Question Raptor Lake - Official Thread

[Hulk]

Since we already have the first Raptor Lake leak I'm thinking it should have it's own thread.
What do we know so far?
From Anandtech's Intel Process Roadmap articles from July:

Built on Intel 7 with upgraded FinFET
10-15% PPW (performance-per-watt)
Last non-tiled consumer CPU as Meteor Lake will be tiled

I'm guessing this will be a minor update to ADL with just a few microarchitecture changes to the cores. The larger change will be the new process refinement allowing 8+16 at the top of the stack.

Will it work with current z690 motherboards? If yes then that could be a major selling point for people to move to ADL rather than wait.

 

[igor_kavinski]

die size is huge, but Intel have own fabs so i guess it isn't that terrible.

Yeah. They are used to wasting sand.

 

[igor_kavinski]

OEMs would appreciate having an shiny newer generation name associated with it.

Customers won't blame the OEM. They will blame AMD for deceptive marketing practices. Granted, most of these customers are not tech literate. But it feels wrong. I hate to be the one to explain to someone asking me for advice on why 5600U is wayyy better for gaming than 5500U. They will more likely go with Intel then because Intel isn't muddying things up like this.

 

[jpiniero]

Customers won't blame the OEM. They will blame AMD for deceptive marketing practices. Granted, most of these customers are not tech literate. But it feels wrong. I hate to be the one to explain to someone asking me for advice on why 5600U is wayyy better for gaming than 5500U. They will more likely go with Intel then because Intel isn't muddying things up like this.

Speaking of which, I don't think the Raptor Lake IGP has changed. Which means the desktop version is still behind the laptop one.

 

[John Carmack]

The 5950x has similar power consumption to the 5800x in Cinebench because it's all core boost is substantially lower; 3.9ghz vs 4.5ghz for the 5800x at stock. Zen 3's operating sweet spot in terms of performance per watt is the mid to upper 3ghz range.

The 13900K on the other hand doubled the efficiency cores, significantly increased the core frequencies, expanded the L2 and L3 cache for both performance and efficiency cores without a substantial increase in the power draw, which to me is impressive.

I forgot to mention the savings from power delivery improvements which can be pumped back into the chip for more speed.

The only problem with comparisons like this, is that Zen 4 will be out before Raptor lake, and it also has a lot of improvements. Unfortunately there are very few performance leaks of Zen 4 to compare to.

If anything this is just more proof the latest Raptor Lake 'leak' (6 GHz overclocked chiller demo) is indeed seeded by the marketing machine. The other guy seems to think these are genuine leaks because once in motherboard makers hands it's inevitable but...

Ryzen 7000 is probably going to launch anywhere from 3-5 weeks ahead of Raptor Lake. It's in the hands of the same companies but how many 'leaks' have we seen with tests showing max clock potential, memory overclocks, or AVX-512 performance? Next to nothing.

We see this information out there because someone in marketing wants us to see it. A real leak would be the data from the Gigabyte ransomware hack. You can be sure that didn't originate from any marketing drone at the company.

And while you guys argue about naming schemes, Comet Lake-U and Ice Lake-U says hello.

 

[LightningZ71]

Customers won't blame the OEM. They will blame AMD for deceptive marketing practices. Granted, most of these customers are not tech literate. But it feels wrong. I hate to be the one to explain to someone asking me for advice on why 5600U is wayyy better for gaming than 5500U. They will more likely go with Intel then because Intel isn't muddying things up like this.

Or why 5700u is better than 5600u in most cases for gaming while typically being priced lower by a notable margin, at least until very recently. Its as if the numbers do mean something...

 

[DrMrLordX]

I wouldn't use that word for what they do. The correct word is DECEPTION.

AMD did tell us all what they were doing. It was in all the specs. Intel will do the same. I wouldn't say it's deceptive. Maybe a little disappointing. At least in the case of AMD, they did (and still do) have some wafer restrictions. Intel either has a lot of left over unsold Alder Lake dice to get rid of, or has some other underlying reason to continue selling Alder Lake as 13000-series chips.

