Atlas Fallen Optimization Fail: Gain 50% Additional Performance by Turning off the E-cores

[AnotherReader]

You can even shave off 100W from ADL/RPL with like a 5% penalty. They're configured pretty badly ootb, but that doesn't mean there's not a power efficient chip in there.


Now maybe, but 7950X launched at $750 MSRP.

Both AMD and Intel have configured their higher end processors, bar the 7950X3D, pretty badly out of the box. The 7950X launched at $699. As far as this game is concerned, it seems to be the case of a game developer thinking they can outsmart the OS scheduler.

 

[Crackong]

Little reality check: a 7950X under full load can consume up to 240W

Could you pay attention and realize we were talking about the 7950X3D.

But I guess you are so blindfolded when things comes to fanboyism.

 

[chrcoluk]

I think the difference between the two is less than $50. The 7950X is available for $599 at multiple retailers such as Best Buy and Newegg while the 13900k is being sold for $568.2 by Amazon and B&H photo video.

AMD has higher platform cost though. Boards cost more, and have to buy DDR5 as is no DDR4 option 7000 series.

So its swings and roundabouts really.

 

[AnotherReader]

AMD has higher platform cost though. Boards cost more, and have to buy DDR5 as is no DDR4 option 7000 series.

So its swings and roundabouts really.

The difference between DDR5 and DDR4 is not that significant anymore. However, Intel has the more reasonably priced motherboards. With that being said, I doubt that a prospective 7950X or 13900K buyer would be looking for the cheapest motherboards.

 

[Squared]

While consuming double the power consumption (140 vs 276) ?

You're comparing Raptor Lake to Zen 4. But E-cores were introduced with Alder Lake. Alder Lake offered better gaming performance and equivalent multithreading performance to Zen 3 while consuming a similar amount of power. Alder Lake was built with Intel 7 and Zen 3 with TSMC N7. Raptor Lake is built with Intel 7 and Zen 4 with TSMC N5. Intel is at a power efficiency disadvantage today, but that is better explained by the manufacturing technology than by the presence of E-cores.

 

[bug]

The difference between DDR5 and DDR4 is not that significant anymore. However, Intel has the more reasonably priced motherboards. With that being said, I doubt that a prospective 7950X or 13900K buyer would be looking for the cheapest motherboards.

They wouldn't be looking at DDR4. Still, if you can save $50 or so, who would turn that down?

 

[Crackong]

equivalent multithreading performance to Zen 3 while consuming a similar amount of power.

Techpowerup 12900k launch review says otherwise:

Since it is whole system power,
Let's take the idle consumption away (~50W)
Then it is 129W vs 247W (+91.4%)


Then, in the previously mentioned 7950X3D review

It is already calculated as CPU-only
So it is 140w vs 276w (+97.1%)

 

[Max(IT)]

Could you pay attention and realize we were talking about the 7950X3D.

But I guess you are so blindfolded when things comes to fanboyism.

No, we weren’t:

Apparently you lack reading skills, in addition to knowledge

Techpowerup 12900k launch review says otherwise:

View attachment 309059
Since it is whole system power,
Let's take the idle consumption away (~50W)
Then it is 129W vs 247W (+91.4%)


Then, in the previously mentioned 7950X3D review
View attachment 309060
It is already calculated as CPU-only
So it is 140w vs 276w (+97.1%)

Keep using the 7950X3D which is slower than 13900K in multithreaded workloads…
The 7950X3D is a tuned down 7950X, so if you “tune” a 7950X or a 13900K you can reduce the gap. Not saying Intel CPUs are power efficient (they are not !), but presenting the number the way you are doing is misleading

 

[Squared]

Techpowerup 12900k launch review says otherwise:

View attachment 309059
Since it is whole system power,
Let's take the idle consumption away (~50W)
Then it is 129W vs 247W (+91.4%)

The 12900K outpetformed the 5950X in that test.

And TPU didn't do a lot of efficiency tests but here you can see that 12x series processors have efficiency close to 5x series. The 12900K actually has a poor showing and the 5950X a great showing, probably because the 12900K was designed to be thermally unconstrained, whereas the 5950X can't handle the heat its cores produce at full load, so it clocks down, and desktop processors are way more efficient at lower clock speeds.

 

[Crackong]

No, we weren’t:
Apparently you lack reading skills, in addition to knowledge
Keep using the 7950X3D which is slower than 13900K in multithreaded workloads…
The 7950X3D is a tuned down 7950X, so if you “tune” a 7950X or a 13900K you can reduce the gap. Not saying Intel CPUs are power efficient (they are not !), but presenting the number the way you are doing is misleading

Maybe you can first argue with him and figure out why he was quoting the 7950X3D Techpowerup review.

And about your 7950X3D vs 13900k arguement.
Yes 7950X3D is slower then 13900k in multithreaded workloads..by 2% according to Techpowerup's Application performance summary, that's fact.
But it is also Yes it is 140W vs 276W, which is also fact.

While your claim was "The 7950X3D is a tuned down 7950X, so if you “tune” a 7950X or a 13900K you can reduce the gap"
I must tell you that Intel did tune down their 13900k and release the 13900T.
And the 13900T is a very rare CPU and almost no reviews existed.

You might not like it.
But we all know that it is not looking good when Intel tried to do the same.

The 12900K outpetformed the 5950X in that test.
And TPU didn't do a lot of efficiency tests but here you can see that 12x series processors have efficiency close to 5x series. The 12900K actually has a poor showing and the 5950X a great showing, probably because the 12900K was designed to be thermally unconstrained, whereas the 5950X can't handle the heat its cores produce at full load, so it clocks down, and desktop processors are way more efficient at lower clock speeds.

Yes it outperformances the 5950x by 7.6% , while consuming 91% more power.
12900k is faster, but also comsumes a lot more.

And about your "12x series processors have efficiency close to 5x series" arguement.
I don't see where is that came from.
Your quoted picture clearly shows
The best 12th gen sample was 9.6kj
The best 5000 series sample was 6.4kj

Which, the 5000 series had a 50% efficiency advantage.
And the 12900k isn't the most efficient 12th gen either...


And about the"thermally unconstrained" arguement.
"Hey my CPU can eat more electricity" is a good point in your mindset?

Okay I get that as a personal preference thing.
If you are judging CPUs on how many energy they can take before it overheats, I won't argue with you on that.
Intel had their previously very famous 7980XE which can take >1000W even.
I guess that's you favourite CPU.
I don't judge on these personal preference choices.
Just note that many of us do take the power bills very seriously at the times
And energy concern is very real.

 

[Max(IT)]

As I said several time: no point in arguing with AMD cheerleaders

 

[Crackong]

And Fanboyism will make people so blindfolded and ignoring the facts.

 

[Squared]

And about your "12x series processors have efficiency close to 5x series" arguement.
I don't see where is that came from.
Your quoted picture clearly shows
The best 12th gen sample was 9.6kj
The best 5000 series sample was 6.4kj

What about the worst against the worst?
The 5800X was 10.0kJ
The 12900K was 10.2kJ
Was the 5800X unpopular on account of its Intel-like inefficiency? Why did the 12900K perform less efficiently with the E-cores disabled?

 

[Crackong]

What about the worst against the worst?
The 5800X was 10.0kJ
The 12900K was 10.2kJ
Was the 5800X unpopular on account of its Intel-like inefficiency? Why did the 12900K perform less efficiently with the E-cores disabled?

Your worst against worst example just showed us the worst Zen3 part still has the average efficiency matching the 12th gen products.
It is like the worst student in the red class scored 50 and everyone else scored better.
but in the blue class, everyone scored 50.

The 5800x doesn't have good efficiency mainly because of the unnecessary high power target and bad voltage tuning.
The OEM 5800 non-X proved that by retaining most of the performance with insane efficiency.

As for the E-cores disabled 12900k
It is the same as 5800x, unnecessary high power target and bad voltage tuning.
Basically the full power target was given to the 8 P-cores and they went too far out of the efficiency window.

 

[Squared]

Your worst against worst example just showed us the worst Zen3 part still has the average efficiency matching the 12th gen products.
It is like the worst student in the red class scored 50 and everyone else scored better.
but in the blue class, everyone scored 50.

The 5800x doesn't have good efficiency mainly because of the unnecessary high power target and bad voltage tuning.
The OEM 5800 non-X proved that by retaining most of the performance with insane efficiency.

As for the E-cores disabled 12900k
It is the same as 5800x, unnecessary high power target and bad voltage tuning.
Basically the full power target was given to the 8 P-cores and they went too far out of the efficiency window.

So the E-cores aren't hurting the Intel precessors on power efficiency. And power targets play a huge role in efficiency. The 5950X uses 179W when multithreading, compared to 175W on the 5800X, so 16 cores / 179W verses 8 cores / 175W. The 12900K is 16 cores / 297W. What if the 12900K's power target was reduced to 179W (or 135W since it has 8 E-cores which should have a lower power target), what would that do to its efficiency?

Actually the E-cores do hurt efficiency in a way; because their maximum power consumption is fairly low, they don't eat into the 297W power limit very much, so they don't force the P-cores to clock down very much under full load. More E-cores at the same power target or a lower power target would help with this.

 

[Crackong]

So the E-cores aren't hurting the Intel precessors on power efficiency. And power targets play a huge role in efficiency. The 5950X uses 179W when multithreading, compared to 175W on the 5800X, so 16 cores / 179W verses 8 cores / 175W. The 12900K is 16 cores / 297W. What if the 12900K's power target was reduced to 179W (or 135W since it has 8 E-cores which should have a lower power target), what would that do to its efficiency?

Actually the E-cores do hurt efficiency in a way; because their maximum power consumption is fairly low, they don't eat into the 297W power limit very much, so they don't force the P-cores to clock down very much under full load. More E-cores at the same power target or a lower power target would help with this.

Please noted that in the 12900k benchmark TPU measured the total system power draw.
TPU improved the measurement to CPU-only power draw later in the 13900k / 7950X3D tests.

So to counting the power draw in the 12900k test, the idle power should be subtracted.
So it was 129 vs 247, a much larger difference.

The 12th gen E-cores aren't particularly power efficient, as already being tested on TPU's E-cores only test.
12th gen E-cores are more like space-efficient, so to put 8 physical cores into an area roughly equal to 3 P-cores.
13th gen E-cores are the other way around, they are much more power efficient, but the nature of having more E-cores in 13th gen CPUs just cancelled out that benefit.

As for a reduced power target 12900k.
Some reviewers turned the MCE off so to test the 12900k at the "Default" power then run some tests that exceeds the PL2 time limit.
Let's say 12900k power scale very well and it actually needs the power.
Without some undervolting a reduced power target 12900k would perform a bit less than excpected.

 

[AnotherReader]

So the E-cores aren't hurting the Intel precessors on power efficiency. And power targets play a huge role in efficiency. The 5950X uses 179W when multithreading, compared to 175W on the 5800X, so 16 cores / 179W verses 8 cores / 175W. The 12900K is 16 cores / 297W. What if the 12900K's power target was reduced to 179W (or 135W since it has 8 E-cores which should have a lower power target), what would that do to its efficiency?

Actually the E-cores do hurt efficiency in a way; because their maximum power consumption is fairly low, they don't eat into the 297W power limit very much, so they don't force the P-cores to clock down very much under full load. More E-cores at the same power target or a lower power target would help with this.

We don't have to speculate. @W1zzard tested this about a month after the release of the 12900k. The most efficient configuration tested was 75 W for PL1 and PL2, and even then, it didn't catch up to the stock 5950X in multithreaded applications like Cinebench. Note that Sapphire Rapids, based off the same Golden Cove cores, struggles to beat Zen 3 based Epyc despite higher power draw.

 

[Squared]

We don't have to speculate. @W1zzard tested this about a month after the release of the 12900k. The most efficient configuration tested was 75 W for PL1 and PL2, and even then, it didn't catch up to the stock 5950X in multithreaded applications like Cinebench. Note that Sapphire Rapids, based off the same Golden Cove cores, struggles to beat Zen 3 based Epyc despite higher power draw.

No but it did catch up with the 5900X. At P1=100W, the multithreaded energy efficiency test measured 7.9kJ, verses 7.8kJ for the 5900X. This was at comparable power draw, 172W for the 12900K and 183W for the 5900X. At P1=75W it was more efficient but also a bit slower. The 5950X is still more efficient but it's still an outlier within Zen 3, possibly because of its lower power targets, more exclusive binning, and perhaps the review sample is exceptional. (The 12900KS would've taken from the 12900K bin at some point.)

I'm not arguing that the 12th-gen Intel processors are exactly as efficient nor that Intel tuned the K-series models with efficiency in mind. I'm arguing that the 12th-gen Intel processors have similar efficiency to the 5000-series AMD processors, and that the E-cores are not inherently bad for efficiency.

 

[AnotherReader]

No but it did catch up with the 5900X. At P1=100W, the multithreaded energy efficiency test measured 7.9kJ, verses 7.8kJ for the 5900X. This was at comparable power draw, 172W for the 12900K and 183W for the 5900X. At P1=75W it was more efficient but also a bit slower. The 5950X is still more efficient but it's still an outlier within Zen 3, possibly because of its lower power targets, more exclusive binning, and perhaps the review sample is exceptional. (The 12900KS would've taken from the 12900K bin at some point.)

I'm not arguing that the 12th-gen Intel processors are exactly as efficient nor that Intel tuned the K-series models with efficiency in mind. I'm arguing that the 12th-gen Intel processors have similar efficiency to the 5000-series AMD processors, and that the E-cores are not inherently bad for efficiency.

You're right; Golden Cove, while being behind, isn't too far from Zen 3 in efficiency. The E cores could have been better for efficiency if they had been clocked below 3.5 GHz as Chips and Cheese found out.

 

[chrcoluk]

The difference between DDR5 and DDR4 is not that significant anymore. However, Intel has the more reasonably priced motherboards. With that being said, I doubt that a prospective 7950X or 13900K buyer would be looking for the cheapest motherboards.

Why would I buy DDR4 if I already have DDR4?

So its not DDR4 price vs DDR5 price its zero vs DDR5 price.

Now if one already didnt have DDR4 then its just the cheaper boards, but most people choosing to go DDR4 on 12/13 gen very likely already have DDR4, as thats the only time it makes sense.

 

[AnotherReader]

Why would I buy DDR4 if I already have DDR4?

So its not DDR4 price vs DDR5 price its zero vs DDR5 price.

Now if one already didnt have DDR4 then its just the cheaper boards, but most people choosing to go DDR4 on 12/13 gen very likely already have DDR4, as thats the only time it makes sense.

In that situation, it's a no-brainer to go with Raptor Lake. However, if you're upgrading from a generation before Skylake, then you might have chosen DDR4 to reduce costs. I'm just pointing out that for that use case, the choice to go with DDR4 isn't a good one anymore, and the choice between Intel and AMD isn't as straightforward.