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
A couple months ago, we took a look at the low voltage (LV) server CPU market. At the time, we focused on four-way solutions using two dual-core processors, since those represent the largest slice of the server pie. Our conclusion was that while the power savings brought about by using low voltage CPUs were real, processor choice was only one part of the equation. AMD came out ahead overall in performance/watt, not because they were faster or because their CPUs used less power, but rather because their platform as a whole offered competitive performance while using less power.
We discussed previously exactly what's involved in a low voltage part, but of course the picture is far bigger than just talking about power requirements. Take for example Intel's low-voltage Woodcrest parts; they are rated at 40W compared to the regular Woodcrest parts that are rated at 80W. The price premium for upgrading to a low-voltage part varies; in the case of AMD it's typically anywhere from $100 to $300 per CPU, while on the Intel side some low-voltage parts cost more, the same, or even less than the regular parts (i.e., the Xeon 5140 currently sells for about $450 while the low voltage Xeon 5148 only costs $400). Regardless of price, it's difficult to justify low-voltage processors in terms of power bill savings.
An extra 40W of power in a device running 24/7 for an entire year works out to around $35 per year, so at the low-end of the equation you would need a minimum of three years to recoup the investment (at which point it's probably time to upgrade the server). Other factors are usually the driving consideration.
Saving 40W per CPU socket may not save you money directly in terms of power bills, but generally speaking these chips are going into servers that sit in a datacenter. Air conditioning for the datacenter typically has costs directly related to the amount of power being consumed, so every 40W of power you can save could end up saving another 20W-40W of power in air conditioning requirements. That's still not even the primary concern for a lot of companies, though.
Datacenters often run dozens or even hundreds of servers within a single large room, and the real problem is making sure that there's enough power available to run all of the equipment. The cost of building a datacenter is anything but cheap, and if you can pack more processing power into the same amount of space, that is where low-voltage parts can really become useful. Blade servers were specifically created to address this requirement, and if you can reduce the total power use of the servers by 20% that means some companies could choose to run 20% more servers.
Of course, that doesn't mean that every company out there is interested in running a datacenter with hundreds of computers, so individually businesses need to look at what sort of server setup will best fit their needs. After determining that, then they need to look at low-voltage CPUs and decide whether or not they would actually be helpful. Assuming low-voltage parts are desired, the good news is that it's extremely easy to get them in most modern servers. Dell, HP, and other large server vendors usually include low-voltage parts as an easy upgrade for a small price premium. And that brings us to our low-voltage CPU update.
Intel Quad G-Stepping
Intel doesn't seem to sit still these days, pushing the power and performance envelope further and further. Recently, Intel announced two new G-stepping quad-core parts. The new parts run at the extreme ends of the power consumption spectrum. The first is a 2.0GHz 1333FSB part that runs at 50W while the second is a 3.0GHz 1333FSB part that runs at 120W. There are two main changes to the G-stepping parts, the first of which is power consumption: G-stepping introduces optimizations for idle state power. The second change involves enhancements to the Virtualization Extensions (VT), which mainly improve interrupt handling in the virtualization of Microsoft Windows 32-bit operating systems.
Of course, we would be remiss if we didn't mention AMD's recently launched Barcelona processor here. AMD expects their new quad-core processor to run within the same power envelope as the previous dual-core Opterons, which means twice as many CPU cores potentially without increasing power requirements, resulting in a potential doubling of performance/watt on the socket level. Low-voltage (HE) Barcelona parts will still be available, but even the regular chips include many new enhancements to help with power requirements. We are doing our best to get some additional Barcelona servers in-house in order to test this aspect of the performance/power equation and we hope to follow up in the near future.
One final item worth mentioning is that Intel's 45nm Harpertown refresh of Clovertown is due out in the very near future, which is one more item we can to look forward to testing. Unlike the desktop world, however, acquiring and testing server products often requires a lot more time and effort. Even with the appropriate hardware, the sort of benchmarks we run on servers can often take many hours just to complete a single test, and there are many parameters that can be tuned to improve performance. Since there aren't a lot of early adopters in the server market, though, we should be able to provide you with results before any of the IT departments out there are ready to upgrade. Now let's get on to the testing.
