backtop


Print 30 comment(s) - last by aalaardb.. on Dec 12 at 4:38 PM

SPEC has introduced a new power-efficiency measurement standard for CPU architectures. The winner? The consumer

SPEC, the Standard Performance Evaluation Corporation, is a non-profit corporation whose goal is to provide "fair, impartial and meaningful benchmarks for computers."

With the latest excitement and fuss over AMD's K10 power usage figures, SPEC conveniently announced a new set of benchmarks to compare power efficiency of CPUs based on an independent and unbiased standard.  The standard holds the promise of a level playing field for CPU manufacturers to test the quality of their products on. 

SPEC's new solution is dubbed the SPECpower_ssj2008.  The test, which is to be run on a server, takes the chip through a series of graduated descending workloads, starting at 100% usage and dropping by 10% per set period of time until idle is reached.  The total processor throughputs for each segment are first summed and then divided by the sum of the average power consumed for each segment.  The final product is a performance measure called "ssj_opps/Watt."

The test is promising, as it takes into account that workloads on a server vary greatly, and calculates efficiency based on a sensible averaging approach.  With AMD championing their new ACP standard, and Intel still advertising its modified TDP standard, finding understandable and accurate comparative power-performance figures has become a rather confusing business for the average customer.

A unified power-performance standard could certainly change that.  It provides Intel and AMD with a chance to truly put their processors' power prowess to the test in an unbiased benchmark -- if they are willing.

This test is geared towards measuring power-efficiency across a wide pattern of usage, and probably would not be very applicable to providing information on the specific cooling solutions needed for a particular processor.  For cooling evaluation, traditional TDP measurements would be of greatest use, as they test the processor power under a steady 100% real load scenario.

In terms of power-efficiency, though, SPEC's new system hopes to bring honesty, integrity, a renewed sense of competition to the processor market.  At a lowly cost of $1,600 for the software, Intel and AMD should be eager to put this independent benchmarking suite to work.


Comments     Threshold


This article is over a month old, voting and posting comments is disabled

Confused
By Cobra Commander on 12/11/2007 3:34:58 PM , Rating: 2
I presume I'm promoting my ignorance here, but how exactly does software determine the power usage of hardware?




RE: Confused
By Moishe on 12/11/2007 3:38:53 PM , Rating: 2
I would think that you cannot measure the heat output since that can be changed by a cold room or a good heatsink. You would have to measure actual power draw, and not for the whole system, but for just the chip.

I have no idea how they would do that with software.


RE: Confused
By TomZ on 12/11/2007 4:09:04 PM , Rating: 2
It requires external instrumentation. The setup is described in the following document:

http://www.spec.org/power_ssj2008/docs/SPECpower_s...

Especially see the diagram at the top of page 5.


RE: Confused
By caqde on 12/11/2007 4:44:02 PM , Rating: 2
damn I was close lol.. I think I see USB used in there.. Although it is hard to read but apparantly it communicates via TCP/IP (RJ-45?) well whatever it is still via a piece of hardware that is controlled by the software..


RE: Confused
By jordanclock on 12/11/2007 6:08:57 PM , Rating: 2
TCP/IP is a protocol and doesn't have to be used with RJ-45. And RJ-45 doesn't always have to be used with TCP/IP or Ethernet. The diagram you are referring to also shows RS-232 as an interface. The spec for that recommends a D-SUB25.

Also, TCP/IP can be done over USB as well. They aren't mutually exclusive in any way.


RE: Confused
By Calin on 12/12/2007 2:37:04 AM , Rating: 2
My audio card (Audigy 2 with Firewire) allows the creation of a TCP/IP network (two points only) over Firewire. It was suggested for ultra fast networking when gaming.


RE: Confused
By caqde on 12/12/2007 11:56:16 AM , Rating: 2
Yea and the diagram also doesn't show the TCP/IP communications going through any know wire type. It just says TCP/IP which could mean anything. But it will most likely be through RJ-45 as this is a server environment they are working on.


RE: Confused
By caqde on 12/11/2007 4:38:05 PM , Rating: 2
There might be hardware connected to the software. Sounds possible. If I connect the software to a USB enabled power meter that is hooked up to the computer then I could using the software find out how much power the computer is drawing during a period of time.


RE: Confused
By LumbergTech on 12/11/2007 3:51:37 PM , Rating: 2
well....modern cpus have the ability to adjust their voltage based on what they need..so it seems that based on that it could measure it..although i could be completely full of crap..and down rate me if i am


RE: Confused
By TomZ on 12/11/2007 4:12:34 PM , Rating: 2
To self-measure the power, the motherboard would have to be able to monitor both the voltage and the current (power = voltage x current). Most motherboards can monitor the voltage, but I've never seen any that can monitor the current.

Therefore, some external power measurement instrumentation would be required. See my other post above.


"If they're going to pirate somebody, we want it to be us rather than somebody else." -- Microsoft Business Group President Jeff Raikes

Related Articles
AMD Clarifies ACP, TDP Enigma
December 10, 2007, 6:45 PM
Intel Prices "Penryn" Xeons
July 17, 2007, 4:06 PM













botimage
Copyright 2014 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki