[MfA]

The pace of development is irrelevant, as is the "powerwall" ... those are only relevant to the ON state power, which aren't what this regulation is about.

If this regulation couldn't be met because the ASICs are too large and power regulation not advanced enough that would be one thing ... but those things aren't true. These regulations can be met, when they aren't met it's because the engineering cost to meet them was deemed too high ... now for sure they are not.

[UniversalTruth]

Originally Posted by MfA

this regulation is about

Once again. Then, wth is this regulation about? What is the relation between memory bandwidth and power consumption? Do these people realise that tomorrow we may have 1 TB/s bandwidth achiveable with ultra-low voltage memory modules?

[Simon F]

Originally Posted by UniversalTruth

Once again. Then, wth is this regulation about? What is the connection between memory bandwidth and power consumption?

At a guess, perhaps because going "off-die" for data is a relatively large consumer of energy?

[MfA]

Originally Posted by UniversalTruth

Once again. Then, wth is this regulation about?

"SLEEP/IDLE/OFF power consumption"

What is the relation between memory bandwidth and power consumption?

It's used as a proxy for performance, and it's a pretty decent one at that ... there is an exemption for the very highest performance desktop machines (CPU/GPU/PSU wise) for the next 12 months.

[Dave Baumann]

Slicing by memory bandwidths is a rough proxy for segementation (or chip sizes); this has been used in a number of cases previously. It undersood that that a bigger ASIC is going to have more static leakage power, even in relatively low power states and so a "one size fits all" categorization will not work, so some mechanism is needed to slice the market.

[Gubbi]

Originally Posted by UniversalTruth

http://www.techpowerup.com/reviews/H...D_6870/29.html
http://www.techpowerup.com/reviews/A...dition/28.html

45% once (4890 vs 6870), and 117.4% (6870 vs 7970 GE) for th second time.

At 1900x1200, the resolution I use, techpowerup's numbers for the 7970 GE add up to 2.13 x performance of the 4890 (ie. 113% faster)

Originally Posted by UniversalTruth

108 W on average vs 209 W on average.

AFAICT from the links you gave, 131 W average for 4890 vs 209 W for the 7970 GE. It still means that performance/watt is less than 50% better than 3½ years ago.

Cheers

[UniversalTruth]

To be accurate- slightly more than 3 years between April 02, 2009 and June 21, 2012.
But if we count the original 7970, then it would be 2.5 years.

[Gubbi]

Originally Posted by UniversalTruth

To be accurate- slightly more than 3 years between April 02, 2009 and June 21, 2012.
But if we count the original 7970, then it would be 2.5 years.

Which you then should compare to the original 4870. The 4890 was a speed optimized 4870, clocking 13% higher, exactly the same ratio as 7970 GE vs 7970.

The 4870 was introduced late june 2008, the 7970 late december 2011, exactly 3½ years apart.

Cheers

[Alexko]

Originally Posted by Gubbi

At 1900x1200, the resolution I use, techpowerup's numbers for the 7970 GE add up to 2.13 x performance of the 4890 (ie. 113% faster)

Cheers

Err… I got a factor of 2.76. How did you get to 2.13?

Even a factor of just 2 in 5 years would be much faster than almost any other industry.

[Blazkowicz]

Originally Posted by Gubbi

I think Roderic's point is that AMD and Nvidia has pushed power consumption to absurd levels trying to get highest absolute performance with no regard to electricity usage, - causing excessive heat production and associated noise.

I remember a time when computer ICs didn't have heat sinks at all (not even passive ones) and computers were silent.

Cheers

Maybe a ZX81 was silent, or an amiga/atari when floppy drive wasn't in use, but I sure remember hard disk drives to be noisy as hell

[UniversalTruth]

Originally Posted by Gubbi

Which you then should compare to the original 4870. The 4890 was a speed optimized 4870, clocking 13% higher, exactly the same ratio as 7970 GE vs 7970.

The 4870 was introduced late june 2008, the 7970 late december 2011, exactly 3½ years apart.

Cheers

RV790 has more work on it done in comparison to 7970---> 7970 GHz where you had different binning only.

[Gubbi]

Originally Posted by UniversalTruth

RV790 has more work on it done in comparison to 7970---> 7970 GHz where you had different binning only.

I know. It still had the same architecture and the same amount of shaders.

Regarding the 2.13 x performance increase. I misread one of the graphs. The speedup is 2.8x. However don't forget the 7970 is 26% bigger than the 4890 (365 mm^2 vs 289 mm^2)

Cheers

[homerdog]

Seems like power consumption at the high end is actually trending down a bit anyway.

Even if it hadn't been, legislators have far, far more important things to waste spend their time on. What a joke.

[MfA]

Actually from an economic point of view I'm pretty sure that idle power consumption legislation has been one of the better uses of EU time ...

[kache]

Bad regulations. They should have just added incentivea for lower consumptions (by making energy consumption classes, each of which has a different taxation), not go so deep since, as someone said above, technology in this field evolves too fast

[3dcgi]

Originally Posted by MfA

Actually from an economic point of view I'm pretty sure that idle power consumption legislation has been one of the better uses of EU time ...

