AMD Zen 5 "Strix Point" Processors Rumored To Feature big.LITTLE Core Design

[Uskompuf]

AMD launched the 7 nm Zen 3 microarchitecture which powers Ryzen 5000 processors in late 2020, we expect AMD to follow this up with a Zen 3+ on 6 nm later this year and a 5 nm Zen 4 in 2022. We are now beginning to receive the first rumors about the 3 nm Zen 5 architecture which is expected to launch in 2024 in Ryzen 8000 series products. The architecture is reportedly known as "Strix Point" and will be manufactured on TSMC's 3 nm node with a big.LITTLE core design similar to the upcoming Intel Alder Lake and the Apple M1. The Strix Point lineup will consist exclusively of APUs and could feature up to 8 high-performance and 4 low-performance cores which would be less than what Intel plans to offer with Alder Lake. AMD has allegedly already set graphics performance targets for the processors and that they will bring significant changes to the memory subsystem but with rumors for a product 3 years away from launch take them with a healthy dose of skepticism.



View at TechPowerUp Main Site

 

[Fouquin]

Incoming "Strix Point? LOL AMD must be working with ASUS on naming LOLOLOL" jokes.

It'll be interesting to see how and if x86 makes the full transition to these core configs. Software will need to catch up but that's just a universal constant at this point. The best built software framework is still half a decade behind the hardware.

 

[Keullo-e]

Incoming "Strix Point? LOL AMD must be working with ASUS on naming LOLOLOL" jokes.

I was going to say that Asus' marketing team must like this..

Anyway, I wouldn't mind if all AMD processors would have an IGP as well.

 

[Vayra86]

2024. 3nm

And it doesn't even seem far fetched given what TSMC has been reporting. Damn.

Incoming "Strix Point? LOL AMD must be working with ASUS on naming LOLOLOL" jokes.

Puzzling indeed. Maybe this is where their APUs finally 'take off'?

 

[Mussels]

Are they all x86 cores or are some ARM, is the question


there seems to be the beginnings of a transition happening

 

[watzupken]

If the Big Little cores apply to the mobile APUs, I think it will make sense. It is always good to run a processor with low power whether its on desktop or mobile, but the impact is probably greater on the mobile side of things due to limited battery capacity. On the desktop, low power consumption is nice to have, but I feel is a waste of die space when you can use it for more performance cores.

 

[zenlaserman]

Are they all x86 cores or are some ARM, is the question


there seems to be the beginnings of a transition happening

I think it will more likely be the "little" x86 procs like Jaguar and Atom that will make up the Little, heh. AMD and Intel can do some crazy things with those with a small power envelope.

Always thought it would be neat if AMD brought back the old Phenom II on modern lithography, they would be tiny and sip power at 3-4GHz. All these procs good enough for most apps.

 

[Vya Domus]

Are they all x86 cores or are some ARM, is the question

Why would you even want to have two cluster with entirely different ISAs ?

 

[1d10t]

Highest end would be ROG Peak and mainstream are TUF Canyon?
big.LITTLE on mobile have bigger impact than it does on desktop. I think this is a sensible step to stem ARM dominance , while still maintaining high performance side.

 

[Wirko]

Why would you even want to have two cluster with entirely different ISAs ?

In 2021: for no reason at all
In 2024: it's an interesting question. The world of computing may become much more heterogeneus by then, with Arm more prominent in laptops and with more use cases that require running both x86 and Arm applications at the same time. That can be done either by means of fat binaries, translation (Arm running x86 code as well as x86 running Arm code), or processors with both kinds of cores.

 

[NuCore]

Some of the commenters are hypocrites. That's why I made a meme that describes it well

 

[1d10t]

Some of the commenters are hypocrites. That's why I made a meme that describes it well

Made an account just for that? If Intel did prove their 20% IPC claim at Rocket Lake, we wouldn't ridiculed them much. After seeing RKL launch disaster, and they promised bring "another" 20% increase in IPC to Elder Lake in the future, wouldn't that just bring them back to Comet Lake?

 

[NuCore]

Made an account just for that? If Intel did prove their 20% IPC claim at Rocket Lake, we wouldn't ridiculed them much. After seeing RKL launch disaster, and they promised bring "another" 20% increase in IPC to Elder Lake in the future, wouldn't that just bring them back to Comet Lake?

I have been following TPU for many years, and today I decided to register on the forum to be able to comment, not just read news and reviews from TPU - do you have a problem with that? It is sad to see you live the lives of other people on the forum

PS
Alder Lake not Elder Lake

 

[TheDeeGee]

Some of the commenters are hypocrites. That's why I made a meme that describes it well View attachment 198400

Atleast Intel should work out of the box.

AMD is a gamble with Memory and WHEAs.

 

[GerKNG]

Atleast Intel should work out of the box.

AMD is a gamble with Memory and WHEAs.

This!
Ryzen is bascially a Mr. Meeseeks on a PCB.

 

[DeathtoGnomes]

@Uskompuf I see what you did there, clever title.

AMD is a gamble with Memory and WHEAs.

what gamble? thats what a CVL is for.

If the Big Little cores apply to the mobile APUs, I think it will make sense. It is always good to run a processor with low power whether its on desktop or mobile, but the impact is probably greater on the mobile side of things due to limited battery capacity. On the desktop, low power consumption is nice to have, but I feel is a waste of die space when you can use it for more performance cores.

I think this will be more for the cheap pre-built desktop economy demograph, and laptops that benefit more from low power.

 

[medi01]

8 small cores in Adler Lake sounds crazy.
If there is something to keep 8 cores busy, why not switch to big cores instead, cough?

Why would you even want to have two cluster with entirely different ISAs ?

Apple is doing it out of greed, so gotta be cool. #3.5mmAudioJacks

 

[1d10t]

I have been following TPU for many years, and today I decided to register on the forum to be able to comment, not just read news and reviews from TPU - do you have a problem with that? It is sad to see you live the lives of other people on the forum

PS
Alder Lake not Elder Lake

First post is a meme, second post straight to personal, you made it clear who you really are.

Atleast Intel should work out of the box.

Which box? Haswell is already long overdue.

 

[Luminescent]

At this point AMD is milking it, TSMC 5nm is available for some time but they drag it out to 2022.
Why bother, scalpers, miners and whatever stupid thing will pop up could make future chips impossible to obtain at normal prices.

 

[Calmmo]

Eh, i can think of more exciting things for the PC than low performance power efficient cores..
I can already see the poor performance threads from users when the magnificent Microsoft scheduler decides to do things less than perfectly

 

[First Strike]

In 2021: for no reason at all
In 2024: it's an interesting question. The world of computing may become much more heterogeneus by then, with Arm more prominent in laptops and with more use cases that require running both x86 and Arm applications at the same time. That can be done either by means of fat binaries, translation (Arm running x86 code as well as x86 running Arm code), or processors with both kinds of cores.

x64 and ARMv8 doesn't even have the same memory order model. They have ZERO possibility of inter-core communication. Since they are fundamentally not co-existable, why not solder an extra Raspberry chip on your board?

 

[Operandi]

8 small cores in Adler Lake sounds crazy.
If there is something to keep 8 cores busy, why not switch to big cores instead, cough?


Apple is doing it out of greed, so gotta be cool. #3.5mmAudioJacks

No there is two reasons why they are doing it. To unify their code base between their two OSs IOS and Mac OS. And secondly because they can design a better chip than Intel and they sick of being dragged down by Intel's internal issues. Talk shit about Apple if you want but they design solid hardware and the M1 chip is very a impressive CPU. They probably could have worked with AMD as partner for desktop CPUs if wasn't for the first point.

First post is a meme, second post straight to personal, you made it clear who you really are.



Which box? Haswell is already long overdue.

No shit, Rocket Lake was a rushed disaster that didn't need to happen. Zen 1 was a pretty much a from the ground up new design on a new platform and AMD (who was extremely resource strapped btw) entering a market that they had to concede for several years, so yeah some bumps along the way are to be expected.

 

[Deleted member 205776]

Some of the commenters are hypocrites. That's why I made a meme that describes it well View attachment 198400

Welcome to these forums.

The opposite can be said whenever both companies experience issues. When it's Intel, they say "oh it'll be fixed whatever". When AMD has an issue, they go "AMD is truly incompetent".

Atleast Intel should work out of the box.

AMD is a gamble with Memory and WHEAs.

No memory or WHEA problems once I undervolted the retarded amount of overvoltage my board applied to my SoC and its derivative voltages. It was even worse on my Gigashite board.

Imagine thinking you need 1.1v on the SoC, 1.1v on both VDDGs and 1v on the VDDP for just 3600 MT/s. Gigabyte moment. Not to mention the board died on me shortly afterwards...

 

[NuCore]

First post is a meme, second post straight to personal, you made it clear who you really are.



Which box? Haswell is already long overdue.

Somehow, almost everyone forgets how AMD rested on its laurels after the Athlon 64 was released. Intel rethought the wrong Pentium 4 policy and kicked AMD's ass with the Core 2 Duo / Quad series, and later the Core series. What did AMD do? It created its counterpart Pentium 4 focused on empty GHz and for years it was not able to create a processor competing with Intel. Suddenly they succeeded after many years and everyone forgets that the path to AMD's current position was not straightforward and similar to Intel's current situation. Intel hasn't collapsed and I'm just waiting for the same prophets to come back to Intel and laugh at AMD, because that's what they can do - stick with the stronger at the moment and laugh at the opponent (it's hypocrisy).

 

[dragontamer5788]

So the general issue is that Windows (and Linux / Android) don't really have much to gain from little cores yet. What kind of thread/process should go on a little core? Its a complicated question: it seems that big cores are more efficient at higher GHz, while little cores really benefit if you downclock them to 200MHz or slower.

The scheduler has to not only pick the threads/processes that go on big vs little cores, but also pick what GHz (or MHz) to run the processor at. There's a bit of a "race to idle" problem. If you spend 1000ms running a task on a little core, you probably would use more power than if you had run the task on a big-core for 100ms and then slept for 900ms afterwards.

But if the sleep is interrupted after 500ms, your calculus changes yet again. So you need to predict the future and know when to turn on big cores (or turn them off), and same thing with when to clock little cores up or down.

---------

Answering these scheduling problems adequately for sizable gains in efficiency is not very easy. Its a lot easier when you have all the same kind of core: the answer in that case is simple. Just estimate the power usage per core and keep the clock as low as reasonable.