Apple A17 Pro SoC Within Reach of Intel i9-13900K in Single-Core Performance

[Wirko]

I remember when Anandtech did the deep dive on the A14 in 2020, it had an eight wide decode block vs intel and AMD having 4 max.

At least Intel is now at 6 in both P and E cores. How do Snapdragons and other Arm designs compare?

 

[progste]

All this discussion about the advantages of soldered RAM makes me wonder how desktop CPUs will evolve in the future.
We're already in a time where basically 2 sizes of RAM makes sense for DDR5 (32 or 64 GB), at least for consumer desktops.
Now imagine if intel and AMD moved to an "embedded" CPU design where you buy the whole CPU+RAM block to be slotted into the motherboard, kinda like GPUs are made where you have a reference design and board partners make their own version with the chips sourced by AMD/intel.
The RAM slots could be replaced by SSDs, secondary expansion memory or other similar stuff.

 

[Ferrum Master]

The only question is why... I don't really give a crap about computational photography and AI/ML in my pocket. Running compute-intensive apps on the phone as-is is also stupid(from usability perspective). Having full-blown AAA games on the go, running natively, isn't that impressive these days either. All it needs is a proper dock with a proper desktop mode, at minimum like DEX. Then we'll talk.

Their camera is basically full of it... also the denoise engine relies on it. They have build their all API around it. Imagine an instagram wh*r5 that actually is a large user base for those flagship iphones, and allow them to be worse than the Android competition? They have to hold the bar high and make is as dumb proof as they can. AI is the only method to evolve phone camera quality further. Nothing else can be done due to basic physics. The size is just too small.

Same applies to the workstation CPU's they have. All productivity related software incorporate some sort of computing these days... let it be AI denoise etc... they don't have AMD or NVIDA cards to have compute cores now... they predicted it right to incorporate into the CPU clusters and actually the Neural Engines ain't that bad.

Imagine that backlash that your new shiny macs could do properly Adobe tasks that use compute in timid fashion? It would be a disaster.

 

[Dave65]

Yeah, Intel really should try that.

Well said.

 

[Deleted member 232534]

such a waste of resources and engineering effort

 

[trparky]

What people are failing to understand here is that if the mobile chip, the A17 Pro, can achieve these kinds of results, imagine what the performance numbers would be if Apple took the A17 Pro chip and took the gloves off by making it a future M3 chip. I have a feeling that the M3 chip would wipe the floor with a 13900K.

I'm by no means an Apple fanatic, I will always buy a PC. However, you have to hand it to their engineers... they're world class.

 

[Jism]

All this discussion about the advantages of soldered RAM makes me wonder how desktop CPUs will evolve in the future.
We're already in a time where basically 2 sizes of RAM makes sense for DDR5 (32 or 64 GB), at least for consumer desktops.
Now imagine if intel and AMD moved to an "embedded" CPU design where you buy the whole CPU+RAM block to be slotted into the motherboard, kinda like GPUs are made where you have a reference design and board partners make their own version with the chips sourced by AMD/intel.
The RAM slots could be replaced by SSDs, secondary expansion memory or other similar stuff.

Because of this, hardware would be half more expensive then it already is.

You forget that apple charge a certain tax - and if you buy a phone, it's usually a 100$ more for just 64GB / 128GB of storage extra.

There's equipment already having memory on the same chip, such as the PS3 GPU.

Apple makes CPU's quite efficient - and to be honest, i really was suprised after having to replace the Macbook 13 inch battery - to find a board the size of a shoe:

That is packing everything - from CPU to Memory and Graphics. And fits in between the screen and battery.

It was a tough job to actually accomplish since it was my first mac's battery replacement. But geezus the super tiny screws at the size of avg flees n stuff.

Apple has some very skilled engineers.

 

[Denver]

It's very interesting, just before Apple launches a new Soc, this benchmark receives an update that boosts the numbers a little compared to the old one.

Anyway, I would say that this software is at least inadequate...

 

[user556]

In that case, the A17 would win by a landslide in single threaded performance. Still, the clock speed is a part of the design and equalizing clocks doesn't make sense for two very different designs.

Comparing power consumption would make a lot of sense.

 

[mohammed2006]

waw 3nn chip is more efficient then 10nn who could have known

 

[RandallFlagg]

The big thing that everyone seems to be forgetting is the additional width in the decode block the A17 likely has for throughput vs Intel and AMD. I remember when Anandtech did the deep dive on the A14 in 2020, it had an eight wide decode block vs intel and AMD having 4 max. Even if the x86 chips can't change, I fully expect that apple has made their CPU design have a 12 or 16 wide decode block now to keep going with their big and wide over max frequency strategy.

What people are failing to understand here is that if the mobile chip, the A17 Pro, can achieve these kinds of results, imagine what the performance numbers would be if Apple took the A17 Pro chip and took the gloves off by making it a future M3 chip. I have a feeling that the M3 chip would wipe the floor with a 13900K.

I'm by no means an Apple fanatic, I will always buy a PC. However, you have to hand it to their engineers... they're world class.

Nuckles answered that question.

Broadly speaking, chip pipelines are either wide and shallow or narrow and deep. Within the same transistor budget, a wider decode with shorter pipelines means lower clocks while a narrower decode with longer pipelines means higher clocks.

Both AMD and Intel and x86 in general use narrow and deep.

AMD and Intel design for higher clocks, they are 4 (Zen) and 1+3 (Intel) wide decode pipelines. Apple was at 7 wide with the A11/A12 and 8 wide back with the A14, not sure where they are now. Samsung was at 6 a couple of years ago and generic ARM Cortex was 6.

This is why clock-for-clock comparisons are meaningless. These are high level design choices the engineers made for their use cases. Apple is designing for lower clocks and higher efficiency, AMD and Intel are mostly going for raw performance hence higher clocks.

 

[zlobby]

Yeah, another year, another ARM vs x86-64 BS from apple!

 

[Vayra86]

Pretty pathetic that tech sites still refer to the utterly useless Geekbench which has virtually zero relevance to real world applications.

But here Apple wins! So this is what matters, we need to keep the Apple does it all better fairy tale alive right

 

[qcmadness]

Apple paid double transistor count per "performance" core. Are you really willing to pay double price for that?

 

[Luminescent]

OMG, i can finally ditch my middle tower PC and edit/work in Adobe on the apple A17 BIONIC, at even has RAY-TRACING, oh wait, i cannot, it's all benchmarks and numbers, i still need that ugly, big and huge middle tower.

 

[FoulOnWhite]

OMG, i can finally ditch my middle tower PC and edit/work in Adobe on the apple A17 BIONIC, at even has RAY-TRACING, oh wait, i cannot, it's all benchmarks and numbers, i still need that ugly, big and huge middle tower.

The phone needs the power. imagine all the time you save when the phone or msg apps open 0.34 seconds quicker than the previous model.

 

[zlobby]

The phone needs the power. imagine all the time you save when the phone or msg apps open 0.34 seconds quicker than the previous model.

0.34s is actually noticeable. But I agree with the general statement.

 

[FoulOnWhite]

0.34s is actually noticeable. But I agree with the general statement.

i made up 0.34 i was being sarcastic sorry

 

[claes]

OMG, i can finally ditch my middle tower PC and edit/work in Adobe on the apple A17 BIONIC, at even has RAY-TRACING, oh wait, i cannot, it's all benchmarks and numbers, i still need that ugly, big and huge middle tower.

I mean, if adobe is your workload, you can buy an iPad or a Studio and get better performance

 

[Aquinus]

I mean, if adobe is your workload, you can buy an iPad or a Studio and get better performance

Adobe's acceleration on most Macs is pretty good. The 5600M in my MBP accelerates workloads in Photoshop and Lightroom pretty well to be completely honest.

 

[Scrizz]

Apple makes CPU's quite efficient - and to be honest, i really was suprised after having to replace the Macbook 13 inch battery - to find a board the size of a shoe:

That is packing everything - from CPU to Memory and Graphics. And fits in between the screen and battery.

It was a tough job to actually accomplish since it was my first mac's battery replacement. But geezus the super tiny screws at the size of avg flees n stuff.

Apple has some very skilled engineers.

I guess you need to take apart more ultrabooks small boards like that are pretty common.
Also, since we're talking ARM... your cellphone also packs the CPU, memory and graphics in a much smaller board.

 

[varase]

The big thing that everyone seems to be forgetting is the additional width in the decode block the A17 likely has for throughput vs Intel and AMD. I remember when Anandtech did the deep dive on the A14 in 2020, it had an eight wide decode block vs intel and AMD having 4 max. Even if the x86 chips can't change, I fully expect that apple has made their CPU design have a 12 or 16 wide decode block now to keep going with their big and wide over max frequency strategy.

CPU width has diminishing returns - I'll bet the Apple Silicon team did a shot whenever they got the out of order execution unit to execute eight instructions simultaneously.

Maybe they've added more arithmetic units so the pipeline is more symmetrical, but I can't see how going much wider will trigger that much of performance improvement.