AMD: Intel's Conroe power advantage claim based on skewed metric
Austin (TX) - With Intel's release of desktop processors based on its new Core Microarchitecture now expected at the end of this month, early tests from Tom's Hardware Guide are lending credence to Intel's claim that it has regained the advantage in the race for best CPU performance per watt of energy. In advance of Intel's release announcement, AMD has mounted what press managers for a political campaign would call a "pre-spin cycle:" an early response to the claims Intel is likely to make. One of AMD's key bullet points is that the numbers Intel boasts for power consumption, and those AMD boasts, aren't determined on a level playing field.
"One thing you need to be aware of," Mike Field, AMD's Athlon FX product manager, told TG Daily, "is the difference in how we measure power versus how Intel measures power." As Tom's Hardware Guide's detailed Core 2 Extreme test showed, AMD reports a Thermal Design Power (TDP) figure of 125 watts for its high-performance Athlon 64 FX-62 processor, while Intel claims 75 watts. "What Intel does states is a typical wattage figure. So there's a difference in those two numbers right off the bat."
In the definition of the term set forth by Tom's Hardware Guide years ago, TDP is "the maximum amount of power the thermal solution is required to dissipate." In other words, TDP is a benchmark figure relative to how a cooling device, such as a heat sink or a fan, dissipates heat. Its original intent was to show the maximal power consumption that a physical system could withstand and still dissipate heat at necessary levels. But as Uwe W. D. Weyden wrote for us almost six years ago, "CPU vendors provide the values TDPmax and TDPtyp to the designers" - meaning, the maximal level of heat dissipation and the typical level under normal loads.
So there are two TDPs... or, at least, there used to be, six years ago. Anyway, AMD's claim is that its 125 watt number represents the FX-62's TDPmax, and Intel's 75 watt number represents Core 2 Extreme's TDPtyp. If Intel represented the maximal TDP instead, the numbers might look much different.
There's also this bit about "thermal... " If you look at it closely enough, TDP isn't really a measure of power consumption anyway, AMD argues. It was never designed to be, states David Schwarzbach, AMD's Athlon 64 X2 product manager: "TDP's origin was as a thermal design point. This is for engineers to design their heat sinks, their ventilations, their fans, all that stuff. It's not a good way to communicate to end users what's actually happening in energy consumption within the box."
"At the end of the day," said Field, "what it comes down to is, what is the power utilization of the platform as a whole?" He reminded us about such perennial factors as the memory controller, which in Intel architecture is on a separate chip drawing power, while in AMD architecture remains on the CPU. "We do have some advantages in our architecture, with our integrated memory controller, that allows other components to use less power on the system as well. So all of that needs to be taken into consideration when you're doing a head-to-head power comparison."
It just so happens, however, that Tom's Hardware Guide did a head-to-head comparison, with some results that AMD won't much like: Under maximum workloads, an overclocked Core 2 Extreme X6800 processor drew 218 watts. That's down remarkably from the Pentium D 840's power draw of a colossal 344 watts, and it's now lower than the Athlon 64 FX-62's draw of 283 watts. There's nothing thermal about this figure.
Schwarzbach was only willing to concede just a little ground to Intel, but not much. "With the Core 2 Duo announcement, he said, "Intel is catching up with the 65 watt TDP specifications. So they're closing the gap a little bit, but I still believe AMD has the leadership position there."
The problem going forward, AMD believes, is not to re-widen the gap, but instead to change the way it's measured. "We would like to see the development of uniform ways of communicating actual power," said Schwarzbach. "TDP has been the default way of doing it to this point. I think it does the industry a disservice overall, because we're still in the dark about what the actual energy consumption is, and I think that's where the industry sensitivity is right now. In commercial [markets] with fleets of PC systems, and mobile with battery life, you really want to know at the plug - which implies this is a total platform energy measurement - what am I actually consuming in terms of wattage? What's the cost to me?"
If the Tom's test is indicative of the results one could get from a more realistic power measurement, then AMD's argument may be an easy target. AMD, however, could continue to tout the differences between Core Microarchitecture and AMD64, in hopes of substantiating one or more "asterisks," if you will, that some could put in front of Intel's power figures.
"While Intel's architecture is an improvement," said Schwarzbach, dusting off one such asterisk, "our architecture still maintains advantages because an integrated [memory] controller means that the overall platform level of energy consumption should continue to be an advantage... We don't have a northbridge chip consuming power. So average wall power, or power at the plug, is going to be a relevant communication point for us, as well as average CPU power consumption."
Would AMD support an independent effort, perhaps from a standards body, to implement a fairer approach to publishing power consumption numbers? "As consortiums and standards-making bodies emerge in this area," Schwarzback replied, "we'll certainly be one of the founding, if not influential, members in those communities."
