AMD More Power-Efficient Than Intel

R

Rich Tate

Supreme [H]ardness
Joined
Jun 9, 2005
Messages
5,955
A recent study has concluded that the Opteron is more power efficient than its Intel counterpart, The Xeon.

Specifically, the independent computer-testing firm announced today that it, in the tests, "the AMD based server used 7.3 to 15.2 percent less power at five different user load levels and 44.1 percent less power while the systems were idle and waiting for work."
Click to expand...
 
I doubt Intel really cares. Sure, power consumption and efficiency are becoming much more important, but Intel isn't in the red. ;)
 
Amd needs to get it in the game if they want to stay in business. So far Intel has handed their arse in a silver platter and from the looks of it even with the upcoming amd proc intel will release pricecuts and 45nm so they better stop worrying about efficiency and get back in the race.
 
No one cares. Why? Intel is faster and in the green; AMD is slow and in the red. Real simple math. ;)
 
InorganicMatter said:
No one cares. Why? Intel is faster and in the green; AMD is slow and in the red. Real simple math. ;)
Click to expand...

actually people DO care. when you're running hundreds of servers, power savings in dollar amounts adds up.

what really should be compared is performance per watt. not just power consumption. a 3ghz xeon is pretty much faster all around than a 3ghz opteron, both of which were tested. it can be easy to make up losses in power bills with faster data crunching.
 
Legenic said:
actually people DO care. when you're running hundreds of servers, power savings in dollar amounts adds up.

what really should be compared is performance per watt. not just power consumption. a 3ghz xeon is pretty much faster all around than a 3ghz opteron, both of which were tested. it can be easy to make up losses in power bills with faster data crunching.
Click to expand...

I agree,a comparision has to be made in every area before you can make a true evaluation.AMD is going to need a lot more than a single area test from one source to get back in the race.
 
look closely at the specifications: two differences besides the processor. Two different power supplies are used, and FBDIMM used on Xeons and DDR used on Opterons.

Let me guess, Neal Nelson and Associates loaded up 8 FBDIMMs they can get their hands on to compare power consumption. Well news to you, that 7% less power Opteron draws is just due to the FBDIMMS. It also means that Opteron is 20% slower. So performance per watt for woodcrest is higher.

The two different power supply might have different efficiency ratings. Delta 600W on the Xeon vs Delta 500W on opteron. Conveniently "Neal Nelson and Associates" measured the power draw at the wall, totally ignoring the difference of power efficiency(usually lower on higher power ratings).

After all the power saving is a mere 20 dollars. Given the typical lifespan of 3 years for those servers, 60 bux is nothing compared to the performance difference. Woodcrest owned Opterons. so I respectfully ask this question: how much did AMD pay nelson and associates?
 
Funny. does this mean AMD provided the mobos and processors?

Acknowledgements
We wish to gratefully acknowledge the assistance provided by MySQL, AMD Corporation,
Novell/Suse and Seagate Corporation for providing resources that were used in these tests.
Click to expand...

They should have used the same power supplies. I do like the fact that they ran all the drives on external power to get a good reading on the motherboards. It would also be interesting to see what they had the power savings settings for the motherboards set at.
 
Rich Tate said:
A recent study has concluded that the Opteron is more power efficient than its Intel counterpart, The Xeon.
Click to expand...

So what? It's also 14.6 to 30.4 % slower at the same power consumption levels.

I don't care how many watts my cpu is using to run at 50%...

I want to know how many watts it's using to get my render done in 1 minute, rather than 2 minutes.
 
It's not quite that simple if you have 400 identical servers. You factor in power consumption plus the cost of the PSU/Mobo/CPU/RAM config and divide that over the life of the servers as well as factor in performance per watt. Honestly most racks I'm seeing put together now are with Conroe Core 2s. They're cheap, use commodity parts and have low power consumption.
 
CyberDeus-RagDoll said:
So what? It's also 14.6 to 30.4 % slower at the same power consumption levels.

I don't care how many watts my cpu is using to run at 50%...

I want to know how many watts it's using to get my render done in 1 minute, rather than 2 minutes.
Click to expand...

Exactly. There's a huge difference between efficiency and absolute power consumption.
 
You must log in or register to reply here.
Back
Top