So, how is Bulldozer's gaming power consumption?

[know of fence]

Don't you think it is strange how people lambaste the FX-8150 in unison? Is it possible that the emotional consensus is at least partly groupthink, triggered by the desire to have clarity and simple answers?

Let's not forget a CPU architecture not only consists of transistors but also a million compromises. When at the end of the day two things remain: performance and power consumption, there is a multitude of ways to distort the perspective.

So let's take a look at reviews: Take this-here-site for example. I'll spare you the quotes.
Anand gives praise when video encoding is benched, which is pretty much the only mainstream thing requiring a massive CPU. So far, so good.

Then he comes down hard on single threaded performance...
(Update: Crysis effectively makes use of two cores, we see the biggest disparity here, presumably since Intel can utilize a half while AMD uses one forth of its core potential).

Last but not least, power consumption under load is high.

So what is your mental picture after that, let me guess: A CPU that can barely run games and devours 229W while at it.

But if old game performance is bad, due to a lack of parallel threading. Shouldn't power consumption during games also be reduced?
Alas, we are never provided with the numbers Anand chooses to present only min and max. I dare you to find a review that has more numbers on gaming power consumption.

In Conclusion
Wouldn't you agree, that maligning SINGLE THREAD PERFORMANCE while only presenting PERFECTLY MULTI THREADED power consumption may be a little bit misleading?

Power consumption still is a deal breaker compared to the i7 2600k for me, but I really would like to know if low performance in those games at least resulted in lower consumption. Then again it may turn out that the 8 core Bulldozer actually scales pretty well with its tasks, surely we can't have that.

(Review)http://www.anandtech.com/show/4955/the-bulldozer-review-amd-fx8150-tested/11

Update: As an enthusiast site AT never put much emphasis on power consumption, only reporting total power at the wall outlet. Supposedly because in a world of silence lovers and power savers desktop computers would only exist in their mini-ITX variants.At least modern desktop hardware throttles down the power and shuts down unused cores, which is one of Bulldozers strengths compared to older Phenoms.
Chart from X-Bit Labs shows idle W measured at the 24 pin connector)

The Questions about single threaded power consumptions were also answered in this topic, thanks to LoneNinja. As well as the issue of performance scaling thanks to frostedflakes; power consumption scales from [>63% to 100%] in almost linear proportion as the number of threads is increased.

 

[gmaster456]

Good luck getting anything positive about bulldozer here.

 

[Don Karnage]

Good luck getting anything positive about bulldozer here.

I don't think BD has any positives to begin with

 

[Flipped Gazelle]

So what is your mental picture after that, let me guess: A CPU that can barely run games and devours 229W while at it.

No, because the data you have posted doesn't show BD's power usage while running a game, it shows BD's power usage while performing an x264 benchmark.

Also, is Crysis Warhead single-threaded?

 

[Flipped Gazelle]

I don't think BD has any positives to begin with

I'm genuinely curious: Do you ever actually contribute anything useful to AMD threads? We get the idea that you don't like BD, and that's fine and even perfectly logical, but the repetitive redundancies of your posts are... redundantly repetitive and empty.

 

[Yukmouth]

How I understand it is that any way you look at it the CPU is running full load voltage the entire time you're gaming so the only difference added load should make is temp related.

 

[Idontcare]

Is this an "I've got an honest question here" type thread?

Or is it more a "I've got an ax to grind here" type thread?

 

[Don Karnage]

I'm genuinely curious: Do you ever actually contribute anything useful to AMD threads? We get the idea that you don't like BD, and that's fine and even perfectly logical, but the repetitive redundancies of your posts are... redundantly repetitive and empty.

I'm still sour and bitter at amd for this catastrophe. I was all ready to build a BD rig before the reviews came out. Main reason why i have nothing but snide remarks in these threads.

 

[Flipped Gazelle]

I'm still sour and bitter at amd for this catastrophe. I was all ready to build a BD rig before the reviews came out. Main reason why i have nothing but snide remarks in these threads.

Let it go... judging by your sig, you've got a wonderful system, be happy!

 

[Maximilian]

Well BF3 can use up to 8 threads, why dont you buy an 8150 and do the benchmarks yourself, or ask one of the 8 people on this entire forum that own a bulldozer to help:

http://forums.anandtech.com/showthread.php?t=2216377

My speculation is that if its power consumption is lousy during x264 then it will be lousy during gaming but with less of a total power draw. It will still get trampled by sandy bridge.

 

[IonusX]

I don't think BD has any positives to begin with

box looks cooler than an intel one imho

 

[janas19]

box looks cooler than an intel one imho

*crickets chirping*

 

[thilanliyan]

How I understand it is that any way you look at it the CPU is running full load voltage the entire time you're gaming so the only difference added load should make is temp related.

