Discussion Apple Silicon SoC thread

Page 340 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Eug

Lifer
Mar 11, 2000
23,926
1,527
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:

Doug S

Platinum Member
Feb 8, 2020
2,888
4,912
136
This is a myth. Every market is "shrinking". People don't upgrade desktops as frequently. IMO, the M4 Max wouldn't make a good desktop chip. The RAM is soldered, the GPU non-upgradeable, I/O not much for a premium desktop and hobbled PCIe connectivity. It's a laptop SoC down to its bones.

Apple knows what a desktop is they used to make em. 2019 Mac Pro with upgradeable CPU, SSD, RAM, GPU and the 2008-2020 iMac/iMac Pro with upgradeable CPU, SSD, RAM and external GPU support for some models. The current Mac Pro and Mac Studios are only desktops because they are not battery powered and headless.

Well, Apple controls the GPU drivers. AMD did provide drivers in the Intel era. But Apple is hyper focused on Metal and its own GPUs.

That's got nothing to do with ARM. The claim YOU made was "why are we talking about ARM, its for laptops".

There's nothing stopping Apple from making a Mac Pro that removes the soldered on memory and uses LPCAMM instead - and I think there's a non zero chance they will do this with LPDDR6, at least on some models. Or a Mac Pro that has DIMM slots in addition to the soldered on memory (if they added DDR5 controllers to the Max die) other than the fact they don't want to. That's a business decision, not due to anything inherent in the ARM architecture that makes it unsuitable for desktops as you seem to be implying.
 
Reactions: poke01

mikegg

Golden Member
Jan 30, 2010
1,849
471
136
Last edited:
Reactions: Tlh97 and Eug

mikegg

Golden Member
Jan 30, 2010
1,849
471
136
OK but that doesn't indicate how many screens it can support. Apple says the M4 has an "entirely new display engine". So far they've really only mentioned it now supports tandem OLED, but that was specifically only in the context of the iPad Pro.

Anyhow, for those unaware, @poke01 was referencing these spec requirements:
I didn't say it won't support two screens, just that it only has 1 display engine still. Therefore, one can reasonably conclude that if it does support dual external screens, the single display controller will have to work harder and consume more total power than say, two display controllers.

Remember that Apple deliberately made display controllers large in order reduce power consumption when using external monitors since they care about that stuff.
 
Reactions: Tlh97 and Eug

poke01

Platinum Member
Mar 8, 2022
2,581
3,409
106
I didn't say it won't support two screens, just that it only has 1 display engine still. Therefore, one can reasonably conclude that if it does support dual external screens, the single display controller will have to work harder and consume more total power than say, two display controllers.
are we forgetting M4 had a Display Engine overhaul? They could have made it use the same power while driving two monitors. Remember, the new display engine was created to drive Tandem OLEDs, so it wouldn’t surprise me if we had improvements there.
 
Reactions: Tlh97 and Eug

Doug S

Platinum Member
Feb 8, 2020
2,888
4,912
136
are we forgetting M4 had a Display Engine overhaul? They could have made it use the same power while driving two monitors. Remember, the new display engine was created to drive Tandem OLEDs, so it wouldn’t surprise me if we had improvements there.

Why did your post attribute @mikegg's post you were replying to here to me? Some sort of weird forum bug?
 
Reactions: Mopetar

DZero

Senior member
Jun 20, 2024
249
98
61
It's maybe also needed for feature-parity for ported iOS features / apps like improved Siri (allegedly lol), captions / translation of live content, portrait screensavers, enhanced dialogue, etc.

Though, the CPU, GPU, and NPU do work together on intensive tasks, so it may make sense to upgrade them all simultaneously (e.g., as they do anyways by re-using older SoCs).

//

In my opinion, it's good the Apple TV SoC is seen as relatively overkill: they still feel speedy years later after apps have grown, tvOS has expanded, etc. Either features, or bloat. Some data on whether a streaming box's hardware perf is relevant for general UI tasks, from CNET's tests.


From the home page, open the movie Endgame: when does playback start? I think the A55s are clocked at ~1.4 GHz, while the A12 Bionic is ~2.5 GHz.

I don't think people only buy Apple TVs for their speed, but it does let them feel "new" even in the long-term.

Streaming BoxTime (button → movie playback)OS & CPU
Roku Ultra (2024) - cold start19 secondsRoku OS & ??
Roku Ultra (2024) - cached start14 secondsRoku OS & ??
Roku Ultra (2022)17 secondsRoku OS & Cortex-A55
Apple TV 4K (2021)8 secondsApple tvOS & A12 Bionic
I want a TV Box with controller support and games on it like Genshin Impact or Honkai Star Rail. The A12 Bionic can deal with that without issue given the correct RAM size. Maybe next gen would pull that? A hybrid powerful console.
 

SpudLobby

Senior member
May 18, 2022
991
684
106
If they were going to work with Mediatek they would have had to do that a few years ago. No point now that they have their own design complete.

They don't need to be competitive with Qualcomm's 5G - nobody achieves the theoretical speeds and there's not much use for speeds over a couple hundred Mbps to a phone. When there's heavy congestion there's not much anyone can do about it. What really matters is in the marginal areas on the edge of a cell where you struggle to get 5 Mbps, and it'll make a difference between maybe Apple manages 3 Mbps or Apple has no bars.
Power in this vein matters too, and is architecturally dependent on the modem independent of the node, and compatibility with bands which will require R&D (testing, QC). We see that with Samsung and Intel modems before them.

