), the fact that most corporations were still buying Intel says something, doesn't it? Yes, AMD made a lot of gains, but with Intel back in the lead those gains are eroding fast.
I for one hope K8L kicks some serious ass. HOPE. I remain unconvinced that AMD can close the gap and then some in the next 6 months. We shall see. Let's just hope it's not more of this Quad FX craziness. If I wanted two dual core AMD CPUs, I think I probably would have bought an Opteron 2xx setup a while back. Unbuffered RAM might improve performance a bit (5% or so?) but not enough to matter. As for octal core systems (dual quad core), don't make me laugh. That's great for the server market, and maybe even high end workstations, but on the desktop we're years away from being able to utilize/need that much CPU power.