Intel's Core 2 Extreme & Core 2 Duo: The Empire Strikes Back
by Anand Lal Shimpi on July 14, 2006 12:00 AM EST- Posted in
- CPUs
Memory Latency: No Integrated Memory Controller Necessary
One thing we pointed out in our earlier preview coverage of Intel's Core 2 Extreme is that the new processors have extremely low latency memory access, despite relying on the same memory controller as the previous generation of Intel CPUs.
Without an on-die memory controller Intel's Core 2 processor must use the memory controller in its chipset, which currently means the 128-bit DDR2 memory controller in either Intel's 965 or 975X chipset. The confusing thing is that although the Core 2 processors use the same memory controller as the old NetBurst processors, memory latency has been improved tremendously:
Intel's Core 2 processors now offer even quicker memory access than AMD's Athlon 64 X2, without resorting to an on-die memory controller. While Intel will eventually add one, the fact of the matter is that it's simply not necessary for competitive memory performance today thanks to Intel's revamped architecture. Update:As many astute readers have pointed out, Core 2's prefetchers are able to work their magic with ScienceMark 2.0, which results in the significant memory latency advantage over AMD's Athlon 64 FX-62. This advantage will not always exist; where it doesn't, AMD will continue to have lower latency memory access and where it does, Intel can gain performance advantages similar to what ScienceMark 2.0 shows.
CPU | Everest |
CPU-Z 1.35 (8192KB, 128-byte stride) | CPU-Z 1.35 (8192KB, 64-byte stride) |
AMD Athlon 64 FX-62 (2.8GHz) | 45.9 ns | 43.2 ns | 19.3 ns |
Intel Core 2 Extreme X6800 (2.93GHz) | 59.8 ns | 52.8 ns | 10.9 ns |
Because of the Core 2's intelligent prefetchers doing too good of a job with ScienceMark memory latency test, we wanted to also showcase situations where Core 2 would feature slower memory accesses than the AMD platform with its integrated memory controller. Everest's results are more in line with what we'd expect to see, with the FX-62 offering over 23% faster memory accesses than the X6800. CPU-Z's latency tool also reported somewhat similar findings, with an 18% performance advantage due to AMD's integrated memory controller. CPU-Z also provided us with numbers that showcase how well Core 2 can perform if its prefetchers are able to "guess" correctly; at lower strides the Core 2 Extreme manages faster memory access than the FX-62. The 128-byte stride numbers are indicative of what will happen if the pre-fetchers are not able to get the Core 2 the data it needs, when it needs it, while the 64-byte numbers show you what can happen when things go well.
202 Comments
View All Comments
MrKaz - Friday, July 14, 2006 - link
So how do you calculate performance/watt?Based on Doom3? Quake4? Lame? PowerDVD? Divx encoding?
My point is, this is "impossible" to do, unless you do it for all progs and games.
Picking up just one of them is being biased...
JarredWalton - Friday, July 14, 2006 - link
Including performance/watt on *ANY* game is a bit odd, given that the GPU will comsume more power than the CPU. That's why when we talk about performance per watt on GPUs, we use the same platform for all tested systems.If we're going to talk about performance per watt and we're worried about the CPU and platform, then we should look at benchmarks that stress that portion of the system more than anything else. In fact, you could argue that we should drop down to the lowest power GPU possible, or even go with an integrated graphics solution. Anyway, here are a few of the results using WME9:
0.358 FPS/W X6800
0.319 FPS/W E6600
0.279 FPS/W 4600+ EE
0.276 FPS/W 3800+ EE
0.273 FPS/W 5000+
0.244 FPS/W FX-62
0.244 FPS/W E6300
0.228 FPS/W PD XE 965
Part of the reasons on the lower performance Core 2 Duo chips score so poorly is because we are measuring Watts of the entire system. It's reasonable to say that the motherboard, hard drives, graphics card, etc. probably use up on average 100 W of power, give or take. The AMD motherboard and peripherals might also use a bit less power than than the Intel board, or vice versa, so the 12 W difference in power draw at idle shouldn't be considered really significant.
What is significant is that other than the two energy efficient AMD chips (which you can't yet purchase on the retail market), Core 2 offers better performance per watt at similar price points. We could go and measure performance per watt on a bunch of the other applications (even games, though the differences are going to be greatly diminished given the GPUs requirements), but the results really aren't likely to change much. Core 2 is faster than AMD, and at worst it matches AMD's power requirements; ergo Core 2 offers better performance for watt.
epsilonparadox - Friday, July 14, 2006 - link
Intel didn't start the focus on performance by watt. AMD started it and ruled the charts based on that measure. Every single X2 vs P4D review has a chart for that measurement. Intel w/ the C2D just turned the table back on them by harping on the same issue. If this measurement didn't become a big deal, you'd likely be running dual 1000W psus to run dual core/multi gpu setups.Furen - Friday, July 14, 2006 - link
It's hard to do a performance/watt chart because processors perform differently under different applications. I'm sure you'll agree with the fact that the E6600 is much faster than an X2 3800+ yet draws only slightly more power.bupkus - Friday, July 14, 2006 - link
: (Where's the pics?
My browser doesn't show them on the first page.
Gary Key - Friday, July 14, 2006 - link
What browser?bupkus - Friday, July 14, 2006 - link
FirefoxGary Key - Friday, July 14, 2006 - link
I have tried three different versions of FireFox on varying machines without an issue so far. Still looking in to it.JarredWalton - Friday, July 14, 2006 - link
Options ->Web features ->
Load Images ->
UNCHECK "for the originating web site only"
ianwhthse - Friday, July 14, 2006 - link
Mine is already unchecked, however I cannot see the pictures either. [Firefox]Kicking and screaming, which is somewhat disruptive @4am, I opened Internet Explorer and I cannot see the images there, either.