We discussed previously exactly what's involved in a low voltage part, but of course the picture is far bigger than just talking about power requirements. Take for example Intel's low-voltage Woodcrest parts; they are rated at 40W compared to the regular Woodcrest parts that are rated at 80W. The price premium for upgrading to a low-voltage part varies; in the case of AMD it's typically anywhere from $100 to $300 per CPU, while on the Intel side some low-voltage parts cost more, the same, or even less than the regular parts (i.e., the Xeon 5140 currently sells for about $450 while the low voltage Xeon 5148 only costs $400). Regardless of price, it's difficult to justify low-voltage processors in terms of power bill savings.
An extra 40W of power in a device running 24/7 for an entire year works out to around $35 per year, so at the low-end of the equation you would need a minimum of three years to recoup the investment (at which point it's probably time to upgrade the server). Other factors are usually the driving consideration.
Saving 40W per CPU socket may not save you money directly in terms of power bills, but generally speaking these chips are going into servers that sit in a datacenter. Air conditioning for the datacenter typically has costs directly related to the amount of power being consumed, so every 40W of power you can save could end up saving another 20W-40W of power in air conditioning requirements. That's still not even the primary concern for a lot of companies, though.
Datacenters often run dozens or even hundreds of servers within a single large room, and the real problem is making sure that there's enough power available to run all of the equipment. The cost of building a datacenter is anything but cheap, and if you can pack more processing power into the same amount of space, that is where low-voltage parts can really become useful. Blade servers were specifically created to address this requirement, and if you can reduce the total power use of the servers by 20% that means some companies could choose to run 20% more servers.
Of course, that doesn't mean that every company out there is interested in running a datacenter with hundreds of computers, so individually businesses need to look at what sort of server setup will best fit their needs. After determining that, then they need to look at low-voltage CPUs and decide whether or not they would actually be helpful. Assuming low-voltage parts are desired, the good news is that it's extremely easy to get them in most modern servers. Dell, HP, and other large server vendors usually include low-voltage parts as an easy upgrade for a small price premium. And that brings us to our low-voltage CPU update.
Intel Quad G-Stepping
Intel doesn't seem to sit still these days, pushing the power and performance envelope further and further. Recently, Intel announced two new G-stepping quad-core parts. The new parts run at the extreme ends of the power consumption spectrum. The first is a 2.0GHz 1333FSB part that runs at 50W while the second is a 3.0GHz 1333FSB part that runs at 120W. There are two main changes to the G-stepping parts, the first of which is power consumption: G-stepping introduces optimizations for idle state power. The second change involves enhancements to the Virtualization Extensions (VT), which mainly improve interrupt handling in the virtualization of Microsoft Windows 32-bit operating systems.
Of course, we would be remiss if we didn't mention AMD's recently launched Barcelona processor here. AMD expects their new quad-core processor to run within the same power envelope as the previous dual-core Opterons, which means twice as many CPU cores potentially without increasing power requirements, resulting in a potential doubling of performance/watt on the socket level. Low-voltage (HE) Barcelona parts will still be available, but even the regular chips include many new enhancements to help with power requirements. We are doing our best to get some additional Barcelona servers in-house in order to test this aspect of the performance/power equation and we hope to follow up in the near future.
One final item worth mentioning is that Intel's 45nm Harpertown refresh of Clovertown is due out in the very near future, which is one more item we can to look forward to testing. Unlike the desktop world, however, acquiring and testing server products often requires a lot more time and effort. Even with the appropriate hardware, the sort of benchmarks we run on servers can often take many hours just to complete a single test, and there are many parameters that can be tuned to improve performance. Since there aren't a lot of early adopters in the server market, though, we should be able to provide you with results before any of the IT departments out there are ready to upgrade. Now let's get on to the testing.
36 Comments
View All Comments
flyck - Friday, September 14, 2007 - link
why didn't you wait to revail this article when the tests were done on a barcelona system ?Now it is just comparing apples with oranges and thus making the conclusion obsolete.
Phynaz - Friday, September 14, 2007 - link
Since you can't buy a Barcelona based system at this point in time, this article is hardly "obsolete".JarredWalton - Friday, September 14, 2007 - link
You'll get Barcelona results for this sort of testing soon enough. The problem is, AnandTech isn't a single location; like many websites, we have people scattered around a large area. Johan and Christoph are even located in Europe, for example. So just because one of us has immediate access to certain hardware (i.e. the Barcelona launch CPUs) doesn't mean we all have access at the same time. Besides, the Barcelona launch articles literally had access to the CPUs for about four days before launch, and they were busy running other tests for the duration of that time.Justin Case - Saturday, September 15, 2007 - link
This article was published 3 days after Johan's Barcelona article.I suppose it's beyond Anandtech's technical ability to run the same benchmarks in the "european" and "american" systems, and compare the results? Maybe they wouldn't be valid due to the time zone or the metric system or something...?
Or maybe this article's "conclusions" had already been written, and doing a real quad vs. quad (instead of quad vs. dual) comparison would have spoiled things?
JarredWalton - Saturday, September 15, 2007 - link
As a matter of fact, yes, the article testing was indeed completed before Barcelona officially launched. The introduction and conclusion were edited to account for the fact that Barcelona is now officially launched (though not actually available for purchase anywhere). Will we test Barcelona performance/watt for a future article? Yes, and probably sooner rather than later. Does that make this article wrong? Nope. The conclusion is that a currently available quad-core Clovertown LV can beat a dual-core Opteron in some cases."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." (Emphasis added.)
I'm not exactly sure what the problem is with that conclusion. Quad-core is better in heavy load environments, and having the ability to choose between quad and dual-core CPUs certainly can't be bad for companies. I guess you would rather have nothing than an article that examines one more facet of the performance spectrum? FB-DIMMs still use a lot of power, but it's nice to see that as the number of CPU cores ramps up, the overall penalty isn't quite as severe. How will Barcelona and Harpertown change the picture? We will have an article on that subject soon enough.
Proteusza - Sunday, September 16, 2007 - link
Then you should have pulled the article. It makes no sense now. "Quad core comes to play"?Intels quad core has been out for how long now? Quad core comes to play, in my mind, implies that either Intels quad cores are new, or that we have quad cores from both tested in this article.
Neither is true.
JarredWalton - Sunday, September 16, 2007 - link
Intel LV Quad-core is in fact brand new, however, and it's actually available for purchase right now. That is what this article is about, and the introduction makes it pretty clear. If the title makes some people click through to check out the article, and they end up disappointed that Barcelona isn't present, they can get over it. I'm sure when we post the Barcelona equivalent that it will have some equally catchy title to get people to give it a look.Perhaps by that point in time Barcelona procs will actually be available at major vendors. You can find prices for the Opteron 2350 at a lot of places, but every site that I've checked out is "temporarily backordered" or "out of stock". At $400-$500, the Opteron 2350 will certainly be an interesting alternative. Companies that have Socket F/1207 servers will definitely be interested. Of course, before they switch they'll want to test for at least a few weeks (or months) in a non-production environment. BIOS flashing on a server is not something IT departments like to do on a regular basis, and my bet is we will see several BIOS updates before the transition is done.
Proteusza - Monday, September 17, 2007 - link
Its LV quad core may be brand new, but quad core itself isnt.Quad core itself is a year old, or more, and your title implies otherwise to me.
JarredWalton - Monday, September 17, 2007 - link
"Low Power" is in the title... I'm not sure we can really do much more beyond changing the title to "Low Power Quad-Core Xeon without Barcelona"... but just wait a bit longer and then you can see other results for other CPUs.Justin Case - Monday, September 17, 2007 - link
So you're saying that this article was published now due to the release of new low-voltage Xeon models, and has absolutely nothing to do with the Barcelona launch?'mkay...
Following that line of thought, the article's title should have been "Quad-core Xeons: Low power models come to play". The "new" thing (and thus what now "comes to play") is the low voltage, not the fact they are quad-core.
It would still be odd (to say the least) that you didn't run a single benchmark on a Barcelona system, but at least the article's title wouldn't be so blatantly deceptive.