Question How in the world has AMD got the Ryzen 7600X and 7700X priced same when they are inferior even in P cores only compared to 13600K and 13700K

[Wolverine2349]

I mean the Ryzen 7700X is an 8 core CPU and Ryzen 7600X is a 6 core CPU. And the 7700X is $399 and 7600X is $299.

Intel has the Core i7 13700K priced at $399 and Core i5 13600K priced at $399. And those CPUs have better P cores being 8 and 6 core counterparts with slightly better IPC than Zen 4 and can clock as high or higher with similar power usage. And for those who do not like e-cores (I am one of them, but I love Intel P cores) can disable them and you get better 6 and 8 core CPUs form Intel Raptor Lake than AMD Ryzen. And for those who want e-cores you get then as well for the same price and better P cores of equal core counts.

SO what is AMD thinking and they still have not budged on the prices of the 7600X and 7700X. They are pricing the like their 6 and 8 Zen 4 cores are better than Intel's Raptor Cove cores of equal count even though they are not any better and in fact not as good?? Or is that debatable??

The Ryzen 7900X and 7950X prices make more sense as then you get more than 8 strong cores and AMD has those by the balls who want more than 8 cores and do nit want to go hybrid route. SO yeah 7900X and 7950X prices make sense.

But 7600X and 7700X are almost a ripoff unless you just have not have AMD as they do nothing better than 13600K and 13700K for exact same price and have slightly weaker P cores and no additional e-cores for those that like the e-core options (And for those that do not it is easy peasy to disable and you get the better 6 and 8 core chips for the same price)

Its puzzling to me AMD is behaving as if they are still superior in all ways like they were with Ryzen 5000 from November 2020 to November 2021 when Intel was of no competition on core count nor per core IPC performance which was only for 1 year. I mean AMD is still much smaller and was underdog for years and hard to believe they think they can act they are premium brand in the 6 and 8 core CPU segment when the 7600X and 7700X are worse than Intel counterparts even with the e-cores off.

Your thoughts

 

[Mopetar]

I do not think it would have been bad but if clock speeds on Zen 4 were not increased, the performance uplift would have been underwhelming as IPC increased by only like 10% or maybe 13% and in some cases worse latency.

Clock speeds would still have increased, just not by quite as much. The last 100 MHz is considerably more expensive than the first.

Everybody would be happier if AMD stuck with their original/standard TDP from previous generations. Even if the top silicon only hit 5/2-5.3ghz the massive efficiency advantage to AMD would offset the Intel unlimited power to the chip philosophy.

AMD wouldn't have been. They'd have locked themselves into a particular TDP for all future Zen CPUs that use AM5. They know more about their future products than we do and it's entirely possible than Zen 5 was conceived with a larger TDP in mind. Or they want to be able to eventually be able to offer more than 16 cores without having to cut the clocks as much.

There are a lot of reasons to push the TDP for the platform higher even if there's not a lot of short term benefits. AM5 will still be around long after we've stopped caring about Zen 4. I hope AMD supports AM5 as well as they did AM4 and that they put a lot of forethought into it as a result.

 

[Wolverine2349]

The hybrid debate is .... interesting to say the least.

Currently Intel is 8+16 and AMD is 16+0 for their top of the stack parts.
Despite being at a transistor density and power disadvantage Intel is more than competitive across the board with 16+0. Yes, they pay a power cost to win the MT benches, but even backing down the power a bit the parts are very competitive.

If, currently, 8 big cores are enough for most applications that are not MT optimized then assuming applications are becoming MORE and not less MT capable, 8 big cores will be enough moving forward.

If Intel 7 can manage 8+32 in the same die as the current 8+16 then MT workload competition is going to be a real challenge for AMD if they don't move to a hybrid architecture. In fact Intel could possible consider 6+40.

Love it or hate it Intel has found a great alternative to squeeze a lot of compute into a small area. I'm quite sure if AMD had done it first there would be a lot more "brilliant" and "genius" adjectives thrown around. That being said if AMD still has the process advantage so if they moved to hybrid they would press Intel against a wall.

Are even 8 big cores needed for apps not multi threaded optimized?? And aren't some apps multi thread optimized but only scale to a finite number of cores like games for instance? In that case big cores are better than less big cores and even more little cores.