The CPU running at load voltage doesn't necessarily mean it will be constantly at 100% usage right? Transistors actually switching contribute to the power consumption. So unless the CPU load is 100% while gaming it wouldn't necessarily be consuming the 229w or whatever it is.

 

[sandorski]

For Power Consumption, what would be interesting is a Typical Day Usage type test. X Idletime, X Gamingtime, X Internettime, etc etc, then give a result. I think specific Apps/Uses don't necessarily mean much to anybody when PCs are used in such diverse ways. Add in the growing complexity of Power Management and it gets even less informative.

 

[Don Karnage]

box looks cooler than an intel one imho

Its just a box

 

[TakeNoPrisoners]

box looks cooler than an intel one imho

Yea so I'll throw a quarter in a shiny box and charge $200 for it.

 

[TakeNoPrisoners]

No, because the data you have posted doesn't show BD's power usage while running a game, it shows BD's power usage while performing an x264 benchmark.

Also, is Crysis Warhead single-threaded?

Crysis Warhead is dual-threaded.

 

[RavenSEAL]

Its just a box

LOL

Only $679.99? D:

 

[frostedflakes]

That's a 4, not a 7.

Anyway OP, I think the takeaway was that Bulldozer is less efficient than SB. Obviously it will use less than 229W while playing a game that doesn't fully load the CPU, just like the 2600K will use less than 155W in the same situation.

 

[Chiropteran]

I agree completely with the OP, and I made this point in the days following the initial bulldozer reviews. Alas, nobody really cared.

 

[Belegost]

So here is how I would look at it: For a given processor there is some curve that relates average power usage to average load. Currently reviews tend to give us two points on that curve, idle and max load. Rigorously this is sufficient to fully define a linear relation, or if we further had some curvature information, to fit a curve.

First I will start by saying I doubt power usage scales linearly with load. My prediction would be a concave down curve that quickly rises and then flattens out, and because of the discrete ability to gate cores and such, I suspect it's not very smooth, but has distinct steps.

So then, given that we don't have the curvature information, the best we can do is question whether the shape between two different processor lines differs greatly. That is, does a BD grow to max more slowly than a SB for some reason? Perhaps, but look at what we know - at idle BD is drawing about 10% more from the wall, and at full load, about 50% more.

So for there to be a significant region in which SB uses the same or more power than BD then SB would have to hit 90% power before BD reaches 60%. Somehow I don't see the two curves being that dissimilar.

 

[Chiropteran]

So for there to be a significant region in which SB uses the same or more power than BD then SB would have to hit 90% power before BD reaches 60%. Somehow I don't see the two curves being that dissimilar.

The problem is the two data points are not equal. In Bulldozer's case, the max power shows usage with 8 cores pegged, while the i5 or i7 power usage shows for 4 cores... since the cpu only contains 4 cores.

For example if i5 2500k is x at 2 cores fully loaded and 2x at 4 cores fully loaded, it does NOT follow that fx-8150 would be at y 2 cores loaded and 2y at 8 cores fully loaded... logically you would expect the power usage to increase more when you go from 2 to 8 cores rather than from 2 to 4 cores.

Because we don't have the numbers for bulldozer's power usage in an application loading 4 cores, we can't get the needed information.

 

[Flipped Gazelle]

Crysis Warhead is dual-threaded.

Exactly... I intended for the OP to realize this, and maybe explain why he uses a graph of Crysis Warhead performance after stating, "Then he comes down hard on single threaded performance... "

 

[Flipped Gazelle]

Its just a box

But don't you understand how much better the AMD tin would be for storing shortbread?

 

[Phynaz]

The problem is the two data points are not equal. In Bulldozer's case, the max power shows usage with 8 cores pegged, while the i5 or i7 power usage shows for 4 cores... since the cpu only contains 4 cores.

For example if i5 2500k is x at 2 cores fully loaded and 2x at 4 cores fully loaded, it does NOT follow that fx-8150 would be at y 2 cores loaded and 2y at 8 cores fully loaded... logically you would expect the power usage to increase more when you go from 2 to 8 cores rather than from 2 to 4 cores.

Because we don't have the numbers for bulldozer's power usage in an application loading 4 cores, we can't get the needed information.

What's the point? So you can say "Oh, Look! It uses less power when half loaded!"? We know it does. And it doesn't make it suck any less.

How about power consumed to perform a task. Otherwise known as performance per watt. BD gets slaughtered in this metric, which is ironic because it's the metric the used to push Opteron. I wonder why they aren't so keen on using that metric anymore?