AMD Announces Ryzen 7000 Series "Zen 4" Desktop Processors

[Dirt Chip]

We have come to the days that it is not absurd to buy a high-end CPU/GPU just to get the better chip bin and then downclock and/or undervolt it to hit the best heat/pref point.

Get a 7950X, shut down 4 cores, limit to 105-95w and enjoy most of the pref at half the watteg and $ cost.

 

[Valantar]

We have come to the days that it is not absurd to buy a high-end CPU/GPU just to get the better chip bin and then downclock and/or undervolt it to hit the best heat/pref point.

Get a 7950X, shut down 4 cores, limit to 105-95w and enjoy most of the pref at half the watteg and $ cost.

There's no reason to disable the cores - they'll stay power gated unless needed, so they don't use power unless the OS + the chips own management systems deem it necessary to wake the cores up.

 

[ratirt]

Modern CPUs are the most efficient (joules for the work accomplished) at the frequency that minimizes operating voltage. Of course, to lower voltage you have to decrease frequency and by extension, power.

To help understanding the idea, here is a graph I made with my i7-12700K at default frequencies, but optimized voltages (my motherboard gives plenty of voltage with default settings). With the settings it has at the moment, the CPU won't require more than 150W, but under overclocked conditions it could take up to 250W or more if cooling allows. Two things are clear from the graph: increasing power yields progressively diminishing performance returns and increases the energy (Joules) required to perform the same work (here, a render test similar to that used in TPU reviews).

All CPUs both from Intel and AMD will exhibit a behavior along these lines.

View attachment 260116

Great but that is not the point we've been arguing about. everyone knows about the efficiency and power a CPU requires to operate. We are talking about limiting a 170W cpu to 65w for efficiency but this will drop the performance very much and it may not be worth paying so much for performance which will not be there any longer.
The other thing is, we are not talking hear about tweaking the CPU but limit its power. That is also different.
Like i said, I undervolted my 6900xt and it runs cooler, uses less power but the performance stayed exactly the same.
Than you have a CPU which uses 170w and you cap it at 65w loosing lets say 30% of performance, since you just want to have a efficient CPU for which you pay a lot money. Now, you pay for performance or for the tweaking? I don't see a gain here but regression in performance instead by lowering power usage exponentially

 

[R0H1T]

You can't undervolt a GPU like you can with CPUs so you can do a lot more wrt efficiency on them. Also efficiency is a big deal these days & one of the major reasons why Apple's taken a huge chunk of notebook marketshare recently, to a lesser extent high end PC as well. Whether we like it or not efficiency will become & more important going into the future, the earth is only getting hotter after all.

 

[gffermari]

No sane person would turn off cores or limit the power massively to gain on efficiency. That’s madness.

on topic: if I didn’t have the 3D and the decent mobo, I would dive into zen 4…

 

[Valantar]

Great but that is not the point we've been arguing about. everyone knows about the efficiency and power a CPU requires to operate. We are talking about limiting a 170W cpu to 65w for efficiency but this will drop the performance very much and it may not be worth paying so much for performance which will not be there any longer.
The other thing is, we are not talking hear about tweaking the CPU but limit its power. That is also different.
Like i said, I undervolted my 6900xt and it runs cooler, uses less power but the performance stayed exactly the same.
Than you have a CPU which uses 170w and you cap it at 65w loosing lets say 30% of performance, since you just want to have a efficient CPU for which you pay a lot money. Now, you pay for performance or for the tweaking? I don't see a gain here but regression in performance instead by lowering power usage exponentially

This is all kind of going in circles though. If you can afford the higher core count CPU, want an extremely efficient CPU rather than peak possible performance, and have the time, knowledge and skills to tune it to a lower power level, by all means do so. That's pretty much a given - unless you go under whatever the tipping point for efficient operation for the CPU is, where it starts being truly starved for power, you'll gain efficiency as you drop in power.

It's like buying Intel's 35W T CPUs back in the day - you got the same core count as the non-T variants, but a much lower power limit and accompanying lower clocks (but higher efficiency) - but you also paid roughly the same as for the non-T SKUs.

The question is the relevance of stock settings, and the effect of their power levels. @fevgatos argues that they are irrelevant because anyone can tune their chips to be more efficient. This, IMO, is nonsense, as we know that the vast majority of users have neither the time, knowledge, skills or desire to do this tuning, meaning stock settings determine the behaviour - and thus efficiency - of the vast majority of CPUs actually used.