Though would you agree no games right now and probably in near future will have any meaningful benefit from more than 6 strong cores and 8 is easily more than enough. This is assuming you are not streaming or running discord or such with the game. Hardware Unboxed even says 6 cores i eaisly enough as long as they are performance and fewer faster cores is way better than more storng cores when you ahve around 6 and even 8 being overkill unless you discord or stream as well.

Though I play it safe with 8 and shun the e-cores as I do not like the e-cores at all, but the Intel P cores rock!!

 

[Exist50]

Well if it is embraced and there are options for more strong cores fine. But some do not like it and want hybrid arch. It can cause compatibility issues with lots of things and you need WIN11. With WIN11 it works well as mostly set and forget. But WIN10 is a different story.

Also those who run lots of VMs and need equal resource allocation between them the big.little not good at all and having same core type with no hybrid is way way better. I do not do either and run games and like 8 super fast cores so Raptor Lake with e-cores off and fast clocked P cores it is for me.

It has been my observation that on this forum, the loudest voices against hybrid (or the E-cores in general) are based on an entirely emotional rejection of the concept, not because of any particular workload complaint. And frankly, I think that's because it's something Intel currently has that AMD doesn't, and that alone is enough for certain people to hate it. They'll mysteriously start accepting the idea around the same time AMD includes it.

This discussion reminds me of some of the early complaints about AMD moving to chiplets. "Oh, higher memory latency is going to suck for gaming or such-and-such use case!". Stuff like that was plentiful. But turns out, those weren't major obstacles for the vast majority of use cases, so it all turned out more than fine.

You talk about W10 as if hybrid is completely broken. It isn't. And gaming? Testing with Raptor Lake shows essentially no difference.

And on top of all that, Intel (and AMD eventually) will have offerings with all big cores for certain markets, but it hardly seems sensible that consumer chips don't match what are largely niche enterprise or server workloads.

 

[TheELF]

Are even 8 big cores needed for apps not multi threaded optimized?? And aren't some apps multi thread optimized but only scale to a finite number of cores like games for instance? In that case big cores are better than less big cores and even more little cores.

Though would you agree no games right now and probably in near future will have any meaningful benefit from more than 6 strong cores and 8 is easily more than enough. This is assuming you are not streaming or running discord or such with the game. Hardware Unboxed even says 6 cores i eaisly enough as long as they are performance and fewer faster cores is way better than more storng cores when you ahve around 6 and even 8 being overkill unless you discord or stream as well.

Though I play it safe with 8 and shun the e-cores as I do not like the e-cores at all, but the Intel P cores rock!!

If they start putting that many e-cores on a cpu it would be better to stay with 8+0 and release add on cards with any number of e-cores on an m.2
Latency isn't much of a worry since the e-cores handle background stuff anyway and for MT stuff it doesn't even matter at all.

But then again if 8+32 or even more sells, then why wouldn't they.

Intel already has the tech to put a whole CPU onto an m.2 they could put a CPU with only e-cores on there and people could put as many of them as they want (or their cooling/psu can handle) into the same system.

https://www.tomshardware.com/news/intel-ice-lake-10nm-nervana-npp-i-accelerator,39731.html

 

[Exist50]

I think a lot of the consternation surrounding Zen 4 on enthusiast forums (especially this one which has a strong pro AMD presence) stems from the absurd hype that Zen 4 had before the AMD presentation.

I think that's a component, but most of the complaints about Zen 4 seem to be around platform cost and CPU pricing vs comparable Intel parts. It's not that Zen 4 isn't a great improvement from Zen 3, but it doesn't exist in a vacuum. But overall, I think Zen 4 has gotten a good reception.

But I do fear that pre-launch hype could be a problem for Zen 5. Some people have truly massive expectations for it, and are even skipping Zen 4 in expectation. Call me a pessimist, but I can't help but think that the reality is bound to disappoint.

AMD was expecting a much greater uplift in performance going from 7nm to 5nm silicon.

Says who? With 5nm + design improvements, they've got one of the largest gen/gen clock speed increases we've seen in years! Certainly if anyone is expecting better from N3, they're in for a rude awakening.

