Low Power Server CPU Redux: Quad-Core Comes to Play
by Jason Clark & Ross Whitehead on September 13, 2007 6:05 AM EST- Posted in
- IT Computing
Conclusion
If you pardon the pun, power continues to be a hot topic in the world of computer servers. The costs associated with operating and cooling an average server are certainly not cheap, and these costs continue to rise over time with higher performing and higher power parts being released. Low-voltage processors try to reverse that trend, although they are only truly effective at halting the CPU power requirements. Unfortunately, the CPU is just a piece of the puzzle. Memory, fans, chipset, drives, HBAs, etc. all play a role in power requirements, and in some of those areas (FB-DIMMs in particular) the increase easily overshadows the power savings associated with low-voltage processors.
In our previous article that compared Intel dual-core parts to AMD dual-core parts, AMD came out on top. The main reason for their victory is their power consumption figures. The Intel dual-core Xeons compete on a performance basis, but FB-DIMMs hurt overall performance/watt numbers. In this article we see the tables turn somewhat. With two extra cores the Intel Clovertown parts are able to easily outpace the AMD Opteron, at least when overall load is near saturation. At low to average workloads, there is little difference between any of the parts, in which case server consolidation might be a better solution. Obviously, the quad-core parts are best suited for loaded database servers and their sweet spot is in virtualized environments.
If there was ever any doubt that Intel made a bad decision not going true quad-core, it should be clear with numbers like these that their decision was sound and is paying off. Quad-core processors may not be faster in every situation, but in heavily threaded CPU intensive environments the extra CPU cores are easily able to make up for any penalties associated with the dual-die packaging.
This is not the end of the story, however. The next few months should prove interesting for the two processor giants, as AMD's Barcelona should begin to show up in volume and Intel is set to refresh their Xeon line-up with Harpertown. Stay tuned; we'll have thorough coverage for both products in the near future.
If you pardon the pun, power continues to be a hot topic in the world of computer servers. The costs associated with operating and cooling an average server are certainly not cheap, and these costs continue to rise over time with higher performing and higher power parts being released. Low-voltage processors try to reverse that trend, although they are only truly effective at halting the CPU power requirements. Unfortunately, the CPU is just a piece of the puzzle. Memory, fans, chipset, drives, HBAs, etc. all play a role in power requirements, and in some of those areas (FB-DIMMs in particular) the increase easily overshadows the power savings associated with low-voltage processors.
In our previous article that compared Intel dual-core parts to AMD dual-core parts, AMD came out on top. The main reason for their victory is their power consumption figures. The Intel dual-core Xeons compete on a performance basis, but FB-DIMMs hurt overall performance/watt numbers. In this article we see the tables turn somewhat. With two extra cores the Intel Clovertown parts are able to easily outpace the AMD Opteron, at least when overall load is near saturation. At low to average workloads, there is little difference between any of the parts, in which case server consolidation might be a better solution. Obviously, the quad-core parts are best suited for loaded database servers and their sweet spot is in virtualized environments.
If there was ever any doubt that Intel made a bad decision not going true quad-core, it should be clear with numbers like these that their decision was sound and is paying off. Quad-core processors may not be faster in every situation, but in heavily threaded CPU intensive environments the extra CPU cores are easily able to make up for any penalties associated with the dual-die packaging.
This is not the end of the story, however. The next few months should prove interesting for the two processor giants, as AMD's Barcelona should begin to show up in volume and Intel is set to refresh their Xeon line-up with Harpertown. Stay tuned; we'll have thorough coverage for both products in the near future.
Facebook
Twitter
RSS
36 Comments
View All Comments
coolme - Monday, September 17, 2007 - link
sorry, I meant MCM.Frags - Saturday, September 15, 2007 - link
AMD has had ample time to scale their processor to a winning choice. MCM was the smartest choice as Intel was bringing in money over the year as AMD showed no competition. Even though Barcelona is still coming (Don't act like it's here already.) AMD is still losing money.Even AMD said themselves they wish they had come out with an MCM design with Intel. Unfortunately since they are behind on processor technology it wouldn't have been feasible.
Even you have said "small, but significant advantage" in other words an advantage that is way too late because they took the long route to revenue. With such a large die size, I can see that yields will still remain low til Intel comes out with definitive competitive beast in very high yields and wide avaiablity. So from a business point of view, AMD is failing. If AMD cannot cut Intels technology lead by half a year, we will continue to see this trend til there is no more AMD.
Justin Case - Sunday, September 16, 2007 - link
Intel's manufacturing lead has been pretty much constant for a decade (if anything, the gap is slightly smaller now).AMD has a much bigger market share today than they did in the K7 (and K6, etc.) days. Add the fact that AMD now has some of the best GPUs in the market, a lot of very important patents, an excellent team of engineers and deals with most top OEMs (all things they didn't have back then), and it's pretty obvious that news of AMD's death are greatly exaggerated.
The problem with AMD is they're trying to grow too fast. To sustain their current growth rate, they're going to have to start turning in a profit very soon (as in under 5 months), which is not very likely.
If AMD manages to ramp Barcelona to, say, 2.6 GHz in volume until the end of the year (which is not impossible; the issue is related to a respin, not progressive improvement), then the risks they've been taking probably will pay off. Otherwise they'll be forced to slow down and compete based on price, at least until Bulldozer is ready. Their latest GPUs are looking pretty good, too, so they might be able to get by on profits from the ATI division even if Barcelona takes longer to ramp (as I suspect it will).
In any case, this idea that some people seem to have that AMD is "ruined" and "about to disappear" is complete nonsense. They're in a much better position today than they were in 2002, and they didn't disappear in 2002, either.
P.S. - A dual-die (2+2) CPU would have been perfectly feasible (just slap a second core on the same package, connected by HT, and treat is as a RAM-less CPU one hop away), and AMD would have easily been able to release it before Intel. It was an executive decision not to do so, and one that I'm sure they regret. The market for quad-core CPUs is small but pretty lucrative. They were probably hoping to have Barcelona out ahead of schedule, and instead it got delayed (hardly something new, chez AMD). On the other hand, I'm sure they're glad they did not go with FB-DIMM (despite having licensed the patents and planned to support it with Barcelona).
Brunnis - Friday, September 14, 2007 - link
That's not the point. The point is that Intel went with an MCM design and was therefore able to sell quads for almost a year before AMD could provide any competition. Intel made a good decision and just because AMD finally have something to compete with, doesn't make that decision go from good to bad in the blink of an eye. It almost seems as if you believe the tested Intel quad core is a new product. It's not, it's still the old Clovertown core, although it's based on the newer G stepping.
Proteusza - Friday, September 14, 2007 - link
I think thats exactly the point. yes Intel had the overrall performance lead for over a year with their Core 2 architecture.And even now, they hold the top spot until Barcelona scales to higher clocks.
but, in a performance per watt race, they no longer hold the top spot because they no longer have the only quad core cpu.
Saying that Intel made the right decision in rushing a quad core to market is true. But it only holds true while AMD doesnt have its own quad core. When AMD does, it doesnt really matter who came first - it matters who offers better performance per watt.
Therefore, now that AMD has quad core chips out, it doesnt matter what Intel did to get theirs out first, it matters which is the best chip.. The Radeon X1950 has been out for longer than the 8800 GTS, does taht mean it is a better graphics card?
Pull Up Banners - Wednesday, May 4, 2011 - link
I am sure Anandtech know very well about these banners and hopefull will avoid all the advertising banners.Thanks,
<a href="ttp://www.ultimatebanners.co.uk/pull-up-banners.htm">Pull Up Banners</a>