That being said, 6p+8e for like $200 wouldn't be a terrible deal for someone looking for budget computing power. Sadly it will still have all the scheduler warts of Alder Lake. Raptor may too, we don't know yet.

 

[Timmah!]

I forgot to mention the savings from power delivery improvements which can be pumped back into the chip for more speed.



If anything this is just more proof the latest Raptor Lake 'leak' (6 GHz overclocked chiller demo) is indeed seeded by the marketing machine. The other guy seems to think these are genuine leaks because once in motherboard makers hands it's inevitable but...

Ryzen 7000 is probably going to launch anywhere from 3-5 weeks ahead of Raptor Lake. It's in the hands of the same companies but how many 'leaks' have we seen with tests showing max clock potential, memory overclocks, or AVX-512 performance? Next to nothing.

We see this information out there because someone in marketing wants us to see it. A real leak would be the data from the Gigabyte ransomware hack. You can be sure that didn't originate from any marketing drone at the company.

And while you guys argue about naming schemes, Comet Lake-U and Ice Lake-U says hello.

I do believe as well, even if its genuine leaks, its all happening with Intels blessing. They want to build hype.

AMD, on other hand, i am curious how will turn out. Will it be somewhat slower, but AMD cool with it, cause of far superior effectivity? Or will it be even better than rumored, and thats a reason for all this 6GHz 380W Intel insanity?

 

[coercitiv]

Or will it be even better than rumored, and thats a reason for all this 6GHz 380W Intel insanity?

6Ghz is the new 5Ghz. Free hype

 

[CakeMonster]

Don't like the naming, but at least there's more models with E-cores in the lineup, which will give even the most clueless buyers more longevity.

 

[biostud]

We don't even know whether it's a further refined version of Intel 7 from what was shipped with Alder Lake.

Intel 7+? (I dare you Intel)

 

[biostud]

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

 

[CakeMonster]

Not much... yet? As I said, I think the E-cores will do wonders for longevity of these CPU's. Not that they will be blazing fast on Windows 12 in 2026, but for people who are too poor to upgrade (or too lazy) there will be threads there to somewhat satisfactorily take care of the work that is currently stalling 2c/4t, 4c/4t, and increasingly 4c/8t CPU's.

 

[DrMrLordX]

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

In theory, they're supposed to pick up background threads to leave the P-cores free for whatever application has focus. In practice it tends to leave a lot of P-cores idle when background threads might need them and foreground applications might not.

 

[Justinus]

In theory, they're supposed to pick up background threads to leave the P-cores free for whatever application has focus. In practice it tends to leave a lot of P-cores idle when background threads might need them and foreground applications might not.

This would mean nothing if there were simply more performance cores.

The main benefit of the E cores is supposed to be being able to handle regular and background tasks while being more energy efficient, like in a laptop to boost battery life. No real point to them on a desktop, except corespamming them to boost multithread benchmarks IMO.

 

[Zucker2k]

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

You certainly have. Have you seen 5950x vs 12600k in many lightly threaded workloads? That's 16 full Zen 3 cores vs 6p Golden Cove cores and 4 e-cores but the 12600k holds it own. This is the area best suited to the "average" user.

The e-cores are for multithreaded scenarios where they complement the big cores for extra ooomph. As the user above has pointed out, that should help the "average" a lot whenever throughput grunt is required.

Of course, the 12700x and 12900x provide even more benefit in this regard.

 

[DrMrLordX]

This would mean nothing if there were simply more performance cores.

The main benefit of the E cores is supposed to be being able to handle regular and background tasks while being more energy efficient, like in a laptop to boost battery life. No real point to them on a desktop, except corespamming them to boost multithread benchmarks IMO.