Of course, if you do have the time, knowledge, skills and desire to do this, you can gain a lot. My 5800X performs better at the 110W PPT I've got it running at than it does at its stock 138W PPT, for some weird reason. Modern boost algorithms and their interactions with thermals, current, and core hopping for ST tasks (and the lack of core hopping for nT tasks) makes the relationship between settings and performance more complicated. But you can't expect the average user to understand, let alone do anything about any of this. And that's what @fevgatos refuses to acknowledge.

I think the clock speed gains AMD are showing here are really impressive, but I still don't like the TDP jumps - but they're essentially forced into those by the competitive situation, seeing how Intel has already gone there (and beyond). Luckily, most consumer applications are not anywhere near continuous nT loads, and will thus not need all of this power. Which of course complicates the efficiency picture even further.

 

[W1zzard]

@W1zzard Can you please add the 7950x with HT off in you cpu test suite?

Hmm, what would that answer? Nobody will run them like that?

 

[Asni]

Hmm, what would that answer? Nobody will run them like that?

Neither they are using a 12900k with e-core disabled since Intel removed AVX-512.
But i'd like to see the scaling with a reasonable amount of threads (16vs32) in a real word scenario. Physical cores perform better than logical ones and they should even boost higher.

 

[Solid State Brain]

Great but that is not the point we've been arguing about. everyone knows about the efficiency and power a CPU requires to operate. We are talking about limiting a 170W cpu to 65w for efficiency but this will drop the performance very much and it may not be worth paying so much for performance which will not be there any longer.
The other thing is, we are not talking hear about tweaking the CPU but limit its power. That is also different.
Like i said, I undervolted my 6900xt and it runs cooler, uses less power but the performance stayed exactly the same.
Than you have a CPU which uses 170w and you cap it at 65w loosing lets say 30% of performance, since you just want to have a efficient CPU for which you pay a lot money. Now, you pay for performance or for the tweaking? I don't see a gain here but regression in performance instead by lowering power usage exponentially

I am not sure what real-world consumer scenarios there are for using a 170W TDP CPU (with even higher peaks) at 65W besides circumstances with severe cooling or power constraints, or just efficiency for the sake of efficiency.

Drawing from personal experience, I was referring more to using it at a more reasonable 100-120W, which will likely yield most of the MT performance at a significantly lower heat output, making cooling manageable with ordinary coolers. Probably many people in recent years got spoiled by affordable commercial AIO water cooler kits, but even a high-end air cooler will have troubles efficiently dissipating 170-180W+ without getting itself noticed.

Depending on your priorities, it can be worth it to trade 10-15% MT performance in exchange for a lower power draw. Perhaps if one used the CPU in a continuously operating rendering cluster of some sort, even losing more (even 25-30%) would be acceptable as well as long as efficiency increased.

 

[JustBenching]

Great but that is not the point we've been arguing about. everyone knows about the efficiency and power a CPU requires to operate. We are talking about limiting a 170W cpu to 65w for efficiency but this will drop the performance very much and it may not be worth paying so much for performance which will not be there any longer.
The other thing is, we are not talking hear about tweaking the CPU but limit its power. That is also different.
Like i said, I undervolted my 6900xt and it runs cooler, uses less power but the performance stayed exactly the same.
Than you have a CPU which uses 170w and you cap it at 65w loosing lets say 30% of performance, since you just want to have a efficient CPU for which you pay a lot money. Now, you pay for performance or for the tweaking? I don't see a gain here but regression in performance instead by lowering power usage exponentially

Nope, i was talking about limiting it to 105w, the same as the 5950x was.

Do you think people should have been runnimg their 5950x at 170 watts instead of stock? Cause if they didnt they would be losing perfromance.

 

[R0H1T]

I don't have an AC here, really hot temps outside & generally very hot ambient temps in Summer. I like to run everything at or close to peak efficiency/cooling even if it means lower overall performance! I'm sure I'm not the only one with similar issues.

 

[JustBenching]

I am not sure what real-world consumer scenarios there are for using a 170W TDP CPU (with even higher peaks) at 65W besides circumstances with severe cooling or power constraints, or just efficiency for the sake of efficiency.

Drawing from personal experience, I was referring more to using it at a more reasonable 100-120W, which will likely yield most of the MT performance at a significantly lower heat output, making cooling manageable with ordinary coolers. Probably many people in recent years got spoiled by affordable commercial AIO water cooler kits, but even a high-end air cooler will have troubles efficiently dissipating 170-180W+ without getting itself noticed.

Depending on your priorities, it can be worth it to trade 10-15% MT performance in exchange for a lower power draw. Perhaps if one used the CPU in a continuously operating rendering cluster of some sort, even losing more (even 25-30%) would be acceptable as well as long as efficiency increased.

