The Xeon E5-2600: Dual Sandy Bridge for Servers
by Johan De Gelas on March 6, 2012 9:27 AM EST- Posted in
- IT Computing
- Virtualization
- Xeon
- Opteron
- Cloud Computing
SQL Server 2008 Enterprise R2
We have been using the Flemish/Dutch Web 2.0 website Nieuws.be as a benchmark for some time. 99% of the loads on the database are selects and about 5% of them are stored procedures. You can find a more detailed description here.
We have improved our testing methodology (read more about it here) and updated the SQL Server, so the results are only comparable to our last Opteron 6276 review (and not comparable to older ones than the latter).
Since performance/watt is an extremely important metric, we follow up with a power measurement:
The Xeon E5-2690 is by far the fastest in this discipline, but the difference power consumption compared to the rest of the pack is significant. The Xeon E5-2690 needs 140W more than its slower brother, the 95W TDP Xeon E5-2660. That is 70W extra per CPU. This clearly indicates that the fastest Xeon is running closer to its TDP than the 2.2 GHz version. The Xeon E5-2660 offers more than 20% better performance per Watt than the 135W TDP Xeon.
The Xeon E5-2660 is especially impressive if you compare it with the older Xeon. Despite the lower clockspeed, the new Xeon is capable of outperforming the Xeon 5650 by 30%.
Clock for clock, core for core the Xeon E5 is 23% more efficient at SQL Server workloads than its older brother. Considering that it is pretty hard to extract higher IPC out of server workloads, we can say that the Sandy-Bridge architecture is a winner when it comes to SQL databases.
Finally, let's check out the response times with 600 users sending off a query every second (on average):
Response times are more or less linear (and low!) when the server is not yet saturated . Once the server is closer to or over its maximum throughput, response times tend to increase almost exponentially. Since the Xeon E5-2690 is capable of sustaining more than 600 users, it can still offer a very low response time. The other CPUs are saturated at this point.
But as we pointed out in our previous article, server benchmarks at 100% are just one datapoint and we should test at lower concurrencies as well. Most people try to make sure that their database server almost never runs at 100% CPU load.
Facebook
Twitter
RSS
81 Comments
View All Comments
BSMonitor - Tuesday, March 6, 2012 - link
My question as well.What is the Intel roadmap for Ivy Bridge in this arena. Would be the same timeframe as IVB-E I would guess.
Wondering if my Intel dividends will pile up enough for me to afford one! Haha
devdeepc - Friday, September 2, 2016 - link
Based on the paper specs, AMD's 6276, 6274 and Intel's 2640 and 2630 are in a neck-and-neck race.fredisdead - Saturday, April 7, 2012 - link
From the 'article' .....'The Opteron might also have a role in the low end, price sensitive HPC market, where it still performs very well. It won't have much of chance in the high end clustered one as Intel has the faster and more power efficient PCIe interface'
Well, if that's the case, why exactly would AMD be scoring so many design wins with Interlagos. Including this one ...
http://www.pcmag.com/article2/0,2817,2394515,00.as...
http://www.eweek.com/c/a/IT-Infrastructure/Cray-Ti...
U think those guys at Cray were going for low performance ? In fact, seems like AMD has being rather cleaning up in the HPC market since the arrival of Interlagos. And the markets have picked up on it, AMD stock is thru the roof since the start of the year. Or just see how many Intel processors occupy the the top 10 supercomputers on the planet. Nuff said ...
iwod - Tuesday, March 6, 2012 - link
And not find a single comment on how and why "making this CPU quite a challenge, even for Intel."In my view It seems Intel is now using Server Market and Atom / SoC for their 32nm capacity when ever they introduce a new node in consumer products.
extide - Tuesday, March 6, 2012 - link
A large part of Intel's long-term strategies include keeping the fabs occupied.Latest gen fabs (currently 22nm) produce bleeding edge cpu's, usually in the consumer space
One gen back (32nm) produces server/workstation/mobile cpus
two gens back (45nm) produces other things like chipsets, and possibly itanium chips
even three gens back (65nm) probably still exists in some places making some chipsets as well.
Their goal is to as much use as possible from their investment into building the fabs themselves.
Kevin G - Tuesday, March 6, 2012 - link
65 nm is still used for Itanium, though the Poulson chip is due sometime this year made on a 32 nm process. If you want to compare die sizes, the 65 nm Tukwila design is 699 mm^2 in size.The main reason why 32 nm Sandybridge-E has been released so close to the release of 22 nm Ivy Bridge chips is that the initial Ivy Bridge chips are consumer centric. Intel performs additional testing on its server centric designs. This is particularly true as Sandybridge-E is not just replacing the dual socket Westmere-EP chips but some of the quad socket Westmere-EX market. RAS demands jump from going from dual to quad socket and that is reflected in additional testing. Implementing PCI-E 3.0 and QPI 1.1 also contributed to the time for additional testing.
Though you are correct that Intel does uses its older process nodes for various chipsets and IO chips. However, as Intel is marching toward SoC designs, the actual utility of keeping these older process nodes in action is decreasing.
meloz - Tuesday, March 6, 2012 - link
>And not find a single comment on how and why "making this CPU quite a challenge, even for Intel."Because it is such a massive die? 416 mm²? Large dies usually have a lower yield, and Intel's 32 nm process is still cutting edge (if only for a few more weeks, heh).
Look at how TSMC, Global Flounderings et al are struggling. An impressive achievement by Intel.
MrSpadge - Tuesday, March 6, 2012 - link
A significant amount of functionality has been added to the SB cores, and Intel can't afford mistakes in such CPUs.BSMonitor - Tuesday, March 6, 2012 - link
More than that though, the SNB-E, Xeon E cores are not duplicates of the SNB desktop cores.Look at Anand's die shot of SNB-E, vs die shot of SNB. The CPU cores, L3 cache, controllers, are arranged completely different. Which makes sense as SNB-E doesn't have to deal with 40% of the die being GPU transistors. So, what we have now with Intel is two completely different dies between Xeon/SNB-E and Core. The individual CPU cores are the same, but the rest of the die is completely different.
SNB-E:
http://www.anandtech.com/show/5091/intel-core-i7-3...
SNB:
http://www.anandtech.com/show/4083/the-sandy-bridg...
cynic783 - Tuesday, March 6, 2012 - link
omg these benches are so biased it's not even funny. everyone knows amd offers clock-for-clock more punch than intel and lower power as well