Ask HN: Can competitors catch up to Apple Silicon? • Hacker News Board

Re: Ask HN: Can competitors catch up to Apple Silicon?

#231

Post by mixmastamyk » Mon, Jul 04, 2022, 6:32 PM UTC

pizlonator wrote: post #144

modeless wrote: post #114

You're looking in the wrong place. The magic comes from TSMC, not Apple. Apple's major innovation is in using their unrivaled bank account to pay TSMC for exclusivity on their newest fabrication technology. As competitors gain access to that TSMC technology they will match or beat Apple's performance. And if Intel succeeds in reclaiming the fabrication technology lead from TSMC (we'll see) then Intel will beat Apple'…

That’s a bold statement. I don’t think we really know how much of the lead is due to Apple’s design. I would bet it’s more due to fab than design, but the design plays a nontrivial role.

Just ARM is known to have much better per watt performance than intel. Folks are desperate that there be a single reason, but that is rarely the case.

The reality is that multiple factors are working in Apple’s favor. Process, architecture, design, investment, focus, OS… firing on all cylinders as they say.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#232

Post by hajile » Mon, Jul 04, 2022, 6:34 PM UTC

saagarjha wrote: post #41

rob74 wrote: post #23

Earlier quoted context omitted.

Both Intel and AMD have the major disadvantage of having (or, let's say, wanting) to maintain x86 backward compatibility - which means not only staying compatible with the almost 45 year old CISC instruction set of the Intel 8086, but also with the whole line of CPUs that came after it. All this ballast makes it harder for them to build an energy-efficient CPU. By contrast, Apple was able to just create a new CPU bas…

Having to support x86 is definitely not a "major" disadvantage.

The X2 cores in 8cx gen3 get similar performance to Zen 2 U-series chips while using 7-10w instead of 15-50w.

How many more ARM chips have to get equivalent performance at a tiny fraction of the power before people will finally start considering that either AMD and Intel hire the most incompetent people out there or that ISA actually matters?

Re: Ask HN: Can competitors catch up to Apple Silicon?

#233

Post by msbarnett » Mon, Jul 04, 2022, 6:37 PM UTC

modeless wrote: post #114

You're looking in the wrong place. The magic comes from TSMC, not Apple. Apple's major innovation is in using their unrivaled bank account to pay TSMC for exclusivity on their newest fabrication technology. As competitors gain access to that TSMC technology they will match or beat Apple's performance. And if Intel succeeds in reclaiming the fabrication technology lead from TSMC (we'll see) then Intel will beat Apple'…

To reach 87% of the perf of a 12900K at a max clock of 3.2 GHz versus the 12900K‘s monstrous 5.2 GHz, the M1 has something like a 75% IPC advantage.

Are you seriously claiming that you expect a single node shrink from Intel 10nm (roughly equivalent to TSMC 7nm) to Intel 7nm (equivalent TSMC 5nm, the M1’s node) to give Intel an enormous 75% increase in IPC such that they’d be able to compete on performance per watt by not having to clock so stratospherically high (with the attendant voltage penalties) to compensate for their low IPC?

That would be an unprecedented outcome for several node shrinks, let alone a single one. It’s Apple’s super-wide design that’s the primary factor in the IPC here. To pin it all on a single node shrink is magical thinking.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#234

Post by hajile » Mon, Jul 04, 2022, 6:37 PM UTC

yxhuvud wrote: post #84

mromanuk wrote: post #75

Earlier quoted context omitted.

Comparing currently available CPUs on the market is pretty fair.

That is definitely true, but you can't reach any conclusion on the cost of the x86 baggage by comparing different process nodes. It has way too much influence on the end result to be ignored. In a few months we will have both AMD and Apple on the same size, so we will finally get some idea of how the baggage compare then. It won't be a long situation, Apple will relatively soon after release a new on a smaller size a…

A13 and Zen 2 were both made in TSMC N7 fabs, but the performance per watt differences were still enormous.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#235

Post by hajile » Mon, Jul 04, 2022, 6:45 PM UTC

alberth wrote: post #111

dmitrygr wrote: post #99

Earlier quoted context omitted.

X86-64 INCLUDES all the legacy cruft of x86-32 and x86-16 and is thus 44 years old. Aarch64 in Apple chips doesn’t include A32 and is thus 11 years old. It is indeed a large age difference.

But ARMv8-A is backward compatible.

Apple dropped support years ago and the last couple ARM chip designs finally dropped support too.

A715 in particular made it's decoder 20+% wider while reducing die area by 75% all due to eliminating 32-bit support.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#236

Post by johnklos » Mon, Jul 04, 2022, 6:58 PM UTC

hnlmorg wrote: post #201

ido wrote: post #148

Earlier quoted context omitted.

And it's also not really "nearly as old" considering how fast stuff developed in the early day - the first ARM CPUs launched in 1986, and the i8086 in 1978 - 8 years earlier.

That still doesn’t make ARM “modern”.

No. The design made it modern.

Look at the m68000 (1979) compared with the i8086 (1978). The m68k was 32 bits from the beginning, so while moving from the m68000 to the m68020 did add some instructions, there were no "special modes" for "backwards compatibility". All binaries that run on the m68000 can directly on the m68020.

Add an MMU and optionally an FPU to an m68020 (1984) or just use an m68030 (1987), and you have a fully modern system that can run modern software in 2022.

The i80386 (1985) is 32 bits and much more modern than the i8086, but real mode and 386 mode are completely different. Even with this modernization, Intel didn't bother with atomic operations, which is why neither Linux nor the BSDs support the original i80386. To run modern software, you'd need an i80486 (1989).

Re: Ask HN: Can competitors catch up to Apple Silicon?

#237

Post by erichocean » Mon, Jul 04, 2022, 7:02 PM UTC

wmf wrote: post #218

wffurr wrote: post #212

Earlier quoted context omitted.

Isn't the packaging part of what makes the very wide memory controllers feasible?

Not really. GPUs regularly implement 256-bit or wider RAM.

With insanely high latency relative to a CPU…

Re: Ask HN: Can competitors catch up to Apple Silicon?

#238

Post by Bud » Mon, Jul 04, 2022, 7:02 PM UTC

modeless wrote: post #183

bearjaws wrote: post #176

Earlier quoted context omitted.

This is just absolutely incorrect. Design is over half the battle, look at Qualcomm n5 performance vs Apple M1 on n5 performance. It's not even comparable in anyway. Even AMD 6900U struggles in many regards compared to M1 pro, and even more so at performance per watt. For example Cinebench runs at 118% more power draw on the Ryzen at only a 11% multi-core performance advantage.

Qualcomm chooses low cost over performance on purpose. AMD 6900U is still at a process disadvantage compared to M1. AMD's comparable chips won't come out for many more months.

You're still wrong. Design counts. Apple has a huge design lead here. There's no way to successfully obscure or distract from that fact.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#239

Post by Bud » Mon, Jul 04, 2022, 7:07 PM UTC

spenvo wrote: post #150

modeless wrote: post #114

You're looking in the wrong place. The magic comes from TSMC, not Apple. Apple's major innovation is in using their unrivaled bank account to pay TSMC for exclusivity on their newest fabrication technology. As competitors gain access to that TSMC technology they will match or beat Apple's performance. And if Intel succeeds in reclaiming the fabrication technology lead from TSMC (we'll see) then Intel will beat Apple'…

Even there, it looks like Samsung is on track to beat TSMC to mass production of 3nm chips: https://www.reuters.com/technology/samsung-elec-starts-3-nan...

...except that Samsung demonstrably lies about every single thing relevant to assessing performance, benchmarks, release dates, etc.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#240

Post by erichocean » Mon, Jul 04, 2022, 7:11 PM UTC

pizlonator wrote: post #140

kaba0 wrote: post #78

Earlier quoted context omitted.

Do we know whether that x86 backward compatibility is all that problematic? If I’m not mistaken, it is only used as a “public API” even in current CPUs, and on a microcode level it doesn’t have as much relevance.

The other answer was awesome but here’s another one: Number of registers. Of course internally the CPU has some huge number of registers. But it matters how many registers the machine code can speak of, and arm64 has 32 while x86 has 16. Consequently, x86 machine code has more cases of data flow obscured by spills to the stack. In a very sophisticated cpu, that might mean more decoding work to try to reconstruct the…

> X86 throws at least one more limiter just for good measure: the TSO memory model, which causes memory effects to have dependencies between them in cases where they wouldn’t on arm.

Apple's M1 supports TSO (on ARM, obviously).