Discussion Apple Silicon SoC thread

[Eug]

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:

Page 78 - Discussion - Apple Silicon SoC thread

Page 78 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M1 Ultra discussion here:

Discussion - Apple Silicon SoC thread

Page 109 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M2 discussion here:

Discussion - Apple Silicon SoC thread

Page 127 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

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:

Page 215 - Discussion - Apple Silicon SoC thread

Page 215 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M4 Family discussion here:

Discussion - Apple Silicon SoC thread

Page 263 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M5 Family discussion here:

Page 431 - Discussion - Apple Silicon SoC thread

Page 431 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

 

[Doug S]

People moving away from Chrome fixes the problem that Chrome's popularity has created. Websites won't be able to use non-standard HTML that breaks on non-Chrome browsers. It's not as bad as the old days with ActiveX and IE6, but there's no reason to stray any closer to that horrible time either.

Yes this.

If Apple was ever forced to fully support third party browsers on iOS (i.e. "real" Chrome rather than making it a wrapper using Safari's Webkit engine) we would quickly return to the dark days of "best viewed on IE6" badges on websites.

Web devs didn't want to build/test their websites on anything other than IE6, so things were pretty bad for Netscape/Firefox for a few years.

The same thing would happen if Apple was forced to allow full Chrome on iOS, they'd support only that and not only Safari users but Firefox users would suffer. With a monopoly in place then Google could do all the things they are slowly moving towards but competition prevents them from doing, like dropping all extensions (so no more ad blocking) and requiring support for all the really insecure capabilities like giving the browser direct access to USB and other system devices on your system, in the name of making "webapps" with the full capability of mobile apps or PC applications.

Recently there was a CVE for a bug discovered on Safari that was part of a one of those long exploit chains. It turned out that bug had been present for a LONG time. How long you ask? So long that the bug was also present in Chrome, because it was present in Webkit before Google forked it. So that same bug was ALSO present in Chrome and Edge, and every other Chromium browser. Only Firefox and other non Chrome/Webkit based browsers were immune.

That's the risk a browser monoculture presents, though this is a rather extreme example since it dates back to before Google's fork. But if you effectively make it so Chrome is all there (Firefox would cease to exist if webdevs could design and test for Chrome only) is then exploits that affect literally every web user (for all practical purposes) will be the result.

So it is in everyone's interest to avoid Chrome on Apple platforms at least, if not elsewhere.

 

[johnsonwax]

So, a performance result that I don't think obviously derives from existing benchmarks.

Many/all of the video editing apps - FCP/Resolve, etc have fairly substantial support for AI filter/effects and/or existing filter/effects reimplemented from a conventional CPU to GPU/AI which usually benefit greatly from the matmul acceleration in the GPU, so these fairly slow tasks are getting 2x-4x boosts from M4 Pro/Max to M5 Pro/Max. Video/audio editing are basically the main use cases for the M5 Max, so it's not some small subset of that market.

This may become a bit of a forward problem for Apple with some of these models that seem quite clearly tailored to particular types of work. If you're just dicking around and want something fast, then the benchmarks will be fine, but if you're doing FCP work, Apple again has the ability to codesign that whole use case if it's a big enough market for them.

 

[johnsonwax]

You never have to check if Chrome is supported for any website.

I've never had to check if Safari is supported for a website. I only did that because I had a hard time believing that the Canadian government had an inoperable website on the phones of ⅔ of their citizens. Seems like the kind of thing they'd get a phone call over. Well, maybe not, y'all really nice up there.

Now the US website - I'm shocked we haven't yet turned it over to a Russian firm that promised to 'do great security cheap, Putin like much' in an unsolicited Signal chat to one our our Ivy League WH grads.

 

[mvprod123]

The C1X is performing very well.

https://www.ookla.com/articles/apple-iphone-air-c1x-modem-q4-2025

 

[mvprod123]

https://twitter.com/x/status/2036018679092318298