Can we please have ONE. SINGLE. SILICON DISCUSSION ON HN. stay on the topic at hand without fanboys spamming "hurr durr, my M2 is da best, Intel suxxx, X86 is dead!!!111one", while not bringing anything useful or relevant to the discussion?
Seeing your comment at the top makes me not want to ever open any silicon topic here again as I'm sure it will be full of these kind of low effort comments vomiting marketing garble on how AS is the best and everything else is doomed to failure, while not bringing any useful info or arguments on-topic.
While I could agree with the general sentiment, I think it's hard to understate how much of a role Apple played in the background of all of this.
But in any case, there's plenty of things to be said about this article. About one year ago (random link with relevant quotes : https://www.pcgamer.com/intels-3d-chip-tech-is-perfect-so-it... ), Intel was mocking AMD for using a chiplet approach, before announcing today that it was - clickbaity title aside - going to change everything.
The sad truth is, both Intel and AMD are in the exact situation. AMD went chiplet in order to make their performance cores at TSMC, and their less critical cores ("IO") at GloFo.
In both cases, this is just a question of using a very limited resource (TSMC's best in class process) the more effectively that you can (by throwing extra engineering at making a chiplet design that works).
And it's supremely relevant to the discussion to talk about how Apple, by throwing capital at a company (TSMC) that was, for the couple of decades I used to cover this, at best 2 years behind the best in class, today where they are (far far in front).
We could definitely have a long discussion about the hubris that led 2015 Intel where they are today (completely stuck with a 7 year old "+ paint coatings" aging 14nm "performance" process), or how Gelsinger is trying to make the best out of the situation (I personally think he's immensely qualified and Intel's best hope, though that may not be enough to bring Intel back to where it was), but at the end of the day, Apple threw a wrench in what seemed like an unshakable performance lead from Intel by spewing a bit of money left and right (they didn't only bet on TSMC early on, they threw money at GF for example, and it wasn't that massive early on from my understanding), and the silicon world hasn't been the same since.
>a role Apple played in the background of all of this
All of what? This topic is about Intel chilpets, which many of those will end up in datacenters where most Intel chips go, and that's not where Apple sells chips for.
Not every chip made and sold in the world revolves around laptops, tablets, smartphones or the apple ecosystem.
So can we please talk about Intel's chiplets impact on the industry and less about Apple silicone which has nothing to do with this?
Maybe I wasn't clear or went too fast on some things, I'm not a native speaker.
This is all about semi manufacturing, and the position that TSMC now has in the fab space, thanks to Apple (yes, really, that's what I went on about in the previous comment). No part of my comment referred to arm, architectures, anything of the sort, just that Apple's money, applied broadly at first in the semi manufacturing space, then in a very very targeted way, took TSMC from tier 2 manufaturer to the best in class.
If you look back a few years, only x86 chips were having volume at the bleeding edge of manufacturing process. Gpus, Smartphone, everything else was one node back at the very least. Apple threw money and orders with a massive volume (iPhone + iPad is pretty close in units to the x86 cpu market, above 300M roughly off the top of my heard) at TSMC and that early + continous investment helped them fast forward their processes while Intel is still stalled in 2015.
Apple is using TSMC today (the best bits), AMD is using TSMC today (the second best bits) for the performance part of their chiplets and so will Intel tomorrow for the exact same reason. This is the relevant bit that I was pointing at.
That's a fair assessment although perhaps not giving AMD enough credit.
IMO GloFo's spin-off worked out very poorly for AMD in the short term, but long term it let them partially-leapfrog Intel much as they had done 20 years prior with the K6/K7.
There's two main things that IMO give the M1/M2 their 'magic';
- Dram on die (helping their PPW, especially single threaded PPW)
- Tight integration between OS and CPU.
This is, perhaps, where the x86 consortium has fallen into a challenge in the face of tight integration; The majority of that group would likely shriek at the idea of a DRAM on CPU, "here you go that's all you get" idea. I saw it a lot when I slung PC hardware; Folks who would insist on having as much upgrade-ability as possible, but never actually bought the upgrades between PC purchases. Even still, RAM is the main thing I personally find myself still upgrading on either purchased or older PCs.
