Apple A17 Bionic SoC Performance Targets Could be Lowered

[T0@st]

Apple's engineering team is rumored to be adjusting performance targets set for its next generation mobile SoC - the A17 Bionic - due to issues at the TSMC foundry. The cutting edge 3 nm process is proving difficult to handle, according to industry tipsters on Twitter. The leaks point to the A17 Bionic's overall performance goals being lowered by 20%, mainly due to the TSMC N3B node not meeting production targets. The factory is apparently lowering its yield and execution targets due to ongoing problems with FinFET limitations.

The leakers have recently revealed more up-to-date A17 Bionic's Geekbench 6 scores, with single thread performance at 3019, and multi-thread at 7860. Various publications have been hyping the mobile SoC's single thread performance as matching that of desktop CPUs from Intel and AMD, more specifically 13th-gen Core i7 and 'high-end' Ryzen models. Naturally the A17 Bionic cannot compete with these CPUs in terms of multi-thread performance.



Apple has an excellent reputation for its chip designs, and a good portion of their customer base are not too concerned with hardware specifications, so the rumors of slightly lowered performance expectations for next's years flagship devices could be less of a headache for the engineering team. The current generation A16 Bionic outperforms Qualcomm's latest Snapdragon 8 Gen 2 in terms of pure processing power, and only lags slightly behind with its GPU's capabilities.



View at TechPowerUp Main Site | Source

 

[Space Lynx]

Still impressive if its single core can match a desktop raptor lake single core. Considering its going into mobile tablet sized devices / like the future ipad mini if I were to place bets.

I don't see a 13600k going into an ipad mini and running cool.

 

[kondamin]

I hope Samsung has more success, an other 20nm would suck especially with gpu prices being what they are

 

[Minus Infinity]

Because N3B is described as one of the worst node updates in history. I can't believe Cook would be moronic enough to use the N3B node. Nearly all companies are waiting for N3E. Given the much higher price for N3B than N4P and the puerile uplifts in transistor density and power reduction, they shoud either wait or offer iPhone 15 with N4P.

Go to semianalysis for a full review of TSMC's 3nm node and how poorly it rates.

 

[BorisDG]

Here you are some A16 benchmarks:

Geekbench 5

Geekbench 6

 

[evernessince]

Apple has an excellent reputation for its chip designs

No, not really. They've had some success in the field but they need to prove they can consistently innovate. The M1 is the really only impressive design I've seen from Apple but that is not nearly enough. The M2 was pretty disappointing.

 

[Steevo]

Apple makes really good cut and paste hardware accelerator designs for CPU's in a highly walled enviroment with the benefit of the cutting edge process node to improve efficiency. They DO NOT make general purpose CPU's which is fine if all you run is their approved software on their approved hardware until a new piece of software comes out that their hardware doesn't support and then you need to buy a new device.

My 1100T is still fine at 4.2Ghz and my 12 year old hard drives are still working, there are however a small number of games that use newer software that my CPU doesn't support natively and they either run poorly or not at all. But I have been through many, many, many phones since I built this machine. My wife has had multiple Ipads and Iphones as they "aren't supported" for general use anymore and they cannot be upgraded, tweaked, or tuned.


If you are fine paying thousands for a 3 year life cycle device, be my guest, but never whine about the cost, how bad things are for the enviroment, workers rights, or tell me that Apple is amazing and not a company making a product for profit with a lifecycle decided on before it for sale.

 

[BorisDG]

No, not really. They've had some success in the field but they need to prove they can consistently innovate. The M1 is the really only impressive design I've seen from Apple but that is not nearly enough. The M2 was pretty disappointing.

Just because M2 is A15 and M1 was A14. A14 and 15 are very very similar. More similar than A15 to A16 imo.

 

[Garrus]

CPU is fine. It's the GPU where Apple is falling behind. We still expect big things there with the new GPU design and 3nm.

 

[trsttte]

Doesn't matter how fast you're going if you're going in the wrong direction

I can't really find a workload that requires more than what the A16 already does because Apple doesn't allow for that workload to exist (the pro's are using M series and even them are massivily over powered for what they are able to do within their walled gardens)

 

[freeagent]

I am still ok with my XS Max 256

Battery is getting a bit old though..

 

[evernessince]

I highly disagree with this take. The M2 was pretty much only a refinement SoC. It wasn't meant to be significantly better than the M1.

That's not really a valid excuse when both AMD and Intel get more out of their refinement "tock" generations.

The name also implies to customers that it's a generation newer. Really the difference isn't even going to be on par with CPU or GPU mid-generation refresh gain. Apple is implying to customers that there will be big gains when in reality they are getting an extremely tiny bump.

But it's Apple so people will defend it tooth and nail.

 

[Flanker]

Considering my 4yo android phone is still doing fine. Perhaps performance isn't that much of a deal for mobile phones these days?

 

[lemonadesoda]

M1/M2 is more than powerful enough for mobile devices. Moar powerz is not needed for what 99% of users do 100% of the time.

But there is always room for improvement in the performance per watt , or indeed the „do the work asap, go to idle asap“ method. And whatever other battery extending tricks can be found.

Are screens, wifi, 4/5G, gps the weaker link? Should mire effort be made in making those more power efficient?

There are definitely gains to be made by the OS thread scheduler. When i put my phone down , if i leave too many apps open , esp navigation apps, they drain the battery really fast. They could make better use of sensor awareness to put the device into idle; app specific.

 

[BoboOOZ]

Considering my 4yo android phone is still doing fine. Perhaps performance isn't that much of a deal for mobile phones these days?

It's the same with PCs, depends on the apps that you are running. If all you do is web browsing and mail, old stuff is fine. If you do desktop mode work, gaming, emulation, photo or video editing, well you start to need more muscle.

 

[zlobby]

Doesn't matter how fast you're going if you're going in the wrong direction

I can't really find a workload that requires more than what the A16 already does because Apple doesn't allow for that workload to exist (the pro's are using M series and even them are massivily over powered for what they are able to do within their walled gardens)

That!

 

[stimpy88]

Apple have not made a meaningful IPC increase in years. They have run out of steam.

 

[Redwoodz]

Boil it down further.... Apple hasn't designed much., just 4 rounded corners.

Apple and Nvidia are claiming ARM's just due.

 

[Gooigi's Ex]

That's not really a valid excuse when both AMD and Intel get more out of their refinement "tock" generations.

The name also implies to customers that it's a generation newer. Really the difference isn't even going to be on par with CPU or GPU mid-generation refresh gain. Apple is implying to customers that there will be big gains when in reality they are getting an extremely tiny bump.

But it's Apple so people will defend it tooth and nail.

I’ve seen more people defend Windows(or Android in the mobile space) than Apple. No matter what tech website I go to, they constantly shit on Apple. When it comes to walled garden, Nvidia is more acceptable than Apple but Apple gets the hate more.

 

[BoboOOZ]

I’ve seen more people defend Windows(or Android in the mobile space) than Apple. No matter what tech website I go to, they constantly shit on Apple. When it comes to walled garden, Nvidia is more acceptable than Apple but Apple gets the hate more.

I have to disagree, we shit on Nvidia a lot, too . It's just that, in terms of vertical integration and monopolistic practices, Nvidia cannot do as much as Apple, although Jensen definitely yearns for it. It doesn't have that closed environment yet, and without the ARM deal, it looks hard to achieve it in the near future.

 

[Aleksandar_038]

It's the same with PCs, depends on the apps that you are running. If all you do is web browsing and mail, old stuff is fine. If you do desktop mode work, gaming, emulation, photo or video editing, well you start to need more muscle.

Gaming on phone? OK, some people like it.
But regarding work, anything bigger than sending e-mail is painful, it is less than 1% of users. Same for photo and video editing...

However, faster "mobile" CPUs are very welcome for tablets and light laptops... Apple already shaken the market with M1, so now they are facing bigger and bigger expectations

 

[evernessince]

I’ve seen more people defend Windows(or Android in the mobile space) than Apple. No matter what tech website I go to, they constantly shit on Apple. When it comes to walled garden, Nvidia is more acceptable than Apple but Apple gets the hate more.

Add Microsoft in there and we can bash all of the above as well. Not a fan of any of those companies.

 

[Punkenjoy]

A lot of people are over exited by news comers that catch up very quickly. Then they suddently lose their hype when the newcomers have an hard time maintaining the same speed.

A lot of mecanism to improve performance have been well documented and many people know how to implement them. This is why the first phase of catching up is always quick.

The problem start when you have to find news ways of improving performance. You can't just reuse already knows trick and you need to come up with your own things.

And not just one time, but every revision of your architecture.

This is where Apple is right now. Doesn't means they won't provide big boost of IPC in the future, but they will have to find new ways of doing it. But they are now in uncharted territory.

 

[BoboOOZ]

Gaming on phone? OK, some people like it.
But regarding work, anything bigger than sending e-mail is painful, it is less than 1% of users. Same for photo and video editing...

However, faster "mobile" CPUs are very welcome for tablets and light laptops... Apple already shaken the market with M1, so now they are facing bigger and bigger expectations

Actually, I do work on a high end phone with a desktop mode. Just use a USB c dock or a lapdock and you're set . Otherwise why pay one grand for a smartphone, if it's just for emails? You can do that on a potato.
And if you look carefully, you have more powerful CPU on flagship phones than on tablets.
Also, if you're filming and taking photos on your phone, it makes sense to edit them on the phone.
If you're buying a high end phone just for emails, well, you do you then

 

[Steevo]

A lot of people are over exited by news comers that catch up very quickly. Then they suddently lose their hype when the newcomers have an hard time maintaining the same speed.

A lot of mecanism to improve performance have been well documented and many people know how to implement them. This is why the first phase of catching up is always quick.

The problem start when you have to find news ways of improving performance. You can't just reuse already knows trick and you need to come up with your own things.

And not just one time, but every revision of your architecture.

This is where Apple is right now. Doesn't means they won't provide big boost of IPC in the future, but they will have to find new ways of doing it. But they are now in uncharted territory.

Meaningful IPC increases are almost at an end with dedicated hardware, increasing cache sizes, larger and faster memory pools, now its a arms race of process technology and Ghz. Almost all new hardware could be 50% more efficient if clocked down 15%, but its the trade off of speed VS power that every company has to make, there are small tricks like artificially decreasing transistor density in hot sopt areas to gain speed but that comes at extra cost per die.