How so?

I think they should encourage power usage numbers on boxes so consumers know what they are buying. Like calorie listings for food.

[CRoland]

You people are overreacting. Read the document. It isn't half bad.

The main problem IMO is that the limits are too high. The initial limits are higher than any current gen GPUs use and idle power (this doesn't touch maximum or average use power) has been trending down recently. Even the later limits are IMO too high, but maybe this will be seen as a precursor to later tightening, and will still guide the manufacturers to lower idle power.

Also, it only affects computers. If AMD or Nvidia somehow ended up with an SKU that wasn't withing these limits they could still sell it in the retail market, just not to OEMs. And again, limiting whole computer systems means OEMs could probably find an idle-efficient CPU to pair it with.

Originally Posted by kache

Bad regulations. They should have just added incentivea for lower consumptions (by making energy consumption classes, each of which has a different taxation), not go so deep since, as someone said above, technology in this field evolves too fast

I agree that a taxing approach might have been more optimal. The problem is that EU has no power to set taxes.

[Ethatron]

Originally Posted by silent_guy

Of course, if Europe is willing to put constraints on its global technology competitiveness this way, that's their choice to make. It's not as if they're not already missing the boat on cloud computing for similar regulatory reasons either...

How is that related? If you want Europe as a market, which I guess is half of the first world countries incl. Norway :P, then you have to make compliant hardware as a vendor. Has nothing to do with where the vendor is situated. If global players don't chim in, I'm sure it'd mean the hole is being filled with european players - making less money and giving space for competitors to grow isn't really so great a strategy.

[MfA]

Originally Posted by 3dcgi

How so?

Because consumers are not always economically smart ... for something which doesn't really affects their user experience like standby power consumption it doesn't make sense to even involve them, just force manufacturers to make the overall good economic choice (ie. more engineering costs up front to save energy).

[eastmen]

Originally Posted by Gubbi

I know. It still had the same architecture and the same amount of shaders.

Regarding the 2.13 x performance increase. I misread one of the graphs. The speedup is 2.8x. However don't forget the 7970 is 26% bigger than the 4890 (365 mm^2 vs 289 mm^2)

Cheers

And the 4890 is DX10.1 while the 7970 is 11.1 not to mention that the 7970 puts a much higher quality image on the screen due to better filtering


Anyway . Any law that limits idle power consumption is a good thing , but i think its a waste of time since the trend has been lower idle power draw for awhile.

[UniversalTruth]

not to mention that the 7970 puts a much higher quality image on the screen due to better filtering

This sounds intriguing to me.
I know that ATI lower quality beginning with either R600 or RV670 generations, don't know why exactly- probably looked to squeeze every last frame per second.

However, it would be highly appreciated if someone shows in reviews this difference- to test 4890 vs 7970. Is it really possible to see it somewhere?

[AlphaWolf]

http://techreport.com/review/14990/a...ics-processor/
http://www.rage3d.com/reviews/video/.../index.php?p=6

Look at the colorful checkerboard circles produced by the d3d AF tester.

[Silent_Buddha]

Originally Posted by Ethatron

How is that related? If you want Europe as a market, which I guess is half of the first world countries incl. Norway :P, then you have to make compliant hardware as a vendor. Has nothing to do with where the vendor is situated. If global players don't chim in, I'm sure it'd mean the hole is being filled with european players - making less money and giving space for competitors to grow isn't really so great a strategy.

That all depends. If manufacturer X makes something for the EU, while manufacturer Y doesn't and manages to make something 50-100% faster because of it. Then you'd basically have manufacturer X owning the EU while manufacturer Y owned the rest of the world. In other words, they'd just split the markets with no competition between them. Although, there's always the possibility that manufacturer Y just sells cut down version in the EU to compete. Which then forces manufacturer X to ditch EU requirements to compete in the rest of the world or risk becoming a minor player.

If that happens the only people that lose out are in the EU, while the rest of the world will have the choice between low power/low perf. or high power/high perf. Of course, then people will end up blaming greedy manufacturers rather than the government just like they currently do with the retail price discrepencies.

Granted that's a rather extreme case, and with the generous idle power numbers used so far certainly not something that will happen anytime soon.

If they do make it too strict, however, there's always a chance of something like that happening...unlikely as it is.

As well, if China continues to develope economically it may eventually end up making up half the revenue for most of the global companies. At which point, potentially restrictive regulations in the EU would just make them a minor player in the global scene.

Regards,
SB

[Ethatron]

That assumes the cut-down version is still of better quality (pick your unit) than the dedicated european version, which may be possible but I wouldn't think it's going to happen.

The energy-thing they try to achieve there is very contextual, the effect is sought to be a reduction of consumption. The long term effects of that are not in your scenario, what if China's growth creates a worldwide energy-crisis and the europeans are prepared, partly because of a joint effort to lower energy consumption.

There are so much pros and cons and scenarios, it hardly matters how reality turns out. European legislation searches for a specific advantage there, and they have the right to do so. If things change (fusion-energy fe.), legislation changes again, so what.