That being said, It would be interesting to see if they try doing DRAM chiplets for these; I'm sure some 'ideal state' would be where DRAM chiplets + slotted RAM cause the chiplets to be dedicated to integrated GPU resources, or act as a form of L4 cache for one or more banks of DRAM.
> This is, perhaps, where the x86 consortium has fallen into a challenge in the face of tight integration; The majority of that group would likely shriek at the idea of a DRAM on CPU, "here you go that's all you get" idea. I saw it a lot when I slung PC hardware; Folks who would insist on having as much upgrade-ability as possible, but never actually bought the upgrades between PC purchases. Even still, RAM is the main thing I personally find myself still upgrading on either purchased or older PCs.
Memory people usually either buy as much as they need, or buy some and then add more. I've done it just about every PC build of mine, sometimes completely swap memory.
GPU generally gets upgraded, unless you're one of those who buy the best every year.
Storage for sure gets upgraded.
Currently sending this from my skylake i7 that seen 3 different GPUs, 2 different RAM kits, I lost count how many times I've upgraded storage.
I would probably get mad if I couldn't upgrade memory down the line. It maybe makes sense for laptops, but I don't see why do that on desktop. While M1 has memory right there, its latency is higher than intel and amd.
I keep wondering, did people always use the word ‘silicon’ when talking about CPUs & SoCs? Somehow I never noticed it before Apple released their ‘Apple Silicon’.
Silicon as a term for semiconductors and the things we make from them is common in my experience. But I've never seen such a concerted effort to pronounce it "silly kin" as Apple Silicon marketing.
Just echoing what others are saying, no, we called them Intel chips/CPUs. What I don't get is why people go along with it. I personally prefer not being a miniature speakerphone for the marketing department at Apple.
This line of reasoning is just dumb. Every single chip on the mother board is made from Silicon. (There maybe some gallium or germanium parts but those are insignificant and irrelevant).
LOL. Anyone who works in chip design would know much M1/M2 changed the hardware game. It is actually the dabbler enthusiast talking about how power/perf isn’t important because his LED-laden shitbox has a wall plug (muh absolute performance) that doesn’t grasp how utterly irrelevant DIY builders are in the market. Just look at the relative sales of servers, laptops and desktop and see what we care about.
Not a single second of thought is ever spent by the architects/designers on optimizing “absolute performance”. We only care about perf/area and perf/watt. It is the marketing teams that try to hype up gamer performance. Overclocking/high voltage performance requires the engineering knowledge of a freshman intern: go raise the voltage/freq, run the test program, make a SKU.
Source: worked on CPU/GPU arch/design for 20 years, including at Intel.
Intel fanboys whine about Apple/Intel CPU comparisons, here is their answer.
The takeaway from the story: connecting a bunch of shitty chiplets together makes a shitty SoC. Except this time, Intel paid TSMC a buttload of money to make their shitty design.
The original thread comment asked if this was a thing before "Apple Silicon", that's what I was referring to; I've seen it before, and not just years before but over a decade before, possibly even two decades.
As such it's not something Apple PR invented, but rather hijacked.
It used to be slang, though. Something you'd use to punch up the first paragraph of an article, not the way people actually talked. For some reason calling it "Apple Silicon" really grates on me, too. But such are the whims of megacorps.
Cosign, and thank you: any CPU discussion past "Apple ARM great" has been impossible to have since launch.
List of places I tried taking conversation over that time, but it was ignored or read as complaints about Apple. (see Disclaimers in footer if you read these and think 'Wow, he just wanted to talk about why Apple was bad')
- M1 was the first processor on a particular node; so there was a short term opportunity to do an apples to apples comparison by taking down M1 numbers and waiting for upcoming launches
- it wasn't as trivial as "manufacturing on the improved node" for AMD, but it was for Qualcomm
- performance of ARM vs. X86 could be teased out by tracking tuple of node x manufactor of chips and being patient; projections and tracking of Qualcomm & AMD chips performance
- the initial M1 was beaten by Tiger Lake in desktop & sustained performance cases, which was two(!) nodes behind
- performance and noise issues from Apple optimizing for absolute fan silence always, leading to them only kicking on at extremely high speeds far into the performance workload, that had already been throttled
== DISCLAIMERS ==
1. I am a happy M2 MBP owner and think its the best chip.
2. My more nuanced view, summarized is that it is almost restrained in that the hardware got bigger, somehow, and in software there are growing pains as drivers adopt from iPhone use case to mostly-plugged-in use case. To wit, throttling seems optimized for ad copy around fan noise at low workloads than the user.
3. If you feel these discussions were focused on denigrating Apple, please recommend curious thoughts to have about chips that aren't denigrating Apple
Apple Silicon is the most exiting thing to happen in the field in decades. Apple handles platform transitions really well so it may seem less of a tectonic shift than it actually is.
It’s normal for people to be enthusiastic amongst such facts.
Then why not be enthusiastic about it on AS threads. This thread is about Intel chiplet design, it ahs nothing to do with AS so why pollute every silicone thread with this offtopic.
Because Apple only sells Apple devices, not chips. AS parts can only be found in the Apple ecosystem and can only be bought exclusively within devices Apple sells, while the other part (X86 from Intel and AMD) can be bough by anyone, run almost any OS and SW to date, and be used in any design/application you can dream of from laptops, PCs, servers, consoles, mainframes, cloud datacenters, robots, planes, even inside Tesla's head unit, while AS is just in a few Apple devices that don't overlap with most for the segments I mentioned before.
One silicone part has an impact over the entire computing sphere, while the other is relevant only within the Apple ecosystem. So bringing up AS in all threads about generic computing chips that anyone can buy directly is pointless as Apple does not cater to that market.
That's like me bringing up how fast my Ferrari is in threads about utilitarian vans and pickup trucks. Sure, they're both cars, but they don't compete in the same segments, so Ferrari making an even faster car has no impact or threat on the market of vans and pickups.
People buy laptops, mostly. They don’t even buy individual chips, aside from niche markets. So comparing MacBooks to Lenovos and the likes seem pretty distant from the Ferrari vs trucks analogy.
I also seems undeniable that Apple's move to custom silicon shook up the entire market, challenged preconceptions. It was a pivotal moment for the industry as a whole, not Macs only.
The compute chip market is much, much bigger than just laptops, iPhones and MacBooks. Like I said, it' also servers, FPGAs, cloud, datacenters, consoles, GPUs, AI-ML, cars, vision, etc. and Apple's silicone is absent form most of those sectors while these are Nvidia's, Intel and AMD's bread and butter. So comparing a chip that can only be found in Apple laptops to chips from Intel and AMD that are sold and used in hundreds of other industries and thousands of different devices is completely pointless as they're not competing in the same sectors.
When Apple will sell its chips to consumers, PC OEMs, datacenters, console manufacturers, AI and car companies, with full documentation and Linux support, in order to compete on the same turf with Intel and AMD, then we can talk about an industry wide revolution. But until then, this "revolution" will not extend beyond the Apple/Mac ecosystem where Apple has no competitors, and who's market share in the general PC space is still tiny.
It would be exciting if you could add more memory to their machines, and maybe gpus, on systems that cost less than 6000 dollars (and even those haven't transitioned to apple's in house cpu architecture).
For now, Apple Silicon is just sorta a blip because most people buy them for coding environments and editing pictures, and apple decides to dedicate all of those performance per watts on having Apple Music boot up as fast as possible on boot.
For me, I get the popcorn out for all the ongoing GPU drama between AMD, Nvidia and now Intel. All of that seems to be the sequel to Pirates of Silicon Valley.
1st paragraph: SOC are not upgradable, that’s the whole point of the trade of and most of what makes this tradition exciting. What will Apple do with the Mac Pro is the most important question in this industry for the last couple of years.
2nd: what? Apple Music what?
3rd: what does that movie, which was about Apple and Microsoft, had to do with any of the current chip industry and its many players?
Why are you so triggered that M2 is the best chip on the market? I'm pretty sure that is relevant in a discussion about the CPU market. AMD did a similar thing to Intel with the Ryzen launch. Intel is currently stagnating. They need a miracle at this point.
There is no such thing as a "best chip on the market". Best chip for what? You're confusing the word SoC/CPU with "chip" which is a very generic word.
The best "chip" is the one that best suits your individual application or business needs, but there is no such thing as a best chip on the market. That's why Apple is only a tiny fraction of the computing market share and so many other chip vendors are still in business, because every application requires different chips.
