AOA Forums

AOA Forums (http://www.aoaforums.com/forum/)
-   General Hardware Discussion (http://www.aoaforums.com/forum/7-general-hardware-discussion/)
-   -   Intel 'energy-efficient' claim debunked (http://www.aoaforums.com/forum/general-hardware-discussion/44109-intel-energy-efficient-claim-debunked.html)

Daniel ~ 16th January, 2008 06:15 PM

Intel 'energy-efficient' claim debunked
 
Written by Daniel
Wednesday, 16 January 2008

AMD Opteron-based servers delivered better power efficiency than comparably configured Intel Xeon-based servers, computer performance consulting firm reports

By Chris Mellor, Techworld.com
January 16, 2008
InfoWorld

Recent tests by Neal Nelson & Associates, an independent computer performance consulting firm, have reported that in 36 of the 57 cases tested an AMD Opteron-based server delivered better power efficiency than a comparably configured Intel Xeon-based server.... Front Page

Gizmo 16th January, 2008 06:32 PM

The article doesn't indicate which Xeons were tested.

cloasters 16th January, 2008 06:51 PM

Good point, Gizmo. AMD needs all the good press it can scrape up, I'll go along with the claim of less power consumed by Opterons just for the fun of it.

ccperf721p 16th January, 2008 07:22 PM

The article doesn't indicate much of anything really. Where are the details?

Daniel ~ 16th January, 2008 09:00 PM

It's hard enough posting the news without everyone hounding you for facts!

I'll try to do better, but don't count on it.":O}

Aedan 17th January, 2008 10:33 AM

The report was performed in August 2007. AMD provided a loan machine for the testing, which was the limit of their participation. Intel refused a technical dialog with them.

Base machine specification:

Intel
Xeon 5160 running at 3GHz (4Mb L2 cache)
8GB FB-DIMM @667MHz
Intel 5000PAL motherboard

AMD
Opteron 2222 running at 3GHz (1Mb L2 cache)
8GB DDR II at 667MHz
Tyan S3992 motherboard



From Neal Nelson & Associates

Quote:

Other observations that can be made from the test results include:
1) Larger memory configurations deliver both higher throughput and better power efficiency,
2) Intel's power efficiency advantages decrease as memory size increases,
3) AMD's power efficiency advantages increase as memory size increases,
4) For primarily calculation type workloads, the Xeon delivers 8.0 to 14.0 percent higher peak throughput, and
5) For primarily disk I/O intensive workloads the Opteron delivers 11.3 to 19.4 percent higher peak throughput.

Daniel ~ 17th January, 2008 09:12 PM

Nice to see AMD bring one home! Thanks for filling out my post with a few facts.":O}

danrok 17th January, 2008 10:02 PM

If only we had plenty of clean and renewable energy, then we wouldn't have to worry so much about power consumption. There has to be a way!

Daniel ~ 17th January, 2008 10:09 PM

Perhaps you've seen the Matrix my little coppertop? ":O}

dsio 17th January, 2008 10:53 PM

Tell you something interesting, on single, and dual socket machines, I always order intel, because my kentsfield and dual clovertown servers have been brilliant, and I run a couple of dual clovertown Xen servers that I'm besotted with at the moment.

But, for certain applications, one in particular that is a rediculously large PGSQL server that has tables with litterally millions upon millions of rows that get crawled over constantly, we changed from a quad Tigerton Xeon (16 cores total) with 16GB of ram to a quad Opteron 8346 (barcelona, also 16 cores total) with 16GB of DDR2, and the performance is actually better, despite the Tigertons being 2.13Ghz as opposed to the 2Ghz of the Opterons.

Same ram size, different ram type, same disk speed, and array size.


All times are GMT +1. The time now is 08:59 PM.


Copyright ©2001 - 2010, AOA Forums


Search Engine Friendly URLs by vBSEO 3.3.0