They're also using essentially the same cores between their mobile and desktop products. Apple is their own ARM ecosystem. An improved core for the A-series chips is an automatic improvement for the next M-series chip. Most arm licensees have to wait for ARM to come out with new cores.
The fact Apple can book the initial runs of any of TSMC's process nodes is just one of many of their advantage over other ARM and x86 manufacturers.
But the process node is also not the main reason.
What matters is only microarchitecture. And Apple has by far the most performant microarchitecture design of all CPUs.
- Variable instruction sizes make the front-end more complex and limits the decoding width;
- Delayslot makes superscalar front-end more complex;
- Page size limits VIPT L1 cache size;
- Dedicated SIMD/FP architectural registers allow dedicated SIMD/FP physical register files;
...
The choice and design of the ISA is extremely important, it's hard to argue that the ARM ISA has no impact on M1&M2 performance.
But the ISA choice is obviously not enough to explain the whole performance of the M1&M2. Likewise, the manufacturing process cannot fully explain the performance of the M1&M2.
The Apple microarchitecture is by far the most performant and efficient of all high-end superscalar CPU.
But be careful with simplistic explanations, the microarchitecture is always constrained by the ISA/architecture, and the x86 ISA has some flaws that can affect the microarchitecture (least on the power consumption).
Quote: “Although I've worked on x86 obviously for 28 years, it's just an ISA, and you can build a low-power design or a high-performance out any ISA. I mean, ISA does matter, but it's not the main component - you can change the ISA if you need some special instructions to do stuff, but really the microarchitecture is in a lot of ways independent of the ISA. There are some interesting quirks in the different ISAs, but at the end of the day, it's really about microarchitecture.”
In the end, ISA is such a small part that impacts the design of a modern high performance CPU that it is almost negligible. It is physically impacting only the decode unit, but the decode unit is only a few percent of die area. Feel free to listen to the whole interview to get a feeling.
Customers kept paying Qualcomm for their SoC with ARM designed cores, so once again, Qualcomm had no reason to actually do anything but sit on their patents.
Intel had a similar story, since Sandy Bridge "x86_64" part of CPU barely changed, most of the performance gain was somewhere from better process, more custom instructions (avx2, etc.), higher TDP (since ryzen).
It's not ARM vs x86, it's Apple ARM cores vs everyone elses cores.