Clear case is a 12900k, at 125w it scores 24.5k. At the full 240w it scores 27k. But according to rairt, you would be dumb to limit it to 125w cause you dont get what you paid for whatever that means.

 

[Valantar]

Nope, i was talking about limiting it to 105w, the same as the 5950x was.

Do you think people should have been runnimg their 5950x at 170 watts instead of stock? Cause if they didnt they would be losing perfromance.

... or we just accept that there exists a thing called a stock configuration, that this is an inherent trait of the product available to consumers, and that stock-to-stock comparisons and metrics are thus the most relevant baseline comparison for any performance measurement, including relative efficiency. Stock settings are a configurable variable inherent to the product just like the number of cores, clock speeds, cache, accelerators, ++++, so it's just another part of the product.

It'll be really interesting to see how the 7950X and 7900X compare to their predecessors in terms of efficiency - my guess would be major improvements in ST (unless 1c core power is up massively), while nT will be more complicated. Then we can start talking about subsequent testing at other power levels, which will also be interesting, but in more of an academic sense seeing how that's not representative of what the vast majority of users will experience. Still informative, still useful, still interesting, but not generally applicable or the best basis to draw conclusions about the product unless you're doing measurements specifically tuned for your use case and you limit your conclusions accordingly.

 

[Solid State Brain]

... or we just accept that there exists a thing called a stock configuration, that this is an inherent trait of the product available to consumers, and that stock-to-stock comparisons and metrics are thus the most relevant baseline comparison for any performance measurement, including relative efficiency. Stock settings are a configurable variable inherent to the product just like the number of cores, clock speeds, cache, accelerators, ++++, so it's just another part of the product.

An issue with this is that over the years motherboard manufacturers have made it impossible to set a real "stock configuration" or "CPU manufacturer default" in the consumer space. Motherboards will come with unlocked limits by default, or even use enhanced frequency settings when possible, pumping up voltages to keep everything stable.

Another issue is that even if one CPU manufacturer enforced stricter motherboard defaults, the other could easily take advantage of this self-limitation by allowing its own partners to configure motherboard settings as they wish, for better "stock" benchmark scores in the reviews.

As I've mentioned elsewhere, it's on the reviewers to come up with improved and fair testing methodologies that don't simply use "motherboard defaults" (often inadequate) or unlocked limits, but it takes more time and research, i.e. money.

 

[ModEl4]

So for those people that they would like a 65W 7600 option now we have:

$300+$20 (or more) cooler = $320 and undervolt it

And if AMD release a 65W 6core Zen4 it will be max $250 with cooler included.

So people will lose around $70 and AMD gains $50 more + the cooler cost

There's no reason why people complaining, right?

 

[Valantar]

An issue with this is that over the years motherboard manufacturers have made it impossible to set a real "stock configuration" or "CPU manufacturer default" in the consumer space. Motherboards will come with unlocked limits by default, or even use enhanced frequency settings when possible, pumping up voltages to keep everything stable.

Another issue is that even if one CPU manufacturer enforced stricter motherboard defaults, the other could easily take advantage of this self-limitation by allowing its own partners to configure motherboard settings as they wish, for better "stock" benchmark scores in the reviews.

As I've mentioned elsewhere, it's on the reviewers to come up with improved and fair testing methodologies that don't simply use "motherboard defaults" (often inadequate) or unlocked limits, but it takes more time and research, i.e. money.

That is definitely true, and I agree that reviewers need to set a standard for this and follow it. Thankfully AMD mandates that motherboard makers follow their PPT/TDC/EDC limits, and doesn't have the mechanisms for something like MCE - their boost systems are aggressively opportunistic to begin with. And Intel with ADL decided to throw everything out the window and just set PL1=PL2=240W for their K SKUs, despite nominal 125W TDPs. So the MCE enabled/disabled at stock issue is less of a problem now than with Skylake and earlier. IMO, reviewers should follow chipmaker defaults for chip testing, as that's just a variable that needs to be controlled for.

 

[R0H1T]

Don't buy (PC)hardware right at launch, unless you absolutely need it ~ best free advise ever

 

[Solid State Brain]

[...] And Intel with ADL decided to throw everything out the window and just set PL1=PL2=240W for their K SKUs, despite nominal 125W TDPs

I think PL1=PL2=240W must have been just in the reviewers' guides provided by Intel, possibly in expectation that every motherboard can and will behave differently depending on default settings.

The publicly available ADL spec sheet recommends PL1=125W, PL2=241W and Tau=56s. These are not mandated, and there are and even suggestions of using lower PL limits and Tau time if the cooler/system cannot handle them.

[...] reviewers should follow chipmaker defaults for chip testing, as that's just a variable that needs to be controlled for.

Curiously, the true Intel hardware default (as per spec sheet notes) for PL2 is supposed to be PL1 * 1.25, with Tau=1s. That means that for a 125W TDP processor, PL2 would be 156W.

 

[Valantar]

I think PL1=PL2=240W must have been just in the reviewers' guides provided by Intel, possibly in expectation that every motherboard can and will behave differently depending on default settings.

The publicly available ADL spec sheet recommends PL1=125W, PL2=241W and Tau=56s. These are not mandated, and there are and even suggestions of using lower PL limits and Tau time if the cooler/system cannot handle them.



Curiously, the true Intel hardware default (as per spec sheet notes) for PL2 is supposed to be PL1 * 1.25, with Tau=1s. That means that for a 125W TDP processor, PL2 would be 156W.


View attachment 260143

All of that is true, except that for K SKUs, the official Intel spec, confirmed by among others Anandtech at launch (not in a reviewers' guide but directly from company contacts IIRC) differs from their general guidelines and is PL1=PL2=241W. This might have been only for the 12900K and 12700K, but it is official Intel guidance, and what motherboard makers held to. As you say, Intel doesn't enforce these limits at all, but that also kind of goes out the window when Intel sets their guidance that high.

Of course, it's also possible that they've changed this since - I wouldn't be surprised, given the shitstorm they faced for those ridiculous numbers.

 

[Solid State Brain]

I'm referring to this datasheet, accessible from this page, see relevant table below. I don't recall previous revisions of this document to have ever listed PL1 to be the same as PL2, nor seeing it mentioned here as a suggested mode of operation or as the default; that's why I suspect that was intended to be a testing suggestion for getting the best scores in the initial reviews.

https://cdrdv2.intel.com/v1/dl/getContent/655258

After some brief digging, PL1=PL2=241W was indeed mentioned in the launch slide deck cited on the Anandtech review of the i9-12900k, but the explanation provided in the article is not exactly convincing. This in my opinion was simply Intel semi-officially admitting that they preferred their CPUs to be reviewed at max turbo, instead of ambiguously letting motherboard makers decide and potentially create confusing results (which has already brought in the past clickbait videos by techtubers).

Why would Intel write something in a launch slide and then recommend something else in technical documentation?

Intel 12th Gen Core Alder Lake for Desktops: Top SKUs Only, Coming November 4th

www.anandtech.com

Intel 12th Gen Core Debut: Alder Lake CPUs Are Ready For Battle

Intel revealed 12th Gen Core Alder Lake processor details at its inaugural Intel InnovatiON event today.

hothardware.com

 

[RandallFlagg]

When will the real AMD fans stand up and make a thread about how to get higher clocks, more power, better cooling, and better benchmarks?

This like watching a car enthusiast forum where everyone is talking about swapping in taller gears (less acceleration) and disabling cylinders on their car to get more MPG.

 

[ratirt]

This is all kind of going in circles though. If you can afford the higher core count CPU, want an extremely efficient CPU rather than peak possible performance, and have the time, knowledge and skills to tune it to a lower power level, by all means do so. That's pretty much a given - unless you go under whatever the tipping point for efficient operation for the CPU is, where it starts being truly starved for power, you'll gain efficiency as you drop in power.

It's like buying Intel's 35W T CPUs back in the day - you got the same core count as the non-T variants, but a much lower power limit and accompanying lower clocks (but higher efficiency) - but you also paid roughly the same as for the non-T SKUs.

The question is the relevance of stock settings, and the effect of their power levels. @fevgatos argues that they are irrelevant because anyone can tune their chips to be more efficient. This, IMO, is nonsense, as we know that the vast majority of users have neither the time, knowledge, skills or desire to do this tuning, meaning stock settings determine the behaviour - and thus efficiency - of the vast majority of CPUs actually used.

Of course, if you do have the time, knowledge, skills and desire to do this, you can gain a lot. My 5800X performs better at the 110W PPT I've got it running at than it does at its stock 138W PPT, for some weird reason. Modern boost algorithms and their interactions with thermals, current, and core hopping for ST tasks (and the lack of core hopping for nT tasks) makes the relationship between settings and performance more complicated. But you can't expect the average user to understand, let alone do anything about any of this. And that's what @fevgatos refuses to acknowledge.

I think the clock speed gains AMD are showing here are really impressive, but I still don't like the TDP jumps - but they're essentially forced into those by the competitive situation, seeing how Intel has already gone there (and beyond). Luckily, most consumer applications are not anywhere near continuous nT loads, and will thus not need all of this power. Which of course complicates the efficiency picture even further.