Capitalizing on the 'emerging purchase criteria'
The coming days, from AMD's perspective, will require a kind of re-educational effort as to what power really means. Just like in a political campaign, when one candidate seizes the advantage on a key issue, the other side tends to devote time to redefining the terminology used to describe that issue.
"We've got a team internally focused on, how do we develop some messaging that can better educate the market... as to what the true power consumption attributes are," AMD's David Schwarzbach told TG Daily. "When we released our energy-efficient line back in May, our press release stated a factoid that, when running in a typical load, our 65 watt TDP processor, end users can expect to see as low as 14 watt power consumption at the platform level." So much of a computer's time is spent in idle mode that any metric that would claim to be more fair, should take idle time into account, AMD believes.
"We're looking for a way to communicate this more effectively to the market," added Schwarzbach. "We're just not satisfied right now that the industry is doing a good job of communicating these attributes, so look for better things to come from us in market education for the second half of the year."
The second half of the year is when AMD plans to unveil the first products in its new "4x4" architecture, which promises two sockets for a pair of dual-core processors. Here is where AMD will have the opportunity to respond with performance figures; but unless AMD has plans to make a U-turn in its design strategy on the order of the U-turn Intel is making - perhaps successfully - then AMD has a fundamental dichotomy to overcome: How can it make its key message of "performance-per-watt" - what, in marketing parlance, is called an emerging purchase criteria - play to an enthusiast market for whom low power, singularly and most uniquely, isn't cool?
"[Performance-per-watt] is an emerging purchase criteria area," said Schwarzbach, "specifically in commercial [markets], more there than elsewhere, [but] less so with the enthusiast space [for whom] the power consumption is of slightly less concern, but still it's got to figure into the overall mix."
Mike Field added, "At the high end, enthusiasts really are looking for the absolute highest performance that they can get, and they are willing to make tradeoffs to get that. One of them, power consumption, is less critical to them. In fact, if you look at the trends, they are willing to go to multiples. If you look at this space, you look at multiple GPUs, they're willing to throw more at [their systems] to get that absolute highest performance."
If the mainstream market cares about power conservation more than the enthusiast market cares about power consumption, then with the mainstream market growing at a faster rate by many analysts' standards, doesn't that mean the two markets will eventually become segmented? In AMD's opinion... yes.
"It all comes down to the specific customer, and what they're looking for," replied Field. "It is a customer-centric innovation message [where] we look at the specific segment of the customers." For example, he said, the 4x4 architecture will address certain "key competencies" associated with AMD. But 4x4's "customer-centric" message will be devoted to what Field describes as deficiencies that the enthusiast market perceives with being able to derive greater performance from their current systems. For them, conservation is less of an issue.
"Based on the customer segmentation, the enthusiasts are going to be the last area of our industry to to really elevate power consumption as their key purchase criteria," admitted Schwarzbach. "[Among] the majority of purchasers... enthusiasts are a small but very influential part... but for the mainstream and value portions of the industry, [power] is an increasing purchase concern for them."
"But in other areas, there is more of a focus on power utilization," Field made certain we understood, "and in those areas, we're focused on being the leader as well."
If AMD continues with its earlier plan to be the performance-per-watt leader, then so long as it continues to address the enthusiast market, doesn't it risk contradicting itself? AMD's perspective, quite literally, is this: As long as the two markets remain separated like split continents, if you will - and perhaps if there's enough concerted effort to keep them separate - and AMD maintains leadership perceptions on both continents, then if it speaks a different message to each one, the plan could still work.
As David Schwarzbach put it, "We feel like we're covering all bases, and because of the differences in the way this market segments itself, we don't think the potential for contradiction is there."
One other "key competency" AMD may choose to focus on for 4x4 is price. Not once, but twice this week, AMD revealed it would be dropping its price of Athlon 64 processors and others in its performance desktop product line, in a move AMD spokesperson Damon Muzny described as an "aggressive" way "to maintain our price/performance leadership." Since that news was very, very fresh, David Schwarzbach was only willing to allude to it during our interview: "Our price/performance position will remain competitive; our traditional value-based pricing remains in-place," he said, quite carefully. "We price to the value we provide, as denoted by the market, and what their purchase criteria are. So we are in full preparation to respond once these products become available."
For years, AMD's marketing claims implied that Intel's perceived position of leadership was merely a trick of perception, and that once the facts were made clear, AMD's performance position would be secured. Now with that position in clear danger, it would appear AMD's plan to maintain the appearance of leadership will require a substantively similar change in the way we view the market. Perhaps we should adopt a new corollary to Moore's Law: Every year, the number of ways customers are asked to perceive their own technology, doubles.