 

[Wolverine2349]

It has been my observation that on this forum, the loudest voices against hybrid (or the E-cores in general) are based on an entirely emotional rejection of the concept, not because of any particular workload complaint. And frankly, I think that's because it's something Intel currently has that AMD doesn't, and that alone is enough for certain people to hate it. They'll mysteriously start accepting the idea around the same time AMD includes it.

This discussion reminds me of some of the early complaints about AMD moving to chiplets. "Oh, higher memory latency is going to suck for gaming or such-and-such use case!". Stuff like that was plentiful. But turns out, those weren't major obstacles for the vast majority of use cases, so it all turned out more than fine.

You talk about W10 as if hybrid is completely broken. It isn't. And gaming? Testing with Raptor Lake shows essentially no difference.

And on top of all that, Intel (and AMD eventually) will have offerings with all big cores for certain markets, but it hardly seems sensible that consumer chips don't match what are largely niche enterprise or server workloads.

I like Intel better than AMD in almost all regards when on equal footing and especially when they are better. Only when AMD is truly superior do I like them better like during 2003 to 2006 Athlon 64 days and Zen 3 for 1 year. Intel is better.

If AMD was offering a max of 8 P cores and just a bunch of little cores, I would criticize them just as much. It has nothing to do with AMD or Intel as in fact once again I like Intel better.

The hybrid arch just does not make snese to me for a power user on desktop. E-cores make more sense in a mobile device like a phone laptop or tablet.

I am a traditionalist and opposed to too much change. I like advancements in IPC and speed and core count though to stick in an SMP world like the first multi processing Operating systems have had.

 

[Exist50]

I am a traditionalist and opposed to too much change. I like advancements in IPC and speed and core count though to stick in an SMP world like the first multi processing Operating systems have had.

But see, that's an emotional argument, not a rational one. Of course, your own purchasing decisions don't have to be strictly rational, but it doesn't make for much of a discussion topic.

 

[Thibsie]

The hybrid debate is .... interesting to say the least.

Currently Intel is 8+16 and AMD is 16+0 for their top of the stack parts.
Despite being at a transistor density and power disadvantage Intel is more than competitive across the board with 16+0. Yes, they pay a power cost to win the MT benches, but even backing down the power a bit the parts are very competitive.

If, currently, 8 big cores are enough for most applications that are not MT optimized then assuming applications are becoming MORE and not less MT capable, 8 big cores will be enough moving forward.

If Intel 7 can manage 8+32 in the same die as the current 8+16 then MT workload competition is going to be a real challenge for AMD if they don't move to a hybrid architecture. In fact Intel could possible consider 6+40.

Love it or hate it Intel has found a great alternative to squeeze a lot of compute into a small area. I'm quite sure if AMD had done it first there would be a lot more "brilliant" and "genius" adjectives thrown around. That being said if AMD still has the process advantage so if they moved to hybrid they would press Intel against a wall.

Yeah but area interests nobody but Intel itself. Had they designed and produced big cores with acceptable power draw, none of this krap would be.
And with none of the software issues associated with it.
Hybrid, at least Intel's (current) way, is a (acceptable) patch on a bug (their inability to produce cores with acceptable power draw). Nothing else.

 

[Exist50]

Yeah but area interests nobody but Intel itself.

Area directly correlates to cost, and in mobile, also form factor and battery life. Those are all things users definitely care about.

Hybrid, at least Intel's (current) way, is a (acceptable) patch on a bug (their inability to produce cores with acceptable power draw). Nothing else.

And yet AMD looks poised to go the exact same way. The fundamental benefits are undeniable, which is why most of the complaints have zero correlation to the data.

 

[Carfax83]

Hybrid, at least Intel's (current) way, is a (acceptable) patch on a bug (their inability to produce cores with acceptable power draw). Nothing else.

Both Intel and AMD are quite capable of making cores with acceptable power draw. The thing is, they want maximum performance so that they stand the best chance of beating the competition. Nvidia is doing the same thing, by maximizing the performance of their GPU cores and putting power efficiency second.

Raptor Lake is actually very power efficient at certain clock speeds. I've said it in the Raptor Lake threads, but this CPU responds absurdly well to undervolting. I have mine running at 5.2ghz with just 1.066v and the E cores are at stock clocks, 4.3ghz. My PL1 and PL2 are set to 210w, idle temps are in the 30s and maximum temps are in the upper 70s.....with air cooling.

To me, anything above 5ghz is going to be lightning fast so I feel no compulsion to even bother with anything more than 5.2ghz... Plus I game at 4K resolution as well which makes chasing absurdly high clock speeds unreasonable.

 

[Hulk]

If they start putting that many e-cores on a cpu it would be better to stay with 8+0 and release add on cards with any number of e-cores on an m.2
Latency isn't much of a worry since the e-cores handle background stuff anyway and for MT stuff it doesn't even matter at all.

But then again if 8+32 or even more sells, then why wouldn't they.

Intel already has the tech to put a whole CPU onto an m.2 they could put a CPU with only e-cores on there and people could put as many of them as they want (or their cooling/psu can handle) into the same system.

https://www.tomshardware.com/news/intel-ice-lake-10nm-nervana-npp-i-accelerator,39731.html

Anything is possible but math-coprocessors and other upgrade CPU cards have never been big sellers.

Really where we are going architecture-wise depends a lot on who comes out with the next big thing next. Meaning If AMD decides to say release a 24 big core part then Intel will have to respond with more E cores. If on the other hand AMD stays with 16 cores but really works on ST IPC then Intel will have to really go hard on the P's.

I'm sure both Intel and AMD are looking at the mainstream apps that require a lot of compute, gaming, rendering, and encoding probably being the big three and are looking at how to make meaningful improvements for the next gen. Rendering and encoding are well optimized for MT. Gaming seems to drive the development of the big cores these days.

Thank God for the gamers. Otherwise we'd have crap CPU's and GPU's!

 

[Markfw]

It has been my observation that on this forum, the loudest voices against hybrid (or the E-cores in general) are based on an entirely emotional rejection of the concept, not because of any particular workload complaint. And frankly, I think that's because it's something Intel currently has that AMD doesn't, and that alone is enough for certain people to hate it. They'll mysteriously start accepting the idea around the same time AMD includes it.

This discussion reminds me of some of the early complaints about AMD moving to chiplets. "Oh, higher memory latency is going to suck for gaming or such-and-such use case!". Stuff like that was plentiful. But turns out, those weren't major obstacles for the vast majority of use cases, so it all turned out more than fine.

You talk about W10 as if hybrid is completely broken. It isn't. And gaming? Testing with Raptor Lake shows essentially no difference.

And on top of all that, Intel (and AMD eventually) will have offerings with all big cores for certain markets, but it hardly seems sensible that consumer chips don't match what are largely niche enterprise or server workloads.

I have no idea if you are talking about me. BUT, my take on e-cores/p-cores is this: The human brain is so far ahead of computers right now, that I don't see this working to most peoples satisfaction for many years. Thats not emotional, thats logical. Intel used them to fill a need, and that is on a highly threaded app, to come to parity with AMD while making the heat created tolerable. In many cases here, I have seen its failure to correctly assign cores to one or the other. MS can try for years, but I doubt that we will see a good mix in even my sons lifetime. Look at the OS situation ? Apple fills a need, linux fills a need and windows fills a need. Is any one the nest at everything ? NO. Can all 3 manage these hybrid cores any time soon ? No way.

Yes, thats an opinion, but with logic attached, not emotions. Time will tell.

 

[DrMrLordX]

I have no idea if you are talking about me. BUT, my take on e-cores/p-cores is this: The human brain is so far ahead of computers right now, that I don't see this working to most peoples satisfaction for many years. Thats not emotional, thats logical. Intel used them to fill a need, and that is on a highly threaded app, to come to parity with AMD while making the heat created tolerable. In many cases here, I have seen its failure to correctly assign cores to one or the other. MS can try for years, but I doubt that we will see a good mix in even my sons lifetime. Look at the OS situation ? Apple fills a need, linux fills a need and windows fills a need. Is any one the nest at everything ? NO. Can all 3 manage these hybrid cores any time soon ? No way.

Yes, thats an opinion, but with logic attached, not emotions. Time will tell.

God help us then, since it looks like Phoenix 2 also has a heterogeneous core architecture. Maybe. At least in the case of Phoenix 2, the cores will be pretty similar (Zen4 vs Zen4c), so load balancing won't necessarily be as confusing.

