Discussion Apple Silicon SoC thread

Page 360 - 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:

poke01

Platinum Member
Mar 8, 2022
2,581
3,409
106
But instead we only got the blandest marketing apple has done to date
Notice how there was no Tim Cook in the M4 Mac event. It was all John Turnus. The Mac mini marketing/event was really good. Tim Cook wouldn’t have pulled the same reveal reaction nor had the charm to do it.
 
Reactions: Mopetar

Eug

Lifer
Mar 11, 2000
23,926
1,527
126

dosdude did an upgrade to 256GB to 1TB
Heh. I believe that's a 24" Cinema HD Display he's using, circa 2008.

EDIT:

Also, check out these screen grabs.

He's placed an M1 on top of the M4 to demonstrate their relative sizes.



 
Last edited:

johnsonwax

Member
Jun 27, 2024
96
160
66
For those debating storage, it's just a matter of time before someone (likely Satechi) ships an updated one of these. Likely multiple to choose from. These have been a mainstay of the Mini since launch as it was one of the first desktops to ship with 3.5" drives which at the time were relatively low capacity, so external enclosures/RAID for anyone wanting a media box were basically a requirement.

There's going to be a pretty big uptick in demand for improved Plex server support.
 

Eug

Lifer
Mar 11, 2000
23,926
1,527
126
For those debating storage, it's just a matter of time before someone (likely Satechi) ships an updated one of these. Likely multiple to choose from. These have been a mainstay of the Mini since launch as it was one of the first desktops to ship with 3.5" drives which at the time were relatively low capacity, so external enclosures/RAID for anyone wanting a media box were basically a requirement.

There's going to be a pretty big uptick in demand for improved Plex server support.
You cannot use this type of design with the new Mac mini, because it would block the air flow. However, they can make it similar in foot print, just without the valley that was present in the old design to cup the base of the Mac mini. And heat dissipation has been a significant issue with these too. Also, they are notoriously buggy.

The other issue is the wireless antennae for the new Mac mini are located in the round disc part of the base, so it might not be a good idea to put the hub right underneath it.
 
Reactions: Mopetar and Viknet

poke01

Platinum Member
Mar 8, 2022
2,581
3,409
106
You cannot use this type of design with the new Mac mini, because it would block the air flow. However, they can make it similar in foot print, just without the valley that was present in the old design to cup the base of the Mac mini. And heat dissipation has been a significant issue with these too. Also, they are notoriously buggy.

The other issue is the wireless antennae for the new Mac mini are located in the round disc part of the base, so it might not be a good idea to put the hub right underneath it.
I think it’s best if you put storage base on top now.
 
Reactions: digitaldreamer

Eug

Lifer
Mar 11, 2000
23,926
1,527
126





 
Last edited:

MS_AT

Senior member
Jul 15, 2024
365
798
96
So about 25% higher IPC than Zen 5 X3D? Pretty damn good.
Maybe a bit less, he is still using znver3 flag for Zen5 -> no avx512 enabled. That could boost geomean score by few percents by boosting x264 subtest actually that is the subtest that M4 is doing very well at
 

Meteor Late

Member
Dec 15, 2023
116
98
61
Huang is saying how LPDDR vs DDR affects scores, so yeah, there are many variables here. Also 6000 CL26 is no slouch at all, something you don't get with normal RAM without tuning.
One can check HX 370 and compare to the desktop 9950X, difference is higher than 10% clock for clock, even against JEDEC timings.
 
Last edited:

poke01

Platinum Member
Mar 8, 2022
2,581
3,409
106
Maybe a bit less, he is still using znver3 flag for Zen5 -> no avx512 enabled. That could boost geomean score by few percents by boosting x264 subtest actually that is the subtest that M4 is doing very well at
It apparently decreases performance.

Purely backwards, when testing SPEC integers with gcc, turning on AVX512 will slightly reduce overall performance. Many media use -march=native or znver4/5 to test, but the results are actually too low.
 

MS_AT

Senior member
Jul 15, 2024
365
798
96
It apparently decreases performance.

Purely backwards, when testing SPEC integers with gcc, turning on AVX512 will slightly reduce overall performance. Many media use -march=native or znver4/5 to test, but the results are actually too low.
There is a bug in 12.3 that he is using that was doing suboptimal stores for znver4 [12.3 doesnt have znver5 target] that is why he switched to znver3, but the bug should have been solved in 14.2 and 14.2 should have zen5 specific tunings which afaik were not backported to 12.3.

Chips&Cheese is using 14.2 with march=native but they are not using lto (link time optimization) what makes direct comparison impossible.
 

name99

Senior member
Sep 11, 2010
526
412
136
lol these two points kinda exclude each other, if Apple is the most deliberate company in tech, it definitely was NOT a choice for them "in general".

Personally I do think steve jobs may have been the most deliberate CEO, but idk that we see that at apple now. On many occasions jobs admitted live on stage that prices were too high, or specs were too low, and he always was great at spinning that into a consumer win instead of the fact that at times they sold macs with meh specs for a year straight.

Steve cared more about tech, cared more about the product itself than just money IMO, ruthless as he was. That why in all the old powermac demos he really goes out of his way to do live benchmarking and even having engineers come up on stage and explain what CPU pipelines are and other deep details.

Feel free to disagree with me but I see tim cook as being way more capitalist and stingy when it comes to money. I think if steve were around we'd have moved to 16gb long ago. Especially with the immense power of apple silicon. Steve would have been able to hype up going from 8gb to 16gb and make it seem meaningful. But instead we only got the blandest marketing apple has done to date.
They could easily go together.
If Apple's preferred policy is more or less: a base Mac Mini costs $600 (or whatever) then to some extent what ships depends on what Apple can put together to hit an internal price of $400 + margin of 50% (again or whatever).

Obviously the precise details will vary, and sometimes things will be added or removed based on other considerations, but it could be as simple as "averaged across the entire line, using a base of 16GB this year allowed all the target prices+margin to be met, whereas that just was not true last year"...
 
Last edited:
Reactions: The Hardcard

poke01

Platinum Member
Mar 8, 2022
2,581
3,409
106

m4 pro review
 

FlameTail

Diamond Member
Dec 15, 2021
4,238
2,594
106

m4 pro review
In addition, there are now two clusters with five performance cores, whereby only four are active in the entry-level M4 Pro. The P-cores can reach a clock rate of up to 4.512 GHz and 3.852 GHz on all cores
Interesting.

So ST core boost clock speed is about almost 20% higher than the all-core clock

But doesn't the base M4 chip have an all-core clock of about 4 GHz?
 
Mar 11, 2004
23,341
5,772
146
You cannot use this type of design with the new Mac mini, because it would block the air flow. However, they can make it similar in foot print, just without the valley that was present in the old design to cup the base of the Mac mini. And heat dissipation has been a significant issue with these too. Also, they are notoriously buggy.

The other issue is the wireless antennae for the new Mac mini are located in the round disc part of the base, so it might not be a good idea to put the hub right underneath it.

Er, not sure how it'd block airflow considering it'd be the same if you set it on a flat desk. It shouldn't need much airflow. Plus, you could make a cutout so you can actually press the friggin power button without having to liftup the entire thing.
 

Eug

Lifer
Mar 11, 2000
23,926
1,527
126
Er, not sure how it'd block airflow considering it'd be the same if you set it on a flat desk. It shouldn't need much airflow. Plus, you could make a cutout so you can actually press the friggin power button without having to liftup the entire thing.
No. The old design includes a valley in which the base of the Mac mini is cupped, so it doesn’t move and it provides a cleaner look. My point is you’d have to remove this valley part of the design.
 

Eug

Lifer
Mar 11, 2000
23,926
1,527
126
This M4 Mac mini feels as light as a feather. My M1 Mac mini seems like an old school beast in comparison. And no I can't slide my finger under the lip to turn it on. You have to lift up the machine to turn it on.

Will set up some time today.

P.S. When you open up the shipping box, the whole thing falls open like a flower.

 
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/    |