• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

AnandTech's IBM POWER8 Review

S

Sweepr

Diamond Member
From a high level, the S822L is more expensive and consumes a lot more than a comparable Xeon system.

With limited optimization and with the current Ubuntu 15.04, the performance-per-watt ratio favors Intel even more as the POWER8 barely outperforms the very efficient 120W TDP Xeons. So there is no denying that the Intel systems offer a superior performance/watt ratio.

However, it would be unfair to base our judgement on our first attempt as we have to admit this our first real attempt to benchmark and test the POWER8 platform. It is very likely that we will manage to extract quite a bit more performance out of the system on our second attempt. IBM POWER8 also has a big advantage in memory bandwidth. But we did not manage to port OpenFOAM to the POWER platform, probably the most likely candidate for leveraging that advantage.

...We are less convinced that the POWER8 platform has a huge "raw CPU compute advantage," contrary to what for example IBM's SPECJBB (85% faster ) and SAP (29% faster) results seem to suggest.
Click to expand...

61428.png


67413c.png


78012.png


So let's sum things up. The IBM S822L is definitely not a good choice for those looking to lower their energy bills or operate in a location with limited cooling. The pricing of the CDIMMs causes it to be more expensive than a comparable Xeon E5 based server. However, you get something in return: the CDIMMs should offer higher reliability and are more similar to the memory subsystem of the E7 than the E5. Also, PCIe adapters are hot-pluggable on the S822L and can be replaced without bringing down the system. With most Xeon E5 systems, only disks, fans and PSU are hot-pluggable.

2x Xeon E5-2699v3 x 2x IBM POWER8 3.4 10c
Idle 110-120W x 360-380W

Running NAMD (FP)
540-560W x 700-740W

Running 7-zip (Integer)
300-350W x 780-800W
Click to expand...

www.anandtech.com/show/9567/the-power-8-review-challenging-the-intel-xeon-
 
I love the open software stack. I love the hot-plugging.

Overall performance looks pretty good too!

But once you factor in performance per watt, jesus, it is really hard to brawl with Intel.
 
I thought Power8 was faster clock for clock but higher price. So it's both slower and more expensive and more power than Xeon?
 
hardly matters. what matters is 1) IBM has way to facilitate integration of new systems in your production line. 2) support (disputable, but IBM has ways to convince you that their support is the best), and 3) marketing and more marketing.

i worked for them, and i can't think of a single australian industry name that wasn't our customer, from government agencies, to megacorporations, and private businesses.
(same for italy, pretty much)

they have a neverending list of customers using their propretary software, on IBM platforms, and they sell them the upgrades. a company would have to spend a boatload of money if they wanted to change say, to Sun, just to account for the system design and a possible huge downtime on the production line as well.
 
Your quotes don't tell the full story, I urge you guys to read the article before declaring Power dead. In fact Power is rapidly growing and I believe this is do to OpenPower and a competitive platform.

Johan De Gelas said:
Ultimately however, the performance-per-dollar Xeon E5 competitors will most likely be OpenPOWER third party servers. Those servers do not use CDIMMS, but regular RDIMMs. Other components such as disks, networkcards and PSUs will probably be cheaper but potentially also slightly less reliable.

All in all, the arrival of OpenPOWER servers is much more exciting than most of us anticipated. Although the IBM POWER8 servers can not beat the performance/watt ratio of the Xeon, we now have a server processor that is not only cheaper than Intel's best Xeons, but that can also keep up with them. Combine that with the fact that IBM has lined up POWER8+ for next year and a whole range of server vendors is building their own POWER8 based servers, and we have a lot to look forward to!
Click to expand...


Power8 is the first platform in awhile that is truly competitive on a price/performance basis. The only negative really is it's performance/watt and software. It's just too early to count Power out of the game especially when it's ecosystem is growing.
 
Last edited:
Essence_of_War said:
I love the open software stack. I love the hot-plugging.

Overall performance looks pretty good too!

But once you factor in performance per watt, jesus, it is really hard to brawl with Intel.
Click to expand...
There's the locked-in factor going for IBM at least.

Come to think of it, I don't see ARM making much headway into servers even though they are supposed performance/watt king.
 
Given that there are no PowerPC workstations or laptops, developing for this thing must be a bit of a pain.
 
ShintaiDK said:
You can start by reading the review on Anandtech about it instead of your comments.

http://www.anandtech.com/show/8357/exploring-the-low-end-and-micro-server-platforms

Xeon-D only put the foot down for good later on.

http://www.anandtech.com/show/9185/intel-xeon-d-review-performance-per-watt-server-soc-champion
Click to expand...

Keep in mind ARM was on 40nm process and the Intel chips 22nm.

http://www.anandtech.com/show/8357/exploring-the-low-end-and-micro-server-platforms/5
 
ChronoReverse said:
That's probably the point. Intel has a process advantage. But I wonder if that gap will narrow in the coming years.
Click to expand...

Apparently the software leaves some room for improvement as well:

http://www.anandtech.com/show/8357/exploring-the-low-end-and-micro-server-platforms/18

The 40nm X-Gene can compete with the 22nm Atom C2000 performance wise, and that is definitely an accomplishment on its own. But the 40nm process technology and the current "untuned" state of ARMv8 software does not allow it to compete in performance/watt. The biggest advantage of the first 64-bit ARM SoCs is the ability for an ARM processor to use eight DIMM slots and address more RAM. Better software support (compilers, etc.) and the 28nm X-Gene 2 SoC will be necessary for AppliedMicro to compete with the Intel Xeon performance/watt wise.
Click to expand...
 
You can start by reading the review on Anandtech about it instead of your comments
Click to expand...

Aside from comparing an underperforming design at 40nm you generalize to ARM vs Intel? That's ridiculous.
 
You must log in or register to reply here.
Back
Top