 

[Exist50]

I have no idea if you are talking about me. BUT, my take on e-cores/p-cores is this: The human brain is so far ahead of computers right now, that I don't see this working to most peoples satisfaction for many years.

And yet, it does. How many millions of Alder Lake chips have been sold? Or beyond that, how many phones from the last few years? The vast majority use hybrid, and whether you're willing to acknowledge it or not, it works. To insist that millions of people must be silently suffering from hybrid issues is absurd.

And no, that is an entirely emotional argument. You can't accept that OS scheduling works, so you choose to ignore all of the data we have on the subject. But review after review, test after test show the same conclusion. In the vast majority of workloads and use cases, it works very well.

As I said above, you can use the exact same hand wavy claims to dismiss AMD's chiplet approach. But the data speaks for itself.

Ironically, if you listen to AMD's comments on the matter, they're way more accepting of the concept. Because of course they are. Sooner or later, they'll use it themselves. If you believe recent rumors, maybe in as little as a few months.

 

[Markfw]

And yet, it does. How many millions of Alder Lake chips have been sold? Or beyond that, how many phones from the last few years? The vast majority use hybrid, and whether you're willing to acknowledge it or not, it works. To insist that millions of people must be silently suffering from hybrid issues is absurd.

And no, that is an entirely emotional argument. You can't accept that OS scheduling works, so you choose to ignore all of the data we have on the subject. But review after review, test after test show the same conclusion. In the vast majority of workloads and use cases, it works very well.

As I said above, you can use the exact same hand wavy claims to dismiss AMD's chiplet approach. But the data speaks for itself.

Ironically, if you listen to AMD's comments on the matter, they're way more accepting of the concept. Because of course they are. Sooner or later, they'll use it themselves. If you believe recent rumors, maybe in as little as a few months.

I was trying not to include servers or the DC environment, but none of US are happy or use Alder lake or Raptor lake. I think that is millions (speaking worldwide).

My phone ? (I have an iphone 11, does that count??) Its not near as fast in anything as my desktop, but I don't expect that. As far as how many alder lake have been sold, we all know that Intel is still the market leader (market share wise) and most people just cruise the web and do the occasional word,excel etc, and have no clue how fast it is , or could be, or would notice if it was a 7950x or a 13900k. Or gaming is still in Intel court for the most part (5800x3d is knocking at the door and actually wins more than it loses.)

So since the light case use you mention works, that does not mean its the best for everyone. A lot of people have no idea if its working or not. I am working on a computer for a friend right now, and he had no idea the difference between a quad core and am Alder lake 12700F.. His computer died, and since I am selling it, I am replacing his dead quad core (or the motherboard or... Its an all-in one in a monitor, 7 years old) with my 12700F that does not work for me.

If you want to convince me it works good for all cases, find a large group of people that know something about computers and statistics to prove they think its the future. Not your average joe that has no idea what NVME even means.

 

[TheELF]

Yeah but area interests nobody but Intel itself. Had they designed and produced big cores with acceptable power draw, none of this krap would be.

Intel cores use less power in stock as well as in "out-of-the-box" settings and they are more efficient.
And you can also see that "out-of-the-box" settings are nowhere near as much "pushing to the limits" as everybody here tries to make it seem.
You can almost triple the power the intel cores can draw above "out-of-the-box" ,making it almost trice lower in efficiency.

Here you can see intel drawing 32W in single core, multiplied by 8 full cores that would be 256W which is very close to the stock power limit that intel warrants so you can have all 8 cores run at very close to full speed.
The 7950x uses 43W so a 12 core CPU running at full speed would use 516W and a 16 core CPU, well the 7950x ,running all its cores at full speed would use 688W.
And yeah, other software is going to use even more power, for intel as well as for amd.

ZEN only looks like it uses less power if you only look at the performance of the complete package, in software that doesn't need high core clocks, which is a completely valid way to choose what CPU you want, but it is not an indication of how good the cores are, or what power draw they have.

