I once had a friend that worked in the concert business. When one of the biggest names in music came to town (they were exiled on main street), they brought several semi trailers full of equipment. There was a packing list and everything had to go into the trailer in the exact order or the doors would not close. It was literally that tight, and yes, they did have to unload and reload a trailer.
Many people in the cloud and dense computing world have data center racks that are packed that tight. Every watt counts because at load, they are maximizing everything in their power budget per rack.
For customers like this we have a new feature in our upcoming processors codenamed “Interlagos” and “Valencia”: TDP Power Cap. [eWeek takes a look at TDP Power Cap and potential impact for cloud/mega datacenter customers here.]
In today’s products you can cap the power of a server by turning off processor states, though that ultimately can lead to somewhat lower performance. There are a lot of our customers who value power efficiency over performance, so it is not a real issue for them. But what if you could set low power limits AND get the performance that the platform offers?
With today’s AMD Power Cap Manager, you can limit the processor P-states and cut power consumption although this limits the processor’s ability to get to the top frequency (which is also the most power-hungry spot on the curve as you can imagine…). By essentially “locking out” the top P-state, the processor never gets into that state, even under heavy utilization, helping cut down total power to the processor.
With the new TDP Power Cap for AMD Opteron™ processors based on the upcoming “Bulldozer” core, customers will be able to set TDP power limits in 1 watt increments. This means that instead of having to choose between different TDPs for processors, you can actually buy any power range and then modulate down.
Why would someone want to limit TDP?
Well, let’s say that you have a maximum power draw on your fully configured server of 300W, and you have 42 slots in your server. The simple math says that you have 12.6Kw of power load that you need to be able to support. Now, if your power budget only allows you to bring 12Kw to the rack, you essentially have 2 slots that need to be left open in the rack because you can only support 40 and not 42 servers. But, by utilizing a custom TDP, you could drop the max power that some servers could draw, bringing you in under the limit of 12Kw and still getting 42 servers in the rack.
Best of all, if your workload does not exceed the new modulated power limit, you can still get top speed because you aren’t locking out the top P-state just to reach a power level.
This is truly essential for blades, clouds and other dense environments where every watt counts.
John Fruehe is the Director of Product Marketing for Server, Embedded and FireStream products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only. Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.