I am not a chip expert it’s just so night and day different using a Mac with an arm chip compared to an Intel one from thermals to performance and battery life and everything in between. Intel isn’t even in the same ballpark imo.
But competition is good and let’s hope they both do —- Intel and AMD because the consumer wins.
1982 - 1998, DEC Alpha processors (loved them)
1998 - 1999, AMD Athlon
1999 - 2004, MIPS
2008 - 2012, Apple A4/A5
2012 - 2015, AMD Ryzen/Zen
2016 - 2018, Tesla
2018 - 2020, Intel
Apple did a ton of work on the power efficiency of iOS on their own ARM chips for iPhone for a decade before introducing the M1.
Since iOS and macOS share the same code base (even when they were on different architectures) it makes much more sense to simplify to a single chip architecture that they already had major expertise with and total control over.
There would be little to no upside for cutting Intel in on it.
It's not like Intel or AMD are known for letting other customize their existing chip designs.
Genuinely asking -- what is it due to? Because like the person you're replying to, the m* processors are simply better: desktop-class perf on battery that hangs with chips with 250 watt TDP. I have to assume that amd and intel would like similar chips, so why don't they have them if not due to the instruction set? And AMD is using TSMC, so that can't be the difference.
If you don't care to clock that high, you can reduce space and power requirements at all clocks; AMD does that for the Zen4c and Zen5c cores, but they don't (currently) ship an all compact core mobile processor. Apple can sell a premium branded CPU where there's no option to burn a lot of power to get a little faster; but AMD and Intel just can't, people may say they want efficiency, but having higher clocks is what makes an x86 processor premium.
In addition to the basic efficiency improvements you get by having a clock limit, Apple also utilizes wider execution; they can run more things in parallel, this is enabled to some degree by the lower clock rates, but also by the commitment to higher memory bandwidth via on package memory; being able to count on higher bandwidth means you can expect to have more operations that are waiting on execution rather than waiting on memory, so wider execution has more benefits. IIRC, Intel released some chips with on package memory, but they can't easily just drop in a couple more integer units onto an existing core.
The weaker memory model of ARM does help as well. The M series chips have a much wider out of order window, because they don't need to spend as much effort on ordering constraints (except when running in the x86 support mode); this also helps justify wider execution, because they can keep those units busy.
I think these three things are listed in order of impact, but I'm just an armchair computer architecture philosopher.
My understanding is that both Intel and AMD are pushing high clocks not because it's what consumers want, but because it's the only lever they have to pull to get more gains. If this year's CPU is 2% faster than your current CPU, why would you buy it? So after they have their design they cover the rest of the target performance gain by cranking the clock, and that's how you get 200 W desktop CPUs.
>the commitment to higher memory bandwidth via on package memory; being able to count on higher bandwidth means you can expect to have more operations that are waiting on execution rather than waiting on memory, so wider execution has more benefits.
I believe you could make a PC (compatible) with unified memory and a 256-bit memory bus, but then you'd have to make the whole thing. Soldered motherboard, CPU/GPU, and RAM. I think at the time the M1 came out there weren't any companies making hardware like that. Maybe now that x86 handhelds are starting to come out, we may see laptops like that.
>Releasing low frequency high core count part for consumers would be greeted with questions, like "what for is this CPU?".
It's for homelab and SOHO servers. It won't get the same attention as the sexy parts... because it's not a sexy part. It's something put in a box and stuff in a corner to chug away for ten years without looking at it again.
That's not really what we're talking about. Apple's cores are faster yet lower clocked. (Not just faster per clock but absolutely faster.) So some people are wondering if Intel/AMD targeting 6 GHz actually reduced performance.
But most every OS can.
(This is mostly because resolving priority inversions turns out to be very important on a phone, and almost noone designs for this properly because it's not important on servers.)
I think this is very context dependent. Is this a big, heavy 15”+ desktop replacement notebook where battery life was never going to be a selling point in the first place? One of those with a power brick that could be used as a dumbbell? Sure, push those clocks.
In a machine that’s more balanced or focused on portability however, high clock speeds do nothing but increase the likelihood of my laptop sounding like a jet and chewing through battery. In that situation higher clocks makes a laptop feel less premium because it’s worse at its core use case for practically no gain in exchange.
They historically haven't. They've wanted the higher single-core performance and frequency and they've pulled out all the stops to get it. Everything had been optimized for this. (Also, they underinvested in their uncores, the nastiest part of a modern processor. Part of the reason AMD is beating Intel right now despite being overall very similar is their more recent and more reliable uncore design.)
They are now realizing that this was, perhaps, a mistake.
AMD is only now in a position to afford to invest otherwise (they chose quite well among the options actually available to them, in my opinion), but Intel has no such excuse.
Thank you.
I suspect one of the issues is that pushing the clock is a really easy way to get an extra 2% so you can claim the crown of fastest or try to win benchmarks. It’s easy to fall into a trap of continuing to do that over and over.
But we know the long-term result. You end up blasting out a ton of heat and taking up a ton of power, even though you may only be 10% faster than a competitor who did things differently. Or worse you try to optimize for ever increasing clocks and get stuck like the Pentium 4.
As said up thread, no one really compares Apple CPU speeds with megahertz. That’s partially because Apple doesn’t talk about it or emphasize it which makes it more difficult, and partially because it’s not like you have a choice anyway.
It would never happen but it would be interesting to see how things would develop if it was possible to simply ban talking about clock speeds somehow. What would that do to the market?
And that has made all the difference.
- more advanced silicon architecture. Apple spends billions to get access to the latest generation a couple of years before AMD.
- world class team, with ~25 years of experience building high speed low power chips. (Apple bought PA Semi to make these chips, which was originally the team that build the DEC StrongARM). And then paid & treated them properly, unlike Intel & AMD
- a die budget to spend transistors for performance: the M chips are generally quite large compared to the competition
- ARM's weak memory model also helps, but it's very minor IMO compared to the above 3.
- a die budget to spend transistors for performance: the M chips are generally quite large compared to the competition
re: apple getting exclusive access to the best fab stuff: https://appleinsider.com/articles/23/08/07/apple-has-sweethe... . Interesting.
I think Apple helps them with money (loan?) to get some of the equipment or build the new lines. In exchange they get first shot at buying capacity.
And of course Apple is certainly paying for the privilege of the best process. At least more than other companies are willing. And they must buy a pretty tremendous volume across a couple of sizes.
It benefits both companies, otherwise they wouldn’t do it.
Relatively properly. Nothing like the pampering software people get. I've heard Mr. Srouji is very strict about approving promotions personally etc.
(…by heard I mean I read Blind posts)
P.S. hearsay and speculation, not direct experience. I haven't worked at Apple and anybody who has is pretty closed lip. You have to read between the lines.
P.P.S. It's sort of a circular argument. I say Apple has the best team because they have the best chip && they have the best chip because they have the best team.
But having worked (briefly) in the field, I'm very confident that their success is much more likely due to having the best team rather than anything else.
Apple's primary product is consumer smartphones and tablets so they are solely focused on power efficient mobile chips.
Mostly memory/cache subsystem.
Apple was willing to spend a lot of transistors on cache because they were optimizing the chips purely for mobile and can bury the extra cost in their expensive end products.
You will note that after the initial wins from putting stonking amounts of cache and memory bandwidth in place, Apple has not had any significant performance jump beyond the technology node improvements.
There's tons of people that would pay $300+ for an equivalent perf + heat x86 competitor.
The M2 was certainly nothing amazing in jump.
Apple Silicon macs are far less impressive if you came from an 8c/16t Ryzen 7 laptop. Especially if you consider the Apple parts are consistently enjoying the next best TSMC node vs. AMD (e.g. 5nm (M1) vs. 7nm (Zen2))
What's _really_ impressive is how badly Intel fell behind and TSMC has been absolutely killing it.
This is basically it. Coming from dated Intel CPUs, Mac users got a shockingly good upgrade when the M-series computers were released. That amplified Apple's claims of Macs being the fastest computers, even when some key metrics (such as disk performance) were significantly behind PC parts in reality.
Yes, they're still better in performance/watt - but the node difference largely explains it like you were saying.
On the flip side, if you look at servers... Compare a 128+core AMD server CPU vs a large core ARM option and AMD perf/watt is much better.
Its just Apple buys next gen fabs while AMD and intel has to be on last gen, so the M computers people compare are always one fab gen ahead. It has very little to do with CPU architecture.
They do have some cool stuff about their CPU, but the thing most laud them for has to do with fabs.
A better comparison is to take the total package area of the AI Max+ 395 that includes a 16 core CPU + a massive GPU tile and you get ~448mm^2 across all 3 chiplets.
The area has nothing to do with peak performance... based on the node, it has to do with the amount of components you can cram into a given space. The CRAY-1 cpu was massive compared to both of your examples, but doesn't come close to either in terms of performance.
Also, Ryzen AI Max+ 395 is top dog on the AMD mobile CPU front and is around 308mm^2 combined.
Of course it does. For single-threaded performance, the knobs I can turn are clockspeed (minimal area impact for higher speed standard cells, large power impact), core width (significant area impact for decoder, execution resources, etc, smaller power impact), and cache (huge area impact, smaller power impact). So if I want higher single-threaded performance on a power budget, area helps. And of course for multi-threaded performance the knobs I have are number of cores, number of memory controllers, and last-level cache size, all of which drive area. There's a reason Moore's law was so often interpreted as talking about performance and not transistor count -- transistor count gives you performance. If you're willing to build a 432 mm^2 chip instead of a 308 mm^2 chip iso-process, you're basically gaining a half-node of performance right there.
Again, the CRAY-1 CPU is around 42000 mm^2, so I'm guessing you'd rather run that today, right?
Basically yeah, if you compare CPU from same fab then its basically the same.
AMD has done a LOT for parallelization and their server options are impressive... I mean, you're still talking 500W+ in total load, but that's across 128+ cores. Strix Halo scaling goes down impressively to the ~10-15W range under common usage, not as low as Apple does under similar loads but impressive in its own way.
I've used laptops for 15+ years (transitioned from a Mac Cube to a white Macbook. Macbook Pro etc.) but have migrated to a desktop some years ago (first iMac Pro, now AMD), as I work at my desk and when I'm not at my desk I'm not working.
Some years ago I got a 3900X and a 2080TI. And they still work fine, and I don't have performance problems, and although I thought of getting PCI5/NVMe with a 9950x3d/395+ (or a Threadripper), I just don't need it. I've upgraded the SSDs several times for speed and capacity (now at the PCI4/M2 limit and don't want to go into RAID), and added solar panels and a battery pack for energy usage, but I'm fine otherwise.
Indeed I want to buy a new CPU and GPU, but I don't find enough reasons (though might get a Mac Studio for local AI).
But I understand your point if you need a laptop, I just decided I no longer need one, and get more power with faster compiling for less money.