Intel Core i9-13900K Review - Power-Hungry Beast

With the Core i9-13900K, Intel delivers impressive performance. Our in-depth review confirms: Raptor Lake is the world's fastest CPU for gaming. Even in applications the processor is able to match AMD's Zen 4 Ryzen 9 7950X flagship. If only power consumption wasn't so high...

www.techpowerup.com

 

[Markfw]

Intel cores use less power in stock as well as in "out-of-the-box" settings and they are more efficient.
And you can also see that "out-of-the-box" settings are nowhere near as much "pushing to the limits" as everybody here tries to make it seem.
You can almost triple the power the intel cores can draw above "out-of-the-box" ,making it almost trice lower in efficiency.

Here you can see intel drawing 32W in single core, multiplied by 8 full cores that would be 256W which is very close to the stock power limit that intel warrants so you can have all 8 cores run at very close to full speed.
The 7950x uses 43W so a 12 core CPU running at full speed would use 516W and a 16 core CPU, well the 7950x ,running all its cores at full speed would use 688W.
And yeah, other software is going to use even more power, for intel as well as for amd.

ZEN only looks like it uses less power if you only look at the performance of the complete package, in software that doesn't need high core clocks, which is a completely valid way to choose what CPU you want, but it is not an indication of how good the cores are, or what power draw they have.

Intel Core i9-13900K Review - Power-Hungry Beast

With the Core i9-13900K, Intel delivers impressive performance. Our in-depth review confirms: Raptor Lake is the world's fastest CPU for gaming. Even in applications the processor is able to match AMD's Zen 4 Ryzen 9 7950X flagship. If only power consumption wasn't so high...

www.techpowerup.com

Because of the IO die power use, you can not say that it uses 43 watt for one core, as about 23 watt of that is the IO die, using one or 16 cores. So if you take that 22 and add 20*16 that would be 320 watts + 23 watts or 343, but due to the power usage curve (the curve optimizer) it uses 230.

Do you research before making crazy claims. Zen 4 is more efficient than Raptor lake. Even in the article you linked, AT STOCK Raptor lake took 287 watts to 235 for Zen 4 7950x.

 

[TheELF]

Because of the IO die power use, you can not say that it uses 43 watt for one core, as about 23 watt of that is the IO die, using one or 16 cores. So if you take that 22 and add 20*16 that would be 320 watts + 23 watts or 343, but due to the power usage curve (the curve optimizer) it uses 230.

Do you research before making crazy claims. Zen 4 is more efficient than Raptor lake. Even in the article you linked, AT STOCK Raptor lake took 287 watts to 235 for Zen 4 7950x.

Wait, AMD makes the CPU report the IO power draw as part of the core power draw???????

 

[Markfw]

Wait, AMD makes the CPU report the IO power draw as part of the core power draw???????

I could be wrong about this page, but I do know the IO die has a fixed power usage in addition to the cores. Below is my 5950x screen copy of Ryzen master, and I think the IO die is called the SOC power

 

[Exist50]

I was trying not to include servers or the DC environment, but none of US are happy or use Alder lake or Raptor lake.

So you're mad that a mainstream consumer/low end workstation chip is not a great fit for the datacenter?

And ironically, for your particular use case, the ideal configuration would look more Bergamo or Sierra Forest. Smaller cores are best for throughput for any given power or cost envelope.

My phone ? (I have an iphone 11, does that count??)

Yes, that is a 2+4 config.

So since the light case use you mention works, that does not mean its the best for everyone.

I'm not just talking about light use cases. Gaming, content creation, engineering, etc. all run quite well with hybrid. Those cover the vast majority of performance-intensive workloads for a mainstream part.

And you started by claiming that "most people" would not be satisfied with hybrid, and now you want to discount "most people" entirely?

If you want to convince me it works good for all cases, find a large group of people that know something about computers and statistics to prove they think its the future.

That "large group of people" is called the engineering departments at Intel, Apple, Qualcomm, Mediatek, Samsung, and soon enough AMD as well. Hybrid isn't the future, it's the present.

And you've made it abundantly clear that no amount of evidence is sufficient to convince you.

 

[Abwx]

Intel cores use less power in stock as well as in "out-of-the-box" settings and they are more efficient.
And you can also see that "out-of-the-box" settings are nowhere near as much "pushing to the limits" as everybody here tries to make it seem.
You can almost triple the power the intel cores can draw above "out-of-the-box" ,making it almost trice lower in efficiency.

Here you can see intel drawing 32W in single core, multiplied by 8 full cores that would be 256W which is very close to the stock power limit that intel warrants so you can have all 8 cores run at very close to full speed.
The 7950x uses 43W so a 12 core CPU running at full speed would use 516W and a 16 core CPU, well the 7950x ,running all its cores at full speed would use 688W.
And yeah, other software is going to use even more power, for intel as well as for amd.

ZEN only looks like it uses less power if you only look at the performance of the complete package, in software that doesn't need high core clocks, which is a completely valid way to choose what CPU you want, but it is not an indication of how good the cores are, or what power draw they have.

Intel Core i9-13900K Review - Power-Hungry Beast

With the Core i9-13900K, Intel delivers impressive performance. Our in-depth review confirms: Raptor Lake is the world's fastest CPU for gaming. Even in applications the processor is able to match AMD's Zen 4 Ryzen 9 7950X flagship. If only power consumption wasn't so high...

www.techpowerup.com

MP3 encoding..???..

In Handbrake ST a 13900K core use 42W while the 7950X is at about 41W.

Core i9-13900K, i7-13700K & i5-13600K: Gaming-Könige im Test: Leistungsaufnahme und Effizienz

Intel Raptor Lake im Test: Leistungsaufnahme und Effizienz / Leistungsaufnahme in Anwendungen ab Werk / Der Verbrauch steigt

www.computerbase.de

 

[TheELF]

I could be wrong about this page, but I do know the IO die has a fixed power usage in addition to the cores. Below is my 5950x screen copy of Ryzen master, and I think the IO die is called the SOC power

Yes.

And if this is fixed, and truly you always burn 20 something watt just to get into windows and look at the wallpaper not even counting the cores, then that is maybe even worse.

MP3 encoding..???..

In Handbrake ST a 13900K core use 42W while the 7950X is at about 41W.

Core i9-13900K, i7-13700K & i5-13600K: Gaming-Könige im Test: Leistungsaufnahme und Effizienz

Intel Raptor Lake im Test: Leistungsaufnahme und Effizienz / Leistungsaufnahme in Anwendungen ab Werk / Der Verbrauch steigt

www.computerbase.de

Did you link the wrong page?
They don't have any power draw results for single thread handbrake.

 

[DrMrLordX]

Wait, AMD makes the CPU report the IO power draw as part of the core power draw???????

No. It looks like TPU is reporting it that way, though.

 

[Mopetar]

It has been my observation that on this forum, the loudest voices against hybrid (or the E-cores in general) are based on an entirely emotional rejection of the concept, not because of any particular workload complaint.

Personally, I wish Intel would release something that's just e-cores so that they'd have a chip that could compete against Threadripper. Strip out the GPU and they could make something with 64-cores that doesn't take up too much more space than Raptor Lake does right now. No one is going to care if a chip like that doesn't have graphics on board or doesn't clock terribly high. The raw performance would be there and it wouldn't cost Intel a fortune to make.

The only real problem with hybrid is that you get a lowest common denominator approach to instruction support which means Intel chips have regressed in terms of AVX-512 performance. Not a huge deal for most consumers, but it was one thing they used to be able to tout. Beyond that it doesn't really matter how you get to the performance. If it looks stupid and it works it's clearly not stupid.

 

[Hulk]

Personally, I wish Intel would release something that's just e-cores so that they'd have a chip that could compete against Threadripper. Strip out the GPU and they could make something with 64-cores that doesn't take up too much more space than Raptor Lake does right now. No one is going to care if a chip like that doesn't have graphics on board or doesn't clock terribly high. The raw performance would be there and it wouldn't cost Intel a fortune to make.

The only real problem with hybrid is that you get a lowest common denominator approach to instruction support which means Intel chips have regressed in terms of AVX-512 performance. Not a huge deal for most consumers, but it was one thing they used to be able to tout. Beyond that it doesn't really matter how you get to the performance. If it looks stupid and it works it's clearly not stupid.

They could fit 41 E's on the Raptor die and it would score about 46,000 CB R23 MT running 4.3GHz. Downside of course would be the ~1140 ST score.