In general I agree with you on all points. ARM designs have somehow managed to make "small" cores relevant on laptops and desktops, but Intel's implementation leaves something to be desired. It's not to say that more "big" cores wouldn't be preferable in ARM/Apple designs, per se. It's just that the "medium"/"small" cores in ARM designs don't seem to get in the way as much as Intel's e-cores. Also it doesn't help that Gracemont in particular seems to be more area-efficient than Golden Cove/Raptor Cove than power efficient.

 

[Asterox]

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

Not for gaming, or R5 7600X will be faster in gaming vs any "old/new Alder Lake=Raptor lake i5" with added more E Cores.

 

[dullard]

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

The concept is simple: The E-cores run background and multitasking tasks, leaving the P-cores cool and fully available for your foreground tasks. Cool means more turbo time. Fully available means the P-cores don't have to switch back and forth between tasks (meaning snappier and faster performance).

However, the current Alder Lake implementation is awful though when you only have 4 E cores and most software has not yet been recompiled to handle the different cores properly. That will work itself out over time. But until then, just avoid any chip with 4 E cores. Meaning don't buy the 12700K, 12700KF, 12700, 12700F, 12700T, 12600K, 12600KF, or 13400 (Assuming the rumor is true about core counts on Raptor Lake).

 

[shady28]

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

Your logic might make some kind of sense if the 12600K wasn't beating the 5950X at common day to day desktop tasks. Those would be things like Browser performance, office functions, and yes even gaming.

About the only place you'll find a $550 5950X beating the $260-$280 12600K is encryption, some (h.265/h.265) encoding, and rendering. Even in those use cases, the 6 P-core 12600K usually matches the 12 big core 5900X.

That would be like the 5600X laying waste to the 10900K. Only, that never happened.

I mean, do we really have to go throw these charts up again?

 

[Carfax83]

Not for gaming, or R5 7600X will be faster in gaming vs any "old/new Alder Lake=Raptor lake i5" with added more E Cores.

I'm curious, what makes you so confident that Zen 4 is going to be faster than the equivalent Raptor Lake part in games?

Alder Lake to me is stronger than Zen 3 in gaming, particularly CPU bound games and Raptor Lake looks like it's going to shore up Alder Lakes weak points in the form of increased cache capacity and performance (plus a better IMC) which was Zen 3s biggest advantage over the midrange Alder Lake CPUs which had less cache than the higher models

The most I see is Zen 4 achieving parity with Raptor Lake in cache bound games but losing handedly in CPU bound games. So basically the status quo will not change.

 

[szrpx]

Your logic might make some kind of sense if the 12600K wasn't beating the 5950X at common day to day desktop tasks. Those would be things like Browser performance, office functions, and yes even gaming.

About the only place you'll find a $550 5950X beating the $260-$280 12600K is encryption, some (h.265/h.265) encoding, and rendering. Even in those use cases, the 6 P-core 12600K usually matches the 12 big core 5900X.

That would be like the 5600X laying waste to the 10900K. Only, that never happened.

I mean, do we really have to go throw these charts up again?

They asked about the E-cores, you answered with the 12600K beating the 5950x. Is this supposed to imply that E-cores are somehow responsible for this?

For the average user, doing the three things that you described: Browsing the web, office functions and gaming, all benefit from single thread performance. So the 12600K beating the 5950x has everything to do with Goldencove being better than Zen 3. Gracemont is more or less irrelevant in those tasks.

So to answer biostud's question: Gracemont cores exist to boost MT performance, while being area efficient. That's basically it. In their current implementation, that's their only real advantage. They can be power efficient, but you need to run them in their V/F sweet spot which sits somewhere around 2.5 to 3.2 GHz or thereabouts. But then you have Skylake level cores running at 2.5 to 3 GHz, which isn't great either.

Edit: The E cores will get better, I'm commenting on the current form as seen in Alderlake.

 

[Hulk]

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

I don't know if I'm the average user but I like having the E cores in my 12700K. I always have all 8 P cores available for the foreground application I'm interacting with but I can still complete work (video rendering, audio multitrack rendering, photo RAW conversion, etc..) in the background. Since all of the background tasks are relegated to the E's I have full P power available at my fingertips at all times. It's important when playing back a multitrack audio file in my DAW with lots of plugs, editing photos, and things like that.