M2 doesn't solve every needs neither as a CPU (since you can't buy it outside the Apple ecosystem), neither a a generic "chip". Why can't you accept that?
Why are you so excited? Did you design the M2? Do you manufacture the M2? Did you fund the M2? If so, feel free to be proud of it. You made a technological advance happen. But if you just walked into a store and bought one, I dunno, I think you're arriving pretty late in the evolution to take a personal interest in its success.
Not sure about others but I personally am not a big fan of generalising that much: I'd prefer it if people would ideally say that it was for example the "most power efficient general purpose CPU/SoC" or at least something in that regard, not just "the best".
For example, have a look at https://openbenchmarking.org/vs/Processor/AMD%20Ryzen%20Thre... (user benchmarks of M1 and Threadripper). Compiling Linux on the 2990WX appears to be about 4 times faster than on the M2. (There are lots of other examples of one of the two CPUs being faster than the other but compiling Linux is the most time-expensive task I regularly do on my 2990WX. The energy usage in this task on the 2990WX is almost certainly a lot higher of course; this will be true for most tasks. However, the 2990WX is also 4 years older of course, manufactured in a different node, not very optimized for power saving and not operated in a very power saving mode.)
I think a suitable counter argument is that Apple has grown too large and needs to be split into multiple smaller companies to better aid competition.
Between what they're doing to silicon, the outrageous App Store behavior, and how they flaunt that they're a quazi-government entity, I think this could find broad support in Congress and the DOJ.
Nobody can compete with Apple, and that's a bad thing for everyone.
So Apple brought competitiveness to an industry that was badly needing it and stalling in the most recent years.. and your “solution” is that we should prevent them from doing so?
It's a strawman. Apple has the capacity to do immense good, but only because they're the single largest company in the world! We should scrutinize concentration of power heavily, and so far Apple has done nothing to suggest their benevolence to the rest of the market. They're blowing off Dutch regulators like it's a middle school homework assignment, and refusing to loose their asinine monopoly over software distribution on iPhone. They're behaving childishly, and everyone knows they're not a child. They're a company with hundreds of billions of dollars, and they're demonstrating organizational failure to address the demand of the market. On top of that, they're largest revenue sources are rent-collection and unibody aluminum computers made by political prisoners in Chinese concentration camps.
No comment on the other stuff, but the “silicon” part of this argument boils down to “anyone who makes something way better than the competition must be shut down because that’s unfair”.
We’d still be in the Stone Age if everybody had that mentality
Apple successfully monopolized the 5nm node by buying out all of TSMC's manufacturing capability at that node size. Characterizing it as "anyone who makes something way better than the competition" is a strawman portrayal of the underlying issue at hand.
They made a chip that's vastly better than anything out there at a given power consumption level. They are not attempting to use this advantage to corner the silicon market; indeed, they are neither licensing the design, nor selling the chips outside their own end-user hardware.
Using their enormous lead on cellphones and their incredible negotiation power and playing that into mobile business computing and supply chain / process monopoly.
The same goes for Google. They have higher market share in many categories and cover many more of them. Near-monopoly on search, ads, online video, email, and at least half of the smartphone OS market...
This is US site. Apple is US company. The biggest company in the world, source of so much pride. So tons and tons and tons of fanboyism here is inevitable. I'd say most of it is damn well earned.
That said, fanboyism makes people blind and uncritical, and (at least to me) its apparent company like Apple needs some good old criticism, rather than blind worship. Otherwise they will fall (if not fallen) into "we know whats best for you and you have no say in it" like with cough cough "child porn" filters or battery-gate.
I truly honestly don't trust their "we are more secure" marketing pitch, especially as non-US person.
At the end, its just another corporation driven by huge army of managers with main focus on salaries and bonuses. The idea that they are somehow morally better than everybody else when they keep hiring from companies like Facebook is pretty dangerous and goes back to beginning of my post.
Seeing your comment at the top makes me not want to ever open any silicon topic here again as I'm sure it will be full of these kind of low effort comments vomiting marketing garble on how AS is the best and everything else is doomed to failure, while not bringing any useful info or arguments on-topic.