Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Intel Problems

stratechery.com

Post reply on HN
Print view View original

201–210 of 431 posts

Re: Intel Problems

#201

Post by ncmncm »

DreadY2K wrote: post #176
dfgdghdf wrote: post #143

Earlier quoted context omitted.

Aren't most of us already programming against a virtual machine, such as Node, .NET or the JVM? I think the CPU architecture hardly matters today.

Many people do code against some sort of VM, but there are still people writing code in C/C++/Rust/Go/&c that gets compiled to machine code and run directly. Also, even if you're running against a VM, your VM is running on an ISA, so performance differences between them are still relevant to your code's performance.

C, C++, Rust, & Go compile to an abstract machine, instead. It is quite hard these days to get it to do something different between x86, ARM, and Power, except relying on memory model features not guaranteed on the latter two; and on M1 the memory model apes x86's. Given a compatible memory model (which, NB, ARM has not had until M1) compiling for the target is trivial.

The x86 memory model makes it increasingly hard to scale performance to more cores. That has not held up AMD much, mainly because people don't scale things out that don't perform well when they do, and use a GPU when that does better. In principle it has to break at some point, but that has been said for a long time. It is indefinitely hard to port code developed on x86 to a more relaxed memory model, so the overwhelming majority of such codes will never be ported.

Re: Intel Problems

#202

Post by ineedasername »

okl wrote: post #173
ineedasername wrote: post #152

I found the geopolitical portion to be the most important aspect here. China has shown a willingness to flex its muscles on enforcing its values beyond their borders. China is smart, and plays a long game. We don't want to wake up one day and find they've flexed their muscles on their regional neighbors similar to their rare earths strong-arming from 2010-2014 and not have fab capabilities to fall back on in the West…

> [...] and not have fab capabilities to fall back on in the West. I'm not too concerned: - There are still a number of foundries in western countries that produce chips which are good enough for "military equipment". - Companies like TSMC are reliant on imports of specialized chemicals and tools mostly from Japan/USA/Europe. - Any move from China against Taiwan would likely be followed by significant emigration/"bra…

National security doesn't just extend to direct military applications. Pretty much every industry and piece of critical infrastructure comes into play here. It won't matter if western fabs can produce something "good enough" if every piece of technological infrastructure from the past 5 years was built with something better.

As for moves again at Taiwan, China hasn't given up that prize. Brain drain would be moot if China simply prevented emigration. I view Hong Kong right now as China testing the waters for future actions of that sort.

Happily though I also view TSMC's pending build of a fab in Arizona as exactly that sort of geographical diversification of industrial and human resources necessary. We just need more of it.

Re: Intel Problems

#203

Post by lars-b2018 »

treve wrote: post #107
Const-me wrote: post #92

Earlier quoted context omitted.

Building server software on Graviton ARM creates a vendor lock-in to Amazon, with very high costs of switching elsewhere. Despite using A64 ISA and ARM’s cores, they are Amazon’s proprietary chips no one else has access to. Migrating elsewhere gonna be very expensive. I wouldn’t be surprised if they sponsor their Graviton offering taking profits elsewhere. This might make it seem like a good deal for customers, but I…

Maybe I'm missing something, but don't the vast majority of applications don't care about what architecture they run on? The main difference for us was lower bills.

Our experience as well. We run a stack that comprises Python, Javascript via Node, Common Lisp and Ruby/Rails. It's been completely transparent to the application code itself.

Re: Intel Problems

#204

Post by toonies555 »

Lets speed run a doomsday:

2022: share price tanks, ceo booted, they shuffle but dont have a plan, no longer blue chip so finance is hard to come by. delisting. everyone booted. doors close.

2023/4: AMD only game in town. profits and volumes up. so are the faults and vulnerabilities. They spend most of their effort in fixes and not innovation.

2024: M1 chip available on dells/hps/thinkpads. AWS only use Graviton unless customer specifically buys another chip.

2025: Desktop ARM chip available on dells/hps/thinkpads. 2025: AWS makes a 'compile-to-anything' service. decompiler and recompiler on demand.

2026: AMD still suffering. Hires Jim Keller for the 20th time. makes a new ZEN generation that beats M1 and Arm. AMD goes into mobile CPUs.

Re: Intel Problems

#205

Post by MangoCoffee »

oldgradstudent wrote: post #56
dogma1138 wrote: post #36

Earlier quoted context omitted.

At that point if it will be trouble for Intel it would be a death sentence for AMD... Intel has fabs, yes it’s what maybe holding them back atm but it also a big factor in what maintains their value. If x86 dies and neither Intel nor AMD pivot in time Intel can become a fab company they already offer these services, yes no where near the scale of say TSMC but they have a massive portfolio of fabs and their fabs are l…

> Intel can become a fab company Not unless they catch up with TSMC in process technology. Otherwise, they become an uncompetitive foundry.

>Not unless they catch up with TSMC in process technology

1. Intel doesn't have to catch up. Intel's 14nm is more than enough for a lot of fabless. Not every chip needs cutting edge node

2. split up Intel foundry into a pure play allowed Intel to build up an ecosystem like TSMC.

3. Intel's 10nm is much denser than TSMC's 7nm. Intel is not too far behind. they just needs to solve the yield problem. split up Intel's design and foundry allowed each group to be more agile and not handcuffed to each other.

in fact Intel Design should licensed out x86 like ARM. why not take best biz model from the current leaders? Intel Design take ARM business model and Intel foundry take TSMC business model.