My only complaint is that my 12700K doesn't have enough E's to make this really productive. 4 just isn't enough. I think 8 would work really well. 16 would be fantastic.

I'm hoping the 13900K is a simple plug and play operation from my 12700K.

 

[Asterox]

I'm curious, what makes you so confident that Zen 4 is going to be faster than the equivalent Raptor Lake part in games?

Alder Lake to me is stronger than Zen 3 in gaming, particularly CPU bound games and Raptor Lake looks like it's going to shore up Alder Lakes weak points in the form of increased cache capacity and performance (plus a better IMC) which was Zen 3s biggest advantage over the midrange Alder Lake CPUs which had less cache than the higher models

The most I see is Zen 4 achieving parity with Raptor Lake in cache bound games but losing handedly in CPU bound games. So basically the status quo will not change.

Well, we know i5 12600K vs R5 5600X they have very similar gaming performance.

Intel Core i5-12600K Review: 5600X Defeated

The Core i5-12600K is Intel's latest mainstream CPU and a direct competitor to AMD's popular Ryzen 5 5600X. The Alder Lake chip packs 6 P-cores and 4...

www.techspot.com

i5 12600K, 6P+4E

i5 13600K, 6P+8E, this is hm Alder Lake with 4mb more Cache. For gaming, you look only at 6P Cores same as i5 12600K

R5 7600X, if the rumors are legit

- 700mhz higher Singlecore CPU boost or 5.3ghz
- 5-5.1ghz all cores boost, or 500-600mhz higher vs R5 5600X
- 8-10% higher IPC

 

[shady28]

They asked about the E-cores, you answered with the 12600K beating the 5950x. Is this supposed to imply that E-cores are somehow responsible for this?
<SNIP>

I don't need to see anything beyond that part of your response because it's a false misdirection, below is the statement I was replying to.

Here I'll bold it for you so you don't miss it again.

Maybe I've missed something, but what benefit does the average desktop user have of the E-cores? I can understand adding tons of them to compete with 5900X and 5950X, but bellow that segment doesn't they just seem to complicate things unnecessarily?

If you look at how something like the 12600K performs in average desktop user use cases (which is to say, superbly, crushing much higher tier Zen 3 chips), what anyone 'thinks' about the e-cores kind of pales next to that reality.

Since we're going down this road again, I'll once again show what it is for a top line chip to get smacked down in typical day to day use cases :

12600K 13.5% faster than 5950X in Octane / Web browser benchmark :



12600 > 10% faster than 5950X on all MS Office benchmarks :





Faster in Photoshop :



Faster in video editing:



Faster in games :

 

[szrpx]

I don't need to see anything beyond that part of your response because it's a false misdirection, below is the statement I was replying to.

Here I'll bold it for you so you don't miss it again.




If you look at how something like the 12600K performs in average desktop user use cases (which is to say, superbly, crushing much higher tier Zen 3 chips), what anyone 'thinks' about the e-cores kind of pales next to that reality.

Since we're going down this road again, I'll once again show what it is for a top line chip to get smacked down in typical day to day use cases :

12600K 13.5% faster than 5950X in Octane / Web browser benchmark :

View attachment 66386

12600 > 10% faster than 5950X on all MS Office benchmarks :

View attachment 66387

View attachment 66388

Faster in Photoshop :

View attachment 66389

Faster in video editing:

View attachment 66390

Faster in games :
View attachment 66391

....I agreed with you. The 12600K is faster than all of Zen 3 in those tasks. But it's because of the P-cores, not the E-cores.

Only reason I say this is because that's what Biostud was asking about. What the E-cores provide. The truth is not much, they boost MT perf at the benefit of Intel's bottom line due to BoM. So if you don't really use programs that benefit from more MT performance, the E-cores don't really give you much.