Hacker News Reader

Comment by dgacmu | Hacker News Reader

Intel was ahead, and hit the wall first. Apple & AMD are not ahead, they're just catching up. I don't want to understate how big a problem that could be for Intel, of course. But they're also doing it on low margin parts, and Intel continues to make bank with their data center parts.

I don't think any of this represents a short-term problem for Intel, other than the general downturn in processor sales because fewer people will need to upgrade. But I think it represents a very serious long-term threat.

They have some really cool technical advances, like 3D xpoint. But I'm concerned that they do so badly on embedded and custom integration from a long-term perspective.

View on HN

Apple sold millions of iPhones with 7nm chips while Intel struggles to build comparable 10nm chips and keeps releasing 14+++ nm. AMD will release 7nm chips very soon. It does not seem like they are catching up. Quite the opposite.

You can’t compare nm between vendors - it’s just marketing numbers.

Not directly no, but the actual feature size and density of TSMC 7nm and Intel 10nm are comparable.

What about die size?

Then you have to ensure you're comparing chips designed for the same market segment. Die size comparisons work well if you're talking about a Cortex-A53 on 16nm vs 12nm. It doesn't work as well when you're talking about a full SoC, or even a desktop CPU+GPU combo where core counts for both sides of the chip can vary greatly.

Die size is independent of process size, customers can order most any die size they want.

My simplest laptop in current use has 4 times more memory than my current phone and I probably would need to make huge compromises to live with half as much. A lot of the chips in phones don't even have external memory buses. A top-of-the-line iPad Pro sports an 8-core asymmetrical core design, with 4 fast cores and 4 slow ones and, overall, is slower than a 2-core Core M-based MacBook (although it feels great because iOS does a lot less than macOS).

Also, Apple doesn't make its own A-series processors - it uses TSMC for that.

And iPhones still don't come close to competing with desktop-class processors in terms of performance. iPhones also use much less electricity, of course, but the point remains.

I don't know enough about this, but the GP's argument of "Intel hit the wall first because they were the first to reach that level of performance" makes logical sense to me.

"Apple’s iPhone Xs is faster than an iMac Pro on the Speedometer 2.0 JavaScript benchmark"

Yes, Safari, but iPhones do compete with your average desktop processor (not the top end).

https://macdailynews.com/2018/09/23/apples-iphone-xs-is-fast...

They can compete in certain workloads. As a computational tool however, desktop Intel CPUs can be optimized far, far beyond the capabilities of any A-series CPU.

Don't forget that Intel CPUs have things that A CPUs are missing like QuickSync, AVX2, massive PCIe interconnectivity.

Whether the A-series CPU could be modified into something competitive on that front is yet to be seen. Whether this actually matters considering the state of our compilers and software development is yet another question.

Apple's newest CPUs have hardware explicitly for accelerating Javascript, so it's not surprising they'd pull ahead there.

And as you said, you're comparing the top-of-the-line iPhone to an "average" CPU.

> Apple's newest CPUs have hardware explicitly for accelerating Javascript

They really don't. A12 added a couple of instructions for floating point conversions, but contrary to claims making rounds on Twitter at the time, they were not even generated by WebKit when the benchmarks were run.

Right, but Intel isn't falling behind AMD or apple in this comparison - it is falling behind TSMC.

Intel made one single bad bet - their 10 nm process didn't work as well as they expected - and TSMC, who made the right bet, leapfrogged them.

In terms of architecture and vulnerabilities, it's not prudent to bet Intel chips are more vulnerable to exploits than others - it's just that we know more about those vulnerabilities. If you want to find vulnerabilities with high impact in cloud and enterprise data centers, Intel Xeon CPUs will be your primary research target.

We're not really sure yet whether TSMC have leapfrogged Intel in the longer term though. Intel's 10nm issues seem to have delayed their smaller process nodes in the medium term, but by how much is yet to be seen. It seems, for example, that Intel 7nm isn't in quite as much trouble as one might expect.

It's also naive to dismiss the possibility for Intel to have learnt a lot from some of the failures in 10nm that will prove useful in accelerating node development in the future.

If the speculation about AMD's Rome / EPYC 2 performance is true, they have now surpassed Intel.

More accurately, AMD's 7nm processors should be ahead of Intel's 14nm processors. That's great, but it's not a huge surprise.

We've yet to see how competitive they'll be once Intel leapfrogs that 10nm node. That's assuming that they can, of course...

Reply on news.ycombinator.com