Intel Meteor Lake to Feature 50% Increase in Efficiency, 2X Faster iGPU

[Regenweald]

I've lived in hope since Early 2020 for a decent Ryzen APU that can do lightweight modern gaming without a dGPU.

I had Renoir, it was underwhelming old Vega architecture hampered by DDR4 rather than LPDDR4 in so many models.
I have a few 6800U Lenovo models at work, they are choked by lousy bios and pathetic cooling - with so few other options with 6800U in the UK, I've written off RDNA2 for now.

128xe2 doesn't have to be amazing, it just has to be comparable to the 12CU RDNA2 IGP in Ryzen 6000-series. AMD's product is excellent but the very limited number of design wins mean that there aren't (m)any good options available to me and Intel is just a powerhouse in terms of sales and design wins. Every major brand will have 10+ different configs in various form factors and all the stupid no-name Amazon/AliExpress OEMs will throw a few hats into the ring too.

So yeah, Battlemage IGP doesn't have to be the clear winner, it just has to be good enough and widely-available. It'll take that over "theoretically better, but not available to me in the format I want, or at a reasonable price"

Since Llano launched I've been waiting for that 'killer' GPU centric APU from AMD and I'm still waiting, It would be funny to me if the first GPU centric APU I bought was an Intel product...

 

[HisDivineOrder]

Since Llano launched I've been waiting for that 'killer' GPU centric APU from AMD and I'm still waiting, It would be funny to me if the first GPU centric APU I bought was an Intel product...

AMD doesn't compete like that when it comes to graphics. If it's about graphics, they're pretty uninterested to try. It's probably going to take Intel showing up to get them in the game.

 

[Regenweald]

AMD doesn't compete like that when it comes to graphics. If it's about graphics, they're pretty uninterested to try. It's probably going to take Intel showing up to get them in the game.

Agreed. Man I hope they show up, APUs have been a decade of meh...

 

[Chrispy_]

Um, sir, we need to have a chat on what a "chungus" is. That 16" machine is in the same body as a normal 15" ultrabook. It's nowhere near as heavy/thick as options with 3060s. It's also worth pointing out that those machines with 3060s often use plastics construction, not magnesium like business machines.

They also have a 14" model that will likely receive an update for ryzen 7000 once the "u" chips come out.

The 16" starfighter is 1.4kg, or just over 3 lbs. That's less then the 11" plastic chromebooks used in education. That's pretty light. The LG gram is 1.285 kg for the 16" model, and that is one of the lightest laptops out there. Even the 14" gram is still 1.2kg.

I think maybe your requirements are just a little unrealistic. In such small chassis you're not going to find many 28w APUs, all those intel models you pointed out will also be hamstrung by low TDP values. The other thing is if you get a 12-14" thin n light you're likely to end up with a sub 15w intel chip, like the m3 series. Do you guys not have the thinkpad x13? the hp envy x360? thinkbook 13s? thinkpad l13? thinkpad e13? I get not having choice, my ideal 14" machine will likely never exist, but dont you guys get any of the sub 14" AMD laptops? Can you import from the rest of europe?

Chungus refers mostly to the size - The weight's not to bad for a 16" but I mean a Zephyrus G14 is cheaper, faster, smaller, and a similar weight. When you have a small bag, weight is irrelevant because the 16" won't fit in it.

28W is absolutely doable in 1.2Kg laptops because I've already owned two of them - a Lenovo S540 13" Ryzen with a 35W cTDP (dual-fan) and an HP Envy with 28W in a very thin chassis. The S540 was exceptionally small, light, and powerful for under £1000. We seem to be taking steps backwards when it comes to adequately-cooled, reasonably priced AMD ultraportables. My hope with these new Intels is that there will be so many design wins (because Intel) that at least some of them won't suck!

