Apple CPU tricks: memory reordering, JavaScript support, ref counting • Hacker News Board

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#141

Post by tambourine_man » Sat, Nov 28, 2020, 12:07 PM UTC

pjmlp wrote: post #120

atq2119 wrote: post #91

Earlier quoted context omitted.

This is what happens when a huge proportion of your die isn't doing instruction decoding. That's a misconception. Yes, decoding x86 is somewhat more complicated, as far as I'm aware that's mostly because instruction length differs at a byte granularity. Still, the area dedicated to it simply isn't that large on those huge out of order designs. I'm sure the instruction encoding plays some role, but I suspect what we'r…

Intel failed because AMD exists and has a cross license agreement that allowed them to be clever. Without AMD in the picture, Itanium issues would have eventually been sorted out.

There would have been no Intel on IBM compatible PCs without x86 cross licensing, so you could make the point that AMD allowed Intel to thrive.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#142

Post by legulere » Sat, Nov 28, 2020, 12:28 PM UTC

It would be really interesting to see the performance difference of TSO on and off for the arm assembly.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#143

Post by nicoburns » Sat, Nov 28, 2020, 12:57 PM UTC

joachimma wrote: post #138

anfilt wrote: post #102

Earlier quoted context omitted.

That's because apple bought the entire 5nm production capacity/runs for basically for the entire last quarter of 2020. I can tell you some companies were not too pleased about that.

Is there anything preventing those companies from "ganging" up on Apple and buying capacity jointly? Are they too many and too small? Is it possible to share wafer-space with other companies or does having multiple designs add too much complexity/cost?

I think Apple essentially outbid them, which it was able to do because it is has both large volume and large profit margins.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#144

Post by raverbashing » Sat, Nov 28, 2020, 12:57 PM UTC

anfilt wrote: post #102

ylyn wrote: post #100

Earlier quoted context omitted.

Yes, and they are the only ones on TSMC 5nm currently.

That's because apple bought the entire 5nm production capacity/runs for basically for the entire last quarter of 2020. I can tell you some companies were not too pleased about that.

Ah yeah, Apple has f-you money and it knows how to use it.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#145

Post by jorvi » Sat, Nov 28, 2020, 1:01 PM UTC

simonh wrote: post #97

jorvi wrote: post #56

Earlier quoted context omitted.

People won’t believe it’s not Apple its magic sauce and ARM is really just that good until ARM processors start being a mainstream thing in Windows laptops. ARM its ARM-X already looks pretty juicy and the follow-ups are sure to get better and better.

If Apple is free riding on how great ARM is, how come everybody else’s mobile ARM chips are such pants in comparison?

You (and apparently most of HN) is misunderstanding me: I’m not saying Apple isn’t doing great stuff or that they’re just coasting on ARMs tech, but it is the ARM ISA that enables them to make the M1 so ridiculously good. But people won’t believe that and will attribute it to Apple’s vertical integration until they are holding a Windows laptop with an ARM CPU and crazy battery life, thermals etc.

And again: ARM already has the X in the pipeline which is going to close part of the ARM-Apple A-series gap.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#146

Post by normaljoe » Sat, Nov 28, 2020, 1:40 PM UTC

raverbashing wrote: post #144

anfilt wrote: post #102

Earlier quoted context omitted.

That's because apple bought the entire 5nm production capacity/runs for basically for the entire last quarter of 2020. I can tell you some companies were not too pleased about that.

Ah yeah, Apple has f-you money and it knows how to use it.

They did this with FedEx planes out of China years back, forget which iPhone version, but they basically did the same thing they booked everything. All FedEx planes only had iPhones and everybody complained. I don't think they have tried that stunt again.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#147

Post by layoutIfNeeded » Sat, Nov 28, 2020, 1:53 PM UTC

>When you recompile code for a new architecture, it usually breaks.

Yeah, then your code is shit and was relying on undefined behaviour.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#148

Post by normaljoe » Sat, Nov 28, 2020, 2:08 PM UTC

apendleton wrote: post #104

simonh wrote: post #101

Earlier quoted context omitted.

Wait, where did the goal posts go. Has anyone seen them? I swear they were here a minute ago.

To be fair to the person you're responding to, the goalposts look to have been "disrupt a large existing industry." "Large" is obviously subjective, but if the example of the disrupted industry is the watch industry, "the watch industry isn't large so it doesn't count" is a reasonable response within the constraints of the original goalposts.

Except it did by creating a larger market. Some of that was flashy at the start like the gold watches but ultimately created a new market. Personally I quit wearing a watch sometime around 2010 when I found I was checking my phone and didn't need a watch. Now I am checking my watch for time and weather and not pulling my phone out.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#149

Post by skywhopper » Sat, Nov 28, 2020, 2:34 PM UTC

lern_too_spel wrote: post #78

GeekyBear wrote: post #75

Earlier quoted context omitted.

> The Apple Watch is a successful product, but it really didn't completely disrupt a large existing industry For some values of large? >Apple now sells more watches than the entire Swiss watch industry https://www.theverge.com/2020/2/5/21125565/apple-watch-sales...

The Swiss watch industry isn't what it was. Most people I know don't wear a watch.

I hadn’t worn a watch for decades. Then Apple Watch came along and I’ve worn one every day for the last five years. I call that disruption.

Re: Apple CPU tricks: memory reordering, JavaScript support, ref counting

#150

Post by rwmj » Sat, Nov 28, 2020, 2:34 PM UTC

I wonder if TSO "violates" ARM standard conformance in some way? Perhaps not since it makes the memory ordering stronger, and is therefore upwards compatible. Or perhaps Apple doesn't care any more about strictly conforming to ARM's specs, which would be interesting news.