AMD Streches Power Consumption Truths

Rob Williams

Staff member
From our front-page news:
It's a good thing that their ATI division is starting to shape back up, because AMD themselves are having one heck of a difficult year. Most of the problems have been directly linked to their Barcelona processors, with no solutions (in the form of a revision) until early next year. We linked to a Tech Report article last week which investigated the problematic errata issue plaguing most Barcelona-based processors, and now, DailyTech have arisen another potential problem - AMDs ACP ratings.

Unlike TDP, which assumes the total wattage for a processor at full load, ACP offers what AMD feels to be an average wattage during normal use. So, if a CPU is rated for 70W ACP, it means that during normal use, that's the average wattage you should expect. However, as common sense would imply, listing an "average" doesn't make much sense. It's simply too difficult to declare an average, as usage varies from user to user. Thanks to this fact, many are claiming that AMD "lies", or stretch truths.

The article at DailyTech points out more specifics, including a fact that ACP ratings were not changed in whitepapers as they should have been - although that could have been an accidentally overlook on AMDs part. But when it comes to AMD, it seems everyone has their own opinions. Right now though, it's hard to ignore the facts. AMD needs to change how they do business, while cutting out the stretching truths part.

<table align="center"><tbody><tr><td>

The first thing to notice is that TDP measurements are significantly higher than ACP. When AMD compared its power consumption figures to Intel's TDP, ACP measurements significantly underestimate power consumption. TDP differed between the two versions of the white paper by as much as 20 W, which is a 21% increase in the case of the quad-core Opteron. AMD did not increased its ACP estimates, emphasized in bold, despite the TDP increase.

Source: DailyTech