The reason I keep mentioning ultraportables with APUs is because anything approaching 1.5kg is going to lose out to the enormous selection of good, readily-available 13-14" gaming laptops. Not just in size/portability - but also cost, because those small gaming laptops are popular and seem to have economy of scale. So giving up a dGPU and going with integrated graphics isn't just for fun; it's a massive performance sacrifice that isn't worth making unless there's a significant benefit in portability.

 

[wheresmycar]

potential ~50% efficiency and hopefully improved overclocking potential and maintaining reasonable pricing.... that would be a TREAT!!

 

[Minus Infinity]

It also comes with cool stories, bro. "50% increased efficiency", I'll believe it when I see it (and I won't).

Now of course they won't run it in that configuration for all models. It's a trade-off, they'll probably choose 25% higher performance and 25% higher efficiency in higher end models, possibly in HX models going for broke and getting 50% more performance at Raptor Lake levels of efficiency.

 

[Flanker]

Since Llano launched I've been waiting for that 'killer' GPU centric APU from AMD and I'm still waiting, It would be funny to me if the first GPU centric APU I bought was an Intel product...

LOL it would be. Phoenix point is supposed to be "it" but I guess we heard that before? If meteor lake APUs can compete, maybe we can finally see it. Still waiting for something capable of 1080 gaming for a deskmini

 

[BArms]

They're really gunning for Apple silicon efficiency.

 

[Minus Infinity]

They're really gunning for Apple silicon efficiency.

Arrow Lake is the big one. Meteor Lake is the test bed. I have high hopes for Arrow Lake both mobile and desktop.

 

[watzupken]

Agreed. Man I hope they show up, APUs have been a decade of meh...

On the contrary, I feel APUs have progressed a lot of the last 3 to 4 years. You have core count jumping from 4 that Intel happily capped us, to 8 as of now. GPU performance progressed significantly as well. As of what's available, the 680M allows 1080p gaming at reasonable FPS. Add FSR to the mix, and you get some extra performance boost. So overall, I think it's progressing well for the limitations these APUs face in my opinion.

 

[Prima.Vera]

With 2 lesser Cores, naturally they are more "efficient"...

 

[BoboOOZ]

On the contrary, I feel APUs have progressed a lot of the last 3 to 4 years. You have core count jumping from 4 that Intel happily capped us, to 8 as of now. GPU performance progressed significantly as well. As of what's available, the 680M allows 1080p gaming at reasonable FPS. Add FSR to the mix, and you get some extra performance boost. So overall, I think it's progressing well for the limitations these APUs face in my opinion.

Agreed, and the proof for the fact that APUs have come a long way is the fact that Nvidia killed the MX series, which has seen too heavy competition from APUs.

Now I agree that APUs are still not what we are expecting of them, but maybe we're expecting too much? Or too much of a niche market, or both?

 

[pressing on]

Soo, what's the reason for the 6 P-cores maximum limit?
Sure, maybe Intel could do better than that in the end, but then again it's a bit risky using a pic like this when everyone's already seen the rumors of that limit.

View attachment 282626

It's unlikely there is a 6 P-cores maximum limit.

The clue is in the sentence "... Supposedly, Meteor Lake will feature 128 EUs running 2.0+GHz compared to 96 EUs found inside Raptor Lake..." contained in this particular story. First of all, only mobile Raptor Lake CPUs have 96 EUs so we are not talking about the desktop here. Secondly, there are only 6 Raptor Lake mobile CPUs with 96 EUs, they are all 6P + 8E and they form part of the H series. There is an HX Raptor Lake series that includes 8P + 16E, 8P + 12E and 8P + 8E processors but only with 32/16 EU graphic units (because they will ship with NVIDIA mobile graphics chipsets).

So all this seems to add up to is that these particular H series Raptor Lake mobile CPUs when upgraded to Meteor Lake will retain their current 6P + 8E cores, and the graphics unit will be replaced by a 128 EU graphics tile. That's it.

And those pics... Probably from an Intel presentation on the Meteor Lake H series processors. Of the Raptor Lake H series, the top 6 are 6P + 8E there is then a 6P + 4E, some 4P + 8E and a 4P + 4E chip. So in that context the diagram makes sense, and does not have wider implications, I think.

 

[pavle]

Thank You AMD ), like come on they wouldn't be doing this most likely if AMD did not push it.

It's not only that, the liars at intel have to come clean eventually, I mean they've been selling 14nm and 10nm as new for far too long, time to move on already. Unless they have some new transistor design that doesn't dissipate any heat conducting current.

 

[Taisho]

Depending on the workload, you can say that 12400 H0 is over 100% more efficient than 13900KS. Meteor Lake downgrade confirmed.

 

[SL2]

Intel usually debuts its new processes with small chips. The first product built using the 14 nm process was Broadwell-Y: a dual core SOC. That has been the way for a while yet, and given the troubles they had with 10 nm, it's a good approach.

You're right, I forgot about that. Cannon lake was so long ago, and it took them 3,5 years to get from there to Alder lake..

 

[Sabotaged_Enigma]

I wonder how good that actually is. I mean, the power efficiency of Raptor Lake is already pretty bad, to achieve that performance and that frequencies. It's better if Intel could reduce power consumption dramatically than they increase performance.
As for the iGPU... well it's tough to say when Intel has a lot to do with their dGPU, not to mention Intel iGPU has nearly never outperformed AMD iGPU. But perhaps with the experience they've gained through developing dGPU, their iGPU has a chance to evolve.
One more thing, I hope one day Intel could make real progress in making a power-efficient enough architecture, in which case they could get rid of so-called E-cores. P+E is never a final method. It does more scores than real-world performance, otherwise they would have already applied E-cores to their busniess processors.

 

[JustBenching]

I wonder how good that actually is. I mean, the power efficiency of Raptor Lake is already pretty bad, to achieve that performance and that frequencies. It's better if Intel could reduce power consumption dramatically than they increase performance.
As for the iGPU... well it's tough to say when Intel has a lot to do with their dGPU, not to mention Intel iGPU has nearly never outperformed AMD iGPU. But perhaps with the experience they've gained through developing dGPU, their iGPU has a chance to evolve.
One more thing, I hope one day Intel could make real progress in making a power-efficient enough architecture, in which case they could get rid of so-called E-cores. P+E is never a final method. It does more scores than real-world performance, otherwise they would have already applied E-cores to their busniess processors.

Thats a very weird uneducated post. Wow

 

[BArms]

I wonder how good that actually is. I mean, the power efficiency of Raptor Lake is already pretty bad, to achieve that performance and that frequencies. It's better if Intel could reduce power consumption dramatically than they increase performance.
As for the iGPU... well it's tough to say when Intel has a lot to do with their dGPU, not to mention Intel iGPU has nearly never outperformed AMD iGPU. But perhaps with the experience they've gained through developing dGPU, their iGPU has a chance to evolve.
One more thing, I hope one day Intel could make real progress in making a power-efficient enough architecture, in which case they could get rid of so-called E-cores. P+E is never a final method. It does more scores than real-world performance, otherwise they would have already applied E-cores to their busniess processors.

I'd much rather they had 16 P cores where each core can enter "E Mode" instead myself. I wonder how much energy E cores actually save over simply throttling P Cores.

 

[JustBenching]

I'd much rather they had 16 P cores where each core can enter "E Mode" instead myself. I wonder how much energy E cores actually save over simply throttling P Cores.

They are not there to save energy. They are there to offer more performance at a given die space.

 

[watzupken]

I wonder how good that actually is. I mean, the power efficiency of Raptor Lake is already pretty bad, to achieve that performance and that frequencies. It's better if Intel could reduce power consumption dramatically than they increase performance.
As for the iGPU... well it's tough to say when Intel has a lot to do with their dGPU, not to mention Intel iGPU has nearly never outperformed AMD iGPU. But perhaps with the experience they've gained through developing dGPU, their iGPU has a chance to evolve.
One more thing, I hope one day Intel could make real progress in making a power-efficient enough architecture, in which case they could get rid of so-called E-cores. P+E is never a final method. It does more scores than real-world performance, otherwise they would have already applied E-cores to their busniess processors.