But I agree the idea the theoretical performance maximums or MMWave matters is largely ridiculous. As long as these are roughly as efficient at idle and loads and have pretty good compatibility with the latest standards it’s fine. They could be MediaTek-tier and they’d be okay, but save marginal $.
 

mikegg

Golden Member
Jan 30, 2010
1,849
471
136
I'm very curious how they will configure the M4 Pro this time around. I wonder if the M3 Pro was downgraded because N3B is an expensive low yield node or if Apple wanted to differentiate the Pro and the Max more.

I'm also curious how this affected overall Mac sales. I think a lot of people saw less value in the M3 Pro which might have caused them to buy the M3 Max or skip the upgrade entirely. Overall, did it net more revenue for Apple?
 

Doug S

Platinum Member
Feb 8, 2020
2,888
4,912
136
Power in this vein matters too, and is architecturally dependent on the modem independent of the node, and compatibility with bands which will require R&D (testing, QC). We see that with Samsung and Intel modems before them.

But I agree the idea the theoretical performance maximums or MMWave matters is largely ridiculous. As long as these are roughly as efficient at idle and loads and have pretty good compatibility with the latest standards it’s fine. They could be MediaTek-tier and they’d be okay, but save marginal $.

Band compatibility is not gonna be their problem. I keep saying this and maybe people don't believe it, but the baseband software is where all the hard problems lie. Adding a new band is child's play by comparison. Modern phones handle dozens of bands, other than perhaps when you're adding bands in totally new areas of the spectrum (i.e. the 6 GHz stuff Verizon marks as "UW" and the real mmwave stuff in the 10-30 GHz range) but that's more of a front end problem for e.g. antennas and LOs than the modem itself. I imagine Apple is supporting all that because the modem in the current SE supports mmwave and while I suppose they could backtrack on that on the SE without too much complaint they sure couldn't on the "regular" iPhone lineup.

I agree power matters, and will be of particular importance to Apple like it always is. I have no doubt they would sacrifice some performance to save power, as the specs get into crazier and crazier territory, with theoretical bandwidth of 10 Gbps in Qualcomm's recent modems. I'm sure there are some devices OEMs might put an X75 in that could need/use that level of bandwidth, but it sure isn't relevant in a phone. Apple will design with the needs of a phone as the primary/only design goal, and probably target being the best in Mbps per nanowatt or something like that. They'll figure rather than delivering 400 Mbps they'd be better off delivering 200 Mbps using 1/3 of the power.

That's not to say they will beat Qualcomm in power use in version 1.0, in fact I'd be shocked if they did. Nonetheless, that'll be their target and it'll be reflected in the future evolution of their modem. Maybe Qualcomm is starting to figure that out too, I think they've gone three generations now with 10 Gbps as the max speed, and they've quit bragging about that when announcing a new generation. I have a feeling it'll make a comeback as a talking point when Apple's modem doesn't support anywhere near that much.

I imagine Apple's engineers will also feel that rather than constantly blasting out at maximum power trying to reach a cell when one is out or range or you're at the edge (ever notice how quickly your battery runs down in such cases) they'll seek contact less often which will make for a longer delay to acquire a signal but avoid wasting so much power trying to find something that isn't there or vainly hold onto one of those phantom 1 bar signals that goes away the moment you try to use it to make a call or send a message.
 

FlameTail

Diamond Member
Dec 15, 2021
4,238
2,594
106
I am curious what changes Apple has made to the P-core cluster in M4 Pro/M4 Max. More cores and/or More L2 cache?
M1 Max​
4P​
12 MB L2​
M2 Max​
4P​
16 MB L2​
M3 Max​
6P​
16 MB L2​
 

FlameTail

Diamond Member
Dec 15, 2021
4,238
2,594
106
baseProMaxUltra
M14P+4E8P+2E8P+2E16P+4E
M24P+4E8P+4E8P+4E16P+8E
M34P+4E6P+6E12P+4E-
M44P+6E???

I reckon there'll be a core count upgrade for M4 Pro. I doubt it will have the same 6P+6E configuration as M3 Pro, because M4 is 4P+6E. So if M4 Pro is 6P+6E, it would be only 2 more P-cores than base M4, which would be pitiful.
 

mvprod123

Member
Jun 22, 2024
186
198
76
I think Apple will add Thunderbolt 5 support to the M4 Max, given that M4 Ultra = 2x M4 Max. This fits in well with the long-standing rumours of a new 120Hz Pro Display XDR and possibly TandemOLED in 2025 along with the new Mac Studio and Mac Pro.
 

mikegg

Golden Member
Jan 30, 2010
1,849
471
136
baseProMaxUltra
M14P+4E8P+2E8P+2E16P+4E
M24P+4E8P+4E8P+4E16P+8E
M34P+4E6P+6E12P+4E-
M44P+6E???

I reckon there'll be a core count upgrade for M4 Pro. I doubt it will have the same 6P+6E configuration as M3 Pro, because M4 is 4P+6E. So if M4 Pro is 6P+6E, it would be only 2 more P-cores than base M4, which would be pitiful.
Hopefully M4 Pro gets 8P+6E config. At least it'll equal M1 and M2 Pros.

I think M4 Max will get 12P + 6E. So not much improvement.

If the M4 Ultra is 24P + 12E, that's a very nice upgrade over the 16P + 8E M2 Ultra. Worthy upgrade.
 
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/    |