Re: Intel Problems

#206

Post by adrian_b »

cbozeman wrote: post #166
chaorace wrote: post #139

Earlier quoted context omitted.

I did not know that! Though, that answer raises its own questions... If the two are entirely unlinked, what's stopping Intel from slapping "Now 3nm!" on their next gen processors? Surely some components must be at the advertised size, even if it's no longer a clear cut all-or-nothing descriptor, right? What's actually being sized down and why is it seemingly posing so many challenges for Intel's supply chain?

I think it'll be a good thing when people stop worrying about process node technology and start worrying about performance and power usage. Intel's 14nm chips are already competitive with AMD's (TSMC's, really) 7nm chips. The i7-11700 or whatever the newest one coming out soon is called, is going to be pretty much exactly on parity with AMD's Ryzen 5000 series. So if node shrinkage is such a dramatic increase in perf…

Since AMD has introduced its first 7 nm chip, Intel's 14-nm chips have never been competitive.

Intel's 14-nm process has only 1 advantage over any other process node, including Intel's own 10 nm: the highest achievable clock frequency, of up to 5.3 GHz.

This advantage is very important for games, but not for most other purposes.

Since the first 7-nm chip of AMD, their CPUs consume much less power at a given clock frequency than Intel's 14 nm.

Because of this, whenever more cores are active, so that the clock frequency is limited by the total power consumption, the clock frequency of the AMD CPUs is higher than of any Intel CPU with the same number of active cores, which lead to AMD winning any multi-threaded benchmark even with Zen 2, when they still did not have the advantage of a higher IPC than Intel, like they have with Zen 3.

With the latest Intel's 10 nm process variant, Intel has about the same power consumption at a given frequency and the same maximum clock frequency as the TSMC 7 nm proces.

So Intel should have been able to compete now with AMD, except that they still appear to have huge difficulties in making larger chips in sufficient quantities, so they are forced to use workarounds, like the launch of the Tiger Lake H35 series of laptop CPUs with smaller dies, to have something to sell until they will be able to produce the larger 8-core Tiger Lake H CPUs.

Re: Intel Problems

#207

Post by erosenbe0 »

sf_rob wrote: post #172
skohan wrote: post #151

Earlier quoted context omitted.

This is kind of what should happen right? I'm not an expert, but my understanding is that one of the takeaways from the M1 success has been the weaknesses of x86 and CISC in general. It seems as if there is a performance ceiling which exists for x86 due to things like memory ordering requirements, and complexity of legacy instructions, which just don't exist for other instruction sets. My impression is that we have b…

Isn't most of M1's performance success due to being a SoC / increasing component locality/bandwidth? I think ARM vs x86 performance on its own isn't a disadvantage. Instead the disadvantages are a bigger competitive landscape (due to licensing and simplicity), growing performance parity, and SoCs arguable being contrary to x86 producers' business models.

Umm, Intel laptop chips are SoC with onchip graphics, pci4, wifi, usb4, and thunderbolt4 controller, connectivity direct to many audio codec channels, plus some other functionality for dsp and encryption.

Re: Intel Problems

#208

Post by viktorcode »

thoughtsimple wrote: post #55

How does Moore's law figure into this? I suspect that TSMC runs into the wall that is quantum physics at around 1-2nm. Considering that TSMC has said that they will be in full production of 3nm in 2022, I can't see 1nm being much beyond 2026-2028. What happens then? Does a stall in die shrinks allow other fabs to catch up? It appears to me that Intel stalling at 14nm is what opened the door for TSMC and Samsung to ca…

Eventually, CPUs will have to focus on going wide, i.e. growing number of cores and improving interconnections.

Re: Intel Problems

#209

Post by npunt »

ineedasername wrote: post #152

I found the geopolitical portion to be the most important aspect here. China has shown a willingness to flex its muscles on enforcing its values beyond their borders. China is smart, and plays a long game. We don't want to wake up one day and find they've flexed their muscles on their regional neighbors similar to their rare earths strong-arming from 2010-2014 and not have fab capabilities to fall back on in the West…

Ben missed an important part of the geopolitical difference between TSMC and Intel: Taiwan is much more invested in TSMC's success than America is in Intel's.

Taiwan's share of the semiconductor industry is 66% and TSMC is the leader of that industry. Semiconductors helps keep Taiwan from China's encroachment because it buys them protection from allies like the US and Europe, whose economies heavily rely on them.

To Taiwan, semiconductor leadership is an existential question. To America, semiconductors are just business.

This means Taiwan is also likely to do more politically to keep TSMC competitive, much like Korea with Samsung.

Re: Intel Problems

#210

Post by sobellian »

jng wrote: post #101
thoughtsimple wrote: post #55

How does Moore's law figure into this? I suspect that TSMC runs into the wall that is quantum physics at around 1-2nm. Considering that TSMC has said that they will be in full production of 3nm in 2022, I can't see 1nm being much beyond 2026-2028. What happens then? Does a stall in die shrinks allow other fabs to catch up? It appears to me that Intel stalling at 14nm is what opened the door for TSMC and Samsung to ca…

Modern process node designations (5nm, 3nm...) are not measurements any more, they are marketing terms. The actual measure of shrinking is a lot smaller than the name would mean to indicate, and not approaching the quantum limits as fast as it may seem.

If I recall correctly from my uni days, one of the big challenges with further shrinking the physical gates is that the parasitic capacitance on the gates becomes very hard to control, and the power consumption of the chip is directly related to that capacitance. Of course, nothing is so simple and I'm sure Intel can make some chips at very small process sizes, but at the cost of horrible yield.
Post reply on HN