In my opinion, Alder Lake and Raptor Lake are only efficient up to the i7 model. Beyond that, it is just Intel that must win the performance crown, so much so that threw power consumption out the window. Fortunately, that only happens under very heavy multithreaded CPU load. In most cases, I think the E-cores probably runs most tasks well enough without pulling a lot of power. My guess is for Meteor Lake will leverage heavily on faster E-cores with lesser P-cores to try and achieve that efficiency target. At the end of the day, 6 fast cores will cover all gaming scenario. If you need high multithreaded performance, then the E-cores will all come online to make up for the lack of threads. This is how Intel is kind of playing with the performance numbers. After all, physical cores are better than "virtual" cores via the hyper threading technology.

For me, what I don't like is that Intel is selling us cheap E-cores which are Celeron/ Pentium Silver class chips at premium prices. The E-cores may be fast, but still much smaller, less complex and cheaper to produce. And you can clearly tell that Intel is spamming these small cores. And you can also tell that Intel is not really targeting efficiency when you have like 16 E-cores on say the i9 13900. In light loads, do we really need 16 E-cores? I am happy with my 12700K with just 4 E-cores.

 

[Sabotaged_Enigma]

I'd much rather they had 16 P cores where each core can enter "E Mode" instead myself.

Yes! That's what I want, as well.

In my opinion, Alder Lake and Raptor Lake are only efficient up to the i7 model. Beyond that, it is just Intel that must win the performance crown, so much so that threw power consumption out the window. Fortunately, that only happens under very heavy multithreaded CPU load.

Very nicely concluded.

 

[SL2]

In my opinion, Alder Lake and Raptor Lake are only efficient up to the i7 model.

While the 13900K is a bit less efficient in gaming, it's more efficient than the 13700K in CBench, which actually pushes the CPU.
Inefficient? No. Using way too much power,? Yes.



I've even seen similar comments about the 4090. Just because it's using a lot of power it doesn't mean it's inefficient.

 

[BoboOOZ]

They are not there to save energy. They are there to offer more performance at a given die space.

That. E cores are there just to optimize die space.
For the others, that ask for more e or p cores, that's a weird way of formulating the question. What matters is what performance and efficiency you are getting for the money, whether Intel or AMD achieve that with one core, one type of multicore or fifteen types of cores, that's completely irrelevant. I would dare to argue that they know a bit more what they should do than the people in this thread.

 

[Vayra86]

LOL it would be. Phoenix point is supposed to be "it" but I guess we heard that before? If meteor lake APUs can compete, maybe we can finally see it. Still waiting for something capable of 1080 gaming for a deskmini

Yeah to be honest that's where my real hope is wrt to Intel's dGPUs... better APUs that can actually game on a tiny form factor.

A fully gaming capable NUC... *drool*

That. E cores are there just to optimize die space.
For the others, that ask for more e or p cores, that's a weird way of formulating the question. What matters is what performance and efficiency you are getting for the money, whether Intel or AMD achieve that with one core, one type of multicore or fifteen types of cores, that's completely irrelevant. I would dare to argue that they know a bit more what they should do than the people in this thread.

Except CPUs don't work like that. Intel's E cores can't do all of what P cores can. So it definitely does matter how they arrive at performance. Similarly, look at AMD's X3Ds. Great at specific tasks, not so great at others. Efficiency is impacted in much the same way; will vary depending on task and CPU layout.

I'd much rather they had 16 P cores where each core can enter "E Mode" instead myself. I wonder how much energy E cores actually save over simply throttling P Cores.

E cores are about saving die space/transistor count and the die space won translates into needing less juice to power it, quite simply. E core is not about flexible cores - throttling a core already happens, but doesn't make it more efficient, its still the same floor plan, so it works on the same curve of power/performance. You can't power half a core - that's the moment you implement another core and divide the load.