Discussion Apple Silicon SoC thread

Page 334 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Eug

Lifer
Mar 11, 2000
23,798
1,370
126
M1
5 nm
Unified memory architecture - LP-DDR4
16 billion transistors

8-core CPU

4 high-performance cores
192 KB instruction cache
128 KB data cache
Shared 12 MB L2 cache

4 high-efficiency cores
128 KB instruction cache
64 KB data cache
Shared 4 MB L2 cache
(Apple claims the 4 high-effiency cores alone perform like a dual-core Intel MacBook Air)

8-core iGPU (but there is a 7-core variant, likely with one inactive core)
128 execution units
Up to 24576 concurrent threads
2.6 Teraflops
82 Gigatexels/s
41 gigapixels/s

16-core neural engine
Secure Enclave
USB 4

Products:
$999 ($899 edu) 13" MacBook Air (fanless) - 18 hour video playback battery life
$699 Mac mini (with fan)
$1299 ($1199 edu) 13" MacBook Pro (with fan) - 20 hour video playback battery life

Memory options 8 GB and 16 GB. No 32 GB option (unless you go Intel).

It should be noted that the M1 chip in these three Macs is the same (aside from GPU core number). Basically, Apple is taking the same approach which these chips as they do the iPhones and iPads. Just one SKU (excluding the X variants), which is the same across all iDevices (aside from maybe slight clock speed differences occasionally).

EDIT:



M1 Pro 8-core CPU (6+2), 14-core GPU
M1 Pro 10-core CPU (8+2), 14-core GPU
M1 Pro 10-core CPU (8+2), 16-core GPU
M1 Max 10-core CPU (8+2), 24-core GPU
M1 Max 10-core CPU (8+2), 32-core GPU

M1 Pro and M1 Max discussion here:


M1 Ultra discussion here:


M2 discussion here:


Second Generation 5 nm
Unified memory architecture - LPDDR5, up to 24 GB and 100 GB/s
20 billion transistors

8-core CPU

4 high-performance cores
192 KB instruction cache
128 KB data cache
Shared 16 MB L2 cache

4 high-efficiency cores
128 KB instruction cache
64 KB data cache
Shared 4 MB L2 cache

10-core iGPU (but there is an 8-core variant)
3.6 Teraflops

16-core neural engine
Secure Enclave
USB 4

Hardware acceleration for 8K h.264, h.264, ProRes

M3 Family discussion here:


M4 Family discussion here:

 
Last edited:

Eug

Lifer
Mar 11, 2000
23,798
1,370
126
Exactly. We're finally getting all the ports everyone has been clamoring for. Functionality over form, finally.
Well, Gurman's rumour suggested that there will be one Mac mini model with only 3 USB-C ports. This would actually be less USB ports than the current 2 USB-C + 2 USB-A. Similarly, the 5-port model would be less USB ports than the current 4 USB-C + 2 USB-A.

Anyhow, we shall see how this all shakes out in terms of functionality, memory options, and cost.

Will it be 12 or 16 GB minimum? What will the upgrade options be? For example, if it starts at 16 GB, will there be a 24 GB M4 Pro model, or will it be a costly jump straight to 32 GB?

Whatever the case, it seems likely the configurations of the 5-port USB-C model will be structured to heavily promote the upsell to the Mac Studio.

BTW, for the MacBook Pros, there are now rumours that Apple is aiming to slim those down again in the next few years.
 

ikjadoon

Senior member
Sep 4, 2006
205
445
146
BTW, for the MacBook Pros, there are now rumours that Apple is aiming to slim those down again in the next few years.
I'm hopeful in the next 13" Air redesign, Apple can accommodate a larger, 70+ WHr battery.

With more compute always-on (e.g., NPU) and who wouldn't love a little more battery life after degradation or left over on the next day.

More Windows OEMs have been packing 65+ WHr batteries into thin & light 13" designs, which I speculate came from greater energy density (e.g., they don't seem physically massive nor particularly weighty).
 

Doug S

Platinum Member
Feb 8, 2020
2,715
4,607
136
Interesting article at Fabricated Knowledge regarding ChatGPT o1's computational demands. If that points to the future direction in LLMs so much for Apple being able to run AI on device on an iPhone. Heck, so much for even someone with a Threadripper and high end Nvidia GPU running on AI on device!

I remain skeptical of the real utility of AI, but with the massively expanded per query power bill for o1 it is going to have to be a LOT better than v4 to pay its way...

 
Reactions: Tlh97 and Racan

Eug

Lifer
Mar 11, 2000
23,798
1,370
126
Does anyone know the details of the various Watch SoCs? I recently got our Apple Watch Series 5s replaced using the battery service from Apple so now we have full battery life again. They have the S5 SoC.

Is this correct?

S6 is 20% faster than S5.
S7 is the same as S6, meaning S7 is 20% faster than S5.
S8 is the same as S7, meaning S8 is 20% faster than S5.
S9 is 30% faster than S8, meaning S9 is 56% faster than S5.
S10 is the same as S9, meaning S10 is 56% faster than S5.

I do note that with WatchOS 10, S5 does lag sometimes, but it's manageable for our usage, and my wife has not been complaining about lag. I figure we can upgrade around S12 or something after yet another SoC speed upgrade, unless I can find a great deal somewhere on an S9 or S10.

I think this maybe for the OLED MBP's. Kuo said 2026?
Yeah, probably around 2026. They likely won't update the design with another LCD, and will wait for OLED for the redesign. The thinner screen alone will necessitate the redesign. I wonder if the thinner MacBook Pro rumours are mainly just because of the thinner screen, or if it could mean they will delete some larger ports again to save space.
 
Reactions: Tlh97 and ikjadoon

Eug

Lifer
Mar 11, 2000
23,798
1,370
126
Report claims that some A16 (not A18) chips are now being made in Arizona by TSMC, on N4P. Yields are supposedly almost as good as in Taiwan.

 

jdubs03

Senior member
Oct 1, 2013
712
317
136
The variance on these GB6 results is surprisingly large.
ST range from high 3100s-3440s. MT range from high 7700s-8700s (and there was an 8800 score!).
Seems to be a lot of mid 3300s, and 8100s scores.


Any idea of reason for such drastic differences?
Could it all just be down to power mode/low power, vs other tasks running in the background?
 

jdubs03

Senior member
Oct 1, 2013
712
317
136
Interesting that they have a Snapdragon 8 Gen 4 sample. Would've figured the A18 score on MT would be equivalent to the A18 Pro. From the GB Browser it looks a little bit down on ST/MT but not by too much.

@FlameTail is there an associated video for this?
The fact that they have an S8G4 sample too is interesting. Would've been nice to see the MT there.

Solid results there though.

Found this too:
Much lower MT score. Goes back to my previous post. The variance is profound.
 
Last edited:

Eug

Lifer
Mar 11, 2000
23,798
1,370
126
The fact that they have an S8G4 sample too is interesting. Would've been nice to see the MT there.
It's 10049 MT according to a Geekbench leak.


I don't think so. They are going with 8 Gen 4 Geekbench listing that popped up recently. If they did have the sample, they would have drawn power curves for it.
ST was 3236 in the above Geekbench leak, slightly different than in the Geekerwan screen grab.

The other Geekerwan screen grab says the results for the 9400 and Snapdragon 8G4 will come later.

The variance on these GB6 results is surprisingly large.
ST range from high 3100s-3440s. MT range from high 7700s-8700s (and there was an 8800 score!).
Seems to be a lot of mid 3300s, and 8100s scores.


Any idea of reason for such drastic differences?
Could it all just be down to power mode/low power, vs other tasks running in the background?
The variance is par for the course. As for the 8800 score, I suspect that might be in the freezer or something like that.
 

jdubs03

Senior member
Oct 1, 2013
712
317
136
Thanks for the link.
It's 10049 MT according to a Geekbench leak.



ST was 3236 in the above Geekbench leak, slightly different than in the Geekerwan screen grab.

The other Geekerwan screen grab says the results for the 9400 and Snapdragon 8G4 will come later.


The variance is par for the course.
Yeah I was figuring that the provided score for the S8G4 would've been from the GB result, but it didn't match.

Found the referenced value:

Strange how that referenced 3236/10049 doesn't display in the list anymore.
 
Reactions: Eug

Eug

Lifer
Mar 11, 2000
23,798
1,370
126
With that 8800 score for A18 Pro, there is a legit chance my iPhone 17 Pro Max next year might just hit 10000.

Even if it doesn't hit 10000, that would put it well ahead of my M1 Mac mini.


Geekerwan's socpk.com is your friend.
Thanks.

It seems 9300+ is already in the 18 W range, and Snapdragon 8 Gen 3 is 16 W. Who knows what Gen 4 will be. 18 W Max?
 

jdubs03

Senior member
Oct 1, 2013
712
317
136
With that 8800 score for A18 Pro, there is a legit chance my iPhone 17 Pro Max next year might just hit 10000.

Even if it doesn't hit 10000, that would put it well ahead of my M1 Mac mini.



Thanks.

It seems 9300+ is already in the 18 W range, and Snapdragon 8 Gen 3 is 16 W. Who knows what Gen 4 will be. 18 W Max?
I think you mean MY iPhone 17 Pro Max
My caveat is: if the battery can hold up on my 14P for another year, I just might be able to hold out for the 18PM.
Though something about the 17 Pro Max with a A19 Pro is appealing with those primes.
 
Reactions: Eug

digitaldreamer

Junior Member
Mar 23, 2007
10
3
81
Report claims that some A16 (not A18) chips are now being made in Arizona by TSMC, on N4P. Yields are supposedly almost as good as in Taiwan.

Are they still going to have to send these chips out (overseas?) for packaging?
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |