You say the M1 cores are different from the A14X cores despite having the same thermals and performance. Why don’t you share the schematics for us to see, if you claim you have access to it?
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
m1 ridiculously fast
- Thread starter 537635
- Start date
- Sort by reaction score
You say the M1 cores are different from the A14X cores despite having the same thermals and performance. Why don’t you share the schematics for us to see, if you claim you have access to it?
Yor „logic“ makes no sense. You simply cannot deduce the design of a chip from its performance gain. There just is no connection between the two
Two COMPLETELY different scenarios. The reason the DTK had the A12Z was because Apple did not want to release details of their upcoming processors yet. Furthermore, there are separate design teams for the A Series and M Series chips. While both series use Apple-designed cores that utilize the ARM ISA (with Apple's secret sauce on top), the processors are actually quite different from an architectural perspective. The M1 also has integrated the functions of the T2 coprocessor into the SoC, whereas it is still a separate chip on iOS devices utilizing A-series processors. There is an excellent writeup of the differences here:
Comparison of Apple M1, A14 Shows Differences in SoC Design - ExtremeTech
A new analysis of the M1 breaks down the die design versus the smartphone-class A14 SoC.
www.extremetech.com
You think you can deduce the chip internals from thermals and performance? ?
Last edited:
If you had taken five minutes to to the research yourself, we wouldn't be here right now. The Icestorm and Firestorm cores are about the only thing unchanged between the A and M-series platforms. Cache sizes, DRAM bandwidth, T2 coprocessor functions, and numerous other internal differences further distinguish the M1 from the A14 (or any A-series processor, for that matter).
By your own logic, an Intel i3 would functionally be the same as an Intel i9 because they share the same microarchitecture. Yet those two processors are best suited for vastly different use cases (the i3 is for basic web browsing/email CPU, and the i9 is a gaming and content creation powerhouse).
Die Shots of Apple's A14 Bionic & M1 SoCs Compared: Same Architecture, Different Goals
Reverse engineering analysts compare Apple's latest SoCs
If you had taken five minutes to to the research yourself, we wouldn't be here right now. The Icestorm and Firestorm cores are about the only thing unchanged between the A and M-series platforms. Cache sizes, DRAM bandwidth, T2 coprocessor functions, and numerous other internal differences further distinguish the M1 from the A14 (or any A-series processor, for that matter).
By your own logic, an Intel i3 would functionally be the same as an Intel i9 because they share the same microarchitecture. Yet those two processors are best suited for vastly different use cases (the i3 is for basic web browsing/email CPU, and the i9 is a gaming and content creation powerhouse).
Die Shots of Apple's A14 Bionic & M1 SoCs Compared: Same Architecture, Different Goals
Reverse engineering analysts compare Apple's latest SoCswww.tomshardware.com
On that same website, it says, A14 is 2 firestorm cores and 4 icestorm cores, while the M1 is 4 firestorm cores and 4 Icestorm. So it is clear that the A14 from the iPhone is the basis for the M1 despite you guys trying to downplay it.
And the A14X would also have 4 high-performance cores (4 firestorm cores like the M1), and 4 energy efficient cores (4 icestorm cores like the M1). Hence why the M1 is now in the iPad Pro.
Last edited:
You are wrong. You know a chip is more - way more in fact - than just „cores“?
Ah yes. The M1 doesn’t use icestorm and firestorm cores. And it is just a coincidence that the thermals and performance align exactly what the A14X would have been and how the M1 runs on the iPad Pro without issues. It is pure coincidence that the M1 iPad Pro performs like the A14X iPad Pro.
I was wrong. The M1 is something brand new and has nothing to do with the A14.
Hahahahaha
I didn’t write that, but I’ll answer - I doubt it.
There is overlap between the teams, people move between teams, but there are separate teams. Same as any other CPU design organization.
When I was designing CPUs, most of the time I couldn’t tell you what “team” I was on. Sometimes I was working on two chips at once - initial design of a brand new architecture and a spin or shrink on an old design. But I was never working on two chips both expected to tape out in the same year, because that’s far too hard.
The M1 also has integrated the functions of the T2 coprocessor into the SoC, whereas it is still a separate chip on iOS devices utilizing A-series processors. There is an excellent writeup of the differences here:
Comparison of Apple M1, A14 Shows Differences in SoC Design - ExtremeTech
A new analysis of the M1 breaks down the die design versus the smartphone-class A14 SoC.
Wasn't the reason Apple made the T1 and T2 because unlike the Apple SoCs, Intel CPUs didn't have the Secure Enclave? Why would Apple need to integrate the function of the T2 coprocessor when it's something that's been integrated into Apple SoCs since the A8?
Secure Enclave
The Secure Enclave is a dedicated secure subsystem in the latest versions of iPhone, iPad, Mac, Apple TV, Apple Watch, and HomePod.
support.apple.com
If you had taken five minutes to to the research yourself, we wouldn't be here right now. The Icestorm and Firestorm cores are about the only thing unchanged between the A and M-series platforms. Cache sizes, DRAM bandwidth, T2 coprocessor functions, and numerous other internal differences further distinguish the M1 from the A14 (or any A-series processor, for that matter).
Die Shots of Apple's A14 Bionic & M1 SoCs Compared: Same Architecture, Different Goals
Reverse engineering analysts compare Apple's latest SoCs
The DRAM bandwidth has traditionally been double on the iPad's A-X series SoCs compared to the regular A-series for iPhone. It's partly how we get such good GPU performance necessary to drive the high resolution displays on the iPad. The one exception was the iPad Pro 9.7 A9X which only had one LPDDR4 chip.