Well some people are blind and they just to narrow minded to understand the difference. I really have no problem with reducing voltage or put a power limit on a CPU to make it run cooler and use less power. I do that myself. My argument is, you pay certain price for a CPU and you deliberately halved his power for efficiency. Why not buy a different CPU that is efficient and you pay less for since you are looking for efficiency which is your main concern not performance. (well there is still a boundary with how much max power it should use at least for me)
That is about the price and money and if you are OK with paying more to get less that is fine with me. My another argument is connected to the first one but extends a bit. Performance, efficiency and price. These are the 3 metrics (lets say the main metrics for a consumer) that determine the CPU general value, how it performs for the money and if the performance comes with a cost of power and heat. For me, the combination of all those is necessary to properly evaluate the CPU. If you wonder why Intel or AMD lock CPUs power at some level it is simple. It has to be limited so that the CPU wont degrade or get damaged instantly by too high voltage or current. The CPUs coming from a producer must perform the same way. As we know different wafer different silicon quality gives different results at the edge or extreme, thus one can work with lower voltage than the other achieving same. Silicon lottery lets say so standard settings for every single CPU. you measure performance per watt or performance per $ to see what this CPU offers. Obviously you want to use the CPU to the max so that element must be in the equation as well.
If you measure with the 3 metrics you evaluate the processors value with the 3 metrics but if you follow our friend @fevgatos argument, that the CPU is efficient when you extremely limit the wattage of a CPU, lowering drastically its performance, the conclusion here is, there are no inefficient CPUs and the performance loss is not important at this point and value of a CPU makes no sense at this point. I'm, not saying you should not purchase a $800 CPU or more, halve its power if that is what the person desires. I'm saying, you can't do that and argue that the CPU is efficient because you've limited it to 45w in a desktop segment, disregarding the performance and power of competing products in a standard evaluation. What the 45w limited CPU tells me, it would have been good for a laptop with the performance you get. Also, why would there be ARM CPUs with low power consumption since you can literally limit x86 cpu power and be efficient. Yet ARM is here and gaining ground. To be fair I'm tired of talking about it I really thought it is crystal clear but apparently it is not and people have such a hard time understanding it.

The frequency is high but also the cache. Have you noticed that the 7950x has around 40% more cache of the 5950x but still less than the 5800x3d. I'm not sure what the L1 cache is. I assume most of the power increase is due to the frequency not the cache but probably the cache takes a bit of it. The other thing I been wondering is, locked 7950x and 5950x at 4Ghz and 13% better result. Probably due to higher cache capacity and lower latency? I think so. Maybe the Ram and Infinity fabric gives a boost in performance as well. but 13% just by ram and IF? not likely.

 

[R0H1T]

When will the real AMD fans stand up and make a thread about how to get higher clocks, more power, better cooling, and better benchmarks?

This like watching a car enthusiast forum where everyone is talking about swapping in taller gears (less acceleration) and disabling cylinders on their car to get more MPG.

Is that supposed to be a joke? Did you miss the once in "half a millenia" drought in Europe, due to Global warming

At this point we should just lump all the climate change deniers with their flat earther brethren, not saying you are a denier (since I don't know your position) but spending more power for very little to virtually no benefit these days makes zero sense!

 

[JustBenching]

If you measure with the 3 metrics you evaluate the processors value with the 3 metrics but if you follow our friend @fevgatos argument, that the CPU is efficient when you extremely limit the wattage of a CPU, lowering drastically its performance, the conclusion here is, there are no inefficient CPUs

Νo, that's not what Im arguing at all. No wonder you disagree since you haven't even understood the point.

Let me try once more, in the hopes you get it.

CPU A is at 100w and scores 100 points at stock (let's say it's the 5950x)
CPU B shows up and it is running at 170w and scores 150 points (let's say it's the 7950x).

CPU B looks more inefficient than A, but when you actually test them both at same wattage, CPU B can score 120 points at 100w. So it is more efficient. So if you are after efficiency, you can run CPU B at the same wattage cpu A was at, and still beat it in both performarnce and efficiency. Yet here we have people complaining about how inefficient zen 4 are. The same thing was going on with alderlake..

If you still don't get what im saying, I give up

 

[RandallFlagg]

Is that supposed to be a joke? Did you miss the once in "half a millenia" drought in Europe, due to Global warming

At this point we should just lump all the climate change deniers with their flat earther brethren, not saying you are a denier (since I don't know your position) but spending more power for very little to virtually no benefit these days makes zero sense!

Try being a little more hypocritical why don't you.