See above regarding T2 and Secure Enclave.
Last edited:
Can I get something straight here without being accused of some kind of dunning krugerism? This thread was featured on the front page and the pile-on is sort of interesting.
The initial claim was ‘the A14 is the base version of the M series chips’
The initial response (I think from cmaier) was ‘no you idiot, the cores in an A14 are completely different to the M1’. The reader is then told to ‘look at’ the A14 cpu cores and the M1 cores, in which case the difference would be plain as day. And in fact, the reader was informed:
‘Once again: the physical design of each firestorm/icestorm core in M1 is completely different than the physical design of the firestorm/icestorm cores in a14. Just look at them - you can easily see that the standard cell placements and the routes are completely different. They have completely different physical designs’
Then someone posted a link to an extreme tech post with photos of the M1 and A14 as ‘proof’ of that.
somehow the goalposts subsequently changed and the pile-on started pointing out that the layout and components of the A14 SOC are different from yeh M1. Which was never the initial claim.
anyway, I looked at the extreme tech photos and as far as I can tell, at least the firestorm cores are identical, but rotated and at a different scale (because the A14 is more zoomed in, being a smaller SOC).
Now, I’m confused. For all those playing at home, can anyone confirm whether or not the A14 cores are in any way different from the M1 cores, other than how many there are, and the ‘stuff’ that’s connected to them?
The initial claim was ‘the A14 is the base version of the M series chips’
The initial response (I think from cmaier) was ‘no you idiot, the cores in an A14 are completely different to the M1’. The reader is then told to ‘look at’ the A14 cpu cores and the M1 cores, in which case the difference would be plain as day. And in fact, the reader was informed:
‘Once again: the physical design of each firestorm/icestorm core in M1 is completely different than the physical design of the firestorm/icestorm cores in a14. Just look at them - you can easily see that the standard cell placements and the routes are completely different. They have completely different physical designs’
Then someone posted a link to an extreme tech post with photos of the M1 and A14 as ‘proof’ of that.
somehow the goalposts subsequently changed and the pile-on started pointing out that the layout and components of the A14 SOC are different from yeh M1. Which was never the initial claim.
anyway, I looked at the extreme tech photos and as far as I can tell, at least the firestorm cores are identical, but rotated and at a different scale (because the A14 is more zoomed in, being a smaller SOC).
Now, I’m confused. For all those playing at home, can anyone confirm whether or not the A14 cores are in any way different from the M1 cores, other than how many there are, and the ‘stuff’ that’s connected to them?
What is also "mind blowing" in addition to raw computing strength, battery life and memory utilization is the disk controller. The ssd speeds that these M1 machines achieve is nothing but next level. This appears to be one of the reasons that the 8Gb systems perform so well. When more ram is needed for a task it swaps to disk and the disk access is blazing fast so not even noticed. Just a spectacular design IMHO. Also makes loading files, photos or whatever much snappier.
Last edited:
Thing is that tells that macbooks were underquipped for handling 5k monitors. My MBP i7:
- works fine with built in display
- after update to Big Sur it is way more snappier
- with eGPU it was as snappy as on internal display
So I'd say M1 has way better integrated GPU (equivalent to 1050 as far as benchmarks say), OS is better and it works fine.
The "This was always like 2fps on the 2020 i5 Intel" claim is exaggeration or a symptome of some serious problem with your computer. My 2015 i7 Intel with integrated GPU seems laggy but the experience is 30fps like.
The cores themselves are the same (Firestorm and Icestorm) except M1 has 2 more Firestorm cores. The number of GPU cores vs A14 is also doubled.
However, Apple added a bunch more stuff that they normally wouldn't for an iPad-only chip to make the M1 more suited for Macs.
If Apple had designed the A14X instead of using the M1, the Geekbench CPU scores would probably be the same. However, it wouldn't have the same display support, peripherals support, virtualization, Thunderbolt, etc.
However, Apple added a bunch more stuff that they normally wouldn't for an iPad-only chip to make the M1 more suited for Macs.
If Apple had designed the A14X instead of using the M1, the Geekbench CPU scores would probably be the same. However, it wouldn't have the same display support, peripherals support, virtualization, Thunderbolt, etc.
So, the claim that the M1 has ’completely different’ ice storm and fire storm cores to the M1, and that this is obvious to anyone who looks at them, is in fact wrong, and the original poster who was getting piled on for asserting otherwise and accused of demonstrating the Dunning-Kruger effect was right?
No. The op insisted that M1 is just a rebranded A14X, which it is not.
They are the same *microarchitecture* but different *physical designs.* This isn’t that difficult so I don’t know why people don’t get it.
Since people keep making this mistake, can you elaborate? You said the ‘different physical designs’ of the cores is obvious from looking at them, but the photos I’ve seen look exactly the same. Are you able to point to the differences in physical designs, because it’s not obvious to a lay person and it’s pretty obvious that people are confused (I’ve heard supposedly well informed commentators say that the M1 cores *are* A14 cores, which is obviously wrong)?
edit: autocorrect typo
Last edited:
the speakers dont get enough credit , they are crazy good, i find sometimes it sounds like a good quality sound bar.
You had a 10/10 scored post until you used the infamous term "snappier." The judges have ruled and deducted